diff options
140 files changed, 13203 insertions, 7954 deletions
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 81911e11a15d..f315425d8468 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -560,6 +560,21 @@ int x86_pmu_hw_config(struct perf_event *event) return -EINVAL; } + /* sample_regs_user never support XMM registers */ + if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS)) + return -EINVAL; + /* + * Besides the general purpose registers, XMM registers may + * be collected in PEBS on some platforms, e.g. Icelake + */ + if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) { + if (x86_pmu.pebs_no_xmm_regs) + return -EINVAL; + + if (!event->attr.precise_ip) + return -EINVAL; + } + return x86_setup_perfctr(event); } @@ -661,6 +676,10 @@ static inline int is_x86_event(struct perf_event *event) return event->pmu == &pmu; } +struct pmu *x86_get_pmu(void) +{ + return &pmu; +} /* * Event scheduler state: * @@ -849,18 +868,43 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) struct event_constraint *c; unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; struct perf_event *e; - int i, wmin, wmax, unsched = 0; + int n0, i, wmin, wmax, unsched = 0; struct hw_perf_event *hwc; bitmap_zero(used_mask, X86_PMC_IDX_MAX); + /* + * Compute the number of events already present; see x86_pmu_add(), + * validate_group() and x86_pmu_commit_txn(). For the former two + * cpuc->n_events hasn't been updated yet, while for the latter + * cpuc->n_txn contains the number of events added in the current + * transaction. + */ + n0 = cpuc->n_events; + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) + n0 -= cpuc->n_txn; + if (x86_pmu.start_scheduling) x86_pmu.start_scheduling(cpuc); for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { - cpuc->event_constraint[i] = NULL; - c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); - cpuc->event_constraint[i] = c; + c = cpuc->event_constraint[i]; + + /* + * Previously scheduled events should have a cached constraint, + * while new events should not have one. + */ + WARN_ON_ONCE((c && i >= n0) || (!c && i < n0)); + + /* + * Request constraints for new events; or for those events that + * have a dynamic constraint -- for those the constraint can + * change due to external factors (sibling state, allow_tfa). + */ + if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) { + c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); + cpuc->event_constraint[i] = c; + } wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); @@ -925,25 +969,20 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (!unsched && assign) { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; - e->hw.flags |= PERF_X86_EVENT_COMMITTED; if (x86_pmu.commit_scheduling) x86_pmu.commit_scheduling(cpuc, i, assign[i]); } } else { - for (i = 0; i < n; i++) { + for (i = n0; i < n; i++) { e = cpuc->event_list[i]; - /* - * do not put_constraint() on comitted events, - * because they are good to go - */ - if ((e->hw.flags & PERF_X86_EVENT_COMMITTED)) - continue; /* * release events that failed scheduling */ if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, e); + + cpuc->event_constraint[i] = NULL; } } @@ -1373,11 +1412,6 @@ static void x86_pmu_del(struct perf_event *event, int flags) int i; /* - * event is descheduled - */ - event->hw.flags &= ~PERF_X86_EVENT_COMMITTED; - - /* * If we're called during a txn, we only need to undo x86_pmu.add. * The events never got scheduled and ->cancel_txn will truncate * the event_list. @@ -1413,6 +1447,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; } + cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; perf_event_update_userpage(event); @@ -2024,7 +2059,7 @@ static int validate_event(struct perf_event *event) if (IS_ERR(fake_cpuc)) return PTR_ERR(fake_cpuc); - c = x86_pmu.get_event_constraints(fake_cpuc, -1, event); + c = x86_pmu.get_event_constraints(fake_cpuc, 0, event); if (!c || !c->weight) ret = -EINVAL; @@ -2072,8 +2107,7 @@ static int validate_group(struct perf_event *event) if (n < 0) goto out; - fake_cpuc->n_events = n; - + fake_cpuc->n_events = 0; ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); out: @@ -2348,6 +2382,15 @@ void arch_perf_update_userpage(struct perf_event *event, cyc2ns_read_end(); } +/* + * Determine whether the regs were taken from an irq/exception handler rather + * than from perf_arch_fetch_caller_regs(). + */ +static bool perf_hw_regs(struct pt_regs *regs) +{ + return regs->flags & X86_EFLAGS_FIXED; +} + void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { @@ -2359,11 +2402,15 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re return; } - if (perf_callchain_store(entry, regs->ip)) - return; + if (perf_hw_regs(regs)) { + if (perf_callchain_store(entry, regs->ip)) + return; + unwind_start(&state, current, regs, NULL); + } else { + unwind_start(&state, current, NULL, (void *)regs->sp); + } - for (unwind_start(&state, current, regs, NULL); !unwind_done(&state); - unwind_next_frame(&state)) { + for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || perf_callchain_store(entry, addr)) return; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index d35f4775d5f1..ef763f535e3a 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -239,6 +239,35 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +static struct event_constraint intel_icl_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + INTEL_UEVENT_CONSTRAINT(0x1c0, 0), /* INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ + INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf), + INTEL_EVENT_CONSTRAINT(0x32, 0xf), /* SW_PREFETCH_ACCESS.* */ + INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf), + INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff), /* CYCLE_ACTIVITY.STALLS_TOTAL */ + INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff), /* CYCLE_ACTIVITY.STALLS_MEM_ANY */ + INTEL_EVENT_CONSTRAINT(0xa3, 0xf), /* CYCLE_ACTIVITY.* */ + INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg intel_icl_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + EVENT_EXTRA_END +}; + EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); @@ -1827,6 +1856,45 @@ static __initconst const u64 glp_hw_cache_extra_regs }, }; +#define TNT_LOCAL_DRAM BIT_ULL(26) +#define TNT_DEMAND_READ GLM_DEMAND_DATA_RD +#define TNT_DEMAND_WRITE GLM_DEMAND_RFO +#define TNT_LLC_ACCESS GLM_ANY_RESPONSE +#define TNT_SNP_ANY (SNB_SNP_NOT_NEEDED|SNB_SNP_MISS| \ + SNB_NO_FWD|SNB_SNP_FWD|SNB_HITM) +#define TNT_LLC_MISS (TNT_SNP_ANY|SNB_NON_DRAM|TNT_LOCAL_DRAM) + +static __initconst const u64 tnt_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = TNT_DEMAND_READ| + TNT_LLC_ACCESS, + [C(RESULT_MISS)] = TNT_DEMAND_READ| + TNT_LLC_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = TNT_DEMAND_WRITE| + TNT_LLC_ACCESS, + [C(RESULT_MISS)] = TNT_DEMAND_WRITE| + TNT_LLC_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, +}; + +static struct extra_reg intel_tnt_extra_regs[] __read_mostly = { + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1), + EVENT_EXTRA_END +}; + #define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ #define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ #define KNL_MCDRAM_LOCAL BIT_ULL(21) @@ -2015,7 +2083,7 @@ static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int /* * We're going to use PMC3, make sure TFA is set before we touch it. */ - if (cntr == 3 && !cpuc->is_fake) + if (cntr == 3) intel_set_tfa(cpuc, true); } @@ -2149,6 +2217,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event) bits <<= (idx * 4); mask = 0xfULL << (idx * 4); + if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) { + bits |= ICL_FIXED_0_ADAPTIVE << (idx * 4); + mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4); + } + rdmsrl(hwc->config_base, ctrl_val); ctrl_val &= ~mask; ctrl_val |= bits; @@ -2692,7 +2765,7 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx, if (x86_pmu.event_constraints) { for_each_event_constraint(c, x86_pmu.event_constraints) { - if ((event->hw.config & c->cmask) == c->code) { + if (constraint_match(c, event->hw.config)) { event->hw.flags |= c->flags; return c; } @@ -2842,7 +2915,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; struct intel_excl_states *xlo; int tid = cpuc->excl_thread_id; - int is_excl, i; + int is_excl, i, w; /* * validating a group does not require @@ -2898,36 +2971,40 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * SHARED : sibling counter measuring non-exclusive event * UNUSED : sibling counter unused */ + w = c->weight; for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) { /* * exclusive event in sibling counter * our corresponding counter cannot be used * regardless of our event */ - if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) + if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) { __clear_bit(i, c->idxmsk); + w--; + continue; + } /* * if measuring an exclusive event, sibling * measuring non-exclusive, then counter cannot * be used */ - if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) + if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) { __clear_bit(i, c->idxmsk); + w--; + continue; + } } /* - * recompute actual bit weight for scheduling algorithm - */ - c->weight = hweight64(c->idxmsk64); - - /* * if we return an empty mask, then switch * back to static empty constraint to avoid * the cost of freeing later on */ - if (c->weight == 0) + if (!w) c = &emptyconstraint; + c->weight = w; + return c; } @@ -2935,11 +3012,9 @@ static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { - struct event_constraint *c1 = NULL; - struct event_constraint *c2; + struct event_constraint *c1, *c2; - if (idx >= 0) /* fake does < 0 */ - c1 = cpuc->event_constraint[idx]; + c1 = cpuc->event_constraint[idx]; /* * first time only @@ -2947,7 +3022,8 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, * - dynamic constraint: handled by intel_get_excl_constraints() */ c2 = __intel_get_event_constraints(cpuc, idx, event); - if (c1 && (c1->flags & PERF_X86_EVENT_DYNAMIC)) { + if (c1) { + WARN_ON_ONCE(!(c1->flags & PERF_X86_EVENT_DYNAMIC)); bitmap_copy(c1->idxmsk, c2->idxmsk, X86_PMC_IDX_MAX); c1->weight = c2->weight; c2 = c1; @@ -3370,6 +3446,12 @@ static struct event_constraint counter0_constraint = static struct event_constraint counter2_constraint = EVENT_CONSTRAINT(0, 0x4, 0); +static struct event_constraint fixed0_constraint = + FIXED_EVENT_CONSTRAINT(0x00c0, 0); + +static struct event_constraint fixed0_counter0_constraint = + INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000001ULL); + static struct event_constraint * hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) @@ -3389,6 +3471,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx, } static struct event_constraint * +icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + /* + * Fixed counter 0 has less skid. + * Force instruction:ppp in Fixed counter 0 + */ + if ((event->attr.precise_ip == 3) && + constraint_match(&fixed0_constraint, event->hw.config)) + return &fixed0_constraint; + + return hsw_get_event_constraints(cpuc, idx, event); +} + +static struct event_constraint * glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { @@ -3403,6 +3500,29 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, return c; } +static struct event_constraint * +tnt_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c; + + /* + * :ppp means to do reduced skid PEBS, + * which is available on PMC0 and fixed counter 0. + */ + if (event->attr.precise_ip == 3) { + /* Force instruction:ppp on PMC0 and Fixed counter 0 */ + if (constraint_match(&fixed0_constraint, event->hw.config)) + return &fixed0_counter0_constraint; + + return &counter0_constraint; + } + + c = intel_get_event_constraints(cpuc, idx, event); + + return c; +} + static bool allow_tsx_force_abort = true; static struct event_constraint * @@ -3414,7 +3534,7 @@ tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx, /* * Without TFA we must not use PMC3. */ - if (!allow_tsx_force_abort && test_bit(3, c->idxmsk) && idx >= 0) { + if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) { c = dyn_constraint(cpuc, c, idx); c->idxmsk64 &= ~(1ULL << 3); c->weight--; @@ -3511,6 +3631,8 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu) { + cpuc->pebs_record_size = x86_pmu.pebs_record_size; + if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { cpuc->shared_regs = allocate_shared_regs(cpu); if (!cpuc->shared_regs) @@ -4118,6 +4240,42 @@ static struct attribute *hsw_tsx_events_attrs[] = { NULL }; +EVENT_ATTR_STR(tx-capacity-read, tx_capacity_read, "event=0x54,umask=0x80"); +EVENT_ATTR_STR(tx-capacity-write, tx_capacity_write, "event=0x54,umask=0x2"); +EVENT_ATTR_STR(el-capacity-read, el_capacity_read, "event=0x54,umask=0x80"); +EVENT_ATTR_STR(el-capacity-write, el_capacity_write, "event=0x54,umask=0x2"); + +static struct attribute *icl_events_attrs[] = { + EVENT_PTR(mem_ld_hsw), + EVENT_PTR(mem_st_hsw), + NULL, +}; + +static struct attribute *icl_tsx_events_attrs[] = { + EVENT_PTR(tx_start), + EVENT_PTR(tx_abort), + EVENT_PTR(tx_commit), + EVENT_PTR(tx_capacity_read), + EVENT_PTR(tx_capacity_write), + EVENT_PTR(tx_conflict), + EVENT_PTR(el_start), + EVENT_PTR(el_abort), + EVENT_PTR(el_commit), + EVENT_PTR(el_capacity_read), + EVENT_PTR(el_capacity_write), + EVENT_PTR(el_conflict), + EVENT_PTR(cycles_t), + EVENT_PTR(cycles_ct), + NULL, +}; + +static __init struct attribute **get_icl_events_attrs(void) +{ + return boot_cpu_has(X86_FEATURE_RTM) ? + merge_attr(icl_events_attrs, icl_tsx_events_attrs) : + icl_events_attrs; +} + static ssize_t freeze_on_smi_show(struct device *cdev, struct device_attribute *attr, char *buf) @@ -4157,6 +4315,50 @@ done: return count; } +static void update_tfa_sched(void *ignored) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + /* + * check if PMC3 is used + * and if so force schedule out for all event types all contexts + */ + if (test_bit(3, cpuc->active_mask)) + perf_pmu_resched(x86_get_pmu()); +} + +static ssize_t show_sysctl_tfa(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, 40, "%d\n", allow_tsx_force_abort); +} + +static ssize_t set_sysctl_tfa(struct device *cdev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + bool val; + ssize_t ret; + + ret = kstrtobool(buf, &val); + if (ret) + return ret; + + /* no change */ + if (val == allow_tsx_force_abort) + return count; + + allow_tsx_force_abort = val; + + get_online_cpus(); + on_each_cpu(update_tfa_sched, NULL, 1); + put_online_cpus(); + + return count; +} + + static DEVICE_ATTR_RW(freeze_on_smi); static ssize_t branches_show(struct device *cdev, @@ -4189,7 +4391,9 @@ static struct attribute *intel_pmu_caps_attrs[] = { NULL }; -static DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort); +static DEVICE_ATTR(allow_tsx_force_abort, 0644, + show_sysctl_tfa, + set_sysctl_tfa); static struct attribute *intel_pmu_attrs[] = { &dev_attr_freeze_on_smi.attr, @@ -4450,6 +4654,32 @@ __init int intel_pmu_init(void) name = "goldmont_plus"; break; + case INTEL_FAM6_ATOM_TREMONT_X: + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; + + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.extra_regs = intel_tnt_extra_regs; + /* + * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS + * for precise cycles. + */ + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.get_event_constraints = tnt_get_event_constraints; + extra_attr = slm_format_attr; + pr_cont("Tremont events, "); + name = "Tremont"; + break; + case INTEL_FAM6_WESTMERE: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: @@ -4698,13 +4928,41 @@ __init int intel_pmu_init(void) x86_pmu.get_event_constraints = tfa_get_event_constraints; x86_pmu.enable_all = intel_tfa_pmu_enable_all; x86_pmu.commit_scheduling = intel_tfa_commit_scheduling; - intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr; + intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr; } pr_cont("Skylake events, "); name = "skylake"; break; + case INTEL_FAM6_ICELAKE_MOBILE: + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_icl_event_constraints; + x86_pmu.pebs_constraints = intel_icl_pebs_event_constraints; + x86_pmu.extra_regs = intel_icl_extra_regs; + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = icl_get_event_constraints; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + hsw_format_attr : nhm_format_attr; + extra_attr = merge_attr(extra_attr, skl_format_attr); + x86_pmu.cpu_events = get_icl_events_attrs(); + x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02); + x86_pmu.lbr_pt_coexist = true; + intel_pmu_pebs_data_source_skl(false); + pr_cont("Icelake events, "); + name = "icelake"; + break; + default: switch (x86_pmu.version) { case 1: diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index d41de9af7a39..6072f92cb8ea 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -578,6 +578,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates), + + X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 10c99ce1fead..7a9f5dac5abe 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -849,6 +849,26 @@ struct event_constraint intel_skl_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_icl_pebs_event_constraints[] = { + INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */ + + INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */ + + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */ + + INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + + /* + * Everything else is handled by PMU_FL_PEBS_ALL, because we + * need the full constraints from the main table. + */ + + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -858,7 +878,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) if (x86_pmu.pebs_constraints) { for_each_event_constraint(c, x86_pmu.pebs_constraints) { - if ((event->hw.config & c->cmask) == c->code) { + if (constraint_match(c, event->hw.config)) { event->hw.flags |= c->flags; return c; } @@ -906,17 +926,87 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) if (cpuc->n_pebs == cpuc->n_large_pebs) { threshold = ds->pebs_absolute_maximum - - reserved * x86_pmu.pebs_record_size; + reserved * cpuc->pebs_record_size; } else { - threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; + threshold = ds->pebs_buffer_base + cpuc->pebs_record_size; } ds->pebs_interrupt_threshold = threshold; } +static void adaptive_pebs_record_size_update(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 pebs_data_cfg = cpuc->pebs_data_cfg; + int sz = sizeof(struct pebs_basic); + + if (pebs_data_cfg & PEBS_DATACFG_MEMINFO) + sz += sizeof(struct pebs_meminfo); + if (pebs_data_cfg & PEBS_DATACFG_GP) + sz += sizeof(struct pebs_gprs); + if (pebs_data_cfg & PEBS_DATACFG_XMMS) + sz += sizeof(struct pebs_xmm); + if (pebs_data_cfg & PEBS_DATACFG_LBRS) + sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry); + + cpuc->pebs_record_size = sz; +} + +#define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \ + PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \ + PERF_SAMPLE_TRANSACTION) + +static u64 pebs_update_adaptive_cfg(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + u64 sample_type = attr->sample_type; + u64 pebs_data_cfg = 0; + bool gprs, tsx_weight; + + if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) && + attr->precise_ip > 1) + return pebs_data_cfg; + + if (sample_type & PERF_PEBS_MEMINFO_TYPE) + pebs_data_cfg |= PEBS_DATACFG_MEMINFO; + + /* + * We need GPRs when: + * + user requested them + * + precise_ip < 2 for the non event IP + * + For RTM TSX weight we need GPRs for the abort code. + */ + gprs = (sample_type & PERF_SAMPLE_REGS_INTR) && + (attr->sample_regs_intr & PEBS_GP_REGS); + + tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) && + ((attr->config & INTEL_ARCH_EVENT_MASK) == + x86_pmu.rtm_abort_event); + + if (gprs || (attr->precise_ip < 2) || tsx_weight) + pebs_data_cfg |= PEBS_DATACFG_GP; + + if ((sample_type & PERF_SAMPLE_REGS_INTR) && + (attr->sample_regs_intr & PEBS_XMM_REGS)) + pebs_data_cfg |= PEBS_DATACFG_XMMS; + + if (sample_type & PERF_SAMPLE_BRANCH_STACK) { + /* + * For now always log all LBRs. Could configure this + * later. + */ + pebs_data_cfg |= PEBS_DATACFG_LBRS | + ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT); + } + + return pebs_data_cfg; +} + static void -pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu) +pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, + struct perf_event *event, bool add) { + struct pmu *pmu = event->ctx->pmu; /* * Make sure we get updated with the first PEBS * event. It will trigger also during removal, but @@ -933,6 +1023,29 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu) update = true; } + /* + * The PEBS record doesn't shrink on pmu::del(). Doing so would require + * iterating all remaining PEBS events to reconstruct the config. + */ + if (x86_pmu.intel_cap.pebs_baseline && add) { + u64 pebs_data_cfg; + + /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */ + if (cpuc->n_pebs == 1) { + cpuc->pebs_data_cfg = 0; + cpuc->pebs_record_size = sizeof(struct pebs_basic); + } + + pebs_data_cfg = pebs_update_adaptive_cfg(event); + + /* Update pebs_record_size if new event requires more data. */ + if (pebs_data_cfg & ~cpuc->pebs_data_cfg) { + cpuc->pebs_data_cfg |= pebs_data_cfg; + adaptive_pebs_record_size_update(); + update = true; + } + } + if (update) pebs_update_threshold(cpuc); } @@ -947,7 +1060,7 @@ void intel_pmu_pebs_add(struct perf_event *event) if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs++; - pebs_update_state(needed_cb, cpuc, event->ctx->pmu); + pebs_update_state(needed_cb, cpuc, event, true); } void intel_pmu_pebs_enable(struct perf_event *event) @@ -960,11 +1073,19 @@ void intel_pmu_pebs_enable(struct perf_event *event) cpuc->pebs_enabled |= 1ULL << hwc->idx; - if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) + if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5)) cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled |= 1ULL << 63; + if (x86_pmu.intel_cap.pebs_baseline) { + hwc->config |= ICL_EVENTSEL_ADAPTIVE; + if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) { + wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg); + cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg; + } + } + /* * Use auto-reload if possible to save a MSR write in the PMI. * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD. @@ -991,7 +1112,7 @@ void intel_pmu_pebs_del(struct perf_event *event) if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs--; - pebs_update_state(needed_cb, cpuc, event->ctx->pmu); + pebs_update_state(needed_cb, cpuc, event, false); } void intel_pmu_pebs_disable(struct perf_event *event) @@ -1004,7 +1125,8 @@ void intel_pmu_pebs_disable(struct perf_event *event) cpuc->pebs_enabled &= ~(1ULL << hwc->idx); - if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) + if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && + (x86_pmu.version < 5)) cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32)); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled &= ~(1ULL << 63); @@ -1125,34 +1247,57 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 0; } -static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs) +static inline u64 intel_get_tsx_weight(u64 tsx_tuning) { - if (pebs->tsx_tuning) { - union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning }; + if (tsx_tuning) { + union hsw_tsx_tuning tsx = { .value = tsx_tuning }; return tsx.cycles_last_block; } return 0; } -static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs) +static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax) { - u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32; + u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32; /* For RTM XABORTs also log the abort code from AX */ - if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1)) - txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT; + if ((txn & PERF_TXN_TRANSACTION) && (ax & 1)) + txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT; return txn; } -static void setup_pebs_sample_data(struct perf_event *event, - struct pt_regs *iregs, void *__pebs, - struct perf_sample_data *data, - struct pt_regs *regs) +static inline u64 get_pebs_status(void *n) { + if (x86_pmu.intel_cap.pebs_format < 4) + return ((struct pebs_record_nhm *)n)->status; + return ((struct pebs_basic *)n)->applicable_counters; +} + #define PERF_X86_EVENT_PEBS_HSW_PREC \ (PERF_X86_EVENT_PEBS_ST_HSW | \ PERF_X86_EVENT_PEBS_LD_HSW | \ PERF_X86_EVENT_PEBS_NA_HSW) + +static u64 get_data_src(struct perf_event *event, u64 aux) +{ + u64 val = PERF_MEM_NA; + int fl = event->hw.flags; + bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); + + if (fl & PERF_X86_EVENT_PEBS_LDLAT) + val = load_latency_data(aux); + else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) + val = precise_datala_hsw(event, aux); + else if (fst) + val = precise_store_data(aux); + return val; +} + +static void setup_pebs_fixed_sample_data(struct perf_event *event, + struct pt_regs *iregs, void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) +{ /* * We cast to the biggest pebs_record but are careful not to * unconditionally access the 'extra' entries. @@ -1160,17 +1305,13 @@ static void setup_pebs_sample_data(struct perf_event *event, struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct pebs_record_skl *pebs = __pebs; u64 sample_type; - int fll, fst, dsrc; - int fl = event->hw.flags; + int fll; if (pebs == NULL) return; sample_type = event->attr.sample_type; - dsrc = sample_type & PERF_SAMPLE_DATA_SRC; - - fll = fl & PERF_X86_EVENT_PEBS_LDLAT; - fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); + fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT; perf_sample_data_init(data, 0, event->hw.last_period); @@ -1185,16 +1326,8 @@ static void setup_pebs_sample_data(struct perf_event *event, /* * data.data_src encodes the data source */ - if (dsrc) { - u64 val = PERF_MEM_NA; - if (fll) - val = load_latency_data(pebs->dse); - else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) - val = precise_datala_hsw(event, pebs->dse); - else if (fst) - val = precise_store_data(pebs->dse); - data->data_src.val = val; - } + if (sample_type & PERF_SAMPLE_DATA_SRC) + data->data_src.val = get_data_src(event, pebs->dse); /* * We must however always use iregs for the unwinder to stay sane; the @@ -1281,10 +1414,11 @@ static void setup_pebs_sample_data(struct perf_event *event, if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) - data->weight = intel_hsw_weight(pebs); + data->weight = intel_get_tsx_weight(pebs->tsx_tuning); if (sample_type & PERF_SAMPLE_TRANSACTION) - data->txn = intel_hsw_transaction(pebs); + data->txn = intel_get_tsx_transaction(pebs->tsx_tuning, + pebs->ax); } /* @@ -1301,6 +1435,140 @@ static void setup_pebs_sample_data(struct perf_event *event, data->br_stack = &cpuc->lbr_stack; } +static void adaptive_pebs_save_regs(struct pt_regs *regs, + struct pebs_gprs *gprs) +{ + regs->ax = gprs->ax; + regs->bx = gprs->bx; + regs->cx = gprs->cx; + regs->dx = gprs->dx; + regs->si = gprs->si; + regs->di = gprs->di; + regs->bp = gprs->bp; + regs->sp = gprs->sp; +#ifndef CONFIG_X86_32 + regs->r8 = gprs->r8; + regs->r9 = gprs->r9; + regs->r10 = gprs->r10; + regs->r11 = gprs->r11; + regs->r12 = gprs->r12; + regs->r13 = gprs->r13; + regs->r14 = gprs->r14; + regs->r15 = gprs->r15; +#endif +} + +/* + * With adaptive PEBS the layout depends on what fields are configured. + */ + +static void setup_pebs_adaptive_sample_data(struct perf_event *event, + struct pt_regs *iregs, void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct pebs_basic *basic = __pebs; + void *next_record = basic + 1; + u64 sample_type; + u64 format_size; + struct pebs_meminfo *meminfo = NULL; + struct pebs_gprs *gprs = NULL; + struct x86_perf_regs *perf_regs; + + if (basic == NULL) + return; + + perf_regs = container_of(regs, struct x86_perf_regs, regs); + perf_regs->xmm_regs = NULL; + + sample_type = event->attr.sample_type; + format_size = basic->format_size; + perf_sample_data_init(data, 0, event->hw.last_period); + data->period = event->hw.last_period; + + if (event->attr.use_clockid == 0) + data->time = native_sched_clock_from_tsc(basic->tsc); + + /* + * We must however always use iregs for the unwinder to stay sane; the + * record BP,SP,IP can point into thin air when the record is from a + * previous PMI context or an (I)RET happened between the record and + * PMI. + */ + if (sample_type & PERF_SAMPLE_CALLCHAIN) + data->callchain = perf_callchain(event, iregs); + + *regs = *iregs; + /* The ip in basic is EventingIP */ + set_linear_ip(regs, basic->ip); + regs->flags = PERF_EFLAGS_EXACT; + + /* + * The record for MEMINFO is in front of GP + * But PERF_SAMPLE_TRANSACTION needs gprs->ax. + * Save the pointer here but process later. + */ + if (format_size & PEBS_DATACFG_MEMINFO) { + meminfo = next_record; + next_record = meminfo + 1; + } + + if (format_size & PEBS_DATACFG_GP) { + gprs = next_record; + next_record = gprs + 1; + + if (event->attr.precise_ip < 2) { + set_linear_ip(regs, gprs->ip); + regs->flags &= ~PERF_EFLAGS_EXACT; + } + + if (sample_type & PERF_SAMPLE_REGS_INTR) + adaptive_pebs_save_regs(regs, gprs); + } + + if (format_size & PEBS_DATACFG_MEMINFO) { + if (sample_type & PERF_SAMPLE_WEIGHT) + data->weight = meminfo->latency ?: + intel_get_tsx_weight(meminfo->tsx_tuning); + + if (sample_type & PERF_SAMPLE_DATA_SRC) + data->data_src.val = get_data_src(event, meminfo->aux); + + if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) + data->addr = meminfo->address; + + if (sample_type & PERF_SAMPLE_TRANSACTION) + data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning, + gprs ? gprs->ax : 0); + } + + if (format_size & PEBS_DATACFG_XMMS) { + struct pebs_xmm *xmm = next_record; + + next_record = xmm + 1; + perf_regs->xmm_regs = xmm->xmm; + } + + if (format_size & PEBS_DATACFG_LBRS) { + struct pebs_lbr *lbr = next_record; + int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT) + & 0xff) + 1; + next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry); + + if (has_branch_stack(event)) { + intel_pmu_store_pebs_lbrs(lbr); + data->br_stack = &cpuc->lbr_stack; + } + } + + WARN_ONCE(next_record != __pebs + (format_size >> 48), + "PEBS record size %llu, expected %llu, config %llx\n", + format_size >> 48, + (u64)(next_record - __pebs), + basic->format_size); +} + static inline void * get_next_pebs_record_by_bit(void *base, void *top, int bit) { @@ -1318,19 +1586,19 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) if (base == NULL) return NULL; - for (at = base; at < top; at += x86_pmu.pebs_record_size) { - struct pebs_record_nhm *p = at; + for (at = base; at < top; at += cpuc->pebs_record_size) { + unsigned long status = get_pebs_status(at); - if (test_bit(bit, (unsigned long *)&p->status)) { + if (test_bit(bit, (unsigned long *)&status)) { /* PEBS v3 has accurate status bits */ if (x86_pmu.intel_cap.pebs_format >= 3) return at; - if (p->status == (1 << bit)) + if (status == (1 << bit)) return at; /* clear non-PEBS bit and re-check */ - pebs_status = p->status & cpuc->pebs_enabled; + pebs_status = status & cpuc->pebs_enabled; pebs_status &= PEBS_COUNTER_MASK; if (pebs_status == (1 << bit)) return at; @@ -1410,11 +1678,18 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *base, void *top, - int bit, int count) + int bit, int count, + void (*setup_sample)(struct perf_event *, + struct pt_regs *, + void *, + struct perf_sample_data *, + struct pt_regs *)) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; struct perf_sample_data data; - struct pt_regs regs; + struct x86_perf_regs perf_regs; + struct pt_regs *regs = &perf_regs.regs; void *at = get_next_pebs_record_by_bit(base, top, bit); if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { @@ -1429,20 +1704,20 @@ static void __intel_pmu_pebs_event(struct perf_event *event, return; while (count > 1) { - setup_pebs_sample_data(event, iregs, at, &data, ®s); - perf_event_output(event, &data, ®s); - at += x86_pmu.pebs_record_size; + setup_sample(event, iregs, at, &data, regs); + perf_event_output(event, &data, regs); + at += cpuc->pebs_record_size; at = get_next_pebs_record_by_bit(at, top, bit); count--; } - setup_pebs_sample_data(event, iregs, at, &data, ®s); + setup_sample(event, iregs, at, &data, regs); /* * All but the last records are processed. * The last one is left to be able to call the overflow handler. */ - if (perf_event_overflow(event, &data, ®s)) { + if (perf_event_overflow(event, &data, regs)) { x86_pmu_stop(event, 0); return; } @@ -1483,7 +1758,27 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) return; } - __intel_pmu_pebs_event(event, iregs, at, top, 0, n); + __intel_pmu_pebs_event(event, iregs, at, top, 0, n, + setup_pebs_fixed_sample_data); +} + +static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size) +{ + struct perf_event *event; + int bit; + + /* + * The drain_pebs() could be called twice in a short period + * for auto-reload event in pmu::read(). There are no + * overflows have happened in between. + * It needs to call intel_pmu_save_and_restart_reload() to + * update the event->count for this case. + */ + for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) { + event = cpuc->events[bit]; + if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) + intel_pmu_save_and_restart_reload(event, 0); + } } static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) @@ -1513,19 +1808,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) } if (unlikely(base >= top)) { - /* - * The drain_pebs() could be called twice in a short period - * for auto-reload event in pmu::read(). There are no - * overflows have happened in between. - * It needs to call intel_pmu_save_and_restart_reload() to - * update the event->count for this case. - */ - for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, - size) { - event = cpuc->events[bit]; - if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) - intel_pmu_save_and_restart_reload(event, 0); - } + intel_pmu_pebs_event_update_no_drain(cpuc, size); return; } @@ -1538,8 +1821,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) /* PEBS v3 has more accurate status bits */ if (x86_pmu.intel_cap.pebs_format >= 3) { - for_each_set_bit(bit, (unsigned long *)&pebs_status, - size) + for_each_set_bit(bit, (unsigned long *)&pebs_status, size) counts[bit]++; continue; @@ -1578,8 +1860,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * If collision happened, the record will be dropped. */ if (p->status != (1ULL << bit)) { - for_each_set_bit(i, (unsigned long *)&pebs_status, - x86_pmu.max_pebs_events) + for_each_set_bit(i, (unsigned long *)&pebs_status, size) error[i]++; continue; } @@ -1587,7 +1868,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) counts[bit]++; } - for (bit = 0; bit < size; bit++) { + for_each_set_bit(bit, (unsigned long *)&mask, size) { if ((counts[bit] == 0) && (error[bit] == 0)) continue; @@ -1608,11 +1889,66 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) if (counts[bit]) { __intel_pmu_pebs_event(event, iregs, base, - top, bit, counts[bit]); + top, bit, counts[bit], + setup_pebs_fixed_sample_data); } } } +static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs) +{ + short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct perf_event *event; + void *base, *at, *top; + int bit, size; + u64 mask; + + if (!x86_pmu.pebs_active) + return; + + base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_basic *)(unsigned long)ds->pebs_index; + + ds->pebs_index = ds->pebs_buffer_base; + + mask = ((1ULL << x86_pmu.max_pebs_events) - 1) | + (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED); + size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed; + + if (unlikely(base >= top)) { + intel_pmu_pebs_event_update_no_drain(cpuc, size); + return; + } + + for (at = base; at < top; at += cpuc->pebs_record_size) { + u64 pebs_status; + + pebs_status = get_pebs_status(at) & cpuc->pebs_enabled; + pebs_status &= mask; + + for_each_set_bit(bit, (unsigned long *)&pebs_status, size) + counts[bit]++; + } + + for_each_set_bit(bit, (unsigned long *)&mask, size) { + if (counts[bit] == 0) + continue; + + event = cpuc->events[bit]; + if (WARN_ON_ONCE(!event)) + continue; + + if (WARN_ON_ONCE(!event->attr.precise_ip)) + continue; + + __intel_pmu_pebs_event(event, iregs, base, + top, bit, counts[bit], + setup_pebs_adaptive_sample_data); + } +} + /* * BTS, PEBS probe and setup */ @@ -1628,12 +1964,18 @@ void __init intel_ds_init(void) x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; - if (x86_pmu.version <= 4) + if (x86_pmu.version <= 4) { x86_pmu.pebs_no_isolation = 1; + x86_pmu.pebs_no_xmm_regs = 1; + } if (x86_pmu.pebs) { char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; + char *pebs_qual = ""; int format = x86_pmu.intel_cap.pebs_format; + if (format < 4) + x86_pmu.intel_cap.pebs_baseline = 0; + switch (format) { case 0: pr_cont("PEBS fmt0%c, ", pebs_type); @@ -1669,6 +2011,29 @@ void __init intel_ds_init(void) x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; + case 4: + x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl; + x86_pmu.pebs_record_size = sizeof(struct pebs_basic); + if (x86_pmu.intel_cap.pebs_baseline) { + x86_pmu.large_pebs_flags |= + PERF_SAMPLE_BRANCH_STACK | + PERF_SAMPLE_TIME; + x86_pmu.flags |= PMU_FL_PEBS_ALL; + pebs_qual = "-baseline"; + } else { + /* Only basic record supported */ + x86_pmu.pebs_no_xmm_regs = 1; + x86_pmu.large_pebs_flags &= + ~(PERF_SAMPLE_ADDR | + PERF_SAMPLE_TIME | + PERF_SAMPLE_DATA_SRC | + PERF_SAMPLE_TRANSACTION | + PERF_SAMPLE_REGS_USER | + PERF_SAMPLE_REGS_INTR); + } + pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual); + break; + default: pr_cont("no PEBS fmt%d%c, ", format, pebs_type); x86_pmu.pebs = 0; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 580c1b91c454..6f814a27416b 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -488,6 +488,8 @@ void intel_pmu_lbr_add(struct perf_event *event) * be 'new'. Conversely, a new event can get installed through the * context switch path for the first time. */ + if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0) + cpuc->lbr_pebs_users++; perf_sched_cb_inc(event->ctx->pmu); if (!cpuc->lbr_users++ && !event->total_time_running) intel_pmu_lbr_reset(); @@ -507,8 +509,11 @@ void intel_pmu_lbr_del(struct perf_event *event) task_ctx->lbr_callstack_users--; } + if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0) + cpuc->lbr_pebs_users--; cpuc->lbr_users--; WARN_ON_ONCE(cpuc->lbr_users < 0); + WARN_ON_ONCE(cpuc->lbr_pebs_users < 0); perf_sched_cb_dec(event->ctx->pmu); } @@ -658,7 +663,13 @@ void intel_pmu_lbr_read(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - if (!cpuc->lbr_users) + /* + * Don't read when all LBRs users are using adaptive PEBS. + * + * This could be smarter and actually check the event, + * but this simple approach seems to work for now. + */ + if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users) return; if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) @@ -1080,6 +1091,28 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) } } +void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int i; + + cpuc->lbr_stack.nr = x86_pmu.lbr_nr; + for (i = 0; i < x86_pmu.lbr_nr; i++) { + u64 info = lbr->lbr[i].info; + struct perf_branch_entry *e = &cpuc->lbr_entries[i]; + + e->from = lbr->lbr[i].from; + e->to = lbr->lbr[i].to; + e->mispred = !!(info & LBR_INFO_MISPRED); + e->predicted = !(info & LBR_INFO_MISPRED); + e->in_tx = !!(info & LBR_INFO_IN_TX); + e->abort = !!(info & LBR_INFO_ABORT); + e->cycles = info & LBR_INFO_CYCLES; + e->reserved = 0; + } + intel_pmu_lbr_filter(cpuc); +} + /* * Map interface branch filters onto LBR filters */ diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 94dc564146ca..37ebf6fc5415 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -775,6 +775,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init), + + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, skl_rapl_init), {}, }; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 9fe64c01a2e5..fc40a1473058 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1367,6 +1367,11 @@ static const struct intel_uncore_init_fun skx_uncore_init __initconst = { .pci_init = skx_uncore_pci_init, }; +static const struct intel_uncore_init_fun icl_uncore_init __initconst = { + .cpu_init = icl_uncore_cpu_init, + .pci_init = skl_uncore_pci_init, +}; + static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init), @@ -1393,6 +1398,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init), {}, }; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 853a49a8ccf6..79eb2e21e4f0 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -512,6 +512,7 @@ int skl_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); void skl_uncore_cpu_init(void); +void icl_uncore_cpu_init(void); int snb_pci2phy_map_init(int devid); /* uncore_snbep.c */ diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 13493f43b247..f8431819b3e1 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -34,6 +34,8 @@ #define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33 #define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca #define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32 +#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02 +#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -93,6 +95,12 @@ #define SKL_UNC_PERF_GLOBAL_CTL 0xe01 #define SKL_UNC_GLOBAL_CTL_CORE_ALL ((1 << 5) - 1) +/* ICL Cbo register */ +#define ICL_UNC_CBO_CONFIG 0x396 +#define ICL_UNC_NUM_CBO_MASK 0xf +#define ICL_UNC_CBO_0_PER_CTR0 0x702 +#define ICL_UNC_CBO_MSR_OFFSET 0x8 + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); @@ -280,6 +288,70 @@ void skl_uncore_cpu_init(void) snb_uncore_arb.ops = &skl_uncore_msr_ops; } +static struct intel_uncore_type icl_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .perf_ctr_bits = 44, + .perf_ctr = ICL_UNC_CBO_0_PER_CTR0, + .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .msr_offset = ICL_UNC_CBO_MSR_OFFSET, + .ops = &skl_uncore_msr_ops, + .format_group = &snb_uncore_format_group, +}; + +static struct uncore_event_desc icl_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff"), + { /* end: all zeroes */ }, +}; + +static struct attribute *icl_uncore_clock_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group icl_uncore_clock_format_group = { + .name = "format", + .attrs = icl_uncore_clock_formats_attr, +}; + +static struct intel_uncore_type icl_uncore_clockbox = { + .name = "clock", + .num_counters = 1, + .num_boxes = 1, + .fixed_ctr_bits = 48, + .fixed_ctr = SNB_UNC_FIXED_CTR, + .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL, + .single_fixed = 1, + .event_mask = SNB_UNC_CTL_EV_SEL_MASK, + .format_group = &icl_uncore_clock_format_group, + .ops = &skl_uncore_msr_ops, + .event_descs = icl_uncore_events, +}; + +static struct intel_uncore_type *icl_msr_uncores[] = { + &icl_uncore_cbox, + &snb_uncore_arb, + &icl_uncore_clockbox, + NULL, +}; + +static int icl_get_cbox_num(void) +{ + u64 num_boxes; + + rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes); + + return num_boxes & ICL_UNC_NUM_CBO_MASK; +} + +void icl_uncore_cpu_init(void) +{ + uncore_msr_uncores = icl_msr_uncores; + icl_uncore_cbox.num_boxes = icl_get_cbox_num(); + snb_uncore_arb.ops = &skl_uncore_msr_ops; +} + enum { SNB_PCI_UNCORE_IMC, }; @@ -668,6 +740,18 @@ static const struct pci_device_id skl_uncore_pci_ids[] = { { /* end: all zeroes */ }, }; +static const struct pci_device_id icl_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + static struct pci_driver snb_uncore_pci_driver = { .name = "snb_uncore", .id_table = snb_uncore_pci_ids, @@ -693,6 +777,11 @@ static struct pci_driver skl_uncore_pci_driver = { .id_table = skl_uncore_pci_ids, }; +static struct pci_driver icl_uncore_pci_driver = { + .name = "icl_uncore", + .id_table = icl_uncore_pci_ids, +}; + struct imc_uncore_pci_dev { __u32 pci_id; struct pci_driver *driver; @@ -732,6 +821,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */ IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */ IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */ + IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */ + IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */ { /* end marker */ } }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index a878e6286e4a..f3f4c2263501 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -89,6 +89,7 @@ static bool test_intel(int idx) case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_KABYLAKE_MOBILE: case INTEL_FAM6_KABYLAKE_DESKTOP: + case INTEL_FAM6_ICELAKE_MOBILE: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 1e98a42b560a..07fc84bb85c1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -49,28 +49,33 @@ struct event_constraint { unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; u64 idxmsk64; }; - u64 code; - u64 cmask; - int weight; - int overlap; - int flags; + u64 code; + u64 cmask; + int weight; + int overlap; + int flags; + unsigned int size; }; + +static inline bool constraint_match(struct event_constraint *c, u64 ecode) +{ + return ((ecode & c->cmask) - c->code) <= (u64)c->size; +} + /* * struct hw_perf_event.flags flags */ #define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */ #define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */ #define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */ -#define PERF_X86_EVENT_COMMITTED 0x0008 /* event passed commit_txn */ -#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */ -#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */ -#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */ -#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ -#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ -#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ -#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ -#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */ - +#define PERF_X86_EVENT_PEBS_LD_HSW 0x0008 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x0010 /* haswell style datala, unknown */ +#define PERF_X86_EVENT_EXCL 0x0020 /* HT exclusivity on counter */ +#define PERF_X86_EVENT_DYNAMIC 0x0040 /* dynamic alloc'd constraint */ +#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0080 /* grant rdpmc permission */ +#define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */ +#define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */ +#define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -116,6 +121,24 @@ struct amd_nb { (1ULL << PERF_REG_X86_R14) | \ (1ULL << PERF_REG_X86_R15)) +#define PEBS_XMM_REGS \ + ((1ULL << PERF_REG_X86_XMM0) | \ + (1ULL << PERF_REG_X86_XMM1) | \ + (1ULL << PERF_REG_X86_XMM2) | \ + (1ULL << PERF_REG_X86_XMM3) | \ + (1ULL << PERF_REG_X86_XMM4) | \ + (1ULL << PERF_REG_X86_XMM5) | \ + (1ULL << PERF_REG_X86_XMM6) | \ + (1ULL << PERF_REG_X86_XMM7) | \ + (1ULL << PERF_REG_X86_XMM8) | \ + (1ULL << PERF_REG_X86_XMM9) | \ + (1ULL << PERF_REG_X86_XMM10) | \ + (1ULL << PERF_REG_X86_XMM11) | \ + (1ULL << PERF_REG_X86_XMM12) | \ + (1ULL << PERF_REG_X86_XMM13) | \ + (1ULL << PERF_REG_X86_XMM14) | \ + (1ULL << PERF_REG_X86_XMM15)) + /* * Per register state. */ @@ -207,10 +230,16 @@ struct cpu_hw_events { int n_pebs; int n_large_pebs; + /* Current super set of events hardware configuration */ + u64 pebs_data_cfg; + u64 active_pebs_data_cfg; + int pebs_record_size; + /* * Intel LBR bits */ int lbr_users; + int lbr_pebs_users; struct perf_branch_stack lbr_stack; struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; struct er_account *lbr_sel; @@ -257,18 +286,29 @@ struct cpu_hw_events { void *kfree_on_online[X86_PERF_KFREE_MAX]; }; -#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\ +#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \ { .idxmsk64 = (n) }, \ .code = (c), \ + .size = (e) - (c), \ .cmask = (m), \ .weight = (w), \ .overlap = (o), \ .flags = f, \ } +#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \ + __EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f) + #define EVENT_CONSTRAINT(c, n, m) \ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0) +/* + * The constraint_match() function only works for 'simple' event codes + * and not for extended (AMD64_EVENTSEL_EVENT) events codes. + */ +#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \ + __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0) + #define INTEL_EXCLEVT_CONSTRAINT(c, n) \ __EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\ 0, PERF_X86_EVENT_EXCL) @@ -304,6 +344,12 @@ struct cpu_hw_events { EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) /* + * Constraint on a range of Event codes + */ +#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \ + EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT) + +/* * Constraint on the Event code + UMask + fixed-mask * * filter mask to validate fixed counter events. @@ -350,6 +396,9 @@ struct cpu_hw_events { #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) +#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \ + EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) + /* Check only flags, but allow all event/umask */ #define INTEL_ALL_EVENT_CONSTRAINT(code, n) \ EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS) @@ -366,6 +415,11 @@ struct cpu_hw_events { ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) +#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \ + __EVENT_CONSTRAINT_RANGE(code, end, n, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) + #define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \ __EVENT_CONSTRAINT(code, n, \ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ @@ -473,6 +527,7 @@ union perf_capabilities { * values > 32bit. */ u64 full_width_write:1; + u64 pebs_baseline:1; }; u64 capabilities; }; @@ -613,14 +668,16 @@ struct x86_pmu { pebs_broken :1, pebs_prec_dist :1, pebs_no_tlb :1, - pebs_no_isolation :1; + pebs_no_isolation :1, + pebs_no_xmm_regs :1; int pebs_record_size; int pebs_buffer_size; + int max_pebs_events; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); - int max_pebs_events; unsigned long large_pebs_flags; + u64 rtm_abort_event; /* * Intel LBR @@ -714,6 +771,7 @@ static struct perf_pmu_events_ht_attr event_attr_##v = { \ .event_str_ht = ht, \ } +struct pmu *x86_get_pmu(void); extern struct x86_pmu x86_pmu __read_mostly; static inline bool x86_pmu_has_lbr_callstack(void) @@ -941,6 +999,8 @@ extern struct event_constraint intel_bdw_pebs_event_constraints[]; extern struct event_constraint intel_skl_pebs_event_constraints[]; +extern struct event_constraint intel_icl_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_add(struct perf_event *event); @@ -959,6 +1019,8 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in); void intel_pmu_auto_reload_read(struct perf_event *event); +void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr); + void intel_ds_init(void); void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h index ae26df1c2789..8380c3ddd4b2 100644 --- a/arch/x86/include/asm/intel_ds.h +++ b/arch/x86/include/asm/intel_ds.h @@ -8,7 +8,7 @@ /* The maximal number of PEBS events: */ #define MAX_PEBS_EVENTS 8 -#define MAX_FIXED_PEBS_EVENTS 3 +#define MAX_FIXED_PEBS_EVENTS 4 /* * A debug store configuration. diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ca5bc0eacb95..1378518cf63f 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -116,6 +116,7 @@ #define LBR_INFO_CYCLES 0xffff #define MSR_IA32_PEBS_ENABLE 0x000003f1 +#define MSR_PEBS_DATA_CFG 0x000003f2 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8bdf74902293..1392d5e6e8d6 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -7,7 +7,7 @@ */ #define INTEL_PMC_MAX_GENERIC 32 -#define INTEL_PMC_MAX_FIXED 3 +#define INTEL_PMC_MAX_FIXED 4 #define INTEL_PMC_IDX_FIXED 32 #define X86_PMC_IDX_MAX 64 @@ -32,6 +32,8 @@ #define HSW_IN_TX (1ULL << 32) #define HSW_IN_TX_CHECKPOINTED (1ULL << 33) +#define ICL_EVENTSEL_ADAPTIVE (1ULL << 34) +#define ICL_FIXED_0_ADAPTIVE (1ULL << 32) #define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36) #define AMD64_EVENTSEL_GUESTONLY (1ULL << 40) @@ -87,6 +89,12 @@ #define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6 #define ARCH_PERFMON_EVENTS_COUNT 7 +#define PEBS_DATACFG_MEMINFO BIT_ULL(0) +#define PEBS_DATACFG_GP BIT_ULL(1) +#define PEBS_DATACFG_XMMS BIT_ULL(2) +#define PEBS_DATACFG_LBRS BIT_ULL(3) +#define PEBS_DATACFG_LBR_SHIFT 24 + /* * Intel "Architectural Performance Monitoring" CPUID * detection/enumeration details: @@ -177,6 +185,41 @@ struct x86_pmu_capability { #define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55) /* + * Adaptive PEBS v4 + */ + +struct pebs_basic { + u64 format_size; + u64 ip; + u64 applicable_counters; + u64 tsc; +}; + +struct pebs_meminfo { + u64 address; + u64 aux; + u64 latency; + u64 tsx_tuning; +}; + +struct pebs_gprs { + u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di; + u64 r8, r9, r10, r11, r12, r13, r14, r15; +}; + +struct pebs_xmm { + u64 xmm[16*2]; /* two entries for each register */ +}; + +struct pebs_lbr_entry { + u64 from, to, info; +}; + +struct pebs_lbr { + struct pebs_lbr_entry lbr[0]; /* Variable length */ +}; + +/* * IBS cpuid feature detection */ @@ -248,6 +291,11 @@ extern void perf_events_lapic_init(void); #define PERF_EFLAGS_VM (1UL << 5) struct pt_regs; +struct x86_perf_regs { + struct pt_regs regs; + u64 *xmm_regs; +}; + extern unsigned long perf_instruction_pointer(struct pt_regs *regs); extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_misc_flags(regs) perf_misc_flags(regs) @@ -260,14 +308,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); */ #define perf_arch_fetch_caller_regs(regs, __ip) { \ (regs)->ip = (__ip); \ - (regs)->bp = caller_frame_pointer(); \ + (regs)->sp = (unsigned long)__builtin_frame_address(0); \ (regs)->cs = __KERNEL_CS; \ regs->flags = 0; \ - asm volatile( \ - _ASM_MOV "%%"_ASM_SP ", %0\n" \ - : "=m" ((regs)->sp) \ - :: "memory" \ - ); \ } struct perf_guest_switch_msr { diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index f335aad404a4..beef7ad9e43a 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -98,19 +98,6 @@ struct stack_frame_ia32 { u32 return_address; }; -static inline unsigned long caller_frame_pointer(void) -{ - struct stack_frame *frame; - - frame = __builtin_frame_address(0); - -#ifdef CONFIG_FRAME_POINTER - frame = frame->next_frame; -#endif - - return (unsigned long)frame; -} - void show_opcodes(struct pt_regs *regs, const char *loglvl); void show_ip(struct pt_regs *regs, const char *loglvl); #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h index f3329cabce5c..ac67bbea10ca 100644 --- a/arch/x86/include/uapi/asm/perf_regs.h +++ b/arch/x86/include/uapi/asm/perf_regs.h @@ -27,8 +27,29 @@ enum perf_event_x86_regs { PERF_REG_X86_R13, PERF_REG_X86_R14, PERF_REG_X86_R15, - + /* These are the limits for the GPRs. */ PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1, PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1, + + /* These all need two bits set because they are 128bit */ + PERF_REG_X86_XMM0 = 32, + PERF_REG_X86_XMM1 = 34, + PERF_REG_X86_XMM2 = 36, + PERF_REG_X86_XMM3 = 38, + PERF_REG_X86_XMM4 = 40, + PERF_REG_X86_XMM5 = 42, + PERF_REG_X86_XMM6 = 44, + PERF_REG_X86_XMM7 = 46, + PERF_REG_X86_XMM8 = 48, + PERF_REG_X86_XMM9 = 50, + PERF_REG_X86_XMM10 = 52, + PERF_REG_X86_XMM11 = 54, + PERF_REG_X86_XMM12 = 56, + PERF_REG_X86_XMM13 = 58, + PERF_REG_X86_XMM14 = 60, + PERF_REG_X86_XMM15 = 62, + + /* These include both GPRs and XMMX registers */ + PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2, }; #endif /* _ASM_X86_PERF_REGS_H */ diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index c06c4c16c6b6..07c30ee17425 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -59,18 +59,34 @@ static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = { u64 perf_reg_value(struct pt_regs *regs, int idx) { + struct x86_perf_regs *perf_regs; + + if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) { + perf_regs = container_of(regs, struct x86_perf_regs, regs); + if (!perf_regs->xmm_regs) + return 0; + return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0]; + } + if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset))) return 0; return regs_get_register(regs, pt_regs_offset[idx]); } -#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL)) - #ifdef CONFIG_X86_32 +#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \ + (1ULL << PERF_REG_X86_R9) | \ + (1ULL << PERF_REG_X86_R10) | \ + (1ULL << PERF_REG_X86_R11) | \ + (1ULL << PERF_REG_X86_R12) | \ + (1ULL << PERF_REG_X86_R13) | \ + (1ULL << PERF_REG_X86_R14) | \ + (1ULL << PERF_REG_X86_R15)) + int perf_reg_validate(u64 mask) { - if (!mask || mask & REG_RESERVED) + if (!mask || (mask & REG_NOSUPPORT)) return -EINVAL; return 0; @@ -96,10 +112,7 @@ void perf_get_regs_user(struct perf_regs *regs_user, int perf_reg_validate(u64 mask) { - if (!mask || mask & REG_RESERVED) - return -EINVAL; - - if (mask & REG_NOSUPPORT) + if (!mask || (mask & REG_NOSUPPORT)) return -EINVAL; return 0; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1f678f023850..15a82ff0aefe 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -463,7 +463,7 @@ enum perf_addr_filter_action_t { /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage - * @inode: object file's inode for file-based filters + * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop @@ -887,6 +887,9 @@ extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); + +extern void perf_pmu_resched(struct pmu *pmu); + extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); @@ -1054,12 +1057,18 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo #endif /* - * Take a snapshot of the regs. Skip ip and frame pointer to - * the nth caller. We only need a few of the regs: + * When generating a perf sample in-line, instead of from an interrupt / + * exception, we lack a pt_regs. This is typically used from software events + * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. + * + * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests - * - bp for callchains - * - eflags, for future purposes, just in case + * - sp for PERF_SAMPLE_CALLCHAIN + * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) + * + * NOTE: assumes @regs is otherwise already 0 filled; this is important for + * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { diff --git a/kernel/events/core.c b/kernel/events/core.c index dc7dead2d2cc..abbd4b3b96c2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2478,6 +2478,16 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, perf_pmu_enable(cpuctx->ctx.pmu); } +void perf_pmu_resched(struct pmu *pmu) +{ + struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + struct perf_event_context *task_ctx = cpuctx->task_ctx; + + perf_ctx_lock(cpuctx, task_ctx); + ctx_resched(cpuctx, task_ctx, EVENT_ALL|EVENT_CPU); + perf_ctx_unlock(cpuctx, task_ctx); +} + /* * Cross CPU call to install and enable a performance event * @@ -11917,7 +11927,7 @@ static void __init perf_event_init_all_cpus(void) } } -void perf_swevent_init_cpu(unsigned int cpu) +static void perf_swevent_init_cpu(unsigned int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 6a5787233113..7f9e7b9306fe 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -590,7 +590,7 @@ static void lockup_detector_reconfigure(void) * Create the watchdog thread infrastructure and configure the detector(s). * * The threads are not unparked as watchdog_allowed_mask is empty. When - * the threads are sucessfully initialized, take the proper locks and + * the threads are successfully initialized, take the proper locks and * unpark the threads in the watchdog_cpumask if the watchdog is enabled. */ static __init void lockup_detector_setup(void) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 8d3864b061f3..361207387b1b 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -67,6 +67,7 @@ FEATURE_TESTS_BASIC := \ sdt \ setns \ libaio \ + libzstd \ disassembler-four-args # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list @@ -120,6 +121,7 @@ FEATURE_DISPLAY ?= \ get_cpuid \ bpf \ libaio \ + libzstd \ disassembler-four-args # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features. diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 7ceb4441b627..4b8244ee65ce 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -62,7 +62,8 @@ FILES= \ test-clang.bin \ test-llvm.bin \ test-llvm-version.bin \ - test-libaio.bin + test-libaio.bin \ + test-libzstd.bin FILES := $(addprefix $(OUTPUT),$(FILES)) @@ -301,6 +302,9 @@ $(OUTPUT)test-clang.bin: $(OUTPUT)test-libaio.bin: $(BUILD) -lrt +$(OUTPUT)test-libzstd.bin: + $(BUILD) -lzstd + ############################### clean: diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 7853e6d91090..a59c53705093 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -182,6 +182,10 @@ # include "test-disassembler-four-args.c" #undef main +#define main main_test_zstd +# include "test-libzstd.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -224,6 +228,7 @@ int main(int argc, char *argv[]) main_test_libaio(); main_test_reallocarray(); main_test_disassembler_four_args(); + main_test_libzstd(); return 0; } diff --git a/tools/build/feature/test-libzstd.c b/tools/build/feature/test-libzstd.c new file mode 100644 index 000000000000..55268c01b84d --- /dev/null +++ b/tools/build/feature/test-libzstd.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <zstd.h> + +int main(void) +{ + ZSTD_CStream *cstream; + + cstream = ZSTD_createCStream(); + ZSTD_freeCStream(cstream); + + return 0; +} diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c index d463761a58f4..988587840c80 100644 --- a/tools/lib/traceevent/event-parse-api.c +++ b/tools/lib/traceevent/event-parse-api.c @@ -9,6 +9,22 @@ #include "event-utils.h" /** + * tep_get_event - returns the event with the given index + * @tep: a handle to the tep_handle + * @index: index of the requested event, in the range 0 .. nr_events + * + * This returns pointer to the element of the events array with the given index + * If @tep is NULL, or @index is not in the range 0 .. nr_events, NULL is returned. + */ +struct tep_event *tep_get_event(struct tep_handle *tep, int index) +{ + if (tep && tep->events && index < tep->nr_events) + return tep->events[index]; + + return NULL; +} + +/** * tep_get_first_event - returns the first event in the events array * @tep: a handle to the tep_handle * @@ -17,10 +33,7 @@ */ struct tep_event *tep_get_first_event(struct tep_handle *tep) { - if (tep && tep->events) - return tep->events[0]; - - return NULL; + return tep_get_event(tep, 0); } /** @@ -32,7 +45,7 @@ struct tep_event *tep_get_first_event(struct tep_handle *tep) */ int tep_get_events_count(struct tep_handle *tep) { - if(tep) + if (tep) return tep->nr_events; return 0; } @@ -43,19 +56,47 @@ int tep_get_events_count(struct tep_handle *tep) * @flag: flag, or combination of flags to be set * can be any combination from enum tep_flag * - * This sets a flag or mbination of flags from enum tep_flag - */ + * This sets a flag or combination of flags from enum tep_flag + */ void tep_set_flag(struct tep_handle *tep, int flag) { - if(tep) + if (tep) tep->flags |= flag; } -unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data) +/** + * tep_clear_flag - clear event parser flag + * @tep: a handle to the tep_handle + * @flag: flag to be cleared + * + * This clears a tep flag + */ +void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag) +{ + if (tep) + tep->flags &= ~flag; +} + +/** + * tep_test_flag - check the state of event parser flag + * @tep: a handle to the tep_handle + * @flag: flag to be checked + * + * This returns the state of the requested tep flag. + * Returns: true if the flag is set, false otherwise. + */ +bool tep_test_flag(struct tep_handle *tep, enum tep_flag flag) +{ + if (tep) + return tep->flags & flag; + return false; +} + +unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data) { unsigned short swap; - if (!pevent || pevent->host_bigendian == pevent->file_bigendian) + if (!tep || tep->host_bigendian == tep->file_bigendian) return data; swap = ((data & 0xffULL) << 8) | @@ -64,11 +105,11 @@ unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data) return swap; } -unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data) +unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data) { unsigned int swap; - if (!pevent || pevent->host_bigendian == pevent->file_bigendian) + if (!tep || tep->host_bigendian == tep->file_bigendian) return data; swap = ((data & 0xffULL) << 24) | @@ -80,11 +121,11 @@ unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data) } unsigned long long -tep_data2host8(struct tep_handle *pevent, unsigned long long data) +tep_data2host8(struct tep_handle *tep, unsigned long long data) { unsigned long long swap; - if (!pevent || pevent->host_bigendian == pevent->file_bigendian) + if (!tep || tep->host_bigendian == tep->file_bigendian) return data; swap = ((data & 0xffULL) << 56) | @@ -101,175 +142,232 @@ tep_data2host8(struct tep_handle *pevent, unsigned long long data) /** * tep_get_header_page_size - get size of the header page - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * * This returns size of the header page - * If @pevent is NULL, 0 is returned. + * If @tep is NULL, 0 is returned. + */ +int tep_get_header_page_size(struct tep_handle *tep) +{ + if (tep) + return tep->header_page_size_size; + return 0; +} + +/** + * tep_get_header_timestamp_size - get size of the timestamp in the header page + * @tep: a handle to the tep_handle + * + * This returns size of the timestamp in the header page + * If @tep is NULL, 0 is returned. */ -int tep_get_header_page_size(struct tep_handle *pevent) +int tep_get_header_timestamp_size(struct tep_handle *tep) { - if(pevent) - return pevent->header_page_size_size; + if (tep) + return tep->header_page_ts_size; return 0; } /** * tep_get_cpus - get the number of CPUs - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * * This returns the number of CPUs - * If @pevent is NULL, 0 is returned. + * If @tep is NULL, 0 is returned. */ -int tep_get_cpus(struct tep_handle *pevent) +int tep_get_cpus(struct tep_handle *tep) { - if(pevent) - return pevent->cpus; + if (tep) + return tep->cpus; return 0; } /** * tep_set_cpus - set the number of CPUs - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * * This sets the number of CPUs */ -void tep_set_cpus(struct tep_handle *pevent, int cpus) +void tep_set_cpus(struct tep_handle *tep, int cpus) { - if(pevent) - pevent->cpus = cpus; + if (tep) + tep->cpus = cpus; } /** - * tep_get_long_size - get the size of a long integer on the current machine - * @pevent: a handle to the tep_handle + * tep_get_long_size - get the size of a long integer on the traced machine + * @tep: a handle to the tep_handle * - * This returns the size of a long integer on the current machine - * If @pevent is NULL, 0 is returned. + * This returns the size of a long integer on the traced machine + * If @tep is NULL, 0 is returned. */ -int tep_get_long_size(struct tep_handle *pevent) +int tep_get_long_size(struct tep_handle *tep) { - if(pevent) - return pevent->long_size; + if (tep) + return tep->long_size; return 0; } /** - * tep_set_long_size - set the size of a long integer on the current machine - * @pevent: a handle to the tep_handle + * tep_set_long_size - set the size of a long integer on the traced machine + * @tep: a handle to the tep_handle * @size: size, in bytes, of a long integer * - * This sets the size of a long integer on the current machine + * This sets the size of a long integer on the traced machine */ -void tep_set_long_size(struct tep_handle *pevent, int long_size) +void tep_set_long_size(struct tep_handle *tep, int long_size) { - if(pevent) - pevent->long_size = long_size; + if (tep) + tep->long_size = long_size; } /** - * tep_get_page_size - get the size of a memory page on the current machine - * @pevent: a handle to the tep_handle + * tep_get_page_size - get the size of a memory page on the traced machine + * @tep: a handle to the tep_handle * - * This returns the size of a memory page on the current machine - * If @pevent is NULL, 0 is returned. + * This returns the size of a memory page on the traced machine + * If @tep is NULL, 0 is returned. */ -int tep_get_page_size(struct tep_handle *pevent) +int tep_get_page_size(struct tep_handle *tep) { - if(pevent) - return pevent->page_size; + if (tep) + return tep->page_size; return 0; } /** - * tep_set_page_size - set the size of a memory page on the current machine - * @pevent: a handle to the tep_handle + * tep_set_page_size - set the size of a memory page on the traced machine + * @tep: a handle to the tep_handle * @_page_size: size of a memory page, in bytes * - * This sets the size of a memory page on the current machine + * This sets the size of a memory page on the traced machine */ -void tep_set_page_size(struct tep_handle *pevent, int _page_size) +void tep_set_page_size(struct tep_handle *tep, int _page_size) { - if(pevent) - pevent->page_size = _page_size; + if (tep) + tep->page_size = _page_size; } /** - * tep_file_bigendian - get if the file is in big endian order - * @pevent: a handle to the tep_handle + * tep_is_file_bigendian - return the endian of the file + * @tep: a handle to the tep_handle * - * This returns if the file is in big endian order - * If @pevent is NULL, 0 is returned. + * This returns true if the file is in big endian order + * If @tep is NULL, false is returned. */ -int tep_file_bigendian(struct tep_handle *pevent) +bool tep_is_file_bigendian(struct tep_handle *tep) { - if(pevent) - return pevent->file_bigendian; - return 0; + if (tep) + return (tep->file_bigendian == TEP_BIG_ENDIAN); + return false; } /** * tep_set_file_bigendian - set if the file is in big endian order - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * @endian: non zero, if the file is in big endian order * * This sets if the file is in big endian order */ -void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian) +void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian) { - if(pevent) - pevent->file_bigendian = endian; + if (tep) + tep->file_bigendian = endian; } /** - * tep_is_host_bigendian - get if the order of the current host is big endian - * @pevent: a handle to the tep_handle + * tep_is_local_bigendian - return the endian of the saved local machine + * @tep: a handle to the tep_handle * - * This gets if the order of the current host is big endian - * If @pevent is NULL, 0 is returned. + * This returns true if the saved local machine in @tep is big endian. + * If @tep is NULL, false is returned. */ -int tep_is_host_bigendian(struct tep_handle *pevent) +bool tep_is_local_bigendian(struct tep_handle *tep) { - if(pevent) - return pevent->host_bigendian; + if (tep) + return (tep->host_bigendian == TEP_BIG_ENDIAN); return 0; } /** - * tep_set_host_bigendian - set the order of the local host - * @pevent: a handle to the tep_handle + * tep_set_local_bigendian - set the stored local machine endian order + * @tep: a handle to the tep_handle * @endian: non zero, if the local host has big endian order * - * This sets the order of the local host + * This sets the endian order for the local machine. */ -void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian) +void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian) { - if(pevent) - pevent->host_bigendian = endian; + if (tep) + tep->host_bigendian = endian; } /** * tep_is_latency_format - get if the latency output format is configured - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * - * This gets if the latency output format is configured - * If @pevent is NULL, 0 is returned. + * This returns true if the latency output format is configured + * If @tep is NULL, false is returned. */ -int tep_is_latency_format(struct tep_handle *pevent) +bool tep_is_latency_format(struct tep_handle *tep) { - if(pevent) - return pevent->latency_format; - return 0; + if (tep) + return (tep->latency_format); + return false; } /** * tep_set_latency_format - set the latency output format - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * @lat: non zero for latency output format * * This sets the latency output format */ -void tep_set_latency_format(struct tep_handle *pevent, int lat) +void tep_set_latency_format(struct tep_handle *tep, int lat) +{ + if (tep) + tep->latency_format = lat; +} + +/** + * tep_is_old_format - get if an old kernel is used + * @tep: a handle to the tep_handle + * + * This returns true, if an old kernel is used to generate the tracing events or + * false if a new kernel is used. Old kernels did not have header page info. + * If @tep is NULL, false is returned. + */ +bool tep_is_old_format(struct tep_handle *tep) +{ + if (tep) + return tep->old_format; + return false; +} + +/** + * tep_set_print_raw - set a flag to force print in raw format + * @tep: a handle to the tep_handle + * @print_raw: the new value of the print_raw flag + * + * This sets a flag to force print in raw format + */ +void tep_set_print_raw(struct tep_handle *tep, int print_raw) +{ + if (tep) + tep->print_raw = print_raw; +} + +/** + * tep_set_test_filters - set a flag to test a filter string + * @tep: a handle to the tep_handle + * @test_filters: the new value of the test_filters flag + * + * This sets a flag to test a filter string. If this flag is set, when + * tep_filter_add_filter_str() API as called,it will print the filter string + * instead of adding it. + */ +void tep_set_test_filters(struct tep_handle *tep, int test_filters) { - if(pevent) - pevent->latency_format = lat; + if (tep) + tep->test_filters = test_filters; } diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h index 35833ee32d6c..09aa142f7fdd 100644 --- a/tools/lib/traceevent/event-parse-local.h +++ b/tools/lib/traceevent/event-parse-local.h @@ -92,8 +92,8 @@ struct tep_handle { void tep_free_event(struct tep_event *event); void tep_free_format_field(struct tep_format_field *field); -unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data); -unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data); -unsigned long long tep_data2host8(struct tep_handle *pevent, unsigned long long data); +unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data); +unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data); +unsigned long long tep_data2host8(struct tep_handle *tep, unsigned long long data); #endif /* _PARSE_EVENTS_INT_H */ diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 981c6ce2da2c..b36b536a9fcb 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -148,14 +148,14 @@ struct cmdline_list { int pid; }; -static int cmdline_init(struct tep_handle *pevent) +static int cmdline_init(struct tep_handle *tep) { - struct cmdline_list *cmdlist = pevent->cmdlist; + struct cmdline_list *cmdlist = tep->cmdlist; struct cmdline_list *item; struct tep_cmdline *cmdlines; int i; - cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count); + cmdlines = malloc(sizeof(*cmdlines) * tep->cmdline_count); if (!cmdlines) return -1; @@ -169,15 +169,15 @@ static int cmdline_init(struct tep_handle *pevent) free(item); } - qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp); + qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp); - pevent->cmdlines = cmdlines; - pevent->cmdlist = NULL; + tep->cmdlines = cmdlines; + tep->cmdlist = NULL; return 0; } -static const char *find_cmdline(struct tep_handle *pevent, int pid) +static const char *find_cmdline(struct tep_handle *tep, int pid) { const struct tep_cmdline *comm; struct tep_cmdline key; @@ -185,13 +185,13 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid) if (!pid) return "<idle>"; - if (!pevent->cmdlines && cmdline_init(pevent)) + if (!tep->cmdlines && cmdline_init(tep)) return "<not enough memory for cmdlines!>"; key.pid = pid; - comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count, - sizeof(*pevent->cmdlines), cmdline_cmp); + comm = bsearch(&key, tep->cmdlines, tep->cmdline_count, + sizeof(*tep->cmdlines), cmdline_cmp); if (comm) return comm->comm; @@ -199,32 +199,32 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid) } /** - * tep_pid_is_registered - return if a pid has a cmdline registered - * @pevent: handle for the pevent + * tep_is_pid_registered - return if a pid has a cmdline registered + * @tep: a handle to the trace event parser context * @pid: The pid to check if it has a cmdline registered with. * - * Returns 1 if the pid has a cmdline mapped to it - * 0 otherwise. + * Returns true if the pid has a cmdline mapped to it + * false otherwise. */ -int tep_pid_is_registered(struct tep_handle *pevent, int pid) +bool tep_is_pid_registered(struct tep_handle *tep, int pid) { const struct tep_cmdline *comm; struct tep_cmdline key; if (!pid) - return 1; + return true; - if (!pevent->cmdlines && cmdline_init(pevent)) - return 0; + if (!tep->cmdlines && cmdline_init(tep)) + return false; key.pid = pid; - comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count, - sizeof(*pevent->cmdlines), cmdline_cmp); + comm = bsearch(&key, tep->cmdlines, tep->cmdline_count, + sizeof(*tep->cmdlines), cmdline_cmp); if (comm) - return 1; - return 0; + return true; + return false; } /* @@ -232,10 +232,10 @@ int tep_pid_is_registered(struct tep_handle *pevent, int pid) * we must add this pid. This is much slower than when cmdlines * are added before the array is initialized. */ -static int add_new_comm(struct tep_handle *pevent, +static int add_new_comm(struct tep_handle *tep, const char *comm, int pid, bool override) { - struct tep_cmdline *cmdlines = pevent->cmdlines; + struct tep_cmdline *cmdlines = tep->cmdlines; struct tep_cmdline *cmdline; struct tep_cmdline key; char *new_comm; @@ -246,8 +246,8 @@ static int add_new_comm(struct tep_handle *pevent, /* avoid duplicates */ key.pid = pid; - cmdline = bsearch(&key, pevent->cmdlines, pevent->cmdline_count, - sizeof(*pevent->cmdlines), cmdline_cmp); + cmdline = bsearch(&key, tep->cmdlines, tep->cmdline_count, + sizeof(*tep->cmdlines), cmdline_cmp); if (cmdline) { if (!override) { errno = EEXIST; @@ -264,37 +264,37 @@ static int add_new_comm(struct tep_handle *pevent, return 0; } - cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (pevent->cmdline_count + 1)); + cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (tep->cmdline_count + 1)); if (!cmdlines) { errno = ENOMEM; return -1; } - cmdlines[pevent->cmdline_count].comm = strdup(comm); - if (!cmdlines[pevent->cmdline_count].comm) { + cmdlines[tep->cmdline_count].comm = strdup(comm); + if (!cmdlines[tep->cmdline_count].comm) { free(cmdlines); errno = ENOMEM; return -1; } - cmdlines[pevent->cmdline_count].pid = pid; + cmdlines[tep->cmdline_count].pid = pid; - if (cmdlines[pevent->cmdline_count].comm) - pevent->cmdline_count++; + if (cmdlines[tep->cmdline_count].comm) + tep->cmdline_count++; - qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp); - pevent->cmdlines = cmdlines; + qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp); + tep->cmdlines = cmdlines; return 0; } -static int _tep_register_comm(struct tep_handle *pevent, +static int _tep_register_comm(struct tep_handle *tep, const char *comm, int pid, bool override) { struct cmdline_list *item; - if (pevent->cmdlines) - return add_new_comm(pevent, comm, pid, override); + if (tep->cmdlines) + return add_new_comm(tep, comm, pid, override); item = malloc(sizeof(*item)); if (!item) @@ -309,17 +309,17 @@ static int _tep_register_comm(struct tep_handle *pevent, return -1; } item->pid = pid; - item->next = pevent->cmdlist; + item->next = tep->cmdlist; - pevent->cmdlist = item; - pevent->cmdline_count++; + tep->cmdlist = item; + tep->cmdline_count++; return 0; } /** * tep_register_comm - register a pid / comm mapping - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @comm: the command line to register * @pid: the pid to map the command line to * @@ -327,14 +327,14 @@ static int _tep_register_comm(struct tep_handle *pevent, * a given pid. The comm is duplicated. If a command with the same pid * already exist, -1 is returned and errno is set to EEXIST */ -int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid) +int tep_register_comm(struct tep_handle *tep, const char *comm, int pid) { - return _tep_register_comm(pevent, comm, pid, false); + return _tep_register_comm(tep, comm, pid, false); } /** * tep_override_comm - register a pid / comm mapping - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @comm: the command line to register * @pid: the pid to map the command line to * @@ -342,19 +342,19 @@ int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid) * a given pid. The comm is duplicated. If a command with the same pid * already exist, the command string is udapted with the new one */ -int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid) +int tep_override_comm(struct tep_handle *tep, const char *comm, int pid) { - if (!pevent->cmdlines && cmdline_init(pevent)) { + if (!tep->cmdlines && cmdline_init(tep)) { errno = ENOMEM; return -1; } - return _tep_register_comm(pevent, comm, pid, true); + return _tep_register_comm(tep, comm, pid, true); } -int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock) +int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock) { - pevent->trace_clock = strdup(trace_clock); - if (!pevent->trace_clock) { + tep->trace_clock = strdup(trace_clock); + if (!tep->trace_clock) { errno = ENOMEM; return -1; } @@ -408,18 +408,18 @@ static int func_bcmp(const void *a, const void *b) return 1; } -static int func_map_init(struct tep_handle *pevent) +static int func_map_init(struct tep_handle *tep) { struct func_list *funclist; struct func_list *item; struct func_map *func_map; int i; - func_map = malloc(sizeof(*func_map) * (pevent->func_count + 1)); + func_map = malloc(sizeof(*func_map) * (tep->func_count + 1)); if (!func_map) return -1; - funclist = pevent->funclist; + funclist = tep->funclist; i = 0; while (funclist) { @@ -432,34 +432,34 @@ static int func_map_init(struct tep_handle *pevent) free(item); } - qsort(func_map, pevent->func_count, sizeof(*func_map), func_cmp); + qsort(func_map, tep->func_count, sizeof(*func_map), func_cmp); /* * Add a special record at the end. */ - func_map[pevent->func_count].func = NULL; - func_map[pevent->func_count].addr = 0; - func_map[pevent->func_count].mod = NULL; + func_map[tep->func_count].func = NULL; + func_map[tep->func_count].addr = 0; + func_map[tep->func_count].mod = NULL; - pevent->func_map = func_map; - pevent->funclist = NULL; + tep->func_map = func_map; + tep->funclist = NULL; return 0; } static struct func_map * -__find_func(struct tep_handle *pevent, unsigned long long addr) +__find_func(struct tep_handle *tep, unsigned long long addr) { struct func_map *func; struct func_map key; - if (!pevent->func_map) - func_map_init(pevent); + if (!tep->func_map) + func_map_init(tep); key.addr = addr; - func = bsearch(&key, pevent->func_map, pevent->func_count, - sizeof(*pevent->func_map), func_bcmp); + func = bsearch(&key, tep->func_map, tep->func_count, + sizeof(*tep->func_map), func_bcmp); return func; } @@ -472,15 +472,14 @@ struct func_resolver { /** * tep_set_function_resolver - set an alternative function resolver - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @resolver: function to be used * @priv: resolver function private state. * * Some tools may have already a way to resolve kernel functions, allow them to - * keep using it instead of duplicating all the entries inside - * pevent->funclist. + * keep using it instead of duplicating all the entries inside tep->funclist. */ -int tep_set_function_resolver(struct tep_handle *pevent, +int tep_set_function_resolver(struct tep_handle *tep, tep_func_resolver_t *func, void *priv) { struct func_resolver *resolver = malloc(sizeof(*resolver)); @@ -491,38 +490,38 @@ int tep_set_function_resolver(struct tep_handle *pevent, resolver->func = func; resolver->priv = priv; - free(pevent->func_resolver); - pevent->func_resolver = resolver; + free(tep->func_resolver); + tep->func_resolver = resolver; return 0; } /** * tep_reset_function_resolver - reset alternative function resolver - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * * Stop using whatever alternative resolver was set, use the default * one instead. */ -void tep_reset_function_resolver(struct tep_handle *pevent) +void tep_reset_function_resolver(struct tep_handle *tep) { - free(pevent->func_resolver); - pevent->func_resolver = NULL; + free(tep->func_resolver); + tep->func_resolver = NULL; } static struct func_map * -find_func(struct tep_handle *pevent, unsigned long long addr) +find_func(struct tep_handle *tep, unsigned long long addr) { struct func_map *map; - if (!pevent->func_resolver) - return __find_func(pevent, addr); + if (!tep->func_resolver) + return __find_func(tep, addr); - map = &pevent->func_resolver->map; + map = &tep->func_resolver->map; map->mod = NULL; map->addr = addr; - map->func = pevent->func_resolver->func(pevent->func_resolver->priv, - &map->addr, &map->mod); + map->func = tep->func_resolver->func(tep->func_resolver->priv, + &map->addr, &map->mod); if (map->func == NULL) return NULL; @@ -531,18 +530,18 @@ find_func(struct tep_handle *pevent, unsigned long long addr) /** * tep_find_function - find a function by a given address - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @addr: the address to find the function with * * Returns a pointer to the function stored that has the given * address. Note, the address does not have to be exact, it * will select the function that would contain the address. */ -const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr) +const char *tep_find_function(struct tep_handle *tep, unsigned long long addr) { struct func_map *map; - map = find_func(pevent, addr); + map = find_func(tep, addr); if (!map) return NULL; @@ -551,7 +550,7 @@ const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr /** * tep_find_function_address - find a function address by a given address - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @addr: the address to find the function with * * Returns the address the function starts at. This can be used in @@ -559,11 +558,11 @@ const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr * name and the function offset. */ unsigned long long -tep_find_function_address(struct tep_handle *pevent, unsigned long long addr) +tep_find_function_address(struct tep_handle *tep, unsigned long long addr) { struct func_map *map; - map = find_func(pevent, addr); + map = find_func(tep, addr); if (!map) return 0; @@ -572,7 +571,7 @@ tep_find_function_address(struct tep_handle *pevent, unsigned long long addr) /** * tep_register_function - register a function with a given address - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @function: the function name to register * @addr: the address the function starts at * @mod: the kernel module the function may be in (NULL for none) @@ -580,7 +579,7 @@ tep_find_function_address(struct tep_handle *pevent, unsigned long long addr) * This registers a function name with an address and module. * The @func passed in is duplicated. */ -int tep_register_function(struct tep_handle *pevent, char *func, +int tep_register_function(struct tep_handle *tep, char *func, unsigned long long addr, char *mod) { struct func_list *item = malloc(sizeof(*item)); @@ -588,7 +587,7 @@ int tep_register_function(struct tep_handle *pevent, char *func, if (!item) return -1; - item->next = pevent->funclist; + item->next = tep->funclist; item->func = strdup(func); if (!item->func) goto out_free; @@ -601,8 +600,8 @@ int tep_register_function(struct tep_handle *pevent, char *func, item->mod = NULL; item->addr = addr; - pevent->funclist = item; - pevent->func_count++; + tep->funclist = item; + tep->func_count++; return 0; @@ -617,23 +616,23 @@ out_free: /** * tep_print_funcs - print out the stored functions - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * * This prints out the stored functions. */ -void tep_print_funcs(struct tep_handle *pevent) +void tep_print_funcs(struct tep_handle *tep) { int i; - if (!pevent->func_map) - func_map_init(pevent); + if (!tep->func_map) + func_map_init(tep); - for (i = 0; i < (int)pevent->func_count; i++) { + for (i = 0; i < (int)tep->func_count; i++) { printf("%016llx %s", - pevent->func_map[i].addr, - pevent->func_map[i].func); - if (pevent->func_map[i].mod) - printf(" [%s]\n", pevent->func_map[i].mod); + tep->func_map[i].addr, + tep->func_map[i].func); + if (tep->func_map[i].mod) + printf(" [%s]\n", tep->func_map[i].mod); else printf("\n"); } @@ -663,18 +662,18 @@ static int printk_cmp(const void *a, const void *b) return 0; } -static int printk_map_init(struct tep_handle *pevent) +static int printk_map_init(struct tep_handle *tep) { struct printk_list *printklist; struct printk_list *item; struct printk_map *printk_map; int i; - printk_map = malloc(sizeof(*printk_map) * (pevent->printk_count + 1)); + printk_map = malloc(sizeof(*printk_map) * (tep->printk_count + 1)); if (!printk_map) return -1; - printklist = pevent->printklist; + printklist = tep->printklist; i = 0; while (printklist) { @@ -686,41 +685,41 @@ static int printk_map_init(struct tep_handle *pevent) free(item); } - qsort(printk_map, pevent->printk_count, sizeof(*printk_map), printk_cmp); + qsort(printk_map, tep->printk_count, sizeof(*printk_map), printk_cmp); - pevent->printk_map = printk_map; - pevent->printklist = NULL; + tep->printk_map = printk_map; + tep->printklist = NULL; return 0; } static struct printk_map * -find_printk(struct tep_handle *pevent, unsigned long long addr) +find_printk(struct tep_handle *tep, unsigned long long addr) { struct printk_map *printk; struct printk_map key; - if (!pevent->printk_map && printk_map_init(pevent)) + if (!tep->printk_map && printk_map_init(tep)) return NULL; key.addr = addr; - printk = bsearch(&key, pevent->printk_map, pevent->printk_count, - sizeof(*pevent->printk_map), printk_cmp); + printk = bsearch(&key, tep->printk_map, tep->printk_count, + sizeof(*tep->printk_map), printk_cmp); return printk; } /** * tep_register_print_string - register a string by its address - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @fmt: the string format to register * @addr: the address the string was located at * * This registers a string by the address it was stored in the kernel. * The @fmt passed in is duplicated. */ -int tep_register_print_string(struct tep_handle *pevent, const char *fmt, +int tep_register_print_string(struct tep_handle *tep, const char *fmt, unsigned long long addr) { struct printk_list *item = malloc(sizeof(*item)); @@ -729,7 +728,7 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt, if (!item) return -1; - item->next = pevent->printklist; + item->next = tep->printklist; item->addr = addr; /* Strip off quotes and '\n' from the end */ @@ -747,8 +746,8 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt, if (strcmp(p, "\\n") == 0) *p = 0; - pevent->printklist = item; - pevent->printk_count++; + tep->printklist = item; + tep->printk_count++; return 0; @@ -760,21 +759,21 @@ out_free: /** * tep_print_printk - print out the stored strings - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * * This prints the string formats that were stored. */ -void tep_print_printk(struct tep_handle *pevent) +void tep_print_printk(struct tep_handle *tep) { int i; - if (!pevent->printk_map) - printk_map_init(pevent); + if (!tep->printk_map) + printk_map_init(tep); - for (i = 0; i < (int)pevent->printk_count; i++) { + for (i = 0; i < (int)tep->printk_count; i++) { printf("%016llx %s\n", - pevent->printk_map[i].addr, - pevent->printk_map[i].printk); + tep->printk_map[i].addr, + tep->printk_map[i].printk); } } @@ -783,29 +782,29 @@ static struct tep_event *alloc_event(void) return calloc(1, sizeof(struct tep_event)); } -static int add_event(struct tep_handle *pevent, struct tep_event *event) +static int add_event(struct tep_handle *tep, struct tep_event *event) { int i; - struct tep_event **events = realloc(pevent->events, sizeof(event) * - (pevent->nr_events + 1)); + struct tep_event **events = realloc(tep->events, sizeof(event) * + (tep->nr_events + 1)); if (!events) return -1; - pevent->events = events; + tep->events = events; - for (i = 0; i < pevent->nr_events; i++) { - if (pevent->events[i]->id > event->id) + for (i = 0; i < tep->nr_events; i++) { + if (tep->events[i]->id > event->id) break; } - if (i < pevent->nr_events) - memmove(&pevent->events[i + 1], - &pevent->events[i], - sizeof(event) * (pevent->nr_events - i)); + if (i < tep->nr_events) + memmove(&tep->events[i + 1], + &tep->events[i], + sizeof(event) * (tep->nr_events - i)); - pevent->events[i] = event; - pevent->nr_events++; + tep->events[i] = event; + tep->nr_events++; - event->pevent = pevent; + event->tep = tep; return 0; } @@ -1184,7 +1183,7 @@ static enum tep_event_type read_token(char **tok) } /** - * tep_read_token - access to utilities to use the pevent parser + * tep_read_token - access to utilities to use the tep parser * @tok: The token to return * * This will parse tokens from the string given by @@ -1657,8 +1656,8 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field ** else if (field->flags & TEP_FIELD_IS_STRING) field->elementsize = 1; else if (field->flags & TEP_FIELD_IS_LONG) - field->elementsize = event->pevent ? - event->pevent->long_size : + field->elementsize = event->tep ? + event->tep->long_size : sizeof(long); } else field->elementsize = field->size; @@ -2942,14 +2941,14 @@ process_bitmask(struct tep_event *event __maybe_unused, struct tep_print_arg *ar } static struct tep_function_handler * -find_func_handler(struct tep_handle *pevent, char *func_name) +find_func_handler(struct tep_handle *tep, char *func_name) { struct tep_function_handler *func; - if (!pevent) + if (!tep) return NULL; - for (func = pevent->func_handlers; func; func = func->next) { + for (func = tep->func_handlers; func; func = func->next) { if (strcmp(func->name, func_name) == 0) break; } @@ -2957,12 +2956,12 @@ find_func_handler(struct tep_handle *pevent, char *func_name) return func; } -static void remove_func_handler(struct tep_handle *pevent, char *func_name) +static void remove_func_handler(struct tep_handle *tep, char *func_name) { struct tep_function_handler *func; struct tep_function_handler **next; - next = &pevent->func_handlers; + next = &tep->func_handlers; while ((func = *next)) { if (strcmp(func->name, func_name) == 0) { *next = func->next; @@ -3076,7 +3075,7 @@ process_function(struct tep_event *event, struct tep_print_arg *arg, return process_dynamic_array_len(event, arg, tok); } - func = find_func_handler(event->pevent, token); + func = find_func_handler(event->tep, token); if (func) { free_token(token); return process_func_handler(event, func, arg, tok); @@ -3357,14 +3356,14 @@ tep_find_any_field(struct tep_event *event, const char *name) /** * tep_read_number - read a number from data - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @ptr: the raw data * @size: the size of the data that holds the number * * Returns the number (converted to host) from the * raw data. */ -unsigned long long tep_read_number(struct tep_handle *pevent, +unsigned long long tep_read_number(struct tep_handle *tep, const void *ptr, int size) { unsigned long long val; @@ -3373,12 +3372,12 @@ unsigned long long tep_read_number(struct tep_handle *pevent, case 1: return *(unsigned char *)ptr; case 2: - return tep_data2host2(pevent, *(unsigned short *)ptr); + return tep_data2host2(tep, *(unsigned short *)ptr); case 4: - return tep_data2host4(pevent, *(unsigned int *)ptr); + return tep_data2host4(tep, *(unsigned int *)ptr); case 8: memcpy(&val, (ptr), sizeof(unsigned long long)); - return tep_data2host8(pevent, val); + return tep_data2host8(tep, val); default: /* BUG! */ return 0; @@ -3406,7 +3405,7 @@ int tep_read_number_field(struct tep_format_field *field, const void *data, case 2: case 4: case 8: - *value = tep_read_number(field->event->pevent, + *value = tep_read_number(field->event->tep, data + field->offset, field->size); return 0; default: @@ -3414,7 +3413,7 @@ int tep_read_number_field(struct tep_format_field *field, const void *data, } } -static int get_common_info(struct tep_handle *pevent, +static int get_common_info(struct tep_handle *tep, const char *type, int *offset, int *size) { struct tep_event *event; @@ -3424,12 +3423,12 @@ static int get_common_info(struct tep_handle *pevent, * All events should have the same common elements. * Pick any event to find where the type is; */ - if (!pevent->events) { + if (!tep->events) { do_warning("no event_list!"); return -1; } - event = pevent->events[0]; + event = tep->events[0]; field = tep_find_common_field(event, type); if (!field) return -1; @@ -3440,58 +3439,58 @@ static int get_common_info(struct tep_handle *pevent, return 0; } -static int __parse_common(struct tep_handle *pevent, void *data, +static int __parse_common(struct tep_handle *tep, void *data, int *size, int *offset, const char *name) { int ret; if (!*size) { - ret = get_common_info(pevent, name, offset, size); + ret = get_common_info(tep, name, offset, size); if (ret < 0) return ret; } - return tep_read_number(pevent, data + *offset, *size); + return tep_read_number(tep, data + *offset, *size); } -static int trace_parse_common_type(struct tep_handle *pevent, void *data) +static int trace_parse_common_type(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->type_size, &pevent->type_offset, + return __parse_common(tep, data, + &tep->type_size, &tep->type_offset, "common_type"); } -static int parse_common_pid(struct tep_handle *pevent, void *data) +static int parse_common_pid(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->pid_size, &pevent->pid_offset, + return __parse_common(tep, data, + &tep->pid_size, &tep->pid_offset, "common_pid"); } -static int parse_common_pc(struct tep_handle *pevent, void *data) +static int parse_common_pc(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->pc_size, &pevent->pc_offset, + return __parse_common(tep, data, + &tep->pc_size, &tep->pc_offset, "common_preempt_count"); } -static int parse_common_flags(struct tep_handle *pevent, void *data) +static int parse_common_flags(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->flags_size, &pevent->flags_offset, + return __parse_common(tep, data, + &tep->flags_size, &tep->flags_offset, "common_flags"); } -static int parse_common_lock_depth(struct tep_handle *pevent, void *data) +static int parse_common_lock_depth(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->ld_size, &pevent->ld_offset, + return __parse_common(tep, data, + &tep->ld_size, &tep->ld_offset, "common_lock_depth"); } -static int parse_common_migrate_disable(struct tep_handle *pevent, void *data) +static int parse_common_migrate_disable(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->ld_size, &pevent->ld_offset, + return __parse_common(tep, data, + &tep->ld_size, &tep->ld_offset, "common_migrate_disable"); } @@ -3499,28 +3498,28 @@ static int events_id_cmp(const void *a, const void *b); /** * tep_find_event - find an event by given id - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @id: the id of the event * * Returns an event that has a given @id. */ -struct tep_event *tep_find_event(struct tep_handle *pevent, int id) +struct tep_event *tep_find_event(struct tep_handle *tep, int id) { struct tep_event **eventptr; struct tep_event key; struct tep_event *pkey = &key; /* Check cache first */ - if (pevent->last_event && pevent->last_event->id == id) - return pevent->last_event; + if (tep->last_event && tep->last_event->id == id) + return tep->last_event; key.id = id; - eventptr = bsearch(&pkey, pevent->events, pevent->nr_events, - sizeof(*pevent->events), events_id_cmp); + eventptr = bsearch(&pkey, tep->events, tep->nr_events, + sizeof(*tep->events), events_id_cmp); if (eventptr) { - pevent->last_event = *eventptr; + tep->last_event = *eventptr; return *eventptr; } @@ -3529,7 +3528,7 @@ struct tep_event *tep_find_event(struct tep_handle *pevent, int id) /** * tep_find_event_by_name - find an event by given name - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @sys: the system name to search for * @name: the name of the event to search for * @@ -3537,19 +3536,19 @@ struct tep_event *tep_find_event(struct tep_handle *pevent, int id) * @sys. If @sys is NULL the first event with @name is returned. */ struct tep_event * -tep_find_event_by_name(struct tep_handle *pevent, +tep_find_event_by_name(struct tep_handle *tep, const char *sys, const char *name) { struct tep_event *event = NULL; int i; - if (pevent->last_event && - strcmp(pevent->last_event->name, name) == 0 && - (!sys || strcmp(pevent->last_event->system, sys) == 0)) - return pevent->last_event; + if (tep->last_event && + strcmp(tep->last_event->name, name) == 0 && + (!sys || strcmp(tep->last_event->system, sys) == 0)) + return tep->last_event; - for (i = 0; i < pevent->nr_events; i++) { - event = pevent->events[i]; + for (i = 0; i < tep->nr_events; i++) { + event = tep->events[i]; if (strcmp(event->name, name) == 0) { if (!sys) break; @@ -3557,17 +3556,17 @@ tep_find_event_by_name(struct tep_handle *pevent, break; } } - if (i == pevent->nr_events) + if (i == tep->nr_events) event = NULL; - pevent->last_event = event; + tep->last_event = event; return event; } static unsigned long long eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg *arg) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; unsigned long long val = 0; unsigned long long left, right; struct tep_print_arg *typearg = NULL; @@ -3589,7 +3588,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg } /* must be a number */ - val = tep_read_number(pevent, data + arg->field.field->offset, + val = tep_read_number(tep, data + arg->field.field->offset, arg->field.field->size); break; case TEP_PRINT_FLAGS: @@ -3629,11 +3628,11 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg } /* Default to long size */ - field_size = pevent->long_size; + field_size = tep->long_size; switch (larg->type) { case TEP_PRINT_DYNAMIC_ARRAY: - offset = tep_read_number(pevent, + offset = tep_read_number(tep, data + larg->dynarray.field->offset, larg->dynarray.field->size); if (larg->dynarray.field->elementsize) @@ -3662,7 +3661,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg default: goto default_op; /* oops, all bets off */ } - val = tep_read_number(pevent, + val = tep_read_number(tep, data + offset, field_size); if (typearg) val = eval_type(val, typearg, 1); @@ -3763,7 +3762,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg } break; case TEP_PRINT_DYNAMIC_ARRAY_LEN: - offset = tep_read_number(pevent, + offset = tep_read_number(tep, data + arg->dynarray.field->offset, arg->dynarray.field->size); /* @@ -3775,7 +3774,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg break; case TEP_PRINT_DYNAMIC_ARRAY: /* Without [], we pass the address to the dynamic data */ - offset = tep_read_number(pevent, + offset = tep_read_number(tep, data + arg->dynarray.field->offset, arg->dynarray.field->size); /* @@ -3850,7 +3849,7 @@ static void print_str_to_seq(struct trace_seq *s, const char *format, trace_seq_printf(s, format, str); } -static void print_bitmask_to_seq(struct tep_handle *pevent, +static void print_bitmask_to_seq(struct tep_handle *tep, struct trace_seq *s, const char *format, int len_arg, const void *data, int size) { @@ -3882,7 +3881,7 @@ static void print_bitmask_to_seq(struct tep_handle *pevent, * In the kernel, this is an array of long words, thus * endianness is very important. */ - if (pevent->file_bigendian) + if (tep->file_bigendian) index = size - (len + 1); else index = len; @@ -3908,7 +3907,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, struct tep_event *event, const char *format, int len_arg, struct tep_print_arg *arg) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; struct tep_print_flag_sym *flag; struct tep_format_field *field; struct printk_map *printk; @@ -3945,7 +3944,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, * is a pointer. */ if (!(field->flags & TEP_FIELD_IS_ARRAY) && - field->size == pevent->long_size) { + field->size == tep->long_size) { /* Handle heterogeneous recording and processing * architectures @@ -3960,12 +3959,12 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, * on 32-bit devices: * In this case, 64 bits must be read. */ - addr = (pevent->long_size == 8) ? + addr = (tep->long_size == 8) ? *(unsigned long long *)(data + field->offset) : (unsigned long long)*(unsigned int *)(data + field->offset); /* Check if it matches a print format */ - printk = find_printk(pevent, addr); + printk = find_printk(tep, addr); if (printk) trace_seq_puts(s, printk->printk); else @@ -4022,7 +4021,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, case TEP_PRINT_HEX_STR: if (arg->hex.field->type == TEP_PRINT_DYNAMIC_ARRAY) { unsigned long offset; - offset = tep_read_number(pevent, + offset = tep_read_number(tep, data + arg->hex.field->dynarray.field->offset, arg->hex.field->dynarray.field->size); hex = data + (offset & 0xffff); @@ -4053,7 +4052,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, unsigned long offset; struct tep_format_field *field = arg->int_array.field->dynarray.field; - offset = tep_read_number(pevent, + offset = tep_read_number(tep, data + field->offset, field->size); num = data + (offset & 0xffff); @@ -4104,7 +4103,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, f = tep_find_any_field(event, arg->string.string); arg->string.offset = f->offset; } - str_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->string.offset)); + str_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->string.offset)); str_offset &= 0xffff; print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset); break; @@ -4122,10 +4121,10 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, f = tep_find_any_field(event, arg->bitmask.bitmask); arg->bitmask.offset = f->offset; } - bitmask_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->bitmask.offset)); + bitmask_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->bitmask.offset)); bitmask_size = bitmask_offset >> 16; bitmask_offset &= 0xffff; - print_bitmask_to_seq(pevent, s, format, len_arg, + print_bitmask_to_seq(tep, s, format, len_arg, data + bitmask_offset, bitmask_size); break; } @@ -4257,7 +4256,7 @@ static void free_args(struct tep_print_arg *args) static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event *event) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; struct tep_format_field *field, *ip_field; struct tep_print_arg *args, *arg, **next; unsigned long long ip, val; @@ -4265,8 +4264,8 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s void *bptr; int vsize = 0; - field = pevent->bprint_buf_field; - ip_field = pevent->bprint_ip_field; + field = tep->bprint_buf_field; + ip_field = tep->bprint_ip_field; if (!field) { field = tep_find_field(event, "buf"); @@ -4279,11 +4278,11 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s do_warning_event(event, "can't find ip field for binary printk"); return NULL; } - pevent->bprint_buf_field = field; - pevent->bprint_ip_field = ip_field; + tep->bprint_buf_field = field; + tep->bprint_ip_field = ip_field; } - ip = tep_read_number(pevent, data + ip_field->offset, ip_field->size); + ip = tep_read_number(tep, data + ip_field->offset, ip_field->size); /* * The first arg is the IP pointer. @@ -4338,6 +4337,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s case 'S': case 'f': case 'F': + case 'x': break; default: /* @@ -4360,7 +4360,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s vsize = 4; break; case 1: - vsize = pevent->long_size; + vsize = tep->long_size; break; case 2: vsize = 8; @@ -4377,7 +4377,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s /* the pointers are always 4 bytes aligned */ bptr = (void *)(((unsigned long)bptr + 3) & ~3); - val = tep_read_number(pevent, bptr, vsize); + val = tep_read_number(tep, bptr, vsize); bptr += vsize; arg = alloc_arg(); if (!arg) { @@ -4434,13 +4434,13 @@ static char * get_bprint_format(void *data, int size __maybe_unused, struct tep_event *event) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; unsigned long long addr; struct tep_format_field *field; struct printk_map *printk; char *format; - field = pevent->bprint_fmt_field; + field = tep->bprint_fmt_field; if (!field) { field = tep_find_field(event, "fmt"); @@ -4448,12 +4448,12 @@ get_bprint_format(void *data, int size __maybe_unused, do_warning_event(event, "can't find format field for binary printk"); return NULL; } - pevent->bprint_fmt_field = field; + tep->bprint_fmt_field = field; } - addr = tep_read_number(pevent, data + field->offset, field->size); + addr = tep_read_number(tep, data + field->offset, field->size); - printk = find_printk(pevent, addr); + printk = find_printk(tep, addr); if (!printk) { if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0) return NULL; @@ -4835,13 +4835,13 @@ void tep_print_field(struct trace_seq *s, void *data, { unsigned long long val; unsigned int offset, len, i; - struct tep_handle *pevent = field->event->pevent; + struct tep_handle *tep = field->event->tep; if (field->flags & TEP_FIELD_IS_ARRAY) { offset = field->offset; len = field->size; if (field->flags & TEP_FIELD_IS_DYNAMIC) { - val = tep_read_number(pevent, data + offset, len); + val = tep_read_number(tep, data + offset, len); offset = val; len = offset >> 16; offset &= 0xffff; @@ -4861,7 +4861,7 @@ void tep_print_field(struct trace_seq *s, void *data, field->flags &= ~TEP_FIELD_IS_STRING; } } else { - val = tep_read_number(pevent, data + field->offset, + val = tep_read_number(tep, data + field->offset, field->size); if (field->flags & TEP_FIELD_IS_POINTER) { trace_seq_printf(s, "0x%llx", val); @@ -4910,7 +4910,7 @@ void tep_print_fields(struct trace_seq *s, void *data, static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_event *event) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; struct tep_print_fmt *print_fmt = &event->print_fmt; struct tep_print_arg *arg = print_fmt->args; struct tep_print_arg *args = NULL; @@ -5002,7 +5002,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e case '-': goto cont_process; case 'p': - if (pevent->long_size == 4) + if (tep->long_size == 4) ls = 1; else ls = 2; @@ -5063,7 +5063,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e arg = arg->next; if (show_func) { - func = find_func(pevent, val); + func = find_func(tep, val); if (func) { trace_seq_puts(s, func->func); if (show_func == 'F') @@ -5073,7 +5073,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e break; } } - if (pevent->long_size == 8 && ls == 1 && + if (tep->long_size == 8 && ls == 1 && sizeof(long) != 8) { char *p; @@ -5171,8 +5171,8 @@ out_failed: } /** - * tep_data_lat_fmt - parse the data for the latency format - * @pevent: a handle to the pevent + * tep_data_latency_format - parse the data for the latency format + * @tep: a handle to the trace event parser context * @s: the trace_seq to write to * @record: the record to read from * @@ -5180,8 +5180,8 @@ out_failed: * need rescheduling, in hard/soft interrupt, preempt count * and lock depth) and places it into the trace_seq. */ -void tep_data_lat_fmt(struct tep_handle *pevent, - struct trace_seq *s, struct tep_record *record) +void tep_data_latency_format(struct tep_handle *tep, + struct trace_seq *s, struct tep_record *record) { static int check_lock_depth = 1; static int check_migrate_disable = 1; @@ -5195,13 +5195,13 @@ void tep_data_lat_fmt(struct tep_handle *pevent, int softirq; void *data = record->data; - lat_flags = parse_common_flags(pevent, data); - pc = parse_common_pc(pevent, data); + lat_flags = parse_common_flags(tep, data); + pc = parse_common_pc(tep, data); /* lock_depth may not always exist */ if (lock_depth_exists) - lock_depth = parse_common_lock_depth(pevent, data); + lock_depth = parse_common_lock_depth(tep, data); else if (check_lock_depth) { - lock_depth = parse_common_lock_depth(pevent, data); + lock_depth = parse_common_lock_depth(tep, data); if (lock_depth < 0) check_lock_depth = 0; else @@ -5210,9 +5210,9 @@ void tep_data_lat_fmt(struct tep_handle *pevent, /* migrate_disable may not always exist */ if (migrate_disable_exists) - migrate_disable = parse_common_migrate_disable(pevent, data); + migrate_disable = parse_common_migrate_disable(tep, data); else if (check_migrate_disable) { - migrate_disable = parse_common_migrate_disable(pevent, data); + migrate_disable = parse_common_migrate_disable(tep, data); if (migrate_disable < 0) check_migrate_disable = 0; else @@ -5255,79 +5255,79 @@ void tep_data_lat_fmt(struct tep_handle *pevent, /** * tep_data_type - parse out the given event type - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @rec: the record to read from * * This returns the event id from the @rec. */ -int tep_data_type(struct tep_handle *pevent, struct tep_record *rec) +int tep_data_type(struct tep_handle *tep, struct tep_record *rec) { - return trace_parse_common_type(pevent, rec->data); + return trace_parse_common_type(tep, rec->data); } /** * tep_data_pid - parse the PID from record - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @rec: the record to parse * * This returns the PID from a record. */ -int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec) +int tep_data_pid(struct tep_handle *tep, struct tep_record *rec) { - return parse_common_pid(pevent, rec->data); + return parse_common_pid(tep, rec->data); } /** * tep_data_preempt_count - parse the preempt count from the record - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @rec: the record to parse * * This returns the preempt count from a record. */ -int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec) +int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec) { - return parse_common_pc(pevent, rec->data); + return parse_common_pc(tep, rec->data); } /** * tep_data_flags - parse the latency flags from the record - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @rec: the record to parse * * This returns the latency flags from a record. * * Use trace_flag_type enum for the flags (see event-parse.h). */ -int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec) +int tep_data_flags(struct tep_handle *tep, struct tep_record *rec) { - return parse_common_flags(pevent, rec->data); + return parse_common_flags(tep, rec->data); } /** * tep_data_comm_from_pid - return the command line from PID - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @pid: the PID of the task to search for * * This returns a pointer to the command line that has the given * @pid. */ -const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid) +const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid) { const char *comm; - comm = find_cmdline(pevent, pid); + comm = find_cmdline(tep, pid); return comm; } static struct tep_cmdline * -pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline *next) +pid_from_cmdlist(struct tep_handle *tep, const char *comm, struct tep_cmdline *next) { struct cmdline_list *cmdlist = (struct cmdline_list *)next; if (cmdlist) cmdlist = cmdlist->next; else - cmdlist = pevent->cmdlist; + cmdlist = tep->cmdlist; while (cmdlist && strcmp(cmdlist->comm, comm) != 0) cmdlist = cmdlist->next; @@ -5337,7 +5337,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline /** * tep_data_pid_from_comm - return the pid from a given comm - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @comm: the cmdline to find the pid from * @next: the cmdline structure to find the next comm * @@ -5348,7 +5348,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline * next pid. * Also, it does a linear search, so it may be slow. */ -struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm, +struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm, struct tep_cmdline *next) { struct tep_cmdline *cmdline; @@ -5357,25 +5357,25 @@ struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char * If the cmdlines have not been converted yet, then use * the list. */ - if (!pevent->cmdlines) - return pid_from_cmdlist(pevent, comm, next); + if (!tep->cmdlines) + return pid_from_cmdlist(tep, comm, next); if (next) { /* * The next pointer could have been still from * a previous call before cmdlines were created */ - if (next < pevent->cmdlines || - next >= pevent->cmdlines + pevent->cmdline_count) + if (next < tep->cmdlines || + next >= tep->cmdlines + tep->cmdline_count) next = NULL; else cmdline = next++; } if (!next) - cmdline = pevent->cmdlines; + cmdline = tep->cmdlines; - while (cmdline < pevent->cmdlines + pevent->cmdline_count) { + while (cmdline < tep->cmdlines + tep->cmdline_count) { if (strcmp(cmdline->comm, comm) == 0) return cmdline; cmdline++; @@ -5385,12 +5385,13 @@ struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char /** * tep_cmdline_pid - return the pid associated to a given cmdline + * @tep: a handle to the trace event parser context * @cmdline: The cmdline structure to get the pid from * * Returns the pid for a give cmdline. If @cmdline is NULL, then * -1 is returned. */ -int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline) +int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline) { struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline; @@ -5401,9 +5402,9 @@ int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline) * If cmdlines have not been created yet, or cmdline is * not part of the array, then treat it as a cmdlist instead. */ - if (!pevent->cmdlines || - cmdline < pevent->cmdlines || - cmdline >= pevent->cmdlines + pevent->cmdline_count) + if (!tep->cmdlines || + cmdline < tep->cmdlines || + cmdline >= tep->cmdlines + tep->cmdline_count) return cmdlist->pid; return cmdline->pid; @@ -5423,7 +5424,7 @@ void tep_event_info(struct trace_seq *s, struct tep_event *event, { int print_pretty = 1; - if (event->pevent->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW)) + if (event->tep->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW)) tep_print_fields(s, record->data, record->size, event); else { @@ -5444,7 +5445,8 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock) return true; if (!strcmp(trace_clock, "local") || !strcmp(trace_clock, "global") - || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf")) + || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf") + || !strncmp(trace_clock, "mono", 4)) return true; /* trace_clock is setting in tsc or counter mode */ @@ -5453,14 +5455,14 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock) /** * tep_find_event_by_record - return the event from a given record - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @record: The record to get the event from * * Returns the associated event for a given record, or NULL if non is * is found. */ struct tep_event * -tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record) +tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record) { int type; @@ -5469,21 +5471,21 @@ tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record) return NULL; } - type = trace_parse_common_type(pevent, record->data); + type = trace_parse_common_type(tep, record->data); - return tep_find_event(pevent, type); + return tep_find_event(tep, type); } /** * tep_print_event_task - Write the event task comm, pid and CPU - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @s: the trace_seq to write to * @event: the handle to the record's event * @record: The record to get the event from * * Writes the tasks comm, pid and CPU to @s. */ -void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record) { @@ -5491,27 +5493,26 @@ void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s, const char *comm; int pid; - pid = parse_common_pid(pevent, data); - comm = find_cmdline(pevent, pid); + pid = parse_common_pid(tep, data); + comm = find_cmdline(tep, pid); - if (pevent->latency_format) { - trace_seq_printf(s, "%8.8s-%-5d %3d", - comm, pid, record->cpu); - } else + if (tep->latency_format) + trace_seq_printf(s, "%8.8s-%-5d %3d", comm, pid, record->cpu); + else trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu); } /** * tep_print_event_time - Write the event timestamp - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @s: the trace_seq to write to * @event: the handle to the record's event * @record: The record to get the event from - * @use_trace_clock: Set to parse according to the @pevent->trace_clock + * @use_trace_clock: Set to parse according to the @tep->trace_clock * * Writes the timestamp of the record into @s. */ -void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record, bool use_trace_clock) @@ -5522,19 +5523,18 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s, int p; bool use_usec_format; - use_usec_format = is_timestamp_in_us(pevent->trace_clock, - use_trace_clock); + use_usec_format = is_timestamp_in_us(tep->trace_clock, use_trace_clock); if (use_usec_format) { secs = record->ts / NSEC_PER_SEC; nsecs = record->ts - secs * NSEC_PER_SEC; } - if (pevent->latency_format) { - tep_data_lat_fmt(pevent, s, record); + if (tep->latency_format) { + tep_data_latency_format(tep, s, record); } if (use_usec_format) { - if (pevent->flags & TEP_NSEC_OUTPUT) { + if (tep->flags & TEP_NSEC_OUTPUT) { usecs = nsecs; p = 9; } else { @@ -5554,14 +5554,14 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s, /** * tep_print_event_data - Write the event data section - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @s: the trace_seq to write to * @event: the handle to the record's event * @record: The record to get the event from * * Writes the parsing of the record's data to @s. */ -void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record) { @@ -5578,15 +5578,15 @@ void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s, tep_event_info(s, event, record); } -void tep_print_event(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event(struct tep_handle *tep, struct trace_seq *s, struct tep_record *record, bool use_trace_clock) { struct tep_event *event; - event = tep_find_event_by_record(pevent, record); + event = tep_find_event_by_record(tep, record); if (!event) { int i; - int type = trace_parse_common_type(pevent, record->data); + int type = trace_parse_common_type(tep, record->data); do_warning("ug! no event found for type %d", type); trace_seq_printf(s, "[UNKNOWN TYPE %d]", type); @@ -5596,9 +5596,9 @@ void tep_print_event(struct tep_handle *pevent, struct trace_seq *s, return; } - tep_print_event_task(pevent, s, event, record); - tep_print_event_time(pevent, s, event, record, use_trace_clock); - tep_print_event_data(pevent, s, event, record); + tep_print_event_task(tep, s, event, record); + tep_print_event_time(tep, s, event, record, use_trace_clock); + tep_print_event_data(tep, s, event, record); } static int events_id_cmp(const void *a, const void *b) @@ -5649,32 +5649,26 @@ static int events_system_cmp(const void *a, const void *b) return events_id_cmp(a, b); } -struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type sort_type) +static struct tep_event **list_events_copy(struct tep_handle *tep) { struct tep_event **events; - int (*sort)(const void *a, const void *b); - - events = pevent->sort_events; - - if (events && pevent->last_type == sort_type) - return events; - if (!events) { - events = malloc(sizeof(*events) * (pevent->nr_events + 1)); - if (!events) - return NULL; + if (!tep) + return NULL; - memcpy(events, pevent->events, sizeof(*events) * pevent->nr_events); - events[pevent->nr_events] = NULL; + events = malloc(sizeof(*events) * (tep->nr_events + 1)); + if (!events) + return NULL; - pevent->sort_events = events; + memcpy(events, tep->events, sizeof(*events) * tep->nr_events); + events[tep->nr_events] = NULL; + return events; +} - /* the internal events are sorted by id */ - if (sort_type == TEP_EVENT_SORT_ID) { - pevent->last_type = sort_type; - return events; - } - } +static void list_events_sort(struct tep_event **events, int nr_events, + enum tep_event_sort_type sort_type) +{ + int (*sort)(const void *a, const void *b); switch (sort_type) { case TEP_EVENT_SORT_ID: @@ -5687,11 +5681,82 @@ struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sor sort = events_system_cmp; break; default: + sort = NULL; + } + + if (sort) + qsort(events, nr_events, sizeof(*events), sort); +} + +/** + * tep_list_events - Get events, sorted by given criteria. + * @tep: a handle to the tep context + * @sort_type: desired sort order of the events in the array + * + * Returns an array of pointers to all events, sorted by the given + * @sort_type criteria. The last element of the array is NULL. The returned + * memory must not be freed, it is managed by the library. + * The function is not thread safe. + */ +struct tep_event **tep_list_events(struct tep_handle *tep, + enum tep_event_sort_type sort_type) +{ + struct tep_event **events; + + if (!tep) + return NULL; + + events = tep->sort_events; + if (events && tep->last_type == sort_type) return events; + + if (!events) { + events = list_events_copy(tep); + if (!events) + return NULL; + + tep->sort_events = events; + + /* the internal events are sorted by id */ + if (sort_type == TEP_EVENT_SORT_ID) { + tep->last_type = sort_type; + return events; + } } - qsort(events, pevent->nr_events, sizeof(*events), sort); - pevent->last_type = sort_type; + list_events_sort(events, tep->nr_events, sort_type); + tep->last_type = sort_type; + + return events; +} + + +/** + * tep_list_events_copy - Thread safe version of tep_list_events() + * @tep: a handle to the tep context + * @sort_type: desired sort order of the events in the array + * + * Returns an array of pointers to all events, sorted by the given + * @sort_type criteria. The last element of the array is NULL. The returned + * array is newly allocated inside the function and must be freed by the caller + */ +struct tep_event **tep_list_events_copy(struct tep_handle *tep, + enum tep_event_sort_type sort_type) +{ + struct tep_event **events; + + if (!tep) + return NULL; + + events = list_events_copy(tep); + if (!events) + return NULL; + + /* the internal events are sorted by id */ + if (sort_type == TEP_EVENT_SORT_ID) + return events; + + list_events_sort(events, tep->nr_events, sort_type); return events; } @@ -5950,7 +6015,7 @@ static void parse_header_field(const char *field, /** * tep_parse_header_page - parse the data stored in the header page - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @buf: the buffer storing the header page format string * @size: the size of @buf * @long_size: the long size to use if there is no header @@ -5960,7 +6025,7 @@ static void parse_header_field(const char *field, * * /sys/kernel/debug/tracing/events/header_page */ -int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size, +int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size, int long_size) { int ignore; @@ -5970,22 +6035,22 @@ int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long si * Old kernels did not have header page info. * Sorry but we just use what we find here in user space. */ - pevent->header_page_ts_size = sizeof(long long); - pevent->header_page_size_size = long_size; - pevent->header_page_data_offset = sizeof(long long) + long_size; - pevent->old_format = 1; + tep->header_page_ts_size = sizeof(long long); + tep->header_page_size_size = long_size; + tep->header_page_data_offset = sizeof(long long) + long_size; + tep->old_format = 1; return -1; } init_input_buf(buf, size); - parse_header_field("timestamp", &pevent->header_page_ts_offset, - &pevent->header_page_ts_size, 1); - parse_header_field("commit", &pevent->header_page_size_offset, - &pevent->header_page_size_size, 1); - parse_header_field("overwrite", &pevent->header_page_overwrite, + parse_header_field("timestamp", &tep->header_page_ts_offset, + &tep->header_page_ts_size, 1); + parse_header_field("commit", &tep->header_page_size_offset, + &tep->header_page_size_size, 1); + parse_header_field("overwrite", &tep->header_page_overwrite, &ignore, 0); - parse_header_field("data", &pevent->header_page_data_offset, - &pevent->header_page_data_size, 1); + parse_header_field("data", &tep->header_page_data_offset, + &tep->header_page_data_size, 1); return 0; } @@ -6013,11 +6078,11 @@ static void free_handler(struct event_handler *handle) free(handle); } -static int find_event_handle(struct tep_handle *pevent, struct tep_event *event) +static int find_event_handle(struct tep_handle *tep, struct tep_event *event) { struct event_handler *handle, **next; - for (next = &pevent->handlers; *next; + for (next = &tep->handlers; *next; next = &(*next)->next) { handle = *next; if (event_matches(event, handle->id, @@ -6055,7 +6120,7 @@ static int find_event_handle(struct tep_handle *pevent, struct tep_event *event) * /sys/kernel/debug/tracing/events/.../.../format */ enum tep_errno __tep_parse_format(struct tep_event **eventp, - struct tep_handle *pevent, const char *buf, + struct tep_handle *tep, const char *buf, unsigned long size, const char *sys) { struct tep_event *event; @@ -6097,8 +6162,8 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp, goto event_alloc_failed; } - /* Add pevent to event so that it can be referenced */ - event->pevent = pevent; + /* Add tep to event so that it can be referenced */ + event->tep = tep; ret = event_read_format(event); if (ret < 0) { @@ -6110,7 +6175,7 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp, * If the event has an override, don't print warnings if the event * print format fails to parse. */ - if (pevent && find_event_handle(pevent, event)) + if (tep && find_event_handle(tep, event)) show_warning = 0; ret = event_read_print(event); @@ -6162,18 +6227,18 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp, } static enum tep_errno -__parse_event(struct tep_handle *pevent, +__parse_event(struct tep_handle *tep, struct tep_event **eventp, const char *buf, unsigned long size, const char *sys) { - int ret = __tep_parse_format(eventp, pevent, buf, size, sys); + int ret = __tep_parse_format(eventp, tep, buf, size, sys); struct tep_event *event = *eventp; if (event == NULL) return ret; - if (pevent && add_event(pevent, event)) { + if (tep && add_event(tep, event)) { ret = TEP_ERRNO__MEM_ALLOC_FAILED; goto event_add_failed; } @@ -6191,7 +6256,7 @@ event_add_failed: /** * tep_parse_format - parse the event format - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @eventp: returned format * @buf: the buffer storing the event format string * @size: the size of @buf @@ -6204,17 +6269,17 @@ event_add_failed: * * /sys/kernel/debug/tracing/events/.../.../format */ -enum tep_errno tep_parse_format(struct tep_handle *pevent, +enum tep_errno tep_parse_format(struct tep_handle *tep, struct tep_event **eventp, const char *buf, unsigned long size, const char *sys) { - return __parse_event(pevent, eventp, buf, size, sys); + return __parse_event(tep, eventp, buf, size, sys); } /** * tep_parse_event - parse the event format - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @buf: the buffer storing the event format string * @size: the size of @buf * @sys: the system the event belongs to @@ -6226,11 +6291,11 @@ enum tep_errno tep_parse_format(struct tep_handle *pevent, * * /sys/kernel/debug/tracing/events/.../.../format */ -enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf, +enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf, unsigned long size, const char *sys) { struct tep_event *event = NULL; - return __parse_event(pevent, &event, buf, size, sys); + return __parse_event(tep, &event, buf, size, sys); } int get_field_val(struct trace_seq *s, struct tep_format_field *field, @@ -6292,8 +6357,8 @@ void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event, offset = field->offset; if (field->flags & TEP_FIELD_IS_DYNAMIC) { - offset = tep_read_number(event->pevent, - data + offset, field->size); + offset = tep_read_number(event->tep, + data + offset, field->size); *len = offset >> 16; offset &= 0xffff; } else @@ -6386,7 +6451,8 @@ int tep_get_any_field_val(struct trace_seq *s, struct tep_event *event, * @record: The record with the field name. * @err: print default error if failed. * - * Returns: 0 on success, -1 field not found, or 1 if buffer is full. + * Returns positive value on success, negative in case of an error, + * or 0 if buffer is full. */ int tep_print_num_field(struct trace_seq *s, const char *fmt, struct tep_event *event, const char *name, @@ -6418,14 +6484,15 @@ int tep_print_num_field(struct trace_seq *s, const char *fmt, * @record: The record with the field name. * @err: print default error if failed. * - * Returns: 0 on success, -1 field not found, or 1 if buffer is full. + * Returns positive value on success, negative in case of an error, + * or 0 if buffer is full. */ int tep_print_func_field(struct trace_seq *s, const char *fmt, struct tep_event *event, const char *name, struct tep_record *record, int err) { struct tep_format_field *field = tep_find_field(event, name); - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; unsigned long long val; struct func_map *func; char tmp[128]; @@ -6436,7 +6503,7 @@ int tep_print_func_field(struct trace_seq *s, const char *fmt, if (tep_read_number_field(field, record->data, &val)) goto failed; - func = find_func(pevent, val); + func = find_func(tep, val); if (func) snprintf(tmp, 128, "%s/0x%llx", func->func, func->addr - val); @@ -6468,7 +6535,7 @@ static void free_func_handle(struct tep_function_handler *func) /** * tep_register_print_function - register a helper function - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @func: the function to process the helper function * @ret_type: the return type of the helper function * @name: the name of the helper function @@ -6481,7 +6548,7 @@ static void free_func_handle(struct tep_function_handler *func) * The @parameters is a variable list of tep_func_arg_type enums that * must end with TEP_FUNC_ARG_VOID. */ -int tep_register_print_function(struct tep_handle *pevent, +int tep_register_print_function(struct tep_handle *tep, tep_func_handler func, enum tep_func_arg_type ret_type, char *name, ...) @@ -6493,7 +6560,7 @@ int tep_register_print_function(struct tep_handle *pevent, va_list ap; int ret; - func_handle = find_func_handler(pevent, name); + func_handle = find_func_handler(tep, name); if (func_handle) { /* * This is most like caused by the users own @@ -6501,7 +6568,7 @@ int tep_register_print_function(struct tep_handle *pevent, * system defaults. */ pr_stat("override of function helper '%s'", name); - remove_func_handler(pevent, name); + remove_func_handler(tep, name); } func_handle = calloc(1, sizeof(*func_handle)); @@ -6548,8 +6615,8 @@ int tep_register_print_function(struct tep_handle *pevent, } va_end(ap); - func_handle->next = pevent->func_handlers; - pevent->func_handlers = func_handle; + func_handle->next = tep->func_handlers; + tep->func_handlers = func_handle; return 0; out_free: @@ -6560,7 +6627,7 @@ int tep_register_print_function(struct tep_handle *pevent, /** * tep_unregister_print_function - unregister a helper function - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @func: the function to process the helper function * @name: the name of the helper function * @@ -6568,20 +6635,20 @@ int tep_register_print_function(struct tep_handle *pevent, * * Returns 0 if the handler was removed successully, -1 otherwise. */ -int tep_unregister_print_function(struct tep_handle *pevent, +int tep_unregister_print_function(struct tep_handle *tep, tep_func_handler func, char *name) { struct tep_function_handler *func_handle; - func_handle = find_func_handler(pevent, name); + func_handle = find_func_handler(tep, name); if (func_handle && func_handle->func == func) { - remove_func_handler(pevent, name); + remove_func_handler(tep, name); return 0; } return -1; } -static struct tep_event *search_event(struct tep_handle *pevent, int id, +static struct tep_event *search_event(struct tep_handle *tep, int id, const char *sys_name, const char *event_name) { @@ -6589,7 +6656,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id, if (id >= 0) { /* search by id */ - event = tep_find_event(pevent, id); + event = tep_find_event(tep, id); if (!event) return NULL; if (event_name && (strcmp(event_name, event->name) != 0)) @@ -6597,7 +6664,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id, if (sys_name && (strcmp(sys_name, event->system) != 0)) return NULL; } else { - event = tep_find_event_by_name(pevent, sys_name, event_name); + event = tep_find_event_by_name(tep, sys_name, event_name); if (!event) return NULL; } @@ -6606,7 +6673,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id, /** * tep_register_event_handler - register a way to parse an event - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @id: the id of the event to register * @sys_name: the system name the event belongs to * @event_name: the name of the event @@ -6627,14 +6694,14 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id, * negative TEP_ERRNO_... in case of an error * */ -int tep_register_event_handler(struct tep_handle *pevent, int id, +int tep_register_event_handler(struct tep_handle *tep, int id, const char *sys_name, const char *event_name, tep_event_handler_func func, void *context) { struct tep_event *event; struct event_handler *handle; - event = search_event(pevent, id, sys_name, event_name); + event = search_event(tep, id, sys_name, event_name); if (event == NULL) goto not_found; @@ -6669,8 +6736,8 @@ int tep_register_event_handler(struct tep_handle *pevent, int id, } handle->func = func; - handle->next = pevent->handlers; - pevent->handlers = handle; + handle->next = tep->handlers; + tep->handlers = handle; handle->context = context; return TEP_REGISTER_SUCCESS; @@ -6697,7 +6764,7 @@ static int handle_matches(struct event_handler *handler, int id, /** * tep_unregister_event_handler - unregister an existing event handler - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @id: the id of the event to unregister * @sys_name: the system name the handler belongs to * @event_name: the name of the event handler @@ -6711,7 +6778,7 @@ static int handle_matches(struct event_handler *handler, int id, * * Returns 0 if handler was removed successfully, -1 if event was not found. */ -int tep_unregister_event_handler(struct tep_handle *pevent, int id, +int tep_unregister_event_handler(struct tep_handle *tep, int id, const char *sys_name, const char *event_name, tep_event_handler_func func, void *context) { @@ -6719,7 +6786,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id, struct event_handler *handle; struct event_handler **next; - event = search_event(pevent, id, sys_name, event_name); + event = search_event(tep, id, sys_name, event_name); if (event == NULL) goto not_found; @@ -6733,7 +6800,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id, } not_found: - for (next = &pevent->handlers; *next; next = &(*next)->next) { + for (next = &tep->handlers; *next; next = &(*next)->next) { handle = *next; if (handle_matches(handle, id, sys_name, event_name, func, context)) @@ -6750,23 +6817,23 @@ not_found: } /** - * tep_alloc - create a pevent handle + * tep_alloc - create a tep handle */ struct tep_handle *tep_alloc(void) { - struct tep_handle *pevent = calloc(1, sizeof(*pevent)); + struct tep_handle *tep = calloc(1, sizeof(*tep)); - if (pevent) { - pevent->ref_count = 1; - pevent->host_bigendian = tep_host_bigendian(); + if (tep) { + tep->ref_count = 1; + tep->host_bigendian = tep_is_bigendian(); } - return pevent; + return tep; } -void tep_ref(struct tep_handle *pevent) +void tep_ref(struct tep_handle *tep) { - pevent->ref_count++; + tep->ref_count++; } int tep_get_ref(struct tep_handle *tep) @@ -6816,10 +6883,10 @@ void tep_free_event(struct tep_event *event) } /** - * tep_free - free a pevent handle - * @pevent: the pevent handle to free + * tep_free - free a tep handle + * @tep: the tep handle to free */ -void tep_free(struct tep_handle *pevent) +void tep_free(struct tep_handle *tep) { struct cmdline_list *cmdlist, *cmdnext; struct func_list *funclist, *funcnext; @@ -6828,21 +6895,21 @@ void tep_free(struct tep_handle *pevent) struct event_handler *handle; int i; - if (!pevent) + if (!tep) return; - cmdlist = pevent->cmdlist; - funclist = pevent->funclist; - printklist = pevent->printklist; + cmdlist = tep->cmdlist; + funclist = tep->funclist; + printklist = tep->printklist; - pevent->ref_count--; - if (pevent->ref_count) + tep->ref_count--; + if (tep->ref_count) return; - if (pevent->cmdlines) { - for (i = 0; i < pevent->cmdline_count; i++) - free(pevent->cmdlines[i].comm); - free(pevent->cmdlines); + if (tep->cmdlines) { + for (i = 0; i < tep->cmdline_count; i++) + free(tep->cmdlines[i].comm); + free(tep->cmdlines); } while (cmdlist) { @@ -6852,12 +6919,12 @@ void tep_free(struct tep_handle *pevent) cmdlist = cmdnext; } - if (pevent->func_map) { - for (i = 0; i < (int)pevent->func_count; i++) { - free(pevent->func_map[i].func); - free(pevent->func_map[i].mod); + if (tep->func_map) { + for (i = 0; i < (int)tep->func_count; i++) { + free(tep->func_map[i].func); + free(tep->func_map[i].mod); } - free(pevent->func_map); + free(tep->func_map); } while (funclist) { @@ -6868,16 +6935,16 @@ void tep_free(struct tep_handle *pevent) funclist = funcnext; } - while (pevent->func_handlers) { - func_handler = pevent->func_handlers; - pevent->func_handlers = func_handler->next; + while (tep->func_handlers) { + func_handler = tep->func_handlers; + tep->func_handlers = func_handler->next; free_func_handle(func_handler); } - if (pevent->printk_map) { - for (i = 0; i < (int)pevent->printk_count; i++) - free(pevent->printk_map[i].printk); - free(pevent->printk_map); + if (tep->printk_map) { + for (i = 0; i < (int)tep->printk_count; i++) + free(tep->printk_map[i].printk); + free(tep->printk_map); } while (printklist) { @@ -6887,24 +6954,24 @@ void tep_free(struct tep_handle *pevent) printklist = printknext; } - for (i = 0; i < pevent->nr_events; i++) - tep_free_event(pevent->events[i]); + for (i = 0; i < tep->nr_events; i++) + tep_free_event(tep->events[i]); - while (pevent->handlers) { - handle = pevent->handlers; - pevent->handlers = handle->next; + while (tep->handlers) { + handle = tep->handlers; + tep->handlers = handle->next; free_handler(handle); } - free(pevent->trace_clock); - free(pevent->events); - free(pevent->sort_events); - free(pevent->func_resolver); + free(tep->trace_clock); + free(tep->events); + free(tep->sort_events); + free(tep->func_resolver); - free(pevent); + free(tep); } -void tep_unref(struct tep_handle *pevent) +void tep_unref(struct tep_handle *tep) { - tep_free(pevent); + tep_free(tep); } diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index aec48f2aea8a..642f68ab5fb2 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -64,8 +64,8 @@ typedef int (*tep_event_handler_func)(struct trace_seq *s, struct tep_event *event, void *context); -typedef int (*tep_plugin_load_func)(struct tep_handle *pevent); -typedef int (*tep_plugin_unload_func)(struct tep_handle *pevent); +typedef int (*tep_plugin_load_func)(struct tep_handle *tep); +typedef int (*tep_plugin_unload_func)(struct tep_handle *tep); struct tep_plugin_option { struct tep_plugin_option *next; @@ -85,12 +85,12 @@ struct tep_plugin_option { * TEP_PLUGIN_LOADER: (required) * The function name to initialized the plugin. * - * int TEP_PLUGIN_LOADER(struct tep_handle *pevent) + * int TEP_PLUGIN_LOADER(struct tep_handle *tep) * * TEP_PLUGIN_UNLOADER: (optional) * The function called just before unloading * - * int TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) + * int TEP_PLUGIN_UNLOADER(struct tep_handle *tep) * * TEP_PLUGIN_OPTIONS: (optional) * Plugin options that can be set before loading @@ -278,7 +278,7 @@ struct tep_print_fmt { }; struct tep_event { - struct tep_handle *pevent; + struct tep_handle *tep; char *name; int id; int flags; @@ -393,9 +393,9 @@ struct tep_plugin_list; #define INVALID_PLUGIN_LIST_OPTION ((char **)((unsigned long)-1)) -struct tep_plugin_list *tep_load_plugins(struct tep_handle *pevent); +struct tep_plugin_list *tep_load_plugins(struct tep_handle *tep); void tep_unload_plugins(struct tep_plugin_list *plugin_list, - struct tep_handle *pevent); + struct tep_handle *tep); char **tep_plugin_list_options(void); void tep_plugin_free_options_list(char **list); int tep_plugin_add_options(const char *name, @@ -409,8 +409,10 @@ void tep_print_plugins(struct trace_seq *s, typedef char *(tep_func_resolver_t)(void *priv, unsigned long long *addrp, char **modp); void tep_set_flag(struct tep_handle *tep, int flag); +void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag); +bool tep_test_flag(struct tep_handle *tep, enum tep_flag flags); -static inline int tep_host_bigendian(void) +static inline int tep_is_bigendian(void) { unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 }; unsigned int val; @@ -428,37 +430,37 @@ enum trace_flag_type { TRACE_FLAG_SOFTIRQ = 0x10, }; -int tep_set_function_resolver(struct tep_handle *pevent, +int tep_set_function_resolver(struct tep_handle *tep, tep_func_resolver_t *func, void *priv); -void tep_reset_function_resolver(struct tep_handle *pevent); -int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid); -int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid); -int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock); -int tep_register_function(struct tep_handle *pevent, char *name, +void tep_reset_function_resolver(struct tep_handle *tep); +int tep_register_comm(struct tep_handle *tep, const char *comm, int pid); +int tep_override_comm(struct tep_handle *tep, const char *comm, int pid); +int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock); +int tep_register_function(struct tep_handle *tep, char *name, unsigned long long addr, char *mod); -int tep_register_print_string(struct tep_handle *pevent, const char *fmt, +int tep_register_print_string(struct tep_handle *tep, const char *fmt, unsigned long long addr); -int tep_pid_is_registered(struct tep_handle *pevent, int pid); +bool tep_is_pid_registered(struct tep_handle *tep, int pid); -void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record); -void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record, bool use_trace_clock); -void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record); -void tep_print_event(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event(struct tep_handle *tep, struct trace_seq *s, struct tep_record *record, bool use_trace_clock); -int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size, +int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size, int long_size); -enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf, +enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf, unsigned long size, const char *sys); -enum tep_errno tep_parse_format(struct tep_handle *pevent, +enum tep_errno tep_parse_format(struct tep_handle *tep, struct tep_event **eventp, const char *buf, unsigned long size, const char *sys); @@ -490,50 +492,50 @@ enum tep_reg_handler { TEP_REGISTER_SUCCESS_OVERWRITE, }; -int tep_register_event_handler(struct tep_handle *pevent, int id, +int tep_register_event_handler(struct tep_handle *tep, int id, const char *sys_name, const char *event_name, tep_event_handler_func func, void *context); -int tep_unregister_event_handler(struct tep_handle *pevent, int id, +int tep_unregister_event_handler(struct tep_handle *tep, int id, const char *sys_name, const char *event_name, tep_event_handler_func func, void *context); -int tep_register_print_function(struct tep_handle *pevent, +int tep_register_print_function(struct tep_handle *tep, tep_func_handler func, enum tep_func_arg_type ret_type, char *name, ...); -int tep_unregister_print_function(struct tep_handle *pevent, +int tep_unregister_print_function(struct tep_handle *tep, tep_func_handler func, char *name); struct tep_format_field *tep_find_common_field(struct tep_event *event, const char *name); struct tep_format_field *tep_find_field(struct tep_event *event, const char *name); struct tep_format_field *tep_find_any_field(struct tep_event *event, const char *name); -const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr); +const char *tep_find_function(struct tep_handle *tep, unsigned long long addr); unsigned long long -tep_find_function_address(struct tep_handle *pevent, unsigned long long addr); -unsigned long long tep_read_number(struct tep_handle *pevent, const void *ptr, int size); +tep_find_function_address(struct tep_handle *tep, unsigned long long addr); +unsigned long long tep_read_number(struct tep_handle *tep, const void *ptr, int size); int tep_read_number_field(struct tep_format_field *field, const void *data, unsigned long long *value); struct tep_event *tep_get_first_event(struct tep_handle *tep); int tep_get_events_count(struct tep_handle *tep); -struct tep_event *tep_find_event(struct tep_handle *pevent, int id); +struct tep_event *tep_find_event(struct tep_handle *tep, int id); struct tep_event * -tep_find_event_by_name(struct tep_handle *pevent, const char *sys, const char *name); +tep_find_event_by_name(struct tep_handle *tep, const char *sys, const char *name); struct tep_event * -tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record); - -void tep_data_lat_fmt(struct tep_handle *pevent, - struct trace_seq *s, struct tep_record *record); -int tep_data_type(struct tep_handle *pevent, struct tep_record *rec); -int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec); -int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec); -int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec); -const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid); +tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record); + +void tep_data_latency_format(struct tep_handle *tep, + struct trace_seq *s, struct tep_record *record); +int tep_data_type(struct tep_handle *tep, struct tep_record *rec); +int tep_data_pid(struct tep_handle *tep, struct tep_record *rec); +int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec); +int tep_data_flags(struct tep_handle *tep, struct tep_record *rec); +const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid); struct tep_cmdline; -struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm, +struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm, struct tep_cmdline *next); -int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline); +int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline); void tep_print_field(struct trace_seq *s, void *data, struct tep_format_field *field); @@ -541,10 +543,12 @@ void tep_print_fields(struct trace_seq *s, void *data, int size __maybe_unused, struct tep_event *event); void tep_event_info(struct trace_seq *s, struct tep_event *event, struct tep_record *record); -int tep_strerror(struct tep_handle *pevent, enum tep_errno errnum, +int tep_strerror(struct tep_handle *tep, enum tep_errno errnum, char *buf, size_t buflen); -struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type); +struct tep_event **tep_list_events(struct tep_handle *tep, enum tep_event_sort_type); +struct tep_event **tep_list_events_copy(struct tep_handle *tep, + enum tep_event_sort_type); struct tep_format_field **tep_event_common_fields(struct tep_event *event); struct tep_format_field **tep_event_fields(struct tep_event *event); @@ -552,24 +556,28 @@ enum tep_endian { TEP_LITTLE_ENDIAN = 0, TEP_BIG_ENDIAN }; -int tep_get_cpus(struct tep_handle *pevent); -void tep_set_cpus(struct tep_handle *pevent, int cpus); -int tep_get_long_size(struct tep_handle *pevent); -void tep_set_long_size(struct tep_handle *pevent, int long_size); -int tep_get_page_size(struct tep_handle *pevent); -void tep_set_page_size(struct tep_handle *pevent, int _page_size); -int tep_file_bigendian(struct tep_handle *pevent); -void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian); -int tep_is_host_bigendian(struct tep_handle *pevent); -void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian); -int tep_is_latency_format(struct tep_handle *pevent); -void tep_set_latency_format(struct tep_handle *pevent, int lat); -int tep_get_header_page_size(struct tep_handle *pevent); +int tep_get_cpus(struct tep_handle *tep); +void tep_set_cpus(struct tep_handle *tep, int cpus); +int tep_get_long_size(struct tep_handle *tep); +void tep_set_long_size(struct tep_handle *tep, int long_size); +int tep_get_page_size(struct tep_handle *tep); +void tep_set_page_size(struct tep_handle *tep, int _page_size); +bool tep_is_file_bigendian(struct tep_handle *tep); +void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian); +bool tep_is_local_bigendian(struct tep_handle *tep); +void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian); +bool tep_is_latency_format(struct tep_handle *tep); +void tep_set_latency_format(struct tep_handle *tep, int lat); +int tep_get_header_page_size(struct tep_handle *tep); +int tep_get_header_timestamp_size(struct tep_handle *tep); +bool tep_is_old_format(struct tep_handle *tep); +void tep_set_print_raw(struct tep_handle *tep, int print_raw); +void tep_set_test_filters(struct tep_handle *tep, int test_filters); struct tep_handle *tep_alloc(void); -void tep_free(struct tep_handle *pevent); -void tep_ref(struct tep_handle *pevent); -void tep_unref(struct tep_handle *pevent); +void tep_free(struct tep_handle *tep); +void tep_ref(struct tep_handle *tep); +void tep_unref(struct tep_handle *tep); int tep_get_ref(struct tep_handle *tep); /* access to the internal parser */ @@ -581,8 +589,8 @@ const char *tep_get_input_buf(void); unsigned long long tep_get_input_buf_ptr(void); /* for debugging */ -void tep_print_funcs(struct tep_handle *pevent); -void tep_print_printk(struct tep_handle *pevent); +void tep_print_funcs(struct tep_handle *tep); +void tep_print_printk(struct tep_handle *tep); /* ----------------------- filtering ----------------------- */ @@ -709,13 +717,13 @@ struct tep_filter_type { #define TEP_FILTER_ERROR_BUFSZ 1024 struct tep_event_filter { - struct tep_handle *pevent; + struct tep_handle *tep; int filters; struct tep_filter_type *event_filters; char error_buffer[TEP_FILTER_ERROR_BUFSZ]; }; -struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent); +struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep); /* for backward compatibility */ #define FILTER_NONE TEP_ERRNO__NO_FILTER @@ -723,12 +731,6 @@ struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent); #define FILTER_MISS TEP_ERRNO__FILTER_MISS #define FILTER_MATCH TEP_ERRNO__FILTER_MATCH -enum tep_filter_trivial_type { - TEP_FILTER_TRIVIAL_FALSE, - TEP_FILTER_TRIVIAL_TRUE, - TEP_FILTER_TRIVIAL_BOTH, -}; - enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, const char *filter_str); @@ -743,9 +745,6 @@ int tep_event_filtered(struct tep_event_filter *filter, void tep_filter_reset(struct tep_event_filter *filter); -int tep_filter_clear_trivial(struct tep_event_filter *filter, - enum tep_filter_trivial_type type); - void tep_filter_free(struct tep_event_filter *filter); char *tep_filter_make_string(struct tep_event_filter *filter, int event_id); @@ -753,15 +752,8 @@ char *tep_filter_make_string(struct tep_event_filter *filter, int event_id); int tep_filter_remove_event(struct tep_event_filter *filter, int event_id); -int tep_filter_event_has_trivial(struct tep_event_filter *filter, - int event_id, - enum tep_filter_trivial_type type); - int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source); -int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source, - enum tep_filter_trivial_type type); - int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2); #endif /* _PARSE_EVENTS_H */ diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c index e74f16c88398..8ca28de9337a 100644 --- a/tools/lib/traceevent/event-plugin.c +++ b/tools/lib/traceevent/event-plugin.c @@ -269,7 +269,7 @@ void tep_print_plugins(struct trace_seq *s, } static void -load_plugin(struct tep_handle *pevent, const char *path, +load_plugin(struct tep_handle *tep, const char *path, const char *file, void *data) { struct tep_plugin_list **plugin_list = data; @@ -316,7 +316,7 @@ load_plugin(struct tep_handle *pevent, const char *path, *plugin_list = list; pr_stat("registering plugin: %s", plugin); - func(pevent); + func(tep); return; out_free: @@ -324,9 +324,9 @@ load_plugin(struct tep_handle *pevent, const char *path, } static void -load_plugins_dir(struct tep_handle *pevent, const char *suffix, +load_plugins_dir(struct tep_handle *tep, const char *suffix, const char *path, - void (*load_plugin)(struct tep_handle *pevent, + void (*load_plugin)(struct tep_handle *tep, const char *path, const char *name, void *data), @@ -359,15 +359,15 @@ load_plugins_dir(struct tep_handle *pevent, const char *suffix, if (strcmp(name + (strlen(name) - strlen(suffix)), suffix) != 0) continue; - load_plugin(pevent, path, name, data); + load_plugin(tep, path, name, data); } closedir(dir); } static void -load_plugins(struct tep_handle *pevent, const char *suffix, - void (*load_plugin)(struct tep_handle *pevent, +load_plugins(struct tep_handle *tep, const char *suffix, + void (*load_plugin)(struct tep_handle *tep, const char *path, const char *name, void *data), @@ -378,7 +378,7 @@ load_plugins(struct tep_handle *pevent, const char *suffix, char *envdir; int ret; - if (pevent->flags & TEP_DISABLE_PLUGINS) + if (tep->flags & TEP_DISABLE_PLUGINS) return; /* @@ -386,8 +386,8 @@ load_plugins(struct tep_handle *pevent, const char *suffix, * check that first. */ #ifdef PLUGIN_DIR - if (!(pevent->flags & TEP_DISABLE_SYS_PLUGINS)) - load_plugins_dir(pevent, suffix, PLUGIN_DIR, + if (!(tep->flags & TEP_DISABLE_SYS_PLUGINS)) + load_plugins_dir(tep, suffix, PLUGIN_DIR, load_plugin, data); #endif @@ -397,7 +397,7 @@ load_plugins(struct tep_handle *pevent, const char *suffix, */ envdir = getenv("TRACEEVENT_PLUGIN_DIR"); if (envdir) - load_plugins_dir(pevent, suffix, envdir, load_plugin, data); + load_plugins_dir(tep, suffix, envdir, load_plugin, data); /* * Now let the home directory override the environment @@ -413,22 +413,22 @@ load_plugins(struct tep_handle *pevent, const char *suffix, return; } - load_plugins_dir(pevent, suffix, path, load_plugin, data); + load_plugins_dir(tep, suffix, path, load_plugin, data); free(path); } struct tep_plugin_list* -tep_load_plugins(struct tep_handle *pevent) +tep_load_plugins(struct tep_handle *tep) { struct tep_plugin_list *list = NULL; - load_plugins(pevent, ".so", load_plugin, &list); + load_plugins(tep, ".so", load_plugin, &list); return list; } void -tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *pevent) +tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *tep) { tep_plugin_unload_func func; struct tep_plugin_list *list; @@ -438,7 +438,7 @@ tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *peven plugin_list = list->next; func = dlsym(list->handle, TEP_PLUGIN_UNLOADER_NAME); if (func) - func(pevent); + func(tep); dlclose(list->handle); free(list->name); free(list); diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c index af2a1f3b7424..b887e7437d67 100644 --- a/tools/lib/traceevent/kbuffer-parse.c +++ b/tools/lib/traceevent/kbuffer-parse.c @@ -727,3 +727,52 @@ int kbuffer_start_of_data(struct kbuffer *kbuf) { return kbuf->start; } + +/** + * kbuffer_raw_get - get raw buffer info + * @kbuf: The kbuffer + * @subbuf: Start of mapped subbuffer + * @info: Info descriptor to fill in + * + * For debugging. This can return internals of the ring buffer. + * Expects to have info->next set to what it will read. + * The type, length and timestamp delta will be filled in, and + * @info->next will be updated to the next element. + * The @subbuf is used to know if the info is passed the end of + * data and NULL will be returned if it is. + */ +struct kbuffer_raw_info * +kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf, struct kbuffer_raw_info *info) +{ + unsigned long long flags; + unsigned long long delta; + unsigned int type_len; + unsigned int size; + int start; + int length; + void *ptr = info->next; + + if (!kbuf || !subbuf) + return NULL; + + if (kbuf->flags & KBUFFER_FL_LONG_8) + start = 16; + else + start = 12; + + flags = read_long(kbuf, subbuf + 8); + size = (unsigned int)flags & COMMIT_MASK; + + if (ptr < subbuf || ptr >= subbuf + start + size) + return NULL; + + type_len = translate_data(kbuf, ptr, &ptr, &delta, &length); + + info->next = ptr + length; + + info->type = type_len; + info->delta = delta; + info->length = length; + + return info; +} diff --git a/tools/lib/traceevent/kbuffer.h b/tools/lib/traceevent/kbuffer.h index 03dce757553f..ed4d697fc137 100644 --- a/tools/lib/traceevent/kbuffer.h +++ b/tools/lib/traceevent/kbuffer.h @@ -65,4 +65,17 @@ int kbuffer_subbuffer_size(struct kbuffer *kbuf); void kbuffer_set_old_format(struct kbuffer *kbuf); int kbuffer_start_of_data(struct kbuffer *kbuf); +/* Debugging */ + +struct kbuffer_raw_info { + int type; + int length; + unsigned long long delta; + void *next; +}; + +/* Read raw data */ +struct kbuffer_raw_info *kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf, + struct kbuffer_raw_info *info); + #endif /* _K_BUFFER_H */ diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c index cb5ce66dab6e..552592d153fb 100644 --- a/tools/lib/traceevent/parse-filter.c +++ b/tools/lib/traceevent/parse-filter.c @@ -154,7 +154,7 @@ add_filter_type(struct tep_event_filter *filter, int id) filter_type = &filter->event_filters[i]; filter_type->event_id = id; - filter_type->event = tep_find_event(filter->pevent, id); + filter_type->event = tep_find_event(filter->tep, id); filter_type->filter = NULL; filter->filters++; @@ -164,9 +164,9 @@ add_filter_type(struct tep_event_filter *filter, int id) /** * tep_filter_alloc - create a new event filter - * @pevent: The pevent that this filter is associated with + * @tep: The tep that this filter is associated with */ -struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent) +struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep) { struct tep_event_filter *filter; @@ -175,8 +175,8 @@ struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent) return NULL; memset(filter, 0, sizeof(*filter)); - filter->pevent = pevent; - tep_ref(pevent); + filter->tep = tep; + tep_ref(tep); return filter; } @@ -256,7 +256,7 @@ static int event_match(struct tep_event *event, } static enum tep_errno -find_event(struct tep_handle *pevent, struct event_list **events, +find_event(struct tep_handle *tep, struct event_list **events, char *sys_name, char *event_name) { struct tep_event *event; @@ -299,8 +299,8 @@ find_event(struct tep_handle *pevent, struct event_list **events, } } - for (i = 0; i < pevent->nr_events; i++) { - event = pevent->events[i]; + for (i = 0; i < tep->nr_events; i++) { + event = tep->events[i]; if (event_match(event, sys_name ? &sreg : NULL, &ereg)) { match = 1; if (add_event(events, event) < 0) { @@ -1257,7 +1257,7 @@ static void filter_init_error_buf(struct tep_event_filter *filter) enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, const char *filter_str) { - struct tep_handle *pevent = filter->pevent; + struct tep_handle *tep = filter->tep; struct event_list *event; struct event_list *events = NULL; const char *filter_start; @@ -1313,7 +1313,7 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, } /* Find this event */ - ret = find_event(pevent, &events, strim(sys_name), strim(event_name)); + ret = find_event(tep, &events, strim(sys_name), strim(event_name)); if (ret < 0) { free_events(events); free(this_event); @@ -1334,7 +1334,7 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, if (ret < 0) rtn = ret; - if (ret >= 0 && pevent->test_filters) { + if (ret >= 0 && tep->test_filters) { char *test; test = tep_filter_make_string(filter, event->event->id); if (test) { @@ -1346,9 +1346,6 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, free_events(events); - if (rtn >= 0 && pevent->test_filters) - exit(0); - return rtn; } @@ -1380,7 +1377,7 @@ int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err, return 0; } - return tep_strerror(filter->pevent, err, buf, buflen); + return tep_strerror(filter->tep, err, buf, buflen); } /** @@ -1443,7 +1440,7 @@ void tep_filter_reset(struct tep_event_filter *filter) void tep_filter_free(struct tep_event_filter *filter) { - tep_unref(filter->pevent); + tep_unref(filter->tep); tep_filter_reset(filter); @@ -1462,10 +1459,10 @@ static int copy_filter_type(struct tep_event_filter *filter, const char *name; char *str; - /* Can't assume that the pevent's are the same */ + /* Can't assume that the tep's are the same */ sys = filter_type->event->system; name = filter_type->event->name; - event = tep_find_event_by_name(filter->pevent, sys, name); + event = tep_find_event_by_name(filter->tep, sys, name); if (!event) return -1; @@ -1522,167 +1519,6 @@ int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *sour return ret; } - -/** - * tep_update_trivial - update the trivial filters with the given filter - * @dest - the filter to update - * @source - the filter as the source of the update - * @type - the type of trivial filter to update. - * - * Scan dest for trivial events matching @type to replace with the source. - * - * Returns 0 on success and -1 if there was a problem updating, but - * events may have still been updated on error. - */ -int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source, - enum tep_filter_trivial_type type) -{ - struct tep_handle *src_pevent; - struct tep_handle *dest_pevent; - struct tep_event *event; - struct tep_filter_type *filter_type; - struct tep_filter_arg *arg; - char *str; - int i; - - src_pevent = source->pevent; - dest_pevent = dest->pevent; - - /* Do nothing if either of the filters has nothing to filter */ - if (!dest->filters || !source->filters) - return 0; - - for (i = 0; i < dest->filters; i++) { - filter_type = &dest->event_filters[i]; - arg = filter_type->filter; - if (arg->type != TEP_FILTER_ARG_BOOLEAN) - continue; - if ((arg->boolean.value && type == TEP_FILTER_TRIVIAL_FALSE) || - (!arg->boolean.value && type == TEP_FILTER_TRIVIAL_TRUE)) - continue; - - event = filter_type->event; - - if (src_pevent != dest_pevent) { - /* do a look up */ - event = tep_find_event_by_name(src_pevent, - event->system, - event->name); - if (!event) - return -1; - } - - str = tep_filter_make_string(source, event->id); - if (!str) - continue; - - /* Don't bother if the filter is trivial too */ - if (strcmp(str, "TRUE") != 0 && strcmp(str, "FALSE") != 0) - filter_event(dest, event, str, NULL); - free(str); - } - return 0; -} - -/** - * tep_filter_clear_trivial - clear TRUE and FALSE filters - * @filter: the filter to remove trivial filters from - * @type: remove only true, false, or both - * - * Removes filters that only contain a TRUE or FALES boolean arg. - * - * Returns 0 on success and -1 if there was a problem. - */ -int tep_filter_clear_trivial(struct tep_event_filter *filter, - enum tep_filter_trivial_type type) -{ - struct tep_filter_type *filter_type; - int count = 0; - int *ids = NULL; - int i; - - if (!filter->filters) - return 0; - - /* - * Two steps, first get all ids with trivial filters. - * then remove those ids. - */ - for (i = 0; i < filter->filters; i++) { - int *new_ids; - - filter_type = &filter->event_filters[i]; - if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN) - continue; - switch (type) { - case TEP_FILTER_TRIVIAL_FALSE: - if (filter_type->filter->boolean.value) - continue; - break; - case TEP_FILTER_TRIVIAL_TRUE: - if (!filter_type->filter->boolean.value) - continue; - default: - break; - } - - new_ids = realloc(ids, sizeof(*ids) * (count + 1)); - if (!new_ids) { - free(ids); - return -1; - } - - ids = new_ids; - ids[count++] = filter_type->event_id; - } - - if (!count) - return 0; - - for (i = 0; i < count; i++) - tep_filter_remove_event(filter, ids[i]); - - free(ids); - return 0; -} - -/** - * tep_filter_event_has_trivial - return true event contains trivial filter - * @filter: the filter with the information - * @event_id: the id of the event to test - * @type: trivial type to test for (TRUE, FALSE, EITHER) - * - * Returns 1 if the event contains a matching trivial type - * otherwise 0. - */ -int tep_filter_event_has_trivial(struct tep_event_filter *filter, - int event_id, - enum tep_filter_trivial_type type) -{ - struct tep_filter_type *filter_type; - - if (!filter->filters) - return 0; - - filter_type = find_filter_type(filter, event_id); - - if (!filter_type) - return 0; - - if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN) - return 0; - - switch (type) { - case TEP_FILTER_TRIVIAL_FALSE: - return !filter_type->filter->boolean.value; - - case TEP_FILTER_TRIVIAL_TRUE: - return filter_type->filter->boolean.value; - default: - return 1; - } -} - static int test_filter(struct tep_event *event, struct tep_filter_arg *arg, struct tep_record *record, enum tep_errno *err); @@ -1692,8 +1528,8 @@ get_comm(struct tep_event *event, struct tep_record *record) const char *comm; int pid; - pid = tep_data_pid(event->pevent, record); - comm = tep_data_comm_from_pid(event->pevent, pid); + pid = tep_data_pid(event->tep, record); + comm = tep_data_comm_from_pid(event->tep, pid); return comm; } @@ -1861,7 +1697,7 @@ static int test_num(struct tep_event *event, struct tep_filter_arg *arg, static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *record) { struct tep_event *event; - struct tep_handle *pevent; + struct tep_handle *tep; unsigned long long addr; const char *val = NULL; unsigned int size; @@ -1891,12 +1727,12 @@ static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record * } else { event = arg->str.field->event; - pevent = event->pevent; + tep = event->tep; addr = get_value(event, arg->str.field, record); if (arg->str.field->flags & (TEP_FIELD_IS_POINTER | TEP_FIELD_IS_LONG)) /* convert to a kernel symbol */ - val = tep_find_function(pevent, addr); + val = tep_find_function(tep, addr); if (val == NULL) { /* just use the hex of the string name */ @@ -2036,7 +1872,7 @@ int tep_event_filtered(struct tep_event_filter *filter, int event_id) enum tep_errno tep_filter_match(struct tep_event_filter *filter, struct tep_record *record) { - struct tep_handle *pevent = filter->pevent; + struct tep_handle *tep = filter->tep; struct tep_filter_type *filter_type; int event_id; int ret; @@ -2047,7 +1883,7 @@ enum tep_errno tep_filter_match(struct tep_event_filter *filter, if (!filter->filters) return TEP_ERRNO__NO_FILTER; - event_id = tep_data_type(pevent, record); + event_id = tep_data_type(tep, record); filter_type = find_filter_type(filter, event_id); if (!filter_type) @@ -2409,14 +2245,6 @@ int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter break; if (filter_type1->filter->type != filter_type2->filter->type) break; - switch (filter_type1->filter->type) { - case TEP_FILTER_TRIVIAL_FALSE: - case TEP_FILTER_TRIVIAL_TRUE: - /* trivial types just need the type compared */ - continue; - default: - break; - } /* The best way to compare complex filters is with strings */ str1 = arg_to_str(filter1, filter_type1->filter); str2 = arg_to_str(filter2, filter_type2->filter); diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c index a51b366f47da..3d43b56a6c98 100644 --- a/tools/lib/traceevent/plugin_cfg80211.c +++ b/tools/lib/traceevent/plugin_cfg80211.c @@ -25,9 +25,9 @@ process___le16_to_cpup(struct trace_seq *s, unsigned long long *args) return val ? (long long) le16toh(*val) : 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_print_function(pevent, + tep_register_print_function(tep, process___le16_to_cpup, TEP_FUNC_ARG_INT, "__le16_to_cpup", @@ -36,8 +36,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_print_function(pevent, process___le16_to_cpup, + tep_unregister_print_function(tep, process___le16_to_cpup, "__le16_to_cpup"); } diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c index a73eca34a8f9..7770fcb78e0f 100644 --- a/tools/lib/traceevent/plugin_function.c +++ b/tools/lib/traceevent/plugin_function.c @@ -126,7 +126,7 @@ static int add_and_get_index(const char *parent, const char *child, int cpu) static int function_handler(struct trace_seq *s, struct tep_record *record, struct tep_event *event, void *context) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; unsigned long long function; unsigned long long pfunction; const char *func; @@ -136,12 +136,12 @@ static int function_handler(struct trace_seq *s, struct tep_record *record, if (tep_get_field_val(s, event, "ip", record, &function, 1)) return trace_seq_putc(s, '!'); - func = tep_find_function(pevent, function); + func = tep_find_function(tep, function); if (tep_get_field_val(s, event, "parent_ip", record, &pfunction, 1)) return trace_seq_putc(s, '!'); - parent = tep_find_function(pevent, pfunction); + parent = tep_find_function(tep, pfunction); if (parent && ftrace_indent->set) index = add_and_get_index(parent, func, record->cpu); @@ -164,9 +164,9 @@ static int function_handler(struct trace_seq *s, struct tep_record *record, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_event_handler(pevent, -1, "ftrace", "function", + tep_register_event_handler(tep, -1, "ftrace", "function", function_handler, NULL); tep_plugin_add_options("ftrace", plugin_options); @@ -174,11 +174,11 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { int i, x; - tep_unregister_event_handler(pevent, -1, "ftrace", "function", + tep_unregister_event_handler(tep, -1, "ftrace", "function", function_handler, NULL); for (i = 0; i <= cpus; i++) { diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c index 5db5e401275f..bb434e0ed03a 100644 --- a/tools/lib/traceevent/plugin_hrtimer.c +++ b/tools/lib/traceevent/plugin_hrtimer.c @@ -67,23 +67,23 @@ static int timer_start_handler(struct trace_seq *s, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_event_handler(pevent, -1, + tep_register_event_handler(tep, -1, "timer", "hrtimer_expire_entry", timer_expire_handler, NULL); - tep_register_event_handler(pevent, -1, "timer", "hrtimer_start", + tep_register_event_handler(tep, -1, "timer", "hrtimer_start", timer_start_handler, NULL); return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_event_handler(pevent, -1, + tep_unregister_event_handler(tep, -1, "timer", "hrtimer_expire_entry", timer_expire_handler, NULL); - tep_unregister_event_handler(pevent, -1, "timer", "hrtimer_start", + tep_unregister_event_handler(tep, -1, "timer", "hrtimer_start", timer_start_handler, NULL); } diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c index a5e34135dd6a..04fc125f38cb 100644 --- a/tools/lib/traceevent/plugin_jbd2.c +++ b/tools/lib/traceevent/plugin_jbd2.c @@ -48,16 +48,16 @@ process_jiffies_to_msecs(struct trace_seq *s, unsigned long long *args) return jiffies; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_print_function(pevent, + tep_register_print_function(tep, process_jbd2_dev_to_name, TEP_FUNC_ARG_STRING, "jbd2_dev_to_name", TEP_FUNC_ARG_INT, TEP_FUNC_ARG_VOID); - tep_register_print_function(pevent, + tep_register_print_function(tep, process_jiffies_to_msecs, TEP_FUNC_ARG_LONG, "jiffies_to_msecs", @@ -66,11 +66,11 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_print_function(pevent, process_jbd2_dev_to_name, + tep_unregister_print_function(tep, process_jbd2_dev_to_name, "jbd2_dev_to_name"); - tep_unregister_print_function(pevent, process_jiffies_to_msecs, + tep_unregister_print_function(tep, process_jiffies_to_msecs, "jiffies_to_msecs"); } diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c index 0e3c601f9ed1..edaec5d962c3 100644 --- a/tools/lib/traceevent/plugin_kmem.c +++ b/tools/lib/traceevent/plugin_kmem.c @@ -39,57 +39,57 @@ static int call_site_handler(struct trace_seq *s, struct tep_record *record, if (tep_read_number_field(field, data, &val)) return 1; - func = tep_find_function(event->pevent, val); + func = tep_find_function(event->tep, val); if (!func) return 1; - addr = tep_find_function_address(event->pevent, val); + addr = tep_find_function_address(event->tep, val); trace_seq_printf(s, "(%s+0x%x) ", func, (int)(val - addr)); return 1; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_event_handler(pevent, -1, "kmem", "kfree", + tep_register_event_handler(tep, -1, "kmem", "kfree", call_site_handler, NULL); - tep_register_event_handler(pevent, -1, "kmem", "kmalloc", + tep_register_event_handler(tep, -1, "kmem", "kmalloc", call_site_handler, NULL); - tep_register_event_handler(pevent, -1, "kmem", "kmalloc_node", + tep_register_event_handler(tep, -1, "kmem", "kmalloc_node", call_site_handler, NULL); - tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_alloc", + tep_register_event_handler(tep, -1, "kmem", "kmem_cache_alloc", call_site_handler, NULL); - tep_register_event_handler(pevent, -1, "kmem", + tep_register_event_handler(tep, -1, "kmem", "kmem_cache_alloc_node", call_site_handler, NULL); - tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_free", + tep_register_event_handler(tep, -1, "kmem", "kmem_cache_free", call_site_handler, NULL); return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_event_handler(pevent, -1, "kmem", "kfree", + tep_unregister_event_handler(tep, -1, "kmem", "kfree", call_site_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc", + tep_unregister_event_handler(tep, -1, "kmem", "kmalloc", call_site_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc_node", + tep_unregister_event_handler(tep, -1, "kmem", "kmalloc_node", call_site_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_alloc", + tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_alloc", call_site_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kmem", + tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_alloc_node", call_site_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_free", + tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_free", call_site_handler, NULL); } diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c index 64b9c25a1fd3..c8e623065a7e 100644 --- a/tools/lib/traceevent/plugin_kvm.c +++ b/tools/lib/traceevent/plugin_kvm.c @@ -389,8 +389,8 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record, * We can only use the structure if file is of the same * endianness. */ - if (tep_file_bigendian(event->pevent) == - tep_is_host_bigendian(event->pevent)) { + if (tep_is_file_bigendian(event->tep) == + tep_is_local_bigendian(event->tep)) { trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s", role.level, @@ -445,40 +445,40 @@ process_is_writable_pte(struct trace_seq *s, unsigned long long *args) return pte & PT_WRITABLE_MASK; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { init_disassembler(); - tep_register_event_handler(pevent, -1, "kvm", "kvm_exit", + tep_register_event_handler(tep, -1, "kvm", "kvm_exit", kvm_exit_handler, NULL); - tep_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn", + tep_register_event_handler(tep, -1, "kvm", "kvm_emulate_insn", kvm_emulate_insn_handler, NULL); - tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit", + tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit", kvm_nested_vmexit_handler, NULL); - tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject", + tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject", kvm_nested_vmexit_inject_handler, NULL); - tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page", + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page", kvm_mmu_get_page_handler, NULL); - tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page", + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page", kvm_mmu_print_role, NULL); - tep_register_event_handler(pevent, -1, + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_unsync_page", kvm_mmu_print_role, NULL); - tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page", + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page", kvm_mmu_print_role, NULL); - tep_register_event_handler(pevent, -1, "kvmmmu", + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_prepare_zap_page", kvm_mmu_print_role, NULL); - tep_register_print_function(pevent, + tep_register_print_function(tep, process_is_writable_pte, TEP_FUNC_ARG_INT, "is_writable_pte", @@ -487,37 +487,37 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_event_handler(pevent, -1, "kvm", "kvm_exit", + tep_unregister_event_handler(tep, -1, "kvm", "kvm_exit", kvm_exit_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn", + tep_unregister_event_handler(tep, -1, "kvm", "kvm_emulate_insn", kvm_emulate_insn_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit", + tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit", kvm_nested_vmexit_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject", + tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject", kvm_nested_vmexit_inject_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page", + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page", kvm_mmu_get_page_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page", + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page", kvm_mmu_print_role, NULL); - tep_unregister_event_handler(pevent, -1, + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_unsync_page", kvm_mmu_print_role, NULL); - tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page", + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page", kvm_mmu_print_role, NULL); - tep_unregister_event_handler(pevent, -1, "kvmmmu", + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_prepare_zap_page", kvm_mmu_print_role, NULL); - tep_unregister_print_function(pevent, process_is_writable_pte, + tep_unregister_print_function(tep, process_is_writable_pte, "is_writable_pte"); } diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c index e38b9477aad2..884303c26b5c 100644 --- a/tools/lib/traceevent/plugin_mac80211.c +++ b/tools/lib/traceevent/plugin_mac80211.c @@ -87,17 +87,17 @@ static int drv_bss_info_changed(struct trace_seq *s, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_event_handler(pevent, -1, "mac80211", + tep_register_event_handler(tep, -1, "mac80211", "drv_bss_info_changed", drv_bss_info_changed, NULL); return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_event_handler(pevent, -1, "mac80211", + tep_unregister_event_handler(tep, -1, "mac80211", "drv_bss_info_changed", drv_bss_info_changed, NULL); } diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c index 834c9e378ff8..957389a0ff7a 100644 --- a/tools/lib/traceevent/plugin_sched_switch.c +++ b/tools/lib/traceevent/plugin_sched_switch.c @@ -62,7 +62,7 @@ static void write_and_save_comm(struct tep_format_field *field, comm = &s->buffer[len]; /* Help out the comm to ids. This will handle dups */ - tep_register_comm(field->event->pevent, comm, pid); + tep_register_comm(field->event->tep, comm, pid); } static int sched_wakeup_handler(struct trace_seq *s, @@ -135,27 +135,27 @@ static int sched_switch_handler(struct trace_seq *s, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_event_handler(pevent, -1, "sched", "sched_switch", + tep_register_event_handler(tep, -1, "sched", "sched_switch", sched_switch_handler, NULL); - tep_register_event_handler(pevent, -1, "sched", "sched_wakeup", + tep_register_event_handler(tep, -1, "sched", "sched_wakeup", sched_wakeup_handler, NULL); - tep_register_event_handler(pevent, -1, "sched", "sched_wakeup_new", + tep_register_event_handler(tep, -1, "sched", "sched_wakeup_new", sched_wakeup_handler, NULL); return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_event_handler(pevent, -1, "sched", "sched_switch", + tep_unregister_event_handler(tep, -1, "sched", "sched_switch", sched_switch_handler, NULL); - tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup", + tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup", sched_wakeup_handler, NULL); - tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup_new", + tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup_new", sched_wakeup_handler, NULL); } diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c index 4eba25cc1431..5d0387a4b65a 100644 --- a/tools/lib/traceevent/plugin_scsi.c +++ b/tools/lib/traceevent/plugin_scsi.c @@ -414,9 +414,9 @@ unsigned long long process_scsi_trace_parse_cdb(struct trace_seq *s, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_print_function(pevent, + tep_register_print_function(tep, process_scsi_trace_parse_cdb, TEP_FUNC_ARG_STRING, "scsi_trace_parse_cdb", @@ -427,8 +427,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_print_function(pevent, process_scsi_trace_parse_cdb, + tep_unregister_print_function(tep, process_scsi_trace_parse_cdb, "scsi_trace_parse_cdb"); } diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c index bc0496e4c296..993b208d0323 100644 --- a/tools/lib/traceevent/plugin_xen.c +++ b/tools/lib/traceevent/plugin_xen.c @@ -120,9 +120,9 @@ unsigned long long process_xen_hypercall_name(struct trace_seq *s, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_print_function(pevent, + tep_register_print_function(tep, process_xen_hypercall_name, TEP_FUNC_ARG_STRING, "xen_hypercall_name", @@ -131,8 +131,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_print_function(pevent, process_xen_hypercall_name, + tep_unregister_print_function(tep, process_xen_hypercall_name, "xen_hypercall_name"); } diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 8fe4dffcadd0..58986f4cc190 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -459,6 +459,25 @@ Set affinity mask of trace reading thread according to the policy defined by 'mo node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer cpu - thread affinity mask is set to cpu of the processed mmap buffer +--mmap-flush=number:: + +Specify minimal number of bytes that is extracted from mmap data pages and +processed for output. One can specify the number using B/K/M/G suffixes. + +The maximal allowed value is a quarter of the size of mmaped data pages. + +The default option value is 1 byte which means that every time that the output +writing thread finds some new data in the mmaped buffer the data is extracted, +possibly compressed (-z) and written to the output, perf.data or pipe. + +Larger data chunks are compressed more effectively in comparison to smaller +chunks so extraction of larger chunks from the mmap data pages is preferable +from the perspective of output size reduction. + +Also at some cases executing less output write syscalls with bigger data size +can take less time than executing more output write syscalls with smaller data +size thus lowering runtime profiling overhead. + --all-kernel:: Configure all used events to run in kernel space. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 6d65874e16c3..0c52a01dc759 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -152,6 +152,13 @@ endif FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf +ifdef LIBZSTD_DIR + LIBZSTD_CFLAGS := -I$(LIBZSTD_DIR)/lib + LIBZSTD_LDFLAGS := -L$(LIBZSTD_DIR)/lib +endif +FEATURE_CHECK_CFLAGS-libzstd := $(LIBZSTD_CFLAGS) +FEATURE_CHECK_LDFLAGS-libzstd := $(LIBZSTD_LDFLAGS) + FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi # include ARCH specific config -include $(src-perf)/arch/$(SRCARCH)/Makefile @@ -787,6 +794,19 @@ ifndef NO_LZMA endif endif +ifndef NO_LIBZSTD + ifeq ($(feature-libzstd), 1) + CFLAGS += -DHAVE_ZSTD_SUPPORT + CFLAGS += $(LIBZSTD_CFLAGS) + LDFLAGS += $(LIBZSTD_LDFLAGS) + EXTLIBS += -lzstd + $(call detected,CONFIG_ZSTD) + else + msg := $(warning No libzstd found, disables trace compression, please install libzstd-dev[el] and/or set LIBZSTD_DIR); + NO_LIBZSTD := 1 + endif +endif + ifndef NO_BACKTRACE ifeq ($(feature-backtrace), 1) CFLAGS += -DHAVE_BACKTRACE_SUPPORT diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index e8c9f77e9010..c706548d5b10 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -108,6 +108,9 @@ include ../scripts/utilities.mak # streaming for record mode. Currently Posix AIO trace streaming is # supported only when linking with glibc. # +# Define NO_LIBZSTD if you do not want support of Zstandard based runtime +# trace compression in record mode. +# # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index fa520f4b8095..b80eee455111 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1975,7 +1975,7 @@ int cmd_kmem(int argc, const char **argv) goto out_delete; } - kmem_page_size = tep_get_page_size(evsel->tp_format->pevent); + kmem_page_size = tep_get_page_size(evsel->tp_format->tep); symbol_conf.use_callchain = true; } diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index a8394b4f1167..e0312a1c4792 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -70,10 +70,11 @@ int cmd_list(int argc, const char **argv) print_symbol_events(NULL, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump); else if (strcmp(argv[i], "sw") == 0 || - strcmp(argv[i], "software") == 0) + strcmp(argv[i], "software") == 0) { print_symbol_events(NULL, PERF_TYPE_SOFTWARE, event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump); - else if (strcmp(argv[i], "cache") == 0 || + print_tool_events(NULL, raw_dump); + } else if (strcmp(argv[i], "cache") == 0 || strcmp(argv[i], "hwcache") == 0) print_hwcache_events(NULL, raw_dump); else if (strcmp(argv[i], "pmu") == 0) @@ -113,6 +114,7 @@ int cmd_list(int argc, const char **argv) event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump); print_symbol_events(s, PERF_TYPE_SOFTWARE, event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump); + print_tool_events(s, raw_dump); print_hwcache_events(s, raw_dump); print_pmu_events(s, raw_dump, !desc_flag, long_desc_flag, diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 4e2d953d4bc5..c5e10552776a 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -337,6 +337,41 @@ static int record__aio_enabled(struct record *rec) return rec->opts.nr_cblocks > 0; } +#define MMAP_FLUSH_DEFAULT 1 +static int record__mmap_flush_parse(const struct option *opt, + const char *str, + int unset) +{ + int flush_max; + struct record_opts *opts = (struct record_opts *)opt->value; + static struct parse_tag tags[] = { + { .tag = 'B', .mult = 1 }, + { .tag = 'K', .mult = 1 << 10 }, + { .tag = 'M', .mult = 1 << 20 }, + { .tag = 'G', .mult = 1 << 30 }, + { .tag = 0 }, + }; + + if (unset) + return 0; + + if (str) { + opts->mmap_flush = parse_tag_value(str, tags); + if (opts->mmap_flush == (int)-1) + opts->mmap_flush = strtol(str, NULL, 0); + } + + if (!opts->mmap_flush) + opts->mmap_flush = MMAP_FLUSH_DEFAULT; + + flush_max = perf_evlist__mmap_size(opts->mmap_pages); + flush_max /= 4; + if (opts->mmap_flush > flush_max) + opts->mmap_flush = flush_max; + + return 0; +} + static int process_synthesized_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample __maybe_unused, @@ -546,7 +581,8 @@ static int record__mmap_evlist(struct record *rec, if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, opts->auxtrace_mmap_pages, opts->auxtrace_snapshot_mode, - opts->nr_cblocks, opts->affinity) < 0) { + opts->nr_cblocks, opts->affinity, + opts->mmap_flush) < 0) { if (errno == EPERM) { pr_err("Permission error mapping pages.\n" "Consider increasing " @@ -736,7 +772,7 @@ static void record__adjust_affinity(struct record *rec, struct perf_mmap *map) } static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist, - bool overwrite) + bool overwrite, bool synch) { u64 bytes_written = rec->bytes_written; int i; @@ -759,12 +795,19 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli off = record__aio_get_pos(trace_fd); for (i = 0; i < evlist->nr_mmaps; i++) { + u64 flush = 0; struct perf_mmap *map = &maps[i]; if (map->base) { record__adjust_affinity(rec, map); + if (synch) { + flush = map->flush; + map->flush = 1; + } if (!record__aio_enabled(rec)) { if (perf_mmap__push(map, rec, record__pushfn) != 0) { + if (synch) + map->flush = flush; rc = -1; goto out; } @@ -777,10 +820,14 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli idx = record__aio_sync(map, false); if (perf_mmap__aio_push(map, rec, idx, record__aio_pushfn, &off) != 0) { record__aio_set_pos(trace_fd, off); + if (synch) + map->flush = flush; rc = -1; goto out; } } + if (synch) + map->flush = flush; } if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode && @@ -806,15 +853,15 @@ out: return rc; } -static int record__mmap_read_all(struct record *rec) +static int record__mmap_read_all(struct record *rec, bool synch) { int err; - err = record__mmap_read_evlist(rec, rec->evlist, false); + err = record__mmap_read_evlist(rec, rec->evlist, false, synch); if (err) return err; - return record__mmap_read_evlist(rec, rec->evlist, true); + return record__mmap_read_evlist(rec, rec->evlist, true, synch); } static void record__init_features(struct record *rec) @@ -1340,7 +1387,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (trigger_is_hit(&switch_output_trigger) || done || draining) perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING); - if (record__mmap_read_all(rec) < 0) { + if (record__mmap_read_all(rec, false) < 0) { trigger_error(&auxtrace_snapshot_trigger); trigger_error(&switch_output_trigger); err = -1; @@ -1441,6 +1488,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) record__synthesize_workload(rec, true); out_child: + record__mmap_read_all(rec, true); record__aio_mmap_read_sync(rec); if (forks) { @@ -1846,6 +1894,7 @@ static struct record record = { .uses_mmap = true, .default_per_cpu = true, }, + .mmap_flush = MMAP_FLUSH_DEFAULT, }, .tool = { .sample = process_sample_event, @@ -1912,6 +1961,9 @@ static struct option __record_options[] = { OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]", "number of mmap data pages and AUX area tracing mmap pages", record__parse_mmap_pages), + OPT_CALLBACK(0, "mmap-flush", &record.opts, "number", + "Minimal number of bytes that is extracted from mmap data pages (default: 1)", + record__mmap_flush_parse), OPT_BOOLEAN(0, "group", &record.opts.group, "put the counters into a counter group"), OPT_CALLBACK_NOOPT('g', NULL, &callchain_param, @@ -2224,6 +2276,7 @@ int cmd_record(int argc, const char **argv) pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks); pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]); + pr_debug("mmap flush: %d\n", rec->opts.mmap_flush); err = __cmd_record(&record, argc, argv); out: diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index c3625ec374e0..a3c060878faa 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -244,11 +244,25 @@ perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread, process_synthesized_event, NULL); } +static int read_single_counter(struct perf_evsel *counter, int cpu, + int thread, struct timespec *rs) +{ + if (counter->tool_event == PERF_TOOL_DURATION_TIME) { + u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL; + struct perf_counts_values *count = + perf_counts(counter->counts, cpu, thread); + count->ena = count->run = val; + count->val = val; + return 0; + } + return perf_evsel__read_counter(counter, cpu, thread); +} + /* * Read out the results of a single counter: * do not aggregate counts across CPUs in system-wide mode */ -static int read_counter(struct perf_evsel *counter) +static int read_counter(struct perf_evsel *counter, struct timespec *rs) { int nthreads = thread_map__nr(evsel_list->threads); int ncpus, cpu, thread; @@ -275,7 +289,7 @@ static int read_counter(struct perf_evsel *counter) * (via perf_evsel__read_counter) and sets threir count->loaded. */ if (!count->loaded && - perf_evsel__read_counter(counter, cpu, thread)) { + read_single_counter(counter, cpu, thread, rs)) { counter->counts->scaled = -1; perf_counts(counter->counts, cpu, thread)->ena = 0; perf_counts(counter->counts, cpu, thread)->run = 0; @@ -304,13 +318,13 @@ static int read_counter(struct perf_evsel *counter) return 0; } -static void read_counters(void) +static void read_counters(struct timespec *rs) { struct perf_evsel *counter; int ret; evlist__for_each_entry(evsel_list, counter) { - ret = read_counter(counter); + ret = read_counter(counter, rs); if (ret) pr_debug("failed to read counter %s\n", counter->name); @@ -323,11 +337,11 @@ static void process_interval(void) { struct timespec ts, rs; - read_counters(); - clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); + read_counters(&rs); + if (STAT_RECORD) { if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSEC_PER_SEC + rs.tv_nsec, INTERVAL)) pr_err("failed to write stat round event\n"); @@ -593,7 +607,7 @@ try_again: * avoid arbitrary skew, we must read all counters before closing any * group leaders. */ - read_counters(); + read_counters(&(struct timespec) { .tv_nsec = t1-t0 }); perf_evlist__close(evsel_list); return WEXITSTATUS(status); diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 50df168be326..f470144d1a70 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -78,6 +78,8 @@ static void library_status(void) STATUS(HAVE_LZMA_SUPPORT, lzma); STATUS(HAVE_AUXTRACE_SUPPORT, get_cpuid); STATUS(HAVE_LIBBPF_SUPPORT, bpf); + STATUS(HAVE_AIO_SUPPORT, aio); + STATUS(HAVE_ZSTD_SUPPORT, zstd); } int cmd_version(int argc, const char **argv) diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c index f9b2161e1ca4..2422894a8194 100644 --- a/tools/perf/examples/bpf/augmented_raw_syscalls.c +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -15,6 +15,7 @@ */ #include <unistd.h> +#include <linux/limits.h> #include <pid_filter.h> /* bpf-output associated map */ @@ -41,32 +42,110 @@ struct syscall_exit_args { struct augmented_filename { unsigned int size; int reserved; - char value[256]; + char value[PATH_MAX]; }; -#define SYS_OPEN 2 -#define SYS_ACCESS 21 -#define SYS_OPENAT 257 +/* syscalls where the first arg is a string */ +#define SYS_OPEN 2 +#define SYS_STAT 4 +#define SYS_LSTAT 6 +#define SYS_ACCESS 21 +#define SYS_EXECVE 59 +#define SYS_TRUNCATE 76 +#define SYS_CHDIR 80 +#define SYS_RENAME 82 +#define SYS_MKDIR 83 +#define SYS_RMDIR 84 +#define SYS_CREAT 85 +#define SYS_LINK 86 +#define SYS_UNLINK 87 +#define SYS_SYMLINK 88 +#define SYS_READLINK 89 +#define SYS_CHMOD 90 +#define SYS_CHOWN 92 +#define SYS_LCHOWN 94 +#define SYS_MKNOD 133 +#define SYS_STATFS 137 +#define SYS_PIVOT_ROOT 155 +#define SYS_CHROOT 161 +#define SYS_ACCT 163 +#define SYS_SWAPON 167 +#define SYS_SWAPOFF 168 +#define SYS_DELETE_MODULE 176 +#define SYS_SETXATTR 188 +#define SYS_LSETXATTR 189 +#define SYS_GETXATTR 191 +#define SYS_LGETXATTR 192 +#define SYS_LISTXATTR 194 +#define SYS_LLISTXATTR 195 +#define SYS_REMOVEXATTR 197 +#define SYS_LREMOVEXATTR 198 +#define SYS_MQ_OPEN 240 +#define SYS_MQ_UNLINK 241 +#define SYS_ADD_KEY 248 +#define SYS_REQUEST_KEY 249 +#define SYS_SYMLINKAT 266 +#define SYS_MEMFD_CREATE 319 + +/* syscalls where the first arg is a string */ + +#define SYS_PWRITE64 18 +#define SYS_EXECVE 59 +#define SYS_RENAME 82 +#define SYS_QUOTACTL 179 +#define SYS_FSETXATTR 190 +#define SYS_FGETXATTR 193 +#define SYS_FREMOVEXATTR 199 +#define SYS_MQ_TIMEDSEND 242 +#define SYS_REQUEST_KEY 249 +#define SYS_INOTIFY_ADD_WATCH 254 +#define SYS_OPENAT 257 +#define SYS_MKDIRAT 258 +#define SYS_MKNODAT 259 +#define SYS_FCHOWNAT 260 +#define SYS_FUTIMESAT 261 +#define SYS_NEWFSTATAT 262 +#define SYS_UNLINKAT 263 +#define SYS_RENAMEAT 264 +#define SYS_LINKAT 265 +#define SYS_READLINKAT 267 +#define SYS_FCHMODAT 268 +#define SYS_FACCESSAT 269 +#define SYS_UTIMENSAT 280 +#define SYS_NAME_TO_HANDLE_AT 303 +#define SYS_FINIT_MODULE 313 +#define SYS_RENAMEAT2 316 +#define SYS_EXECVEAT 322 +#define SYS_STATX 332 pid_filter(pids_filtered); +struct augmented_args_filename { + struct syscall_enter_args args; + struct augmented_filename filename; +}; + +bpf_map(augmented_filename_map, PERCPU_ARRAY, int, struct augmented_args_filename, 1); + SEC("raw_syscalls:sys_enter") int sys_enter(struct syscall_enter_args *args) { - struct { - struct syscall_enter_args args; - struct augmented_filename filename; - } augmented_args; - struct syscall *syscall; - unsigned int len = sizeof(augmented_args); + struct augmented_args_filename *augmented_args; + unsigned int len = sizeof(*augmented_args); const void *filename_arg = NULL; + struct syscall *syscall; + int key = 0; + + augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key); + if (augmented_args == NULL) + return 1; if (pid_filter__has(&pids_filtered, getpid())) return 0; - probe_read(&augmented_args.args, sizeof(augmented_args.args), args); + probe_read(&augmented_args->args, sizeof(augmented_args->args), args); - syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr); + syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr); if (syscall == NULL || !syscall->enabled) return 0; /* @@ -109,30 +188,105 @@ int sys_enter(struct syscall_enter_args *args) * * after the ctx memory access to prevent their down stream merging. */ - switch (augmented_args.args.syscall_nr) { + /* + * This table of what args are strings will be provided by userspace, + * in the syscalls map, i.e. we will already have to do the lookup to + * see if this specific syscall is filtered, so we can as well get more + * info about what syscall args are strings or pointers, and how many + * bytes to copy, per arg, etc. + * + * For now hard code it, till we have all the basic mechanisms in place + * to automate everything and make the kernel part be completely driven + * by information obtained in userspace for each kernel version and + * processor architecture, making the kernel part the same no matter what + * kernel version or processor architecture it runs on. + */ + switch (augmented_args->args.syscall_nr) { + case SYS_ACCT: + case SYS_ADD_KEY: + case SYS_CHDIR: + case SYS_CHMOD: + case SYS_CHOWN: + case SYS_CHROOT: + case SYS_CREAT: + case SYS_DELETE_MODULE: + case SYS_EXECVE: + case SYS_GETXATTR: + case SYS_LCHOWN: + case SYS_LGETXATTR: + case SYS_LINK: + case SYS_LISTXATTR: + case SYS_LLISTXATTR: + case SYS_LREMOVEXATTR: + case SYS_LSETXATTR: + case SYS_LSTAT: + case SYS_MEMFD_CREATE: + case SYS_MKDIR: + case SYS_MKNOD: + case SYS_MQ_OPEN: + case SYS_MQ_UNLINK: + case SYS_PIVOT_ROOT: + case SYS_READLINK: + case SYS_REMOVEXATTR: + case SYS_RENAME: + case SYS_REQUEST_KEY: + case SYS_RMDIR: + case SYS_SETXATTR: + case SYS_STAT: + case SYS_STATFS: + case SYS_SWAPOFF: + case SYS_SWAPON: + case SYS_SYMLINK: + case SYS_SYMLINKAT: + case SYS_TRUNCATE: + case SYS_UNLINK: case SYS_ACCESS: case SYS_OPEN: filename_arg = (const void *)args->args[0]; __asm__ __volatile__("": : :"memory"); break; + case SYS_EXECVEAT: + case SYS_FACCESSAT: + case SYS_FCHMODAT: + case SYS_FCHOWNAT: + case SYS_FGETXATTR: + case SYS_FINIT_MODULE: + case SYS_FREMOVEXATTR: + case SYS_FSETXATTR: + case SYS_FUTIMESAT: + case SYS_INOTIFY_ADD_WATCH: + case SYS_LINKAT: + case SYS_MKDIRAT: + case SYS_MKNODAT: + case SYS_MQ_TIMEDSEND: + case SYS_NAME_TO_HANDLE_AT: + case SYS_NEWFSTATAT: + case SYS_PWRITE64: + case SYS_QUOTACTL: + case SYS_READLINKAT: + case SYS_RENAMEAT: + case SYS_RENAMEAT2: + case SYS_STATX: + case SYS_UNLINKAT: + case SYS_UTIMENSAT: case SYS_OPENAT: filename_arg = (const void *)args->args[1]; break; } if (filename_arg != NULL) { - augmented_args.filename.reserved = 0; - augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, - sizeof(augmented_args.filename.value), + augmented_args->filename.reserved = 0; + augmented_args->filename.size = probe_read_str(&augmented_args->filename.value, + sizeof(augmented_args->filename.value), filename_arg); - if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { - len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; - len &= sizeof(augmented_args.filename.value) - 1; + if (augmented_args->filename.size < sizeof(augmented_args->filename.value)) { + len -= sizeof(augmented_args->filename.value) - augmented_args->filename.size; + len &= sizeof(augmented_args->filename.value) - 1; } } else { - len = sizeof(augmented_args.args); + len = sizeof(augmented_args->args); } /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ - return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len); } SEC("raw_syscalls:sys_exit") diff --git a/tools/perf/perf.h b/tools/perf/perf.h index c59743def8d3..369eae61068d 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -85,6 +85,7 @@ struct record_opts { u64 clockid_res_ns; int nr_cblocks; int affinity; + int mmap_flush; }; enum perf_affinity { diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index e7a3524b748f..68618152ea2c 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -4,7 +4,7 @@ "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", - "PublicDescription": "Counter:128 Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" + "PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { "Unit": "CPU-M-CF", diff --git a/tools/perf/pmu-events/arch/x86/bonnell/frontend.json b/tools/perf/pmu-events/arch/x86/bonnell/frontend.json index 935b7dcf067d..ef69540ab61d 100644 --- a/tools/perf/pmu-events/arch/x86/bonnell/frontend.json +++ b/tools/perf/pmu-events/arch/x86/bonnell/frontend.json @@ -77,7 +77,7 @@ "UMask": "0x1", "EventName": "UOPS.MS_CYCLES", "SampleAfterValue": "2000000", - "BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ. ", + "BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ.", "CounterMask": "1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json index b2e681c78466..09c6de13de20 100644 --- a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json @@ -189,7 +189,7 @@ "UMask": "0x8", "EventName": "BR_MISSP_TYPE_RETIRED.IND_CALL", "SampleAfterValue": "200000", - "BriefDescription": "Mispredicted indirect calls, including both register and memory indirect. " + "BriefDescription": "Mispredicted indirect calls, including both register and memory indirect." }, { "EventCode": "0x89", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 00bfdb5c5acb..212b117a8ffb 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -1,164 +1,352 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", - "MetricGroup": "Frontend", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "Branch_Misprediction_Cost" }, { + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" + }, + { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / cycles", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/broadwell/cache.json b/tools/perf/pmu-events/arch/x86/broadwell/cache.json index 0b080b0352d8..7938bf5689ab 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/cache.json @@ -56,10 +56,10 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x41", + "UMask": "0xc1", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "SampleAfterValue": "200003", "BriefDescription": "Demand Data Read requests that hit L2 cache", @@ -68,7 +68,7 @@ { "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x42", + "UMask": "0xc2", "EventName": "L2_RQSTS.RFO_HIT", "SampleAfterValue": "200003", "BriefDescription": "RFO requests that hit L2 cache.", @@ -77,7 +77,7 @@ { "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x44", + "UMask": "0xc4", "EventName": "L2_RQSTS.CODE_RD_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", @@ -87,7 +87,7 @@ "PublicDescription": "This event counts the number of requests from the L2 hardware prefetchers that hit L2 cache. L3 prefetch new types.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x50", + "UMask": "0xd0", "EventName": "L2_RQSTS.L2_PF_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 prefetch requests that hit L2 cache", @@ -433,7 +433,7 @@ }, { "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "EventCode": "0xD0", "Counter": "0,1,2,3", "UMask": "0x41", @@ -445,7 +445,7 @@ }, { "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "EventCode": "0xD0", "Counter": "0,1,2,3", "UMask": "0x42", @@ -771,2628 +771,2628 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010001 ", + "MSRValue": "0x0000010001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that have any response type.", + "BriefDescription": "Counts demand data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020001 ", + "MSRValue": "0x0080020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020001 ", + "MSRValue": "0x0100020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020001 ", + "MSRValue": "0x0200020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020001 ", + "MSRValue": "0x0400020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020001 ", + "MSRValue": "0x1000020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020001 ", + "MSRValue": "0x3F80020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0001 ", + "MSRValue": "0x00803C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0001 ", + "MSRValue": "0x01003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0001 ", + "MSRValue": "0x02003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0001 ", + "MSRValue": "0x04003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0001 ", + "MSRValue": "0x10003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0001 ", + "MSRValue": "0x3F803C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010002 ", + "MSRValue": "0x0000010002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.", + "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0002 ", + "MSRValue": "0x00803C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0002 ", + "MSRValue": "0x01003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0002 ", + "MSRValue": "0x02003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0002 ", + "MSRValue": "0x04003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0002 ", + "MSRValue": "0x10003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0002 ", + "MSRValue": "0x3F803C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010004 ", + "MSRValue": "0x0000010004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that have any response type.", + "BriefDescription": "Counts all demand code reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020004 ", + "MSRValue": "0x0080020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020004 ", + "MSRValue": "0x0100020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020004 ", + "MSRValue": "0x0200020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020004 ", + "MSRValue": "0x0400020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020004 ", + "MSRValue": "0x1000020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020004 ", + "MSRValue": "0x3F80020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0004 ", + "MSRValue": "0x00803C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0004 ", + "MSRValue": "0x01003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0004 ", + "MSRValue": "0x02003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0004 ", + "MSRValue": "0x04003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0004 ", + "MSRValue": "0x10003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0004 ", + "MSRValue": "0x3F803C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive) have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010008 ", + "MSRValue": "0x0000010008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that have any response type.", + "BriefDescription": "Counts writebacks (modified to exclusive) have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020008 ", + "MSRValue": "0x0080020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020008 ", + "MSRValue": "0x0100020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020008 ", + "MSRValue": "0x0200020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020008 ", + "MSRValue": "0x0400020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020008 ", + "MSRValue": "0x1000020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020008 ", + "MSRValue": "0x3F80020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0008 ", + "MSRValue": "0x00803C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0008 ", + "MSRValue": "0x01003C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0008 ", + "MSRValue": "0x02003C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0008 ", + "MSRValue": "0x04003C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0008 ", + "MSRValue": "0x10003C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0008 ", + "MSRValue": "0x3F803C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010010 ", + "MSRValue": "0x0000010010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020010 ", + "MSRValue": "0x0080020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020010 ", + "MSRValue": "0x0100020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020010 ", + "MSRValue": "0x0200020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020010 ", + "MSRValue": "0x0400020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020010 ", + "MSRValue": "0x1000020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020010 ", + "MSRValue": "0x3F80020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0010 ", + "MSRValue": "0x00803C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0010 ", + "MSRValue": "0x01003C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0010 ", + "MSRValue": "0x02003C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0010 ", + "MSRValue": "0x04003C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0010 ", + "MSRValue": "0x10003C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0010 ", + "MSRValue": "0x3F803C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010020 ", + "MSRValue": "0x0000010020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020020 ", + "MSRValue": "0x0080020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020020 ", + "MSRValue": "0x0100020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020020 ", + "MSRValue": "0x0200020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020020 ", + "MSRValue": "0x0400020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020020 ", + "MSRValue": "0x1000020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020020 ", + "MSRValue": "0x3F80020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0020 ", + "MSRValue": "0x00803C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0020 ", + "MSRValue": "0x01003C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0020 ", + "MSRValue": "0x02003C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0020 ", + "MSRValue": "0x04003C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0020 ", + "MSRValue": "0x10003C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0020 ", + "MSRValue": "0x3F803C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010040 ", + "MSRValue": "0x0000010040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that have any response type.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020040 ", + "MSRValue": "0x0080020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020040 ", + "MSRValue": "0x0100020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020040 ", + "MSRValue": "0x0200020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020040 ", + "MSRValue": "0x0400020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020040 ", + "MSRValue": "0x1000020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020040 ", + "MSRValue": "0x3F80020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0040 ", + "MSRValue": "0x00803C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0040 ", + "MSRValue": "0x01003C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0040 ", + "MSRValue": "0x02003C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0040 ", + "MSRValue": "0x04003C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0040 ", + "MSRValue": "0x10003C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0040 ", + "MSRValue": "0x3F803C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010080 ", + "MSRValue": "0x0000010080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020080 ", + "MSRValue": "0x0080020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020080 ", + "MSRValue": "0x0100020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020080 ", + "MSRValue": "0x0200020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020080 ", + "MSRValue": "0x0400020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020080 ", + "MSRValue": "0x1000020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020080 ", + "MSRValue": "0x3F80020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0080 ", + "MSRValue": "0x00803C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0080 ", + "MSRValue": "0x01003C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0080 ", + "MSRValue": "0x02003C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0080 ", + "MSRValue": "0x04003C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0080 ", + "MSRValue": "0x10003C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0080 ", + "MSRValue": "0x3F803C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010100 ", + "MSRValue": "0x0000010100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020100 ", + "MSRValue": "0x0080020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020100 ", + "MSRValue": "0x0100020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020100 ", + "MSRValue": "0x0200020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020100 ", + "MSRValue": "0x0400020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020100 ", + "MSRValue": "0x1000020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020100 ", + "MSRValue": "0x3F80020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0100 ", + "MSRValue": "0x00803C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0100 ", + "MSRValue": "0x01003C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0100 ", + "MSRValue": "0x02003C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0100 ", + "MSRValue": "0x04003C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0100 ", + "MSRValue": "0x10003C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0100 ", + "MSRValue": "0x3F803C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010200 ", + "MSRValue": "0x0000010200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that have any response type.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020200 ", + "MSRValue": "0x0080020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020200 ", + "MSRValue": "0x0100020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020200 ", + "MSRValue": "0x0200020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020200 ", + "MSRValue": "0x0400020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020200 ", + "MSRValue": "0x1000020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020200 ", + "MSRValue": "0x3F80020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0200 ", + "MSRValue": "0x00803C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0200 ", + "MSRValue": "0x01003C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0200 ", + "MSRValue": "0x02003C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0200 ", + "MSRValue": "0x04003C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0200 ", + "MSRValue": "0x10003C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0200 ", + "MSRValue": "0x3F803C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000018000 ", + "MSRValue": "0x0000018000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that have any response type.", + "BriefDescription": "Counts any other requests have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080028000 ", + "MSRValue": "0x0080028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100028000 ", + "MSRValue": "0x0100028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200028000 ", + "MSRValue": "0x0200028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400028000 ", + "MSRValue": "0x0400028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000028000 ", + "MSRValue": "0x1000028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80028000 ", + "MSRValue": "0x3F80028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c8000 ", + "MSRValue": "0x00803C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c8000 ", + "MSRValue": "0x01003C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c8000 ", + "MSRValue": "0x02003C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c8000 ", + "MSRValue": "0x04003C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c8000 ", + "MSRValue": "0x10003C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c8000 ", + "MSRValue": "0x3F803C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010090 ", + "MSRValue": "0x0000010090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that have any response type.", + "BriefDescription": "Counts all prefetch data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020090 ", + "MSRValue": "0x0080020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020090 ", + "MSRValue": "0x0100020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020090 ", + "MSRValue": "0x0200020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020090 ", + "MSRValue": "0x0400020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020090 ", + "MSRValue": "0x1000020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020090 ", + "MSRValue": "0x3F80020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0090 ", + "MSRValue": "0x00803C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0090 ", + "MSRValue": "0x01003C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0090 ", + "MSRValue": "0x02003C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0090 ", + "MSRValue": "0x04003C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0090 ", + "MSRValue": "0x10003C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0090 ", + "MSRValue": "0x3F803C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010120 ", + "MSRValue": "0x0000010120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that have any response type.", + "BriefDescription": "Counts prefetch RFOs have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020120 ", + "MSRValue": "0x0080020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020120 ", + "MSRValue": "0x0100020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020120 ", + "MSRValue": "0x0200020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020120 ", + "MSRValue": "0x0400020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020120 ", + "MSRValue": "0x1000020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020120 ", + "MSRValue": "0x3F80020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0120 ", + "MSRValue": "0x00803C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0120 ", + "MSRValue": "0x01003C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0120 ", + "MSRValue": "0x02003C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0120 ", + "MSRValue": "0x04003C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0120 ", + "MSRValue": "0x10003C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0120 ", + "MSRValue": "0x3F803C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010240 ", + "MSRValue": "0x0000010240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that have any response type.", + "BriefDescription": "Counts all prefetch code reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020240 ", + "MSRValue": "0x0080020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020240 ", + "MSRValue": "0x0100020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020240 ", + "MSRValue": "0x0200020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020240 ", + "MSRValue": "0x0400020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020240 ", + "MSRValue": "0x1000020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020240 ", + "MSRValue": "0x3F80020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0240 ", + "MSRValue": "0x00803C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0240 ", + "MSRValue": "0x01003C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0240 ", + "MSRValue": "0x02003C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0240 ", + "MSRValue": "0x04003C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0240 ", + "MSRValue": "0x10003C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0240 ", + "MSRValue": "0x3F803C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010091 ", + "MSRValue": "0x0000010091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that have any response type.", + "BriefDescription": "Counts all demand & prefetch data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020091 ", + "MSRValue": "0x0080020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020091 ", + "MSRValue": "0x0100020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020091 ", + "MSRValue": "0x0200020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020091 ", + "MSRValue": "0x0400020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020091 ", + "MSRValue": "0x1000020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020091 ", + "MSRValue": "0x3F80020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0091 ", + "MSRValue": "0x00803C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0091 ", + "MSRValue": "0x01003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0091 ", + "MSRValue": "0x02003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0091 ", + "MSRValue": "0x04003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0091 ", + "MSRValue": "0x10003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0091 ", + "MSRValue": "0x3F803C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010122 ", + "MSRValue": "0x0000010122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.", + "BriefDescription": "Counts all demand & prefetch RFOs have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020122 ", + "MSRValue": "0x0080020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020122 ", + "MSRValue": "0x0100020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020122 ", + "MSRValue": "0x0200020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020122 ", + "MSRValue": "0x0400020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020122 ", + "MSRValue": "0x1000020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020122 ", + "MSRValue": "0x3F80020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0122 ", + "MSRValue": "0x00803C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0122 ", + "MSRValue": "0x01003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0122 ", + "MSRValue": "0x02003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0122 ", + "MSRValue": "0x04003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0122 ", + "MSRValue": "0x10003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0122 ", + "MSRValue": "0x3F803C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json index 689d478dae93..15291239c128 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json @@ -1,24 +1,26 @@ [ { - "PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x8", "Errata": "BDM30", "EventName": "OTHER_ASSISTS.AVX_TO_SSE", "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x10", "Errata": "BDM30", "EventName": "OTHER_ASSISTS.SSE_TO_AVX", "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -45,7 +47,7 @@ "UMask": "0x3", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)", "CounterHTOff": "0,1,2,3" }, { @@ -54,7 +56,7 @@ "UMask": "0x4", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -63,7 +65,7 @@ "UMask": "0x8", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -72,7 +74,7 @@ "UMask": "0x10", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -81,7 +83,7 @@ "UMask": "0x15", "EventName": "FP_ARITH_INST_RETIRED.DOUBLE", "SampleAfterValue": "2000006", - "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.", + "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -90,7 +92,7 @@ "UMask": "0x20", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -99,7 +101,7 @@ "UMask": "0x2a", "EventName": "FP_ARITH_INST_RETIRED.SINGLE", "SampleAfterValue": "2000005", - "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.", + "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -108,57 +110,62 @@ "UMask": "0x3c", "EventName": "FP_ARITH_INST_RETIRED.PACKED", "SampleAfterValue": "2000004", - "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x2", "EventName": "FP_ASSIST.X87_OUTPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to output value.", + "BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x4", "EventName": "FP_ASSIST.X87_INPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to input value.", + "BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x8", "EventName": "FP_ASSIST.SIMD_OUTPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to Output values", + "BriefDescription": "SSE* FP micro-code assist when output value is invalid. (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts any input SSE* floating-point (FP) assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x10", "EventName": "FP_ASSIST.SIMD_INPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to input values", + "BriefDescription": "Any input SSE* FP Assist - (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", + "PEBS": "1", + "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1. Uses PEBS.", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x1e", "EventName": "FP_ASSIST.ANY", "SampleAfterValue": "100003", - "BriefDescription": "Cycles with any input/output SSE or FP assist", + "BriefDescription": "Counts any FP_ASSIST umask was incrementing (Precise Event)", "CounterMask": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json index 7142c76d7f11..aa4a5d762f21 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json @@ -211,7 +211,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.", + "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.", "EventCode": "0x9C", "Counter": "0,1,2,3", "UMask": "0x1", @@ -274,7 +274,7 @@ "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.", "EventCode": "0xAB", "Counter": "0,1,2,3", "UMask": "0x2", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/memory.json b/tools/perf/pmu-events/arch/x86/broadwell/memory.json index c9154cebbdf0..b6b5247d3d5a 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/memory.json @@ -311,7 +311,7 @@ }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above four.", + "PublicDescription": "Counts randomly selected loads with latency value being above four.", "EventCode": "0xCD", "MSRValue": "0x4", "Counter": "3", @@ -320,13 +320,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "SampleAfterValue": "100003", - "BriefDescription": "Loads with latency value being above 4", + "BriefDescription": "Randomly selected loads with latency value being above 4", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above eight.", + "PublicDescription": "Counts randomly selected loads with latency value being above eight.", "EventCode": "0xCD", "MSRValue": "0x8", "Counter": "3", @@ -335,13 +335,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "SampleAfterValue": "50021", - "BriefDescription": "Loads with latency value being above 8", + "BriefDescription": "Randomly selected loads with latency value being above 8", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 16.", + "PublicDescription": "Counts randomly selected loads with latency value being above 16.", "EventCode": "0xCD", "MSRValue": "0x10", "Counter": "3", @@ -350,13 +350,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "SampleAfterValue": "20011", - "BriefDescription": "Loads with latency value being above 16", + "BriefDescription": "Randomly selected loads with latency value being above 16", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 32.", + "PublicDescription": "Counts randomly selected loads with latency value being above 32.", "EventCode": "0xCD", "MSRValue": "0x20", "Counter": "3", @@ -365,13 +365,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "SampleAfterValue": "100007", - "BriefDescription": "Loads with latency value being above 32", + "BriefDescription": "Randomly selected loads with latency value being above 32", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 64.", + "PublicDescription": "Counts randomly selected loads with latency value being above 64.", "EventCode": "0xCD", "MSRValue": "0x40", "Counter": "3", @@ -380,13 +380,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "SampleAfterValue": "2003", - "BriefDescription": "Loads with latency value being above 64", + "BriefDescription": "Randomly selected loads with latency value being above 64", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 128.", + "PublicDescription": "Counts randomly selected loads with latency value being above 128.", "EventCode": "0xCD", "MSRValue": "0x80", "Counter": "3", @@ -395,13 +395,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "SampleAfterValue": "1009", - "BriefDescription": "Loads with latency value being above 128", + "BriefDescription": "Randomly selected loads with latency value being above 128", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 256.", + "PublicDescription": "Counts randomly selected loads with latency value being above 256.", "EventCode": "0xCD", "MSRValue": "0x100", "Counter": "3", @@ -410,13 +410,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "SampleAfterValue": "503", - "BriefDescription": "Loads with latency value being above 256", + "BriefDescription": "Randomly selected loads with latency value being above 256", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 512.", + "PublicDescription": "Counts randomly selected loads with latency value being above 512.", "EventCode": "0xCD", "MSRValue": "0x200", "Counter": "3", @@ -425,2620 +425,2620 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "SampleAfterValue": "101", - "BriefDescription": "Loads with latency value being above 512", + "BriefDescription": "Randomly selected loads with latency value being above 512", "TakenAlone": "1", "CounterHTOff": "3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020001 ", + "MSRValue": "0x2000020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0001 ", + "MSRValue": "0x20003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000001 ", + "MSRValue": "0x0084000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000001 ", + "MSRValue": "0x0104000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000001 ", + "MSRValue": "0x0204000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000001 ", + "MSRValue": "0x0404000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000001 ", + "MSRValue": "0x1004000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000001 ", + "MSRValue": "0x2004000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000001 ", + "MSRValue": "0x3F84000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000001 ", + "MSRValue": "0x00BC000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000001 ", + "MSRValue": "0x013C000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000001 ", + "MSRValue": "0x023C000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000001 ", + "MSRValue": "0x043C000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0002 ", + "MSRValue": "0x20003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000002 ", + "MSRValue": "0x3F84000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000002 ", + "MSRValue": "0x00BC000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000002 ", + "MSRValue": "0x013C000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000002 ", + "MSRValue": "0x023C000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000002 ", + "MSRValue": "0x043C000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020004 ", + "MSRValue": "0x2000020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0004 ", + "MSRValue": "0x20003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000004 ", + "MSRValue": "0x0084000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000004 ", + "MSRValue": "0x0104000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000004 ", + "MSRValue": "0x0204000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000004 ", + "MSRValue": "0x0404000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000004 ", + "MSRValue": "0x1004000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000004 ", + "MSRValue": "0x2004000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000004 ", + "MSRValue": "0x3F84000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000004 ", + "MSRValue": "0x00BC000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000004 ", + "MSRValue": "0x013C000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000004 ", + "MSRValue": "0x023C000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000004 ", + "MSRValue": "0x043C000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020008 ", + "MSRValue": "0x2000020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0008 ", + "MSRValue": "0x20003C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000008 ", + "MSRValue": "0x0084000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000008 ", + "MSRValue": "0x0104000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000008 ", + "MSRValue": "0x0204000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000008 ", + "MSRValue": "0x0404000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000008 ", + "MSRValue": "0x1004000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000008 ", + "MSRValue": "0x2004000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000008 ", + "MSRValue": "0x3F84000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000008 ", + "MSRValue": "0x00BC000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000008 ", + "MSRValue": "0x013C000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000008 ", + "MSRValue": "0x023C000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000008 ", + "MSRValue": "0x043C000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020010 ", + "MSRValue": "0x2000020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0010 ", + "MSRValue": "0x20003C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000010 ", + "MSRValue": "0x0084000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000010 ", + "MSRValue": "0x0104000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000010 ", + "MSRValue": "0x0204000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000010 ", + "MSRValue": "0x0404000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000010 ", + "MSRValue": "0x1004000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000010 ", + "MSRValue": "0x2004000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000010 ", + "MSRValue": "0x3F84000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000010 ", + "MSRValue": "0x00BC000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000010 ", + "MSRValue": "0x013C000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000010 ", + "MSRValue": "0x023C000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000010 ", + "MSRValue": "0x043C000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020020 ", + "MSRValue": "0x2000020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0020 ", + "MSRValue": "0x20003C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000020 ", + "MSRValue": "0x0084000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000020 ", + "MSRValue": "0x0104000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000020 ", + "MSRValue": "0x0204000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000020 ", + "MSRValue": "0x0404000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000020 ", + "MSRValue": "0x1004000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000020 ", + "MSRValue": "0x2004000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000020 ", + "MSRValue": "0x3F84000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000020 ", + "MSRValue": "0x00BC000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000020 ", + "MSRValue": "0x013C000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000020 ", + "MSRValue": "0x023C000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000020 ", + "MSRValue": "0x043C000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020040 ", + "MSRValue": "0x2000020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0040 ", + "MSRValue": "0x20003C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000040 ", + "MSRValue": "0x0084000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000040 ", + "MSRValue": "0x0104000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000040 ", + "MSRValue": "0x0204000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000040 ", + "MSRValue": "0x0404000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000040 ", + "MSRValue": "0x1004000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000040 ", + "MSRValue": "0x2004000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000040 ", + "MSRValue": "0x3F84000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000040 ", + "MSRValue": "0x00BC000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000040 ", + "MSRValue": "0x013C000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000040 ", + "MSRValue": "0x023C000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000040 ", + "MSRValue": "0x043C000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020080 ", + "MSRValue": "0x2000020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0080 ", + "MSRValue": "0x20003C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000080 ", + "MSRValue": "0x0084000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000080 ", + "MSRValue": "0x0104000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000080 ", + "MSRValue": "0x0204000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000080 ", + "MSRValue": "0x0404000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000080 ", + "MSRValue": "0x1004000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000080 ", + "MSRValue": "0x2004000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000080 ", + "MSRValue": "0x3F84000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000080 ", + "MSRValue": "0x00BC000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000080 ", + "MSRValue": "0x013C000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000080 ", + "MSRValue": "0x023C000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000080 ", + "MSRValue": "0x043C000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020100 ", + "MSRValue": "0x2000020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0100 ", + "MSRValue": "0x20003C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000100 ", + "MSRValue": "0x0084000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000100 ", + "MSRValue": "0x0104000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000100 ", + "MSRValue": "0x0204000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000100 ", + "MSRValue": "0x0404000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000100 ", + "MSRValue": "0x1004000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000100 ", + "MSRValue": "0x2004000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000100 ", + "MSRValue": "0x3F84000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000100 ", + "MSRValue": "0x00BC000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000100 ", + "MSRValue": "0x013C000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000100 ", + "MSRValue": "0x023C000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000100 ", + "MSRValue": "0x043C000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020200 ", + "MSRValue": "0x2000020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0200 ", + "MSRValue": "0x20003C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000200 ", + "MSRValue": "0x0084000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000200 ", + "MSRValue": "0x0104000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000200 ", + "MSRValue": "0x0204000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000200 ", + "MSRValue": "0x0404000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000200 ", + "MSRValue": "0x1004000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000200 ", + "MSRValue": "0x2004000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000200 ", + "MSRValue": "0x3F84000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000200 ", + "MSRValue": "0x00BC000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000200 ", + "MSRValue": "0x013C000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000200 ", + "MSRValue": "0x023C000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000200 ", + "MSRValue": "0x043C000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000028000 ", + "MSRValue": "0x2000028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c8000 ", + "MSRValue": "0x20003C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084008000 ", + "MSRValue": "0x0084008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104008000 ", + "MSRValue": "0x0104008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204008000 ", + "MSRValue": "0x0204008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404008000 ", + "MSRValue": "0x0404008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004008000 ", + "MSRValue": "0x1004008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004008000 ", + "MSRValue": "0x2004008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84008000 ", + "MSRValue": "0x3F84008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc008000 ", + "MSRValue": "0x00BC008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c008000 ", + "MSRValue": "0x013C008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c008000 ", + "MSRValue": "0x023C008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c008000 ", + "MSRValue": "0x043C008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020090 ", + "MSRValue": "0x2000020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0090 ", + "MSRValue": "0x20003C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000090 ", + "MSRValue": "0x0084000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000090 ", + "MSRValue": "0x0104000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000090 ", + "MSRValue": "0x0204000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000090 ", + "MSRValue": "0x0404000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000090 ", + "MSRValue": "0x1004000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000090 ", + "MSRValue": "0x2004000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000090 ", + "MSRValue": "0x3F84000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000090 ", + "MSRValue": "0x00BC000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000090 ", + "MSRValue": "0x013C000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000090 ", + "MSRValue": "0x023C000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000090 ", + "MSRValue": "0x043C000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020120 ", + "MSRValue": "0x2000020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0120 ", + "MSRValue": "0x20003C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000120 ", + "MSRValue": "0x0084000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000120 ", + "MSRValue": "0x0104000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000120 ", + "MSRValue": "0x0204000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000120 ", + "MSRValue": "0x0404000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000120 ", + "MSRValue": "0x1004000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000120 ", + "MSRValue": "0x2004000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000120 ", + "MSRValue": "0x3F84000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000120 ", + "MSRValue": "0x00BC000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000120 ", + "MSRValue": "0x013C000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000120 ", + "MSRValue": "0x023C000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000120 ", + "MSRValue": "0x043C000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020240 ", + "MSRValue": "0x2000020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0240 ", + "MSRValue": "0x20003C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000240 ", + "MSRValue": "0x0084000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000240 ", + "MSRValue": "0x0104000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000240 ", + "MSRValue": "0x0204000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000240 ", + "MSRValue": "0x0404000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000240 ", + "MSRValue": "0x1004000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000240 ", + "MSRValue": "0x2004000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000240 ", + "MSRValue": "0x3F84000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000240 ", + "MSRValue": "0x00BC000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000240 ", + "MSRValue": "0x013C000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000240 ", + "MSRValue": "0x023C000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000240 ", + "MSRValue": "0x043C000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020091 ", + "MSRValue": "0x2000020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0091 ", + "MSRValue": "0x20003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000091 ", + "MSRValue": "0x0084000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000091 ", + "MSRValue": "0x0104000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000091 ", + "MSRValue": "0x0204000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000091 ", + "MSRValue": "0x0404000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000091 ", + "MSRValue": "0x1004000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000091 ", + "MSRValue": "0x2004000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000091 ", + "MSRValue": "0x3F84000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000091 ", + "MSRValue": "0x00BC000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000091 ", + "MSRValue": "0x013C000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000091 ", + "MSRValue": "0x023C000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000091 ", + "MSRValue": "0x043C000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020122 ", + "MSRValue": "0x2000020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0122 ", + "MSRValue": "0x20003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000122 ", + "MSRValue": "0x0084000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000122 ", + "MSRValue": "0x0104000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000122 ", + "MSRValue": "0x0204000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000122 ", + "MSRValue": "0x0404000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000122 ", + "MSRValue": "0x1004000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000122 ", + "MSRValue": "0x2004000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000122 ", + "MSRValue": "0x3F84000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000122 ", + "MSRValue": "0x00BC000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000122 ", + "MSRValue": "0x013C000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000122 ", + "MSRValue": "0x023C000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000122 ", + "MSRValue": "0x043C000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json index 999cf3066363..bb25574b8d21 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json @@ -1,7 +1,6 @@ [ { "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -11,7 +10,6 @@ }, { "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -20,7 +18,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "AnyThread": "1", @@ -31,7 +28,6 @@ }, { "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -317,7 +313,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", + "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", "EventCode": "0x87", "Counter": "0,1,2,3", "UMask": "0x1", @@ -786,8 +782,8 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.", - "EventCode": "0xA2", + "PublicDescription": "This event counts resource-related stall cycles.", + "EventCode": "0xa2", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "RESOURCE_STALLS.ANY", @@ -973,6 +969,7 @@ "CounterHTOff": "2" }, { + "PublicDescription": "Number of Uops delivered by the LSD.", "EventCode": "0xA8", "Counter": "0,1,2,3", "UMask": "0x1", @@ -1147,7 +1144,8 @@ "CounterHTOff": "1" }, { - "PublicDescription": "This event counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", "EventCode": "0xC0", "Counter": "0,1,2,3", "UMask": "0x2", @@ -1157,12 +1155,12 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PEBS": "1", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x40", "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST", "SampleAfterValue": "100003", - "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1178,26 +1176,28 @@ "Data_LA": "1" }, { - "PublicDescription": "This event counts cycles without actually retired uops.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts cycles without actually retired uops.", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "UOPS_RETIRED.STALL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", + "BriefDescription": "Cycles no executable uops retired (Precise Event)", "CounterMask": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", + "PEBS": "1", + "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to PEBS uops retired event.", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "UOPS_RETIRED.TOTAL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 10 actually retired uops.", + "BriefDescription": "Number of cycles using always true condition applied to PEBS uops retired event.", "CounterMask": "10", "CounterHTOff": "0,1,2,3" }, @@ -1320,13 +1320,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts not taken branch instructions retired.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x10", "EventName": "BR_INST_RETIRED.NOT_TAKEN", "SampleAfterValue": "400009", - "BriefDescription": "Not taken branch instructions retired.", + "BriefDescription": "Counts all not taken macro branch instructions retired. (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1341,14 +1342,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts far branch instructions retired.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts far branch instructions retired.", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x40", "Errata": "BDW98", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "SampleAfterValue": "100007", - "BriefDescription": "Far branch instructions retired.", + "BriefDescription": "Counts the number of far branch instructions retired.(Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json index 4ad425312bdc..bf243fe2a0ec 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json @@ -439,7 +439,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -451,7 +451,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "SampleAfterValue": "100003", "L1_Hit_Indication": "1", "CounterHTOff": "0,1,2,3" diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json index 0d04bf9db000..e2f0540625a2 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "UMask": "0x1", "BriefDescription": "Instructions retired from execution.", "Counter": "Fixed counter 0", @@ -10,7 +9,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when the thread is not in halt state", "Counter": "Fixed counter 1", @@ -20,7 +18,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "Fixed counter 1", @@ -30,7 +27,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x3", "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", @@ -322,7 +318,7 @@ "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "Counter": "0,1,2,3", "EventName": "ILD_STALL.LCP", - "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", + "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 5a7f1ec24200..c6f9762f32c0 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -1,164 +1,370 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", - "MetricGroup": "Frontend", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "Branch_Misprediction_Cost" + }, + { + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * cycles )", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED) ) / (2*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles))", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )", + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "DRAM_Read_Latency" + }, + { + "MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@", + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_Parallel_Reads" + }, + { + "MetricExpr": "cbox_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json index 141b1080429d..75a3098d5775 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json @@ -57,17 +57,17 @@ }, { "EventCode": "0x24", - "UMask": "0x41", + "UMask": "0xc1", "BriefDescription": "Demand Data Read requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache.", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x24", - "UMask": "0x42", + "UMask": "0xc2", "BriefDescription": "RFO requests that hit L2 cache.", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.RFO_HIT", @@ -76,7 +76,7 @@ }, { "EventCode": "0x24", - "UMask": "0x44", + "UMask": "0xc4", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.CODE_RD_HIT", @@ -85,7 +85,7 @@ }, { "EventCode": "0x24", - "UMask": "0x50", + "UMask": "0xd0", "BriefDescription": "L2 prefetch requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.L2_PF_HIT", @@ -396,24 +396,24 @@ { "EventCode": "0xD0", "UMask": "0x11", - "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops that miss the STLB.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", + "PublicDescription": "This event counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x12", - "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS)", + "BriefDescription": "Retired store uops that miss the STLB.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", + "PublicDescription": "This event counts store uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", "SampleAfterValue": "100003", "L1_Hit_Indication": "1", "CounterHTOff": "0,1,2,3" @@ -421,37 +421,37 @@ { "EventCode": "0xD0", "UMask": "0x21", - "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops with locked access.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "Errata": "BDM35", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with locked access retired to the architected path.", + "PublicDescription": "This event counts load uops with locked access retired to the architected path.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x41", - "BriefDescription": "Retired load uops that split across a cacheline boundary.(Precise Event - PEBS)", + "BriefDescription": "Retired load uops that split across a cacheline boundary.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x42", - "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)", + "BriefDescription": "Retired store uops that split across a cacheline boundary.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "SampleAfterValue": "100003", "L1_Hit_Indication": "1", "CounterHTOff": "0,1,2,3" @@ -459,24 +459,24 @@ { "EventCode": "0xD0", "UMask": "0x81", - "BriefDescription": "All retired load uops. (Precise Event - PEBS)", + "BriefDescription": "All retired load uops.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.", + "PublicDescription": "This event counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x82", - "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)", + "BriefDescription": "All retired store uops.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement.", + "PublicDescription": "This event counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement.", "SampleAfterValue": "2000003", "L1_Hit_Indication": "1", "CounterHTOff": "0,1,2,3" @@ -484,69 +484,69 @@ { "EventCode": "0xD1", "UMask": "0x1", - "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops with L1 cache hits as data sources.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data source were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x2", - "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops with L2 cache hits as data sources.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "Errata": "BDM35", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the mid-level (L2) cache.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x4", - "BriefDescription": "Hit in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", "Errata": "BDM100", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.", + "PublicDescription": "This event counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x8", - "BriefDescription": "Retired load uops misses in L1 cache as data sources. Uses PEBS.", + "BriefDescription": "Retired load uops misses in L1 cache as data sources.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.", + "PublicDescription": "This event counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x10", - "BriefDescription": "Retired load uops with L2 cache misses as data sources. Uses PEBS.", + "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.", + "PublicDescription": "This event counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x20", - "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS).", + "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -558,83 +558,84 @@ { "EventCode": "0xD1", "UMask": "0x40", - "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", + "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD2", "UMask": "0x1", - "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS", "Errata": "BDM100", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.", + "PublicDescription": "This event counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD2", "UMask": "0x2", - "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT", "Errata": "BDM100", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.", + "PublicDescription": "This event counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD2", "UMask": "0x4", - "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM", "Errata": "BDM100", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).", + "PublicDescription": "This event counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD2", "UMask": "0x8", - "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_NONE", "Errata": "BDM100", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD3", "UMask": "0x1", + "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", "Errata": "BDE70, BDM100", - "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.", + "PublicDescription": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI).", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD3", "UMask": "0x4", - "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -646,7 +647,7 @@ { "EventCode": "0xD3", "UMask": "0x10", - "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -658,7 +659,7 @@ { "EventCode": "0xD3", "UMask": "0x20", - "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -810,12 +811,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all requests that hit in the L3", - "MSRValue": "0x3f803c8fff", + "BriefDescription": "Counts all requests hit in the L3", + "MSRValue": "0x3F803C8FFF", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -823,12 +824,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c07f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C07F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -836,12 +837,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c07f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C07F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -849,12 +850,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0244", + "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -862,12 +863,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0122", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -875,12 +876,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0122", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -888,12 +889,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0091", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -901,12 +902,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0091", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -914,12 +915,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3", - "MSRValue": "0x3f803c0200", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", + "MSRValue": "0x3F803C0200", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -927,12 +928,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3", - "MSRValue": "0x3f803c0100", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", + "MSRValue": "0x3F803C0100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -940,12 +941,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0002", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -953,12 +954,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3", - "MSRValue": "0x3f803c0002", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3", + "MSRValue": "0x3F803C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json index d7b9d9c9c518..ba0e0c4e74eb 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json @@ -42,7 +42,7 @@ { "EventCode": "0xC7", "UMask": "0x3", - "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", "SampleAfterValue": "2000003", @@ -51,7 +51,7 @@ { "EventCode": "0xC7", "UMask": "0x4", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", "SampleAfterValue": "2000003", @@ -60,7 +60,7 @@ { "EventCode": "0xC7", "UMask": "0x8", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", "SampleAfterValue": "2000003", @@ -69,7 +69,7 @@ { "EventCode": "0xC7", "UMask": "0x10", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", "SampleAfterValue": "2000003", @@ -78,7 +78,7 @@ { "EventCode": "0xC7", "UMask": "0x15", - "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.", + "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.DOUBLE", "SampleAfterValue": "2000006", @@ -87,7 +87,7 @@ { "EventCode": "0xc7", "UMask": "0x20", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", "SampleAfterValue": "2000003", @@ -96,7 +96,7 @@ { "EventCode": "0xC7", "UMask": "0x2a", - "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.", + "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.SINGLE", "SampleAfterValue": "2000005", @@ -105,7 +105,7 @@ { "EventCode": "0xC7", "UMask": "0x3c", - "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.PACKED", "SampleAfterValue": "2000004", diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json index d79a5cfea44b..ecb413bb67ca 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json @@ -170,11 +170,11 @@ { "EventCode": "0xc8", "UMask": "0x4", - "BriefDescription": "Number of times HLE abort was triggered (PEBS)", + "BriefDescription": "Number of times HLE abort was triggered", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "HLE_RETIRED.ABORTED", - "PublicDescription": "Number of times HLE abort was triggered (PEBS).", + "PublicDescription": "Number of times HLE abort was triggered.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -251,11 +251,11 @@ { "EventCode": "0xc9", "UMask": "0x4", - "BriefDescription": "Number of times RTM abort was triggered (PEBS)", + "BriefDescription": "Number of times RTM abort was triggered", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "RTM_RETIRED.ABORTED", - "PublicDescription": "Number of times RTM abort was triggered (PEBS).", + "PublicDescription": "Number of times RTM abort was triggered .", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, @@ -312,14 +312,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 4", + "BriefDescription": "Randomly selected loads with latency value being above 4", "PEBS": "2", "MSRValue": "0x4", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above four.", + "PublicDescription": "Counts randomly selected loads with latency value being above four.", "TakenAlone": "1", "SampleAfterValue": "100003", "CounterHTOff": "3" @@ -327,14 +327,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 8", + "BriefDescription": "Randomly selected loads with latency value being above 8", "PEBS": "2", "MSRValue": "0x8", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above eight.", + "PublicDescription": "Counts randomly selected loads with latency value being above eight.", "TakenAlone": "1", "SampleAfterValue": "50021", "CounterHTOff": "3" @@ -342,14 +342,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 16", + "BriefDescription": "Randomly selected loads with latency value being above 16", "PEBS": "2", "MSRValue": "0x10", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 16.", + "PublicDescription": "Counts randomly selected loads with latency value being above 16.", "TakenAlone": "1", "SampleAfterValue": "20011", "CounterHTOff": "3" @@ -357,14 +357,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 32", + "BriefDescription": "Randomly selected loads with latency value being above 32", "PEBS": "2", "MSRValue": "0x20", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 32.", + "PublicDescription": "Counts randomly selected loads with latency value being above 32.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "3" @@ -372,14 +372,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 64", + "BriefDescription": "Randomly selected loads with latency value being above 64", "PEBS": "2", "MSRValue": "0x40", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 64.", + "PublicDescription": "Counts randomly selected loads with latency value being above 64.", "TakenAlone": "1", "SampleAfterValue": "2003", "CounterHTOff": "3" @@ -387,14 +387,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 128", + "BriefDescription": "Randomly selected loads with latency value being above 128", "PEBS": "2", "MSRValue": "0x80", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 128.", + "PublicDescription": "Counts randomly selected loads with latency value being above 128.", "TakenAlone": "1", "SampleAfterValue": "1009", "CounterHTOff": "3" @@ -402,14 +402,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 256", + "BriefDescription": "Randomly selected loads with latency value being above 256", "PEBS": "2", "MSRValue": "0x100", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 256.", + "PublicDescription": "Counts randomly selected loads with latency value being above 256.", "TakenAlone": "1", "SampleAfterValue": "503", "CounterHTOff": "3" @@ -417,14 +417,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 512", + "BriefDescription": "Randomly selected loads with latency value being above 512", "PEBS": "2", "MSRValue": "0x200", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 512.", + "PublicDescription": "Counts randomly selected loads with latency value being above 512.", "TakenAlone": "1", "SampleAfterValue": "101", "CounterHTOff": "3" @@ -433,12 +433,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all requests that miss in the L3", - "MSRValue": "0x3fbfc08fff", + "BriefDescription": "Counts all requests miss in the L3", + "MSRValue": "0x3FBFC08FFF", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -446,12 +446,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache", - "MSRValue": "0x087fc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache", + "MSRValue": "0x087FC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -459,12 +459,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -472,12 +472,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram", - "MSRValue": "0x063bc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram", + "MSRValue": "0x063BC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -485,12 +485,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram", - "MSRValue": "0x06040007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram", + "MSRValue": "0x06040007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -498,12 +498,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3", - "MSRValue": "0x3fbfc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3", + "MSRValue": "0x3FBFC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -511,12 +511,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0604000244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -524,12 +524,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3", - "MSRValue": "0x3fbfc00244", + "BriefDescription": "Counts all demand & prefetch code reads miss in the L3", + "MSRValue": "0x3FBFC00244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -537,12 +537,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "MSRValue": "0x0604000122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -550,12 +550,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3", - "MSRValue": "0x3fbfc00122", + "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3", + "MSRValue": "0x3FBFC00122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -563,12 +563,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache", - "MSRValue": "0x087fc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache", + "MSRValue": "0x087FC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -576,12 +576,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -589,12 +589,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram", - "MSRValue": "0x063bc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram", + "MSRValue": "0x063BC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -602,12 +602,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0604000091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -615,12 +615,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3", - "MSRValue": "0x3fbfc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss in the L3", + "MSRValue": "0x3FBFC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -628,12 +628,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3", - "MSRValue": "0x3fbfc00200", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", + "MSRValue": "0x3FBFC00200", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -641,12 +641,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3", - "MSRValue": "0x3fbfc00100", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", + "MSRValue": "0x3FBFC00100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -654,12 +654,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc00002", + "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -667,12 +667,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3", - "MSRValue": "0x3fbfc00002", + "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3", + "MSRValue": "0x3FBFC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json index 0d04bf9db000..c2f6932a5817 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "UMask": "0x1", "BriefDescription": "Instructions retired from execution.", "Counter": "Fixed counter 0", @@ -10,7 +9,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when the thread is not in halt state", "Counter": "Fixed counter 1", @@ -20,7 +18,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "Fixed counter 1", @@ -30,7 +27,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x3", "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", @@ -322,7 +318,7 @@ "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "Counter": "0,1,2,3", "EventName": "ILD_STALL.LCP", - "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", + "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -786,12 +782,12 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xa2", "UMask": "0x1", "BriefDescription": "Resource-related stall cycles", "Counter": "0,1,2,3", "EventName": "RESOURCE_STALLS.ANY", - "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.", + "PublicDescription": "This event counts resource-related stall cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1168,12 +1164,12 @@ { "EventCode": "0xC2", "UMask": "0x1", - "BriefDescription": "Actually retired uops. (Precise Event - PEBS)", + "BriefDescription": "Actually retired uops.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "UOPS_RETIRED.ALL", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.", + "PublicDescription": "This event counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1204,11 +1200,11 @@ { "EventCode": "0xC2", "UMask": "0x2", - "BriefDescription": "Retirement slots used. (Precise Event - PEBS)", + "BriefDescription": "Retirement slots used.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "UOPS_RETIRED.RETIRE_SLOTS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of retirement slots used.", + "PublicDescription": "This event counts the number of retirement slots used.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1266,33 +1262,33 @@ { "EventCode": "0xC4", "UMask": "0x1", - "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Conditional branch instructions retired.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.CONDITIONAL", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.", + "PublicDescription": "This event counts conditional branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC4", "UMask": "0x2", - "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Direct and indirect near call instructions retired.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.", + "PublicDescription": "This event counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC4", "UMask": "0x2", - "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS)", + "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_CALL_R3", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect macro near call instructions retired (captured in ring 3).", + "PublicDescription": "This event counts both direct and indirect macro near call instructions retired (captured in ring 3).", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1311,11 +1307,11 @@ { "EventCode": "0xC4", "UMask": "0x8", - "BriefDescription": "Return instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Return instructions retired.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.", + "PublicDescription": "This event counts return instructions retired.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1332,11 +1328,11 @@ { "EventCode": "0xC4", "UMask": "0x20", - "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Taken branch instructions retired.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.", + "PublicDescription": "This event counts taken branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1364,11 +1360,11 @@ { "EventCode": "0xC5", "UMask": "0x1", - "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Mispredicted conditional branch instructions retired.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_MISP_RETIRED.CONDITIONAL", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.", + "PublicDescription": "This event counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1386,22 +1382,22 @@ { "EventCode": "0xC5", "UMask": "0x8", - "BriefDescription": "This event counts the number of mispredicted ret instructions retired.(Precise Event)", + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted return instructions retired.", + "PublicDescription": "This event counts mispredicted return instructions retired.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC5", "UMask": "0x20", - "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).", + "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).", + "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 71e9737f4614..1a1a3501180a 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -1,164 +1,394 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )", - "MetricGroup": "Frontend", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "Branch_Misprediction_Cost" + }, + { + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" }, { + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" + }, + { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Access_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )", + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "DRAM_Read_Latency" + }, + { + "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@", + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_Parallel_Reads" + }, + { + "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 1 == 1 else 0 else 0", + "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "MEM_PMM_Read_Latency" + }, + { + "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 1 == 1 else 0 else 0", + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "PMM_Read_BW" + }, + { + "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 1 == 1 else 0 else 0", + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "PMM_Write_BW" + }, + { + "MetricExpr": "cha_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/goldmont/cache.json b/tools/perf/pmu-events/arch/x86/goldmont/cache.json index f8bbe087b0f8..52a105666afc 100644 --- a/tools/perf/pmu-events/arch/x86/goldmont/cache.json +++ b/tools/perf/pmu-events/arch/x86/goldmont/cache.json @@ -77,7 +77,8 @@ "UMask": "0x21", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Locked load uops retired (Precise event capable)" + "BriefDescription": "Locked load uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -88,7 +89,8 @@ "UMask": "0x41", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -99,7 +101,8 @@ "UMask": "0x42", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -110,7 +113,8 @@ "UMask": "0x43", "EventName": "MEM_UOPS_RETIRED.SPLIT", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -121,7 +125,8 @@ "UMask": "0x81", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired (Precise event capable)" + "BriefDescription": "Load uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -132,7 +137,8 @@ "UMask": "0x82", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Store uops retired (Precise event capable)" + "BriefDescription": "Store uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -143,7 +149,8 @@ "UMask": "0x83", "EventName": "MEM_UOPS_RETIRED.ALL", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired (Precise event capable)" + "BriefDescription": "Memory uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -154,7 +161,8 @@ "UMask": "0x1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)" + "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -165,7 +173,8 @@ "UMask": "0x2", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that hit L2 (Precise event capable)" + "BriefDescription": "Load uops retired that hit L2 (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -176,7 +185,8 @@ "UMask": "0x8", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)" + "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -187,7 +197,8 @@ "UMask": "0x10", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed L2 (Precise event capable)" + "BriefDescription": "Load uops retired that missed L2 (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -198,7 +209,8 @@ "UMask": "0x20", "EventName": "MEM_LOAD_UOPS_RETIRED.HITM", "SampleAfterValue": "200003", - "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)" + "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -209,7 +221,8 @@ "UMask": "0x40", "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Loads retired that hit WCB (Precise event capable)" + "BriefDescription": "Loads retired that hit WCB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -220,26 +233,14 @@ "UMask": "0x80", "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Loads retired that came from DRAM (Precise event capable)" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x40000032b7 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" + "BriefDescription": "Loads retired that came from DRAM (Precise event capable)", + "Data_LA": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x36000032b7 ", + "MSRValue": "0x36000032b7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.ANY", @@ -252,7 +253,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x10000032b7 ", + "MSRValue": "0x10000032b7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HITM_OTHER_CORE", @@ -265,7 +266,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x04000032b7 ", + "MSRValue": "0x04000032b7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -278,20 +279,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x02000032b7 ", + "MSRValue": "0x02000032b7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x00000432b7 ", + "MSRValue": "0x00000432b7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT", @@ -302,35 +303,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x00000132b7 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000022 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000022 ", + "MSRValue": "0x3600000022", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.ANY", @@ -343,7 +318,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000022 ", + "MSRValue": "0x1000000022", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HITM_OTHER_CORE", @@ -356,7 +331,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000022 ", + "MSRValue": "0x0400000022", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -369,20 +344,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000022 ", + "MSRValue": "0x0200000022", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040022 ", + "MSRValue": "0x0000040022", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT", @@ -393,32 +368,6 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010022 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000003091", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", "MSRValue": "0x3600003091", @@ -466,7 +415,7 @@ "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -484,35 +433,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000013091", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000003010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600003010 ", + "MSRValue": "0x3600003010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.ANY", @@ -525,7 +448,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000003010 ", + "MSRValue": "0x1000003010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HITM_OTHER_CORE", @@ -538,7 +461,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400003010 ", + "MSRValue": "0x0400003010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -551,20 +474,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200003010 ", + "MSRValue": "0x0200003010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000043010 ", + "MSRValue": "0x0000043010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_HIT", @@ -575,48 +498,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000013010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000008000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x3600008000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.ANY", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000008000 ", + "MSRValue": "0x1000008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HITM_OTHER_CORE", @@ -629,7 +513,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400008000 ", + "MSRValue": "0x0400008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -642,20 +526,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200008000 ", + "MSRValue": "0x0200008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts requests to the uncore subsystem that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000048000 ", + "MSRValue": "0x0000048000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT", @@ -668,7 +552,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts requests to the uncore subsystem that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000018000 ", + "MSRValue": "0x0000018000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE", @@ -679,22 +563,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000004800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600004800 ", + "MSRValue": "0x3600004800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.ANY", @@ -705,48 +576,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000004800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0400004800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0200004800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000044800 ", + "MSRValue": "0x0000044800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_HIT", @@ -757,35 +589,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000014800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000004000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600004000 ", + "MSRValue": "0x3600004000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.ANY", @@ -798,7 +604,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000004000 ", + "MSRValue": "0x1000004000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE", @@ -811,7 +617,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400004000 ", + "MSRValue": "0x0400004000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -824,20 +630,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200004000 ", + "MSRValue": "0x0200004000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000044000 ", + "MSRValue": "0x0000044000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_HIT", @@ -848,35 +654,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000014000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000002000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600002000 ", + "MSRValue": "0x3600002000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.ANY", @@ -889,7 +669,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000002000 ", + "MSRValue": "0x1000002000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HITM_OTHER_CORE", @@ -902,7 +682,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400002000 ", + "MSRValue": "0x0400002000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -915,20 +695,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200002000 ", + "MSRValue": "0x0200002000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000042000 ", + "MSRValue": "0x0000042000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT", @@ -939,35 +719,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000012000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000001000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600001000 ", + "MSRValue": "0x3600001000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.ANY", @@ -980,7 +734,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000001000 ", + "MSRValue": "0x1000001000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HITM_OTHER_CORE", @@ -993,7 +747,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400001000 ", + "MSRValue": "0x0400001000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1006,20 +760,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200001000 ", + "MSRValue": "0x0200001000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache lines requests by software prefetch instructions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000041000 ", + "MSRValue": "0x0000041000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_HIT", @@ -1030,35 +784,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000011000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000800 ", + "MSRValue": "0x3600000800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.ANY", @@ -1071,7 +799,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000800 ", + "MSRValue": "0x1000000800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE", @@ -1084,7 +812,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000800 ", + "MSRValue": "0x0400000800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1097,20 +825,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000800 ", + "MSRValue": "0x0200000800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040800 ", + "MSRValue": "0x0000040800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_HIT", @@ -1121,100 +849,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x3600000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.ANY", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0400000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0200000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module. ", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000040400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that hit the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts bus lock and split lock requests that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000010400 ", + "MSRValue": "0x0000010400", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE", @@ -1225,113 +862,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x3600000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.ANY", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0400000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0200000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000040200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_HIT", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000100 ", + "MSRValue": "0x3600000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.ANY", @@ -1342,87 +875,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000000100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0400000100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0200000100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module. ", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000040100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000080 ", + "MSRValue": "0x3600000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.ANY", @@ -1433,87 +888,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000000080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0400000080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0200000080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module. ", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000040080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000020 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000020 ", + "MSRValue": "0x3600000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.ANY", @@ -1526,7 +903,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000020 ", + "MSRValue": "0x1000000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HITM_OTHER_CORE", @@ -1539,7 +916,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000020 ", + "MSRValue": "0x0400000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1552,20 +929,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000020 ", + "MSRValue": "0x0200000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040020 ", + "MSRValue": "0x0000040020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT", @@ -1576,35 +953,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010020 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000010 ", + "MSRValue": "0x3600000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.ANY", @@ -1617,7 +968,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000010 ", + "MSRValue": "0x1000000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HITM_OTHER_CORE", @@ -1630,7 +981,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000010 ", + "MSRValue": "0x0400000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1643,20 +994,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000010 ", + "MSRValue": "0x0200000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040010 ", + "MSRValue": "0x0000040010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_HIT", @@ -1667,35 +1018,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000008 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.COREWB.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000008 ", + "MSRValue": "0x3600000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.ANY", @@ -1708,7 +1033,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000008 ", + "MSRValue": "0x1000000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HITM_OTHER_CORE", @@ -1721,7 +1046,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000008 ", + "MSRValue": "0x0400000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1734,20 +1059,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000008 ", + "MSRValue": "0x0200000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040008 ", + "MSRValue": "0x0000040008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L2_HIT", @@ -1758,22 +1083,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010008 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x4000000004 ", + "MSRValue": "0x4000000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING", @@ -1786,7 +1098,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000004 ", + "MSRValue": "0x3600000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.ANY", @@ -1797,22 +1109,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000000004 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000004 ", + "MSRValue": "0x0400000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1825,20 +1124,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000004 ", + "MSRValue": "0x0200000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040004 ", + "MSRValue": "0x0000040004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT", @@ -1849,22 +1148,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010004 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x4000000002 ", + "MSRValue": "0x4000000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING", @@ -1877,7 +1163,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000002 ", + "MSRValue": "0x3600000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.ANY", @@ -1890,7 +1176,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000002 ", + "MSRValue": "0x1000000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HITM_OTHER_CORE", @@ -1903,7 +1189,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000002 ", + "MSRValue": "0x0400000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1916,20 +1202,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000002 ", + "MSRValue": "0x0200000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040002 ", + "MSRValue": "0x0000040002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT", @@ -1940,22 +1226,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010002 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x4000000001 ", + "MSRValue": "0x4000000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING", @@ -1968,7 +1241,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000001 ", + "MSRValue": "0x3600000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.ANY", @@ -1981,7 +1254,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000001 ", + "MSRValue": "0x1000000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HITM_OTHER_CORE", @@ -1994,7 +1267,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000001 ", + "MSRValue": "0x0400000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -2007,20 +1280,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000001 ", + "MSRValue": "0x0200000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040001 ", + "MSRValue": "0x0000040001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT", @@ -2028,18 +1301,5 @@ "SampleAfterValue": "100007", "BriefDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache.", "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010001 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem.", - "Offcore": "1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/goldmont/memory.json b/tools/perf/pmu-events/arch/x86/goldmont/memory.json index 690cebd12a94..197dc76d49dd 100644 --- a/tools/perf/pmu-events/arch/x86/goldmont/memory.json +++ b/tools/perf/pmu-events/arch/x86/goldmont/memory.json @@ -30,265 +30,5 @@ "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", "SampleAfterValue": "200003", "BriefDescription": "Machine clears due to memory ordering issue" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x20000032b7 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000022 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000003091", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000003010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000008000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000004800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000004000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000002000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000001000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000020 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000008 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000004 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000002 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000001 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json b/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json index 254788af8ab6..6342368accf8 100644 --- a/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json @@ -1,7 +1,6 @@ [ { "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -10,7 +9,6 @@ }, { "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses fixed counter 1. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.CORE", @@ -19,7 +17,6 @@ }, { "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. This event uses fixed counter 2. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -188,7 +185,7 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.", + "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.", "EventCode": "0xC3", "Counter": "0,1,2,3", "UMask": "0x1", diff --git a/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json b/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json index 9805198d3f5f..343d66bbd777 100644 --- a/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json @@ -48,7 +48,8 @@ "UMask": "0x11", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -59,7 +60,8 @@ "UMask": "0x12", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -70,6 +72,7 @@ "UMask": "0x13", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json index b4791b443a66..5a6ac8285ad4 100644 --- a/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json +++ b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json @@ -92,7 +92,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Locked load uops retired (Precise event capable)" + "BriefDescription": "Locked load uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -104,7 +105,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -116,7 +118,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -128,7 +131,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -140,7 +144,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired (Precise event capable)" + "BriefDescription": "Load uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -152,7 +157,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Store uops retired (Precise event capable)" + "BriefDescription": "Store uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -164,7 +170,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired (Precise event capable)" + "BriefDescription": "Memory uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -176,7 +183,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)" + "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -188,7 +196,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that hit L2 (Precise event capable)" + "BriefDescription": "Load uops retired that hit L2 (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -200,7 +209,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)" + "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -212,7 +222,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed L2 (Precise event capable)" + "BriefDescription": "Load uops retired that missed L2 (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -224,7 +235,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.HITM", "SampleAfterValue": "200003", - "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)" + "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -236,7 +248,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Loads retired that hit WCB (Precise event capable)" + "BriefDescription": "Loads retired that hit WCB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -248,7 +261,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Loads retired that came from DRAM (Precise event capable)" + "BriefDescription": "Loads retired that came from DRAM (Precise event capable)", + "Data_LA": "1" }, { "CollectPEBSRecord": "1", @@ -292,7 +306,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -367,7 +381,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -442,7 +456,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -517,7 +531,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -592,7 +606,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -667,7 +681,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -742,7 +756,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -817,7 +831,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -892,7 +906,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -967,7 +981,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1042,7 +1056,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1117,7 +1131,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1192,7 +1206,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1267,7 +1281,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1342,7 +1356,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1417,7 +1431,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json index ccf1aed69197..e3fa1a0ba71b 100644 --- a/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json @@ -3,7 +3,6 @@ "PEBS": "2", "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "PEBScounters": "32", @@ -15,7 +14,6 @@ { "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses fixed counter 1. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "PEBScounters": "33", @@ -27,7 +25,6 @@ { "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. This event uses fixed counter 2. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "PEBScounters": "34", @@ -231,7 +228,7 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.", + "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.", "EventCode": "0xC3", "Counter": "0,1,2,3", "UMask": "0x1", diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json index 0b53a3b0dfb8..0d32fd26ded1 100644 --- a/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json @@ -189,7 +189,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -201,7 +202,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -213,6 +215,7 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/haswell/cache.json b/tools/perf/pmu-events/arch/x86/haswell/cache.json index da4d6ddd4f92..7fb0ad8d8ca1 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/cache.json +++ b/tools/perf/pmu-events/arch/x86/haswell/cache.json @@ -63,10 +63,10 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Demand data read requests that hit L2 cache.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x41", + "UMask": "0xc1", "Errata": "HSD78", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "SampleAfterValue": "200003", @@ -77,7 +77,7 @@ "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x42", + "UMask": "0xc2", "EventName": "L2_RQSTS.RFO_HIT", "SampleAfterValue": "200003", "BriefDescription": "RFO requests that hit L2 cache", @@ -87,7 +87,7 @@ "PublicDescription": "Number of instruction fetches that hit the L2 cache.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x44", + "UMask": "0xc4", "EventName": "L2_RQSTS.CODE_RD_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", @@ -97,7 +97,7 @@ "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x50", + "UMask": "0xd0", "EventName": "L2_RQSTS.L2_PF_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 prefetch requests that hit L2 cache", @@ -610,7 +610,7 @@ "Errata": "HSD29, HSD25, HSM26, HSM30", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT", "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ", + "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, @@ -623,7 +623,7 @@ "Errata": "HSD29, HSD25, HSM26, HSM30", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM", "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, @@ -792,7 +792,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "", "EventCode": "0xf4", "Counter": "0,1,2,3", "UMask": "0x10", @@ -802,262 +801,262 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c8fff", + "MSRValue": "0x3F803C8FFF", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all requests that hit in the L3", + "BriefDescription": "Counts all requests hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c07f7", + "MSRValue": "0x10003C07F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c07f7", + "MSRValue": "0x04003C07F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0244", + "MSRValue": "0x04003C0244", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0122", + "MSRValue": "0x10003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0122", + "MSRValue": "0x04003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0091", + "MSRValue": "0x10003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0091", + "MSRValue": "0x04003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0200", + "MSRValue": "0x3F803C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0100", + "MSRValue": "0x3F803C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0080", + "MSRValue": "0x3F803C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0040", + "MSRValue": "0x3F803C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0020", + "MSRValue": "0x3F803C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0010", + "MSRValue": "0x3F803C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0004", + "MSRValue": "0x10003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0004", + "MSRValue": "0x04003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0002", + "MSRValue": "0x10003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0002", + "MSRValue": "0x04003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0001", + "MSRValue": "0x10003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0001", + "MSRValue": "0x04003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json index f9843e5a9b42..f5a3beaa19fc 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json @@ -1,22 +1,26 @@ [ { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x8", "Errata": "HSD56, HSM57", "EventName": "OTHER_ASSISTS.AVX_TO_SSE", "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x10", "Errata": "HSD56, HSM57", "EventName": "OTHER_ASSISTS.SSE_TO_AVX", "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -30,53 +34,58 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of X87 FP assists due to output values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x2", "EventName": "FP_ASSIST.X87_OUTPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to output value.", + "BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of X87 FP assists due to input values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x4", "EventName": "FP_ASSIST.X87_INPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to input value.", + "BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of SIMD FP assists due to output values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x8", "EventName": "FP_ASSIST.SIMD_OUTPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to Output values", + "BriefDescription": "SSE* FP micro-code assist when output value is invalid.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of SIMD FP assists due to input values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x10", "EventName": "FP_ASSIST.SIMD_INPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to input values", + "BriefDescription": "Any input SSE* FP Assist", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles with any input/output SSE* or FP assists.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x1e", "EventName": "FP_ASSIST.ANY", "SampleAfterValue": "100003", - "BriefDescription": "Cycles with any input/output SSE or FP assist", + "BriefDescription": "Counts any FP_ASSIST umask was incrementing", "CounterMask": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 5ab5c78fe580..21b27488b621 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -1,158 +1,322 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", - "MetricGroup": "Frontend", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/haswell/memory.json b/tools/perf/pmu-events/arch/x86/haswell/memory.json index e5f9fa6655b3..ef13ed88e2ea 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/memory.json +++ b/tools/perf/pmu-events/arch/x86/haswell/memory.json @@ -298,7 +298,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "SampleAfterValue": "100003", - "BriefDescription": "Loads with latency value being above 4.", + "BriefDescription": "Randomly selected loads with latency value being above 4.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -312,7 +312,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "SampleAfterValue": "50021", - "BriefDescription": "Loads with latency value being above 8.", + "BriefDescription": "Randomly selected loads with latency value being above 8.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -326,7 +326,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "SampleAfterValue": "20011", - "BriefDescription": "Loads with latency value being above 16.", + "BriefDescription": "Randomly selected loads with latency value being above 16.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -340,7 +340,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "SampleAfterValue": "100003", - "BriefDescription": "Loads with latency value being above 32.", + "BriefDescription": "Randomly selected loads with latency value being above 32.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -354,7 +354,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "SampleAfterValue": "2003", - "BriefDescription": "Loads with latency value being above 64.", + "BriefDescription": "Randomly selected loads with latency value being above 64.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -368,7 +368,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "SampleAfterValue": "1009", - "BriefDescription": "Loads with latency value being above 128.", + "BriefDescription": "Randomly selected loads with latency value being above 128.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -382,7 +382,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "SampleAfterValue": "503", - "BriefDescription": "Loads with latency value being above 256.", + "BriefDescription": "Randomly selected loads with latency value being above 256.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -396,280 +396,280 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "SampleAfterValue": "101", - "BriefDescription": "Loads with latency value being above 512.", + "BriefDescription": "Randomly selected loads with latency value being above 512.", "TakenAlone": "1", "CounterHTOff": "3" }, { - "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc08fff", + "MSRValue": "0x3FFFC08FFF", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all requests that miss in the L3", + "BriefDescription": "Counts all requests miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01004007f7", + "MSRValue": "0x01004007F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram", + "BriefDescription": "miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc007f7", + "MSRValue": "0x3FFFC007F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3", + "BriefDescription": "miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400244", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00244", + "MSRValue": "0x3FFFC00244", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3", + "BriefDescription": "Counts all demand & prefetch code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00122", + "MSRValue": "0x3FFFC00122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3", + "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00091", + "MSRValue": "0x3FFFC00091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3", + "BriefDescription": "Counts all demand & prefetch data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00200", + "MSRValue": "0x3FFFC00200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00100", + "MSRValue": "0x3FFFC00100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00080", + "MSRValue": "0x3FFFC00080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00040", + "MSRValue": "0x3FFFC00040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00020", + "MSRValue": "0x3FFFC00020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00010", + "MSRValue": "0x3FFFC00010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00004", + "MSRValue": "0x3FFFC00004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that miss in the L3", + "BriefDescription": "Counts all demand code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00002", + "MSRValue": "0x3FFFC00002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3", + "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00001", + "MSRValue": "0x3FFFC00001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that miss in the L3", + "BriefDescription": "Counts demand data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json index a4dcfce4a512..734d3873729e 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json @@ -1,7 +1,6 @@ [ { "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. INST_RETIRED.ANY is counted by a designated fixed counter, leaving the programmable counters available for other events. Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "Errata": "HSD140, HSD143", @@ -12,7 +11,6 @@ }, { "PublicDescription": "This event counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -21,7 +19,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "AnyThread": "1", @@ -32,7 +29,6 @@ }, { "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -1071,7 +1067,8 @@ "CounterHTOff": "1" }, { - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", "EventCode": "0xC0", "Counter": "0,1,2,3", "UMask": "0x2", @@ -1081,13 +1078,13 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x40", "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST", "SampleAfterValue": "100003", - "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1102,28 +1099,34 @@ "Data_LA": "1" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "UOPS_RETIRED.STALL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", + "BriefDescription": "Cycles no executable uops retired", "CounterMask": "1", "CounterHTOff": "0,1,2,3" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "UOPS_RETIRED.TOTAL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 10 actually retired uops.", + "BriefDescription": "Number of cycles using always true condition applied to PEBS uops retired event.", "CounterMask": "10", "CounterHTOff": "0,1,2,3" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", @@ -1131,7 +1134,7 @@ "AnyThread": "1", "EventName": "UOPS_RETIRED.CORE_STALL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", + "BriefDescription": "Cycles no executable uops retired on core", "CounterMask": "1", "CounterHTOff": "0,1,2,3" }, @@ -1245,13 +1248,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of not taken branch instructions retired.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x10", "EventName": "BR_INST_RETIRED.NOT_TAKEN", "SampleAfterValue": "400009", - "BriefDescription": "Not taken branch instructions retired.", + "BriefDescription": "Counts all not taken macro branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1265,13 +1269,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of far branches retired.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x40", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "SampleAfterValue": "100003", - "BriefDescription": "Far branch instructions retired.", + "BriefDescription": "Counts the number of far branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { diff --git a/tools/perf/pmu-events/arch/x86/haswellx/cache.json b/tools/perf/pmu-events/arch/x86/haswellx/cache.json index b2fbd617306a..a9e62d4357af 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/cache.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/cache.json @@ -64,18 +64,18 @@ }, { "EventCode": "0x24", - "UMask": "0x41", + "UMask": "0xc1", "BriefDescription": "Demand Data Read requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "Errata": "HSD78", - "PublicDescription": "Demand data read requests that hit L2 cache.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x24", - "UMask": "0x42", + "UMask": "0xc2", "BriefDescription": "RFO requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.RFO_HIT", @@ -85,7 +85,7 @@ }, { "EventCode": "0x24", - "UMask": "0x44", + "UMask": "0xc4", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.CODE_RD_HIT", @@ -95,7 +95,7 @@ }, { "EventCode": "0x24", - "UMask": "0x50", + "UMask": "0xd0", "BriefDescription": "L2 prefetch requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.L2_PF_HIT", @@ -416,7 +416,7 @@ { "EventCode": "0xD0", "UMask": "0x11", - "BriefDescription": "Retired load uops that miss the STLB. (precise Event)", + "BriefDescription": "Retired load uops that miss the STLB.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -428,7 +428,7 @@ { "EventCode": "0xD0", "UMask": "0x12", - "BriefDescription": "Retired store uops that miss the STLB. (precise Event)", + "BriefDescription": "Retired store uops that miss the STLB.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -441,7 +441,7 @@ { "EventCode": "0xD0", "UMask": "0x21", - "BriefDescription": "Retired load uops with locked access. (precise Event)", + "BriefDescription": "Retired load uops with locked access.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -453,34 +453,32 @@ { "EventCode": "0xD0", "UMask": "0x41", - "BriefDescription": "Retired load uops that split across a cacheline boundary. (precise Event)", + "BriefDescription": "Retired load uops that split across a cacheline boundary.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "Errata": "HSD29, HSM30", - "PublicDescription": "This event counts load uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x42", - "BriefDescription": "Retired store uops that split across a cacheline boundary. (precise Event)", + "BriefDescription": "Retired store uops that split across a cacheline boundary.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "Errata": "HSD29, HSM30", "L1_Hit_Indication": "1", - "PublicDescription": "This event counts store uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x81", - "BriefDescription": "All retired load uops. (precise Event)", + "BriefDescription": "All retired load uops.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -492,14 +490,13 @@ { "EventCode": "0xD0", "UMask": "0x82", - "BriefDescription": "All retired store uops. (precise Event)", + "BriefDescription": "All retired store uops.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "Errata": "HSD29, HSM30", "L1_Hit_Indication": "1", - "PublicDescription": "This event counts all store uops retired. This is a precise event.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, @@ -530,13 +527,13 @@ { "EventCode": "0xD1", "UMask": "0x4", - "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", + "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30", - "PublicDescription": "This event counts retired load uops in which data sources were data hits in the L3 cache without snoops required. This does not include hardware prefetches. This is a precise event.", + "PublicDescription": "Retired load uops with L3 cache hits as data sources.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, @@ -549,19 +546,20 @@ "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "Errata": "HSM30", - "PublicDescription": "This event counts retired load uops in which data sources missed in the L1 cache. This does not include hardware prefetches. This is a precise event.", + "PublicDescription": "Retired load uops missed L1 cache as data sources.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x10", - "BriefDescription": "Retired load uops with L2 cache misses as data sources.", + "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "Errata": "HSD29, HSM30", + "PublicDescription": "Retired load uops missed L2. Unknown data source excluded.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, @@ -574,6 +572,7 @@ "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_MISS", "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30", + "PublicDescription": "Retired load uops missed L3. Excludes unknown data source .", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -604,26 +603,24 @@ { "EventCode": "0xD2", "UMask": "0x2", - "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ", + "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT", "Errata": "HSD29, HSD25, HSM26, HSM30", - "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HIT in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD2", "UMask": "0x4", - "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM", "Errata": "HSD29, HSD25, HSM26, HSM30", - "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HITM (hit modified) in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, @@ -642,19 +639,20 @@ { "EventCode": "0xD3", "UMask": "0x1", + "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", "Errata": "HSD74, HSD29, HSD25, HSM30", - "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.", + "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD3", "UMask": "0x4", - "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -666,7 +664,7 @@ { "EventCode": "0xD3", "UMask": "0x10", - "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -678,7 +676,7 @@ { "EventCode": "0xD3", "UMask": "0x20", - "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -833,7 +831,6 @@ "BriefDescription": "Split locks in SQ", "Counter": "0,1,2,3", "EventName": "SQ_MISC.SPLIT_LOCK", - "PublicDescription": "", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -841,12 +838,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0001", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -854,12 +851,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0001", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -867,12 +864,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0002", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -880,12 +877,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0002", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -893,12 +890,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0004", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -906,12 +903,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0004", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -919,12 +916,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3", - "MSRValue": "0x3f803c0010", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", + "MSRValue": "0x3F803C0010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -932,12 +929,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3", - "MSRValue": "0x3f803c0020", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", + "MSRValue": "0x3F803C0020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -945,12 +942,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3", - "MSRValue": "0x3f803c0040", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", + "MSRValue": "0x3F803C0040", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -958,12 +955,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3", - "MSRValue": "0x3f803c0080", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", + "MSRValue": "0x3F803C0080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -971,12 +968,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3", - "MSRValue": "0x3f803c0100", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", + "MSRValue": "0x3F803C0100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -984,12 +981,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3", - "MSRValue": "0x3f803c0200", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", + "MSRValue": "0x3F803C0200", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -997,12 +994,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0091", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1010,12 +1007,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0091", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1023,12 +1020,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0122", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1036,12 +1033,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0122", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1049,12 +1046,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0244", + "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1062,12 +1059,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c07f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C07F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1075,12 +1072,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c07f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C07F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1088,12 +1085,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all requests that hit in the L3", - "MSRValue": "0x3f803c8fff", + "BriefDescription": "Counts all requests hit in the L3", + "MSRValue": "0x3F803C8FFF", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 5ab5c78fe580..e5aac148c941 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -1,158 +1,340 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", - "MetricGroup": "Frontend", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )", + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "DRAM_Read_Latency" + }, + { + "MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@", + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_Parallel_Reads" + }, + { + "MetricExpr": "cbox_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/memory.json b/tools/perf/pmu-events/arch/x86/haswellx/memory.json index 56b0f24b8029..a42d5ce86b6f 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/memory.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/memory.json @@ -291,7 +291,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 4.", + "BriefDescription": "Randomly selected loads with latency value being above 4.", "PEBS": "2", "MSRValue": "0x4", "Counter": "3", @@ -305,7 +305,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 8.", + "BriefDescription": "Randomly selected loads with latency value being above 8.", "PEBS": "2", "MSRValue": "0x8", "Counter": "3", @@ -319,7 +319,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 16.", + "BriefDescription": "Randomly selected loads with latency value being above 16.", "PEBS": "2", "MSRValue": "0x10", "Counter": "3", @@ -333,7 +333,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 32.", + "BriefDescription": "Randomly selected loads with latency value being above 32.", "PEBS": "2", "MSRValue": "0x20", "Counter": "3", @@ -347,7 +347,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 64.", + "BriefDescription": "Randomly selected loads with latency value being above 64.", "PEBS": "2", "MSRValue": "0x40", "Counter": "3", @@ -361,7 +361,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 128.", + "BriefDescription": "Randomly selected loads with latency value being above 128.", "PEBS": "2", "MSRValue": "0x80", "Counter": "3", @@ -375,7 +375,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 256.", + "BriefDescription": "Randomly selected loads with latency value being above 256.", "PEBS": "2", "MSRValue": "0x100", "Counter": "3", @@ -389,7 +389,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 512.", + "BriefDescription": "Randomly selected loads with latency value being above 512.", "PEBS": "2", "MSRValue": "0x200", "Counter": "3", @@ -404,12 +404,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss in the L3", - "MSRValue": "0x3fbfc00001", + "BriefDescription": "Counts demand data reads miss in the L3", + "MSRValue": "0x3FBFC00001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -417,12 +417,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -430,12 +430,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3", - "MSRValue": "0x3fbfc00002", + "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3", + "MSRValue": "0x3FBFC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -443,12 +443,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -456,12 +456,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc00002", + "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -469,12 +469,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss in the L3", - "MSRValue": "0x3fbfc00004", + "BriefDescription": "Counts all demand code reads miss in the L3", + "MSRValue": "0x3FBFC00004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -482,12 +482,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -495,12 +495,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3", - "MSRValue": "0x3fbfc00010", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", + "MSRValue": "0x3FBFC00010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -508,12 +508,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3", - "MSRValue": "0x3fbfc00020", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", + "MSRValue": "0x3FBFC00020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -521,12 +521,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3", - "MSRValue": "0x3fbfc00040", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", + "MSRValue": "0x3FBFC00040", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -534,12 +534,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3", - "MSRValue": "0x3fbfc00080", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", + "MSRValue": "0x3FBFC00080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -547,12 +547,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3", - "MSRValue": "0x3fbfc00100", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", + "MSRValue": "0x3FBFC00100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -560,12 +560,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3", - "MSRValue": "0x3fbfc00200", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", + "MSRValue": "0x3FBFC00200", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -573,12 +573,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3", - "MSRValue": "0x3fbfc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss in the L3", + "MSRValue": "0x3FBFC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -586,12 +586,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -599,12 +599,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram", - "MSRValue": "0x063f800091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram", + "MSRValue": "0x063F800091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -612,12 +612,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -625,12 +625,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache", - "MSRValue": "0x083fc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache", + "MSRValue": "0x083FC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -638,12 +638,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3", - "MSRValue": "0x3fbfc00122", + "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3", + "MSRValue": "0x3FBFC00122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -651,12 +651,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -664,12 +664,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3", - "MSRValue": "0x3fbfc00244", + "BriefDescription": "Counts all demand & prefetch code reads miss in the L3", + "MSRValue": "0x3FBFC00244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -677,12 +677,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -690,12 +690,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3", - "MSRValue": "0x3fbfc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3", + "MSRValue": "0x3FBFC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -703,12 +703,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram", - "MSRValue": "0x06004007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram", + "MSRValue": "0x06004007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -716,12 +716,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram", - "MSRValue": "0x063f8007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram", + "MSRValue": "0x063F8007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -729,12 +729,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -742,12 +742,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache", - "MSRValue": "0x083fc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache", + "MSRValue": "0x083FC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -755,12 +755,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all requests that miss in the L3", - "MSRValue": "0x3fbfc08fff", + "BriefDescription": "Counts all requests miss in the L3", + "MSRValue": "0x3FBFC08FFF", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json index 8a18bfe9e3e4..26f2888341ee 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "UMask": "0x1", "BriefDescription": "Instructions retired from execution.", "Counter": "Fixed counter 0", @@ -11,7 +10,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when the thread is not in halt state.", "Counter": "Fixed counter 1", @@ -21,7 +19,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "Fixed counter 1", @@ -31,7 +28,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x3", "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", @@ -1098,6 +1094,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "UOPS_RETIRED.ALL", + "PublicDescription": "Counts the number of micro-ops retired. Use Cmask=1 and invert to count active cycles or stalled cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1142,6 +1139,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PublicDescription": "This event counts the number of retirement slots used each cycle. There are potentially 4 slots that can be used each cycle - meaning, 4 uops or 4 instructions could retire each cycle.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1201,6 +1199,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.CONDITIONAL", + "PublicDescription": "Counts the number of conditional branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1241,6 +1240,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PublicDescription": "Counts the number of near return instructions retired.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1261,6 +1261,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PublicDescription": "Number of near taken branches retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1312,6 +1313,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PublicDescription": "Number of near branch instructions retired that were taken but mispredicted.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json index 999a01bc6467..5f6cb2abc384 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json @@ -1012,7 +1012,7 @@ "EventName": "OFFCORE_RESPONSE.SPLIT_LOCK_UC_LOCK.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address ", + "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address", "CounterHTOff": "0,1,2,3" }, { @@ -1036,7 +1036,7 @@ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data reads ", + "BriefDescription": "Counts all demand data reads", "CounterHTOff": "0,1,2,3" }, { @@ -1048,7 +1048,7 @@ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand rfo's ", + "BriefDescription": "Counts all demand rfo's", "CounterHTOff": "0,1,2,3" }, { @@ -1084,7 +1084,7 @@ "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch prefetch RFOs ", + "BriefDescription": "Counts all demand & prefetch prefetch RFOs", "CounterHTOff": "0,1,2,3" }, { @@ -1096,7 +1096,7 @@ "EventName": "OFFCORE_RESPONSE.ALL_READS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo references (demand & prefetch) ", + "BriefDescription": "Counts all data/code/rfo references (demand & prefetch)", "CounterHTOff": "0,1,2,3" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 7c2679514efb..bc4d5fc284a0 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -1,164 +1,340 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", - "MetricGroup": "Frontend", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json index 0afbfd95ea30..2a0aad91d83d 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -9,7 +8,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -19,7 +17,6 @@ }, { "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "AnyThread": "1", @@ -29,7 +26,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 7c2679514efb..f3874b5f9995 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -1,164 +1,346 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", - "MetricGroup": "Frontend", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "cbox_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json index 0afbfd95ea30..2a0aad91d83d 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -9,7 +8,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -19,7 +17,6 @@ }, { "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "AnyThread": "1", @@ -29,7 +26,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/cache.json b/tools/perf/pmu-events/arch/x86/jaketown/cache.json index ee22e4a5e30d..52dc6ef40e63 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/cache.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/cache.json @@ -31,7 +31,7 @@ }, { "PEBS": "1", - "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "EventCode": "0xD0", "Counter": "0,1,2,3", "UMask": "0x41", @@ -42,7 +42,7 @@ }, { "PEBS": "1", - "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "EventCode": "0xD0", "Counter": "0,1,2,3", "UMask": "0x42", @@ -179,7 +179,7 @@ "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier. ", + "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.", "EventCode": "0x51", "Counter": "0,1,2,3", "UMask": "0x1", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index fd7d7c438226..98c73e430b05 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -1,140 +1,232 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", - "MetricGroup": "Frontend", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Average CPU Utilization", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "cbox_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json index 34a519d9bfa0..783a5b4a67b1 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json @@ -1,7 +1,6 @@ [ { - "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. ", - "EventCode": "0x00", + "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers.", "Counter": "Fixed counter 1", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -10,8 +9,7 @@ "CounterHTOff": "Fixed counter 1" }, { - "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ", - "EventCode": "0x00", + "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", "Counter": "Fixed counter 2", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -20,8 +18,7 @@ "CounterHTOff": "Fixed counter 2" }, { - "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ", - "EventCode": "0x00", + "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", "Counter": "Fixed counter 3", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -778,7 +775,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", + "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", "EventCode": "0x03", "Counter": "0,1,2,3", "UMask": "0x2", @@ -1098,7 +1095,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x2", "AnyThread": "1", diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json index e434ec723001..e847b0fd696d 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json @@ -32,16 +32,16 @@ "BriefDescription": "Counts the number of L2 cache misses" }, { - "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses. ", + "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses.", "EventCode": "0x86", "Counter": "0,1", "UMask": "0x4", "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cummulative count of core cycles the fetch stalled for all icache misses. " + "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cummulative count of core cycles the fetch stalled for all icache misses." }, { - "PublicDescription": "This event counts the number of load micro-ops retired that miss in L1 Data cache. Note that prefetch misses will not be counted. ", + "PublicDescription": "This event counts the number of load micro-ops retired that miss in L1 Data cache. Note that prefetch misses will not be counted.", "EventCode": "0x04", "Counter": "0,1", "UMask": "0x1", @@ -115,29 +115,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000070 ", + "MSRValue": "0x4000000070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400070 ", + "MSRValue": "0x1000400070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400070 ", + "MSRValue": "0x0800400070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_E_F", @@ -148,29 +148,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080070 ", + "MSRValue": "0x1000080070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080070 ", + "MSRValue": "0x0800080070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010070 ", + "MSRValue": "0x0000010070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.ANY_RESPONSE", @@ -181,29 +181,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x40000032f7 ", + "MSRValue": "0x40000032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts any Read request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x10004032f7 ", + "MSRValue": "0x10004032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x08004032f7 ", + "MSRValue": "0x08004032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_E_F", @@ -214,29 +214,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x10000832f7 ", + "MSRValue": "0x10000832f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x08000832f7 ", + "MSRValue": "0x08000832f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00000132f7 ", + "MSRValue": "0x00000132f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE", @@ -247,29 +247,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000044 ", + "MSRValue": "0x4000000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400044 ", + "MSRValue": "0x1000400044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400044 ", + "MSRValue": "0x0800400044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_E_F", @@ -280,29 +280,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080044 ", + "MSRValue": "0x1000080044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080044 ", + "MSRValue": "0x0800080044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010044 ", + "MSRValue": "0x0000010044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.ANY_RESPONSE", @@ -313,29 +313,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000022 ", + "MSRValue": "0x4000000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Demand cacheable data write requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400022 ", + "MSRValue": "0x1000400022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400022 ", + "MSRValue": "0x0800400022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_E_F", @@ -346,29 +346,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080022 ", + "MSRValue": "0x1000080022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080022 ", + "MSRValue": "0x0800080022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010022 ", + "MSRValue": "0x0000010022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE", @@ -379,29 +379,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000003091 ", + "MSRValue": "0x4000003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000403091 ", + "MSRValue": "0x1000403091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800403091 ", + "MSRValue": "0x0800403091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_E_F", @@ -412,29 +412,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000083091 ", + "MSRValue": "0x1000083091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800083091 ", + "MSRValue": "0x0800083091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000013091 ", + "MSRValue": "0x0000013091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE", @@ -445,29 +445,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000008000 ", + "MSRValue": "0x4000008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000408000 ", + "MSRValue": "0x1000408000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800408000 ", + "MSRValue": "0x0800408000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_E_F", @@ -478,29 +478,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000088000 ", + "MSRValue": "0x1000088000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800088000 ", + "MSRValue": "0x0800088000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000018000 ", + "MSRValue": "0x0000018000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE", @@ -511,7 +511,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0000014800 ", + "MSRValue": "0x0000014800", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE", @@ -522,7 +522,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0000014000 ", + "MSRValue": "0x0000014000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE", @@ -533,29 +533,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000002000 ", + "MSRValue": "0x4000002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000402000 ", + "MSRValue": "0x1000402000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800402000 ", + "MSRValue": "0x0800402000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_E_F", @@ -566,29 +566,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000082000 ", + "MSRValue": "0x1000082000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800082000 ", + "MSRValue": "0x0800082000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000012000 ", + "MSRValue": "0x0000012000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE", @@ -599,29 +599,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000001000 ", + "MSRValue": "0x4000001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000401000 ", + "MSRValue": "0x1000401000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800401000 ", + "MSRValue": "0x0800401000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_E_F", @@ -632,29 +632,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000081000 ", + "MSRValue": "0x1000081000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800081000 ", + "MSRValue": "0x0800081000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000011000 ", + "MSRValue": "0x0000011000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.ANY_RESPONSE", @@ -665,7 +665,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0000010800 ", + "MSRValue": "0x0000010800", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE", @@ -676,29 +676,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000400 ", + "MSRValue": "0x4000000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400400 ", + "MSRValue": "0x1000400400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400400 ", + "MSRValue": "0x0800400400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_E_F", @@ -709,29 +709,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080400 ", + "MSRValue": "0x1000080400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080400 ", + "MSRValue": "0x0800080400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010400 ", + "MSRValue": "0x0000010400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE", @@ -742,29 +742,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000200 ", + "MSRValue": "0x4000000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400200 ", + "MSRValue": "0x1000400200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400200 ", + "MSRValue": "0x0800400200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_E_F", @@ -775,29 +775,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080200 ", + "MSRValue": "0x1000080200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080200 ", + "MSRValue": "0x0800080200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010200 ", + "MSRValue": "0x0000010200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.ANY_RESPONSE", @@ -808,18 +808,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000400100 ", + "MSRValue": "0x1000400100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400100 ", + "MSRValue": "0x0800400100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_E_F", @@ -830,29 +830,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080100 ", + "MSRValue": "0x1000080100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080100 ", + "MSRValue": "0x0800080100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010100 ", + "MSRValue": "0x0000010100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE", @@ -863,29 +863,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000080 ", + "MSRValue": "0x4000000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400080 ", + "MSRValue": "0x1000400080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400080 ", + "MSRValue": "0x0800400080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_E_F", @@ -896,29 +896,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080080 ", + "MSRValue": "0x1000080080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080080 ", + "MSRValue": "0x0800080080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010080 ", + "MSRValue": "0x0000010080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE", @@ -929,29 +929,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000040 ", + "MSRValue": "0x4000000040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400040 ", + "MSRValue": "0x1000400040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400040 ", + "MSRValue": "0x0800400040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_E_F", @@ -962,29 +962,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080040 ", + "MSRValue": "0x1000080040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080040 ", + "MSRValue": "0x0800080040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010040 ", + "MSRValue": "0x0000010040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE", @@ -995,18 +995,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000400020 ", + "MSRValue": "0x1000400020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400020 ", + "MSRValue": "0x0800400020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_E_F", @@ -1017,29 +1017,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080020 ", + "MSRValue": "0x1000080020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080020 ", + "MSRValue": "0x0800080020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000020020 ", + "MSRValue": "0x0000020020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE", @@ -1050,7 +1050,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0000010020 ", + "MSRValue": "0x0000010020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", @@ -1061,29 +1061,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000004 ", + "MSRValue": "0x4000000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400004 ", + "MSRValue": "0x1000400004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400004 ", + "MSRValue": "0x0800400004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_E_F", @@ -1094,29 +1094,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080004 ", + "MSRValue": "0x1000080004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080004 ", + "MSRValue": "0x0800080004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010004 ", + "MSRValue": "0x0000010004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", @@ -1127,29 +1127,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000002 ", + "MSRValue": "0x4000000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400002 ", + "MSRValue": "0x1000400002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400002 ", + "MSRValue": "0x0800400002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_E_F", @@ -1160,29 +1160,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080002 ", + "MSRValue": "0x1000080002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080002 ", + "MSRValue": "0x0800080002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010002 ", + "MSRValue": "0x0000010002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", @@ -1193,29 +1193,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000001 ", + "MSRValue": "0x4000000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400001 ", + "MSRValue": "0x1000400001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400001 ", + "MSRValue": "0x0800400001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_E_F", @@ -1226,29 +1226,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080001 ", + "MSRValue": "0x1000080001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080001 ", + "MSRValue": "0x0800080001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010001 ", + "MSRValue": "0x0000010001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", @@ -1259,722 +1259,722 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0002000001 ", + "MSRValue": "0x0002000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000002 ", + "MSRValue": "0x0002000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000004 ", + "MSRValue": "0x0002000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000020 ", + "MSRValue": "0x0002000020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000080 ", + "MSRValue": "0x0002000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000100 ", + "MSRValue": "0x0002000100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000200 ", + "MSRValue": "0x0002000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000400 ", + "MSRValue": "0x0002000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002001000 ", + "MSRValue": "0x0002001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002002000 ", + "MSRValue": "0x0002002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002008000 ", + "MSRValue": "0x0002008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002003091 ", + "MSRValue": "0x0002003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000022 ", + "MSRValue": "0x0002000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000044 ", + "MSRValue": "0x0002000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00020032f7 ", + "MSRValue": "0x00020032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000070 ", + "MSRValue": "0x0002000070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000001 ", + "MSRValue": "0x0004000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000002 ", + "MSRValue": "0x0004000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000004 ", + "MSRValue": "0x0004000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000020 ", + "MSRValue": "0x0004000020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000040 ", + "MSRValue": "0x0004000040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000080 ", + "MSRValue": "0x0004000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000100 ", + "MSRValue": "0x0004000100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000200 ", + "MSRValue": "0x0004000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000400 ", + "MSRValue": "0x0004000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004001000 ", + "MSRValue": "0x0004001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004002000 ", + "MSRValue": "0x0004002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004008000 ", + "MSRValue": "0x0004008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004003091 ", + "MSRValue": "0x0004003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000022 ", + "MSRValue": "0x0004000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000044 ", + "MSRValue": "0x0004000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00040032f7 ", + "MSRValue": "0x00040032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000070 ", + "MSRValue": "0x0004000070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000001 ", + "MSRValue": "0x0008000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000002 ", + "MSRValue": "0x0008000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000004 ", + "MSRValue": "0x0008000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000020 ", + "MSRValue": "0x0008000020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000080 ", + "MSRValue": "0x0008000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000100 ", + "MSRValue": "0x0008000100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000200 ", + "MSRValue": "0x0008000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000400 ", + "MSRValue": "0x0008000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008001000 ", + "MSRValue": "0x0008001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008002000 ", + "MSRValue": "0x0008002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008008000 ", + "MSRValue": "0x0008008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008003091 ", + "MSRValue": "0x0008003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000022 ", + "MSRValue": "0x0008000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000044 ", + "MSRValue": "0x0008000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00080032f7 ", + "MSRValue": "0x00080032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000001 ", + "MSRValue": "0x0010000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000002 ", + "MSRValue": "0x0010000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000004 ", + "MSRValue": "0x0010000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000020 ", + "MSRValue": "0x0010000020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000040 ", + "MSRValue": "0x0010000040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000080 ", + "MSRValue": "0x0010000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000100 ", + "MSRValue": "0x0010000100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000200 ", + "MSRValue": "0x0010000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000400 ", + "MSRValue": "0x0010000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010001000 ", + "MSRValue": "0x0010001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010002000 ", + "MSRValue": "0x0010002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010008000 ", + "MSRValue": "0x0010008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010003091 ", + "MSRValue": "0x0010003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000022 ", + "MSRValue": "0x0010000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000044 ", + "MSRValue": "0x0010000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00100032f7 ", + "MSRValue": "0x00100032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000070 ", + "MSRValue": "0x0010000070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1800180002 ", + "MSRValue": "0x1800180002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE", @@ -1985,7 +1985,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180004 ", + "MSRValue": "0x1800180004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE", @@ -1996,7 +1996,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180020 ", + "MSRValue": "0x1800180020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE", @@ -2007,7 +2007,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180040 ", + "MSRValue": "0x1800180040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE", @@ -2018,7 +2018,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180080 ", + "MSRValue": "0x1800180080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE", @@ -2029,7 +2029,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180100 ", + "MSRValue": "0x1800180100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE", @@ -2040,7 +2040,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180200 ", + "MSRValue": "0x1800180200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE", @@ -2051,7 +2051,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180400 ", + "MSRValue": "0x1800180400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE", @@ -2062,7 +2062,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800181000 ", + "MSRValue": "0x1800181000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE", @@ -2073,7 +2073,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800182000 ", + "MSRValue": "0x1800182000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE", @@ -2084,7 +2084,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800188000 ", + "MSRValue": "0x1800188000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE", @@ -2095,7 +2095,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800183091 ", + "MSRValue": "0x1800183091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE", @@ -2106,7 +2106,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180022 ", + "MSRValue": "0x1800180022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE", @@ -2117,7 +2117,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180044 ", + "MSRValue": "0x1800180044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE", @@ -2128,7 +2128,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x18001832f7 ", + "MSRValue": "0x18001832f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE", @@ -2139,7 +2139,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180070 ", + "MSRValue": "0x1800180070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE", @@ -2150,7 +2150,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400002 ", + "MSRValue": "0x1800400002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE", @@ -2161,7 +2161,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400004 ", + "MSRValue": "0x1800400004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE", @@ -2172,7 +2172,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400040 ", + "MSRValue": "0x1800400040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE", @@ -2183,7 +2183,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400080 ", + "MSRValue": "0x1800400080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE", @@ -2194,7 +2194,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400100 ", + "MSRValue": "0x1800400100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE", @@ -2205,7 +2205,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400400 ", + "MSRValue": "0x1800400400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE", @@ -2216,7 +2216,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800401000 ", + "MSRValue": "0x1800401000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE", @@ -2227,7 +2227,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800402000 ", + "MSRValue": "0x1800402000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE", @@ -2238,7 +2238,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800408000 ", + "MSRValue": "0x1800408000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE", @@ -2249,7 +2249,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800403091 ", + "MSRValue": "0x1800403091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE", @@ -2260,7 +2260,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400022 ", + "MSRValue": "0x1800400022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE", @@ -2271,7 +2271,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400044 ", + "MSRValue": "0x1800400044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE", @@ -2282,7 +2282,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x18004032f7 ", + "MSRValue": "0x18004032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE", @@ -2293,7 +2293,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400070 ", + "MSRValue": "0x1800400070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE", diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/memory.json index 700652566200..c6bb16ba0f86 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/memory.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/memory.json @@ -9,18 +9,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400070 ", + "MSRValue": "0x0100400070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts any Prefetch requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200070 ", + "MSRValue": "0x0080200070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM_NEAR", @@ -31,18 +31,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000070 ", + "MSRValue": "0x0101000070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts any Prefetch requests that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800070 ", + "MSRValue": "0x0080800070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.DDR_NEAR", @@ -53,18 +53,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x01004032f7 ", + "MSRValue": "0x01004032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts any Read request that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00802032f7 ", + "MSRValue": "0x00802032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM_NEAR", @@ -75,18 +75,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x01010032f7 ", + "MSRValue": "0x01010032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts any Read request that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00808032f7 ", + "MSRValue": "0x00808032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR_NEAR", @@ -97,18 +97,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400044 ", + "MSRValue": "0x0100400044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200044 ", + "MSRValue": "0x0080200044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM_NEAR", @@ -119,18 +119,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000044 ", + "MSRValue": "0x0101000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800044 ", + "MSRValue": "0x0080800044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR_NEAR", @@ -141,18 +141,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400022 ", + "MSRValue": "0x0100400022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200022 ", + "MSRValue": "0x0080200022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM_NEAR", @@ -163,18 +163,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000022 ", + "MSRValue": "0x0101000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800022 ", + "MSRValue": "0x0080800022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR_NEAR", @@ -185,18 +185,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100403091 ", + "MSRValue": "0x0100403091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080203091 ", + "MSRValue": "0x0080203091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM_NEAR", @@ -207,18 +207,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101003091 ", + "MSRValue": "0x0101003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080803091 ", + "MSRValue": "0x0080803091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR_NEAR", @@ -229,18 +229,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100408000 ", + "MSRValue": "0x0100408000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts any request that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080208000 ", + "MSRValue": "0x0080208000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM_NEAR", @@ -251,18 +251,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101008000 ", + "MSRValue": "0x0101008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts any request that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080808000 ", + "MSRValue": "0x0080808000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR_NEAR", @@ -273,18 +273,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100402000 ", + "MSRValue": "0x0100402000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080202000 ", + "MSRValue": "0x0080202000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.MCDRAM_NEAR", @@ -295,18 +295,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101002000 ", + "MSRValue": "0x0101002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080802000 ", + "MSRValue": "0x0080802000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR_NEAR", @@ -317,18 +317,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100401000 ", + "MSRValue": "0x0100401000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Software Prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080201000 ", + "MSRValue": "0x0080201000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM_NEAR", @@ -339,18 +339,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101001000 ", + "MSRValue": "0x0101001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Software Prefetches that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080801000 ", + "MSRValue": "0x0080801000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR_NEAR", @@ -361,18 +361,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400400 ", + "MSRValue": "0x0100400400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200400 ", + "MSRValue": "0x0080200400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM_NEAR", @@ -383,18 +383,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000400 ", + "MSRValue": "0x0101000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800400 ", + "MSRValue": "0x0080800400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR_NEAR", @@ -405,18 +405,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400200 ", + "MSRValue": "0x0100400200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200200 ", + "MSRValue": "0x0080200200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM_NEAR", @@ -427,18 +427,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000200 ", + "MSRValue": "0x0101000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800200 ", + "MSRValue": "0x0080800200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR_NEAR", @@ -449,18 +449,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400100 ", + "MSRValue": "0x0100400100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM_FAR", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200100 ", + "MSRValue": "0x0080200100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM_NEAR", @@ -471,18 +471,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000100 ", + "MSRValue": "0x0101000100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.DDR_FAR", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800100 ", + "MSRValue": "0x0080800100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.DDR_NEAR", @@ -493,7 +493,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x2000020080 ", + "MSRValue": "0x2000020080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.NON_DRAM", @@ -504,18 +504,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400080 ", + "MSRValue": "0x0100400080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200080 ", + "MSRValue": "0x0080200080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM_NEAR", @@ -526,18 +526,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000080 ", + "MSRValue": "0x0101000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800080 ", + "MSRValue": "0x0080800080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR_NEAR", @@ -548,18 +548,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400040 ", + "MSRValue": "0x0100400040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200040 ", + "MSRValue": "0x0080200040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.MCDRAM_NEAR", @@ -570,18 +570,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000040 ", + "MSRValue": "0x0101000040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800040 ", + "MSRValue": "0x0080800040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR_NEAR", @@ -592,7 +592,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x2000020020 ", + "MSRValue": "0x2000020020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.NON_DRAM", @@ -603,18 +603,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400020 ", + "MSRValue": "0x0100400020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200020 ", + "MSRValue": "0x0080200020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM_NEAR", @@ -625,18 +625,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000020 ", + "MSRValue": "0x0101000020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800020 ", + "MSRValue": "0x0080800020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR_NEAR", @@ -647,18 +647,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400004 ", + "MSRValue": "0x0100400004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200004 ", + "MSRValue": "0x0080200004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM_NEAR", @@ -669,18 +669,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000004 ", + "MSRValue": "0x0101000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800004 ", + "MSRValue": "0x0080800004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR_NEAR", @@ -691,18 +691,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400002 ", + "MSRValue": "0x0100400002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200002 ", + "MSRValue": "0x0080200002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM_NEAR", @@ -713,18 +713,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000002 ", + "MSRValue": "0x0101000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800002 ", + "MSRValue": "0x0080800002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR_NEAR", @@ -735,18 +735,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400001 ", + "MSRValue": "0x0100400001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200001 ", + "MSRValue": "0x0080200001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM_NEAR", @@ -757,18 +757,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000001 ", + "MSRValue": "0x0101000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800001 ", + "MSRValue": "0x0080800001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR_NEAR", @@ -779,7 +779,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600001 ", + "MSRValue": "0x0180600001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM", @@ -790,7 +790,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600002 ", + "MSRValue": "0x0180600002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM", @@ -801,7 +801,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600004 ", + "MSRValue": "0x0180600004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM", @@ -812,7 +812,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600020 ", + "MSRValue": "0x0180600020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM", @@ -823,7 +823,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600080 ", + "MSRValue": "0x0180600080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM", @@ -834,7 +834,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600100 ", + "MSRValue": "0x0180600100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM", @@ -845,7 +845,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600200 ", + "MSRValue": "0x0180600200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM", @@ -856,7 +856,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600400 ", + "MSRValue": "0x0180600400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM", @@ -867,7 +867,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180601000 ", + "MSRValue": "0x0180601000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM", @@ -878,7 +878,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180608000 ", + "MSRValue": "0x0180608000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM", @@ -889,7 +889,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180603091 ", + "MSRValue": "0x0180603091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM", @@ -900,7 +900,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600022 ", + "MSRValue": "0x0180600022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM", @@ -911,7 +911,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600044 ", + "MSRValue": "0x0180600044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM", @@ -922,7 +922,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x01806032f7 ", + "MSRValue": "0x01806032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM", @@ -933,7 +933,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600070 ", + "MSRValue": "0x0180600070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM", @@ -944,7 +944,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800001 ", + "MSRValue": "0x0181800001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR", @@ -955,7 +955,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800002 ", + "MSRValue": "0x0181800002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR", @@ -966,7 +966,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800004 ", + "MSRValue": "0x0181800004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR", @@ -977,7 +977,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800020 ", + "MSRValue": "0x0181800020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR", @@ -988,7 +988,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800040 ", + "MSRValue": "0x0181800040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR", @@ -999,7 +999,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800080 ", + "MSRValue": "0x0181800080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR", @@ -1010,7 +1010,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800200 ", + "MSRValue": "0x0181800200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR", @@ -1021,7 +1021,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800400 ", + "MSRValue": "0x0181800400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR", @@ -1032,7 +1032,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181801000 ", + "MSRValue": "0x0181801000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR", @@ -1043,7 +1043,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181802000 ", + "MSRValue": "0x0181802000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR", @@ -1054,7 +1054,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181808000 ", + "MSRValue": "0x0181808000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR", @@ -1065,7 +1065,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181803091 ", + "MSRValue": "0x0181803091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR", @@ -1076,7 +1076,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800022 ", + "MSRValue": "0x0181800022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR", @@ -1087,7 +1087,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800044 ", + "MSRValue": "0x0181800044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR", @@ -1098,7 +1098,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x01818032f7 ", + "MSRValue": "0x01818032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR", diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json index bb5494cfb5ae..92e4ef2e22c6 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json @@ -144,7 +144,7 @@ "BriefDescription": "Counts the number of micro-ops retired that are from the complex flows issued by the micro-sequencer (MS)." }, { - "PublicDescription": "This event counts the number of micro-ops (uops) retired. The processor decodes complex macro instructions into a sequence of simpler uops. Most instructions are composed of one or two uops. Some instructions are decoded into longer sequences such as repeat instructions, floating point transcendental instructions, and assists. ", + "PublicDescription": "This event counts the number of micro-ops (uops) retired. The processor decodes complex macro instructions into a sequence of simpler uops. Most instructions are composed of one or two uops. Some instructions are decoded into longer sequences such as repeat instructions, floating point transcendental instructions, and assists.", "EventCode": "0xC2", "Counter": "0,1", "UMask": "0x10", @@ -218,7 +218,7 @@ "UMask": "0x20", "EventName": "NO_ALLOC_CYCLES.RAT_STALL", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of core cycles when no micro-ops are allocated and a RATstall (caused by reservation station full) is asserted. " + "BriefDescription": "Counts the number of core cycles when no micro-ops are allocated and a RATstall (caused by reservation station full) is asserted." }, { "PublicDescription": "This event counts the number of core cycles when no uops are allocated, the instruction queue is empty and the alloc pipe is stalled waiting for instructions to be fetched.", @@ -251,7 +251,7 @@ "UMask": "0x1f", "EventName": "RS_FULL_STALL.ALL", "SampleAfterValue": "200003", - "BriefDescription": "Counts the total number of core cycles the Alloc pipeline is stalled when any one of the reservation stations is full. " + "BriefDescription": "Counts the total number of core cycles the Alloc pipeline is stalled when any one of the reservation stations is full." }, { "EventCode": "0xC0", @@ -268,11 +268,10 @@ "UMask": "0x1", "EventName": "CYCLES_DIV_BUSY.ALL", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles the number of core cycles when divider is busy. Does not imply a stall waiting for the divider. " + "BriefDescription": "Cycles the number of core cycles when divider is busy. Does not imply a stall waiting for the divider." }, { "PublicDescription": "This event counts the number of instructions that retire. For instructions that consist of multiple micro-ops, this event counts exactly once, as the last micro-op of the instruction retires. The event continues counting while instructions retire, including during interrupt service routines caused by hardware interrupts, faults or traps.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -296,8 +295,7 @@ "BriefDescription": "Counts the number of unhalted reference clock cycles" }, { - "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter\r\n", - "EventCode": "0x00", + "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter", "Counter": "Fixed counter 2", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -305,7 +303,6 @@ "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles" }, { - "EventCode": "0x00", "Counter": "Fixed counter 3", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -343,7 +340,7 @@ "UMask": "0x1", "EventName": "RECYCLEQ.LD_BLOCK_ST_FORWARD", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address partially overlaps with a store ", + "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address partially overlaps with a store", "Data_LA": "1" }, { diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json index f31594507f8c..9e493977771f 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json @@ -36,7 +36,7 @@ "EdgeDetect": "1" }, { - "PublicDescription": "This event counts every cycle when an I-side (walks due to an instruction fetch) page walk is in progress. ", + "PublicDescription": "This event counts every cycle when an I-side (walks due to an instruction fetch) page walk is in progress.", "EventCode": "0x05", "Counter": "0,1", "UMask": "0x2", diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json index 16b04a20bc12..bb79e89c2049 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json @@ -1,207 +1,200 @@ [ { - "PEBS": "1", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x11", - "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops that miss the STLB.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read requests that hit L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x12", - "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", - "SampleAfterValue": "100003", - "BriefDescription": "Retired store uops that miss the STLB.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x3", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read requests.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x21", - "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", - "SampleAfterValue": "100007", - "BriefDescription": "Retired load uops with locked access.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x4", + "EventName": "L2_RQSTS.RFO_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that hit L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x41", - "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops that split across a cacheline boundary.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x8", + "EventName": "L2_RQSTS.RFO_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that miss L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x42", - "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", - "SampleAfterValue": "100003", - "BriefDescription": "Retired store uops that split across a cacheline boundary.", - "CounterHTOff": "0,1,2,3" + "UMask": "0xc", + "EventName": "L2_RQSTS.ALL_RFO", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests to L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts the number of load uops retired", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x81", - "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "SampleAfterValue": "2000003", - "BriefDescription": "All retired load uops.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x10", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts the number of store uops retired.", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x82", - "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "SampleAfterValue": "2000003", - "BriefDescription": "All retired store uops.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x20", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache misses when fetching instructions.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD1", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", - "SampleAfterValue": "2000003", - "BriefDescription": "Retired load uops with L1 cache hits as data sources.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x30", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "SampleAfterValue": "200003", + "BriefDescription": "L2 code requests.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD1", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops with L2 cache hits as data sources.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x40", + "EventName": "L2_RQSTS.PF_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required.", - "EventCode": "0xD1", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT", - "SampleAfterValue": "50021", - "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x80", + "EventName": "L2_RQSTS.PF_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD1", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.", - "CounterHTOff": "0,1,2,3" + "UMask": "0xc0", + "EventName": "L2_RQSTS.ALL_PF", + "SampleAfterValue": "200003", + "BriefDescription": "Requests from L2 hardware prefetchers.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD2", + "EventCode": "0x27", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.", - "CounterHTOff": "0,1,2,3" - }, - { - "PEBS": "1", - "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a non-modified state.", - "EventCode": "0xD2", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.", - "CounterHTOff": "0,1,2,3" + "EventName": "L2_STORE_LOCK_RQSTS.MISS", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that miss cache lines.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2.", - "EventCode": "0xD2", + "EventCode": "0x27", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.", - "CounterHTOff": "0,1,2,3" + "EventName": "L2_STORE_LOCK_RQSTS.HIT_E", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that hit cache lines in E state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD2", + "EventCode": "0x27", "Counter": "0,1,2,3", "UMask": "0x8", - "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.", - "CounterHTOff": "0,1,2,3" + "EventName": "L2_STORE_LOCK_RQSTS.HIT_M", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that hit cache lines in M state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts retired demand loads that missed the last-level (L3) cache. This means that the load is usually satisfied from memory in a client system or possibly from the remote socket in a server. Demand loads are non speculative load uops.", - "EventCode": "0xD4", + "EventCode": "0x27", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS", - "SampleAfterValue": "100007", - "BriefDescription": "Retired load uops with unknown information as data source in cache serviced the load.", - "CounterHTOff": "0,1,2,3" + "UMask": "0xf", + "EventName": "L2_STORE_LOCK_RQSTS.ALL", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that access cache lines in any state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier. ", - "EventCode": "0x51", + "EventCode": "0x28", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "L1D.REPLACEMENT", - "SampleAfterValue": "2000003", - "BriefDescription": "L1D data line replacements.", + "EventName": "L2_L1D_WB_RQSTS.MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x51", + "EventCode": "0x28", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "L1D.ALLOCATED_IN_M", - "SampleAfterValue": "2000003", - "BriefDescription": "Allocated L1D data cache lines in M state.", + "EventName": "L2_L1D_WB_RQSTS.HIT_S", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x51", + "EventCode": "0x28", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "L1D.EVICTION", - "SampleAfterValue": "2000003", - "BriefDescription": "L1D data cache lines in M state evicted due to replacement.", + "EventName": "L2_L1D_WB_RQSTS.HIT_E", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x51", + "EventCode": "0x28", "Counter": "0,1,2,3", "UMask": "0x8", - "EventName": "L1D.ALL_M_REPLACEMENT", - "SampleAfterValue": "2000003", - "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.", + "EventName": "L2_L1D_WB_RQSTS.HIT_M", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "Counter": "0,1,2,3", + "UMask": "0xf", + "EventName": "L2_L1D_WB_RQSTS.ALL", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x2E", + "Counter": "0,1,2,3", + "UMask": "0x41", + "EventName": "LONGEST_LAT_CACHE.MISS", + "SampleAfterValue": "100003", + "BriefDescription": "Core-originated cacheable demand requests missed LLC.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x2E", + "Counter": "0,1,2,3", + "UMask": "0x4f", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "SampleAfterValue": "100003", + "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -224,12 +217,61 @@ "CounterHTOff": "2" }, { - "EventCode": "0x63", + "EventCode": "0x48", + "Counter": "2", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "CounterMask": "1", + "CounterHTOff": "2" + }, + { + "EventCode": "0x48", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "EventName": "L1D_PEND_MISS.FB_FULL", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when L1D is locked.", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.", + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "L1D.REPLACEMENT", + "SampleAfterValue": "2000003", + "BriefDescription": "L1D data line replacements.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "L1D.ALLOCATED_IN_M", + "SampleAfterValue": "2000003", + "BriefDescription": "Allocated L1D data cache lines in M state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "L1D.EVICTION", + "SampleAfterValue": "2000003", + "BriefDescription": "L1D data cache lines in M state evicted due to replacement.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "L1D.ALL_M_REPLACEMENT", + "SampleAfterValue": "2000003", + "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -254,6 +296,16 @@ { "EventCode": "0x60", "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "CounterMask": "6", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "Counter": "0,1,2,3", "UMask": "0x4", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", "SampleAfterValue": "2000003", @@ -263,6 +315,16 @@ { "EventCode": "0x60", "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "SampleAfterValue": "2000003", + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "Counter": "0,1,2,3", "UMask": "0x8", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", "SampleAfterValue": "2000003", @@ -280,6 +342,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x63", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when L1D is locked.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xB0", "Counter": "0,1,2,3", "UMask": "0x1", @@ -325,148 +396,182 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x24", + "EventCode": "0xBF", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "Demand Data Read requests that hit L2 cache.", + "UMask": "0x5", + "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES", + "SampleAfterValue": "100003", + "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x24", + "PEBS": "1", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "L2_RQSTS.RFO_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests that hit L2 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x11", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x24", + "PEBS": "1", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "L2_RQSTS.RFO_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests that miss L2 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x12", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "100003", + "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x24", + "PEBS": "1", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "L2_RQSTS.CODE_RD_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "L2 cache hits when fetching instructions, code reads.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x21", + "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", + "SampleAfterValue": "100007", + "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x24", + "PEBS": "1", + "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K). (Precise Event - PEBS)", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "L2_RQSTS.CODE_RD_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "L2 cache misses when fetching instructions.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x41", + "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops that split across a cacheline boundary. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x24", + "PEBS": "1", + "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K). (Precise Event - PEBS)", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "L2_RQSTS.PF_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x42", + "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", + "SampleAfterValue": "100003", + "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x24", + "PEBS": "1", + "PublicDescription": "This event counts the number of load uops retired (Precise Event)", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "L2_RQSTS.PF_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x81", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "SampleAfterValue": "2000003", + "BriefDescription": "All retired load uops. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x27", + "PEBS": "1", + "PublicDescription": "This event counts the number of store uops retired. (Precise Event - PEBS)", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x82", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "SampleAfterValue": "2000003", + "BriefDescription": "All retired store uops. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xD1", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "L2_STORE_LOCK_RQSTS.MISS", - "SampleAfterValue": "200003", - "BriefDescription": "RFOs that miss cache lines.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "SampleAfterValue": "2000003", + "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x27", + "PEBS": "1", + "EventCode": "0xD1", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "L2_STORE_LOCK_RQSTS.HIT_E", - "SampleAfterValue": "200003", - "BriefDescription": "RFOs that hit cache lines in E state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x27", + "PEBS": "1", + "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required. (Precise Event - PEBS)", + "EventCode": "0xD1", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "L2_STORE_LOCK_RQSTS.HIT_M", - "SampleAfterValue": "200003", - "BriefDescription": "RFOs that hit cache lines in M state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4", + "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT", + "SampleAfterValue": "50021", + "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x27", + "PEBS": "1", + "EventCode": "0xD1", "Counter": "0,1,2,3", - "UMask": "0xf", - "EventName": "L2_STORE_LOCK_RQSTS.ALL", - "SampleAfterValue": "200003", - "BriefDescription": "RFOs that access cache lines in any state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40", + "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x28", + "PEBS": "1", + "EventCode": "0xD2", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "L2_L1D_WB_RQSTS.MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x28", + "PEBS": "1", + "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a non-modified state. (Precise Event - PEBS)", + "EventCode": "0xD2", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "L2_L1D_WB_RQSTS.HIT_S", - "SampleAfterValue": "200003", - "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x28", + "PEBS": "1", + "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2. (Precise Event - PEBS)", + "EventCode": "0xD2", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "L2_L1D_WB_RQSTS.HIT_E", - "SampleAfterValue": "200003", - "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x28", + "PEBS": "1", + "EventCode": "0xD2", "Counter": "0,1,2,3", "UMask": "0x8", - "EventName": "L2_L1D_WB_RQSTS.HIT_M", - "SampleAfterValue": "200003", - "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x28", + "PEBS": "1", + "PublicDescription": "This event counts retired demand loads that missed the last-level (L3) cache. This means that the load is usually satisfied from memory in a client system or possibly from the remote socket in a server. Demand loads are non speculative load uops. (Precise Event - PEBS)", + "EventCode": "0xD4", "Counter": "0,1,2,3", - "UMask": "0xf", - "EventName": "L2_L1D_WB_RQSTS.ALL", - "SampleAfterValue": "200003", - "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2", + "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS", + "SampleAfterValue": "100007", + "BriefDescription": "Retired load uops with unknown information as data source in cache serviced the load. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xF0", @@ -623,24 +728,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x2E", - "Counter": "0,1,2,3", - "UMask": "0x41", - "EventName": "LONGEST_LAT_CACHE.MISS", - "SampleAfterValue": "100003", - "BriefDescription": "Core-originated cacheable demand requests missed LLC.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x2E", - "Counter": "0,1,2,3", - "UMask": "0x4f", - "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "SampleAfterValue": "100003", - "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0xF4", "Counter": "0,1,2,3", "UMask": "0x10", @@ -650,93 +737,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x3", - "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "SampleAfterValue": "200003", - "BriefDescription": "Demand Data Read requests.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0xc", - "EventName": "L2_RQSTS.ALL_RFO", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests to L2 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "L2_RQSTS.ALL_CODE_RD", - "SampleAfterValue": "200003", - "BriefDescription": "L2 code requests.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0xc0", - "EventName": "L2_RQSTS.ALL_PF", - "SampleAfterValue": "200003", - "BriefDescription": "Requests from L2 hardware prefetchers.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xBF", - "Counter": "0,1,2,3", - "UMask": "0x5", - "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES", - "SampleAfterValue": "100003", - "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x60", - "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x60", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", - "CounterMask": "6", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x48", - "Counter": "2", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", - "CounterMask": "1", - "CounterHTOff": "2" - }, - { - "EventCode": "0x48", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "L1D_PEND_MISS.FB_FULL", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0xB7, 0xBB", "MSRValue": "0x10003c0244", "Counter": "0,1,2,3", @@ -1825,7 +1825,7 @@ "EventName": "OFFCORE_RESPONSE.DATA_IN.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = DATA_INTO_CORE and RESPONSE = ANY_RESPONSE", + "BriefDescription": "REQUEST = DATA_INTO_CORE and RESPONSE = ANY_RESPONSE", "CounterHTOff": "0,1,2,3" }, { @@ -1837,7 +1837,7 @@ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT_M.HITM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = DEMAND_RFO and RESPONSE = LLC_HIT_M and SNOOP = HITM", + "BriefDescription": "REQUEST = DEMAND_RFO and RESPONSE = LLC_HIT_M and SNOOP = HITM", "CounterHTOff": "0,1,2,3" }, { @@ -1849,7 +1849,7 @@ "EventName": "OFFCORE_RESPONSE.PF_IFETCH.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_RFO and RESPONSE = ANY_RESPONSE", + "BriefDescription": "REQUEST = PF_RFO and RESPONSE = ANY_RESPONSE", "CounterHTOff": "0,1,2,3" }, { @@ -1861,7 +1861,7 @@ "EventName": "OFFCORE_RESPONSE.PF_L_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_LLC_DATA_RD and RESPONSE = ANY_RESPONSE", + "BriefDescription": "REQUEST = PF_LLC_DATA_RD and RESPONSE = ANY_RESPONSE", "CounterHTOff": "0,1,2,3" }, { @@ -1873,7 +1873,7 @@ "EventName": "OFFCORE_RESPONSE.PF_L_IFETCH.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_LLC_IFETCH and RESPONSE = ANY_RESPONSE", + "BriefDescription": "REQUEST = PF_LLC_IFETCH and RESPONSE = ANY_RESPONSE", "CounterHTOff": "0,1,2,3" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json index 982eda48785e..ce26537c7d47 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json @@ -1,68 +1,5 @@ [ { - "EventCode": "0xC1", - "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "OTHER_ASSISTS.AVX_STORE", - "SampleAfterValue": "100003", - "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xC1", - "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "OTHER_ASSISTS.AVX_TO_SSE", - "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xC1", - "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "OTHER_ASSISTS.SSE_TO_AVX", - "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xCA", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "FP_ASSIST.X87_OUTPUT", - "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to output value.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xCA", - "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "FP_ASSIST.X87_INPUT", - "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to input value.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xCA", - "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "FP_ASSIST.SIMD_OUTPUT", - "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to Output values.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xCA", - "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "FP_ASSIST.SIMD_INPUT", - "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to input values.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0x10", "Counter": "0,1,2,3", "UMask": "0x1", @@ -126,6 +63,69 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xC1", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "OTHER_ASSISTS.AVX_STORE", + "SampleAfterValue": "100003", + "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC1", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "OTHER_ASSISTS.AVX_TO_SSE", + "SampleAfterValue": "100003", + "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC1", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "OTHER_ASSISTS.SSE_TO_AVX", + "SampleAfterValue": "100003", + "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "FP_ASSIST.X87_OUTPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of X87 assists due to output value.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "FP_ASSIST.X87_INPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of X87 assists due to input value.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "FP_ASSIST.SIMD_OUTPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of SIMD FP assists due to Output values.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "FP_ASSIST.SIMD_INPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of SIMD FP assists due to input values.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x1e", diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json index 1b7b1dd36c68..e58ed14a204c 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json @@ -1,24 +1,5 @@ [ { - "EventCode": "0x80", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ICACHE.HIT", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.", - "EventCode": "0x80", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "ICACHE.MISSES", - "SampleAfterValue": "200003", - "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0x79", "Counter": "0,1,2,3", "UMask": "0x2", @@ -39,159 +20,201 @@ { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "IDQ.DSB_UOPS", + "UMask": "0x4", + "EventName": "IDQ.MITE_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "IDQ.MS_DSB_UOPS", + "UMask": "0x8", + "EventName": "IDQ.DSB_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "IDQ.MS_MITE_UOPS", + "UMask": "0x8", + "EventName": "IDQ.DSB_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "IDQ.MS_UOPS", + "UMask": "0x10", + "EventName": "IDQ.MS_DSB_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance. See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more information.", "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "IDQ.MS_CYCLES", + "UMask": "0x10", + "EventName": "IDQ.MS_DSB_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled. In the ideal case 4 uops can be delivered each cycle. The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them. This event is used in determining the front-end bound category of the top-down pipeline slots characterization.", - "EventCode": "0x9C", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "UMask": "0x10", + "EdgeDetect": "1", + "EventName": "IDQ.MS_DSB_OCCUR", "SampleAfterValue": "2000003", - "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x9C", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "UMask": "0x18", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.", "CounterMask": "4", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x9C", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "UMask": "0x18", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", - "CounterMask": "3", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xAB", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "DSB2MITE_SWITCHES.COUNT", + "UMask": "0x20", + "EventName": "IDQ.MS_MITE_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline. It excludes cycles when the back-end cannot accept new micro-ops. The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.", - "EventCode": "0xAB", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "UMask": "0x24", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", + "BriefDescription": "Cycles MITE is delivering 4 Uops.", + "CounterMask": "4", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xAC", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "DSB_FILL.OTHER_CANCEL", + "UMask": "0x24", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.", + "BriefDescription": "Cycles MITE is delivering any Uop.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xAC", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "DSB_FILL.EXCEED_DSB_LINES", + "UMask": "0x30", + "EventName": "IDQ.MS_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance. See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual for more information.", "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "IDQ.MITE_CYCLES", + "UMask": "0x30", + "EventName": "IDQ.MS_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "IDQ.DSB_CYCLES", + "UMask": "0x30", + "EdgeDetect": "1", + "EventName": "IDQ.MS_SWITCHES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.", + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "IDQ.MS_DSB_CYCLES", + "UMask": "0x3c", + "EventName": "IDQ.MITE_ALL_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", - "CounterMask": "1", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x79", + "EventCode": "0x80", "Counter": "0,1,2,3", - "UMask": "0x10", - "EdgeDetect": "1", - "EventName": "IDQ.MS_DSB_OCCUR", + "UMask": "0x1", + "EventName": "ICACHE.HIT", "SampleAfterValue": "2000003", - "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.", - "CounterMask": "1", + "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.", + "EventCode": "0x80", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "ICACHE.MISSES", + "SampleAfterValue": "200003", + "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled. In the ideal case 4 uops can be delivered each cycle. The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them. This event is used in determining the front-end bound category of the top-down pipeline slots characterization.", + "EventCode": "0x9C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x9C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "CounterMask": "4", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x9C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "CounterMask": "3", + "CounterHTOff": "0,1,2,3" + }, + { "EventCode": "0x9C", "Counter": "0,1,2,3", "UMask": "0x1", @@ -223,83 +246,60 @@ "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x79", - "Counter": "0,1,2,3", - "UMask": "0x18", - "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x79", + "EventCode": "0x9C", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0x18", - "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.", + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x79", + "EventCode": "0xAB", "Counter": "0,1,2,3", - "UMask": "0x24", - "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "UMask": "0x1", + "EventName": "DSB2MITE_SWITCHES.COUNT", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles MITE is delivering 4 Uops.", - "CounterMask": "4", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x79", + "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline. It excludes cycles when the back-end cannot accept new micro-ops. The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.", + "EventCode": "0xAB", "Counter": "0,1,2,3", - "UMask": "0x24", - "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "UMask": "0x2", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles MITE is delivering any Uop.", - "CounterMask": "1", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xAC", "Counter": "0,1,2,3", - "UMask": "0xa", - "EventName": "DSB_FILL.ALL_CANCEL", + "UMask": "0x2", + "EventName": "DSB_FILL.OTHER_CANCEL", "SampleAfterValue": "2000003", - "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.", + "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x9C", - "Invert": "1", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0x79", + "EventCode": "0xAC", "Counter": "0,1,2,3", - "UMask": "0x3c", - "EventName": "IDQ.MITE_ALL_UOPS", + "UMask": "0x8", + "EventName": "DSB_FILL.EXCEED_DSB_LINES", "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.", + "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x79", + "EventCode": "0xAC", "Counter": "0,1,2,3", - "UMask": "0x30", - "EdgeDetect": "1", - "EventName": "IDQ.MS_SWITCHES", + "UMask": "0xa", + "EventName": "DSB_FILL.ALL_CANCEL", "SampleAfterValue": "2000003", - "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", - "CounterMask": "1", + "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.", "CounterHTOff": "0,1,2,3,4,5,6,7" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/memory.json b/tools/perf/pmu-events/arch/x86/sandybridge/memory.json index e6dfa89d00f3..78c1a987f9a2 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/memory.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/memory.json @@ -1,5 +1,32 @@ [ { + "EventCode": "0x05", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "MISALIGN_MEM_REF.LOADS", + "SampleAfterValue": "2000003", + "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x05", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "MISALIGN_MEM_REF.STORES", + "SampleAfterValue": "2000003", + "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xBE", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "PAGE_WALKS.LLC_MISS", + "SampleAfterValue": "100003", + "BriefDescription": "Number of any page walk that had a miss in LLC. Does not necessary cause a SUSPEND.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from memory disambiguation, external snoops, or cross SMT-HW-thread snoop (stores) hitting load buffers. Machine clears can have a significant performance impact if they are happening frequently.", "EventCode": "0xC3", "Counter": "0,1,2,3", @@ -126,33 +153,6 @@ "CounterHTOff": "3" }, { - "EventCode": "0xBE", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "PAGE_WALKS.LLC_MISS", - "SampleAfterValue": "100003", - "BriefDescription": "Number of any page walk that had a miss in LLC. Does not necessary cause a SUSPEND.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x05", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MISALIGN_MEM_REF.LOADS", - "SampleAfterValue": "2000003", - "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x05", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MISALIGN_MEM_REF.STORES", - "SampleAfterValue": "2000003", - "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0xB7, 0xBB", "MSRValue": "0x300400244", "Counter": "0,1,2,3", @@ -367,7 +367,7 @@ "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = ANY_REQUEST and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = ANY_REQUEST and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" }, { @@ -379,7 +379,7 @@ "EventName": "OFFCORE_RESPONSE.DATA_IN_SOCKET.LLC_MISS_LOCAL.ANY_LLC_HIT", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = DATA_IN_SOCKET and RESPONSE = LLC_MISS_LOCAL and SNOOP = ANY_LLC_HIT", + "BriefDescription": "REQUEST = DATA_IN_SOCKET and RESPONSE = LLC_MISS_LOCAL and SNOOP = ANY_LLC_HIT", "CounterHTOff": "0,1,2,3" }, { @@ -391,7 +391,7 @@ "EventName": "OFFCORE_RESPONSE.DEMAND_IFETCH.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = DEMAND_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = DEMAND_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" }, { @@ -403,7 +403,7 @@ "EventName": "OFFCORE_RESPONSE.PF_DATA_RD.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = PF_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" }, { @@ -415,7 +415,7 @@ "EventName": "OFFCORE_RESPONSE.PF_IFETCH.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_RFO and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = PF_RFO and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" }, { @@ -427,7 +427,7 @@ "EventName": "OFFCORE_RESPONSE.PF_L_DATA_RD.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_LLC_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = PF_LLC_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" }, { @@ -439,7 +439,7 @@ "EventName": "OFFCORE_RESPONSE.PF_L_IFETCH.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_LLC_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = PF_LLC_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/other.json b/tools/perf/pmu-events/arch/x86/sandybridge/other.json index 64b195b82c50..874eb40a2e0f 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/other.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/other.json @@ -9,6 +9,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x4E", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "HW_PRE_REQ.DL1_MISS", + "SampleAfterValue": "2000003", + "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x5C", "Counter": "0,1,2,3", "UMask": "0x1", @@ -38,15 +47,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x4E", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "HW_PRE_REQ.DL1_MISS", - "SampleAfterValue": "2000003", - "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0x63", "Counter": "0,1,2,3", "UMask": "0x1", diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json index 34a519d9bfa0..b7150f65f16d 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json @@ -1,289 +1,307 @@ [ { - "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. ", - "EventCode": "0x00", - "Counter": "Fixed counter 1", + "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "Counter": "Fixed counter 2", + "UMask": "0x3", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the core is not in halt state.", + "CounterHTOff": "Fixed counter 2" + }, + { + "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers.", + "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", "SampleAfterValue": "2000003", "BriefDescription": "Instructions retired from execution.", - "CounterHTOff": "Fixed counter 1" + "CounterHTOff": "Fixed counter 0" }, { - "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ", - "EventCode": "0x00", - "Counter": "Fixed counter 2", + "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", "SampleAfterValue": "2000003", "BriefDescription": "Core cycles when the thread is not in halt state.", - "CounterHTOff": "Fixed counter 2" + "CounterHTOff": "Fixed counter 1" }, { - "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ", - "EventCode": "0x00", - "Counter": "Fixed counter 3", - "UMask": "0x3", - "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "Counter": "Fixed counter 1", + "UMask": "0x2", + "AnyThread": "1", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the core is not in halt state.", - "CounterHTOff": "Fixed counter 3" - }, - { - "EventCode": "0x88", - "Counter": "0,1,2,3", - "UMask": "0x41", - "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Not taken macro-conditional branches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x88", + "EventCode": "0x03", "Counter": "0,1,2,3", - "UMask": "0x81", - "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired macro-conditional branches.", + "UMask": "0x1", + "EventName": "LD_BLOCKS.DATA_UNKNOWN", + "SampleAfterValue": "100003", + "BriefDescription": "Loads delayed due to SB blocks, preceding store operations with known addresses but unknown data.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", + "EventCode": "0x03", "Counter": "0,1,2,3", - "UMask": "0x82", - "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.", + "UMask": "0x2", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "SampleAfterValue": "100003", + "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x03", "Counter": "0,1,2,3", - "UMask": "0x84", - "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.", + "UMask": "0x8", + "EventName": "LD_BLOCKS.NO_SR", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x03", "Counter": "0,1,2,3", - "UMask": "0x88", - "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.", + "UMask": "0x10", + "EventName": "LD_BLOCKS.ALL_BLOCK", + "SampleAfterValue": "100003", + "BriefDescription": "Number of cases where any load ends up with a valid block-code written to the load buffer (including blocks due to Memory Order Buffer (MOB), Data Cache Unit (DCU), TLB, but load has no DCU miss).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "PublicDescription": "Aliasing occurs when a load is issued after a store and their memory addresses are offset by 4K. This event counts the number of loads that aliased with a preceding store, resulting in an extended address check in the pipeline. The enhanced address check typically has a performance penalty of 5 cycles.", + "EventCode": "0x07", "Counter": "0,1,2,3", - "UMask": "0x90", - "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired direct near calls.", + "UMask": "0x1", + "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "SampleAfterValue": "100003", + "BriefDescription": "False dependencies in MOB due to partial compare.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x07", "Counter": "0,1,2,3", - "UMask": "0xa0", - "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired indirect calls.", + "UMask": "0x8", + "EventName": "LD_BLOCKS_PARTIAL.ALL_STA_BLOCK", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts the number of times that load operations are temporarily blocked because of older stores, with addresses that are not yet known. A load operation may incur more than one block of this type.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x0D", "Counter": "0,1,2,3", - "UMask": "0xc1", - "EventName": "BR_INST_EXEC.ALL_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired macro-conditional branches.", + "UMask": "0x3", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x0D", "Counter": "0,1,2,3", - "UMask": "0xc2", - "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.", + "UMask": "0x3", + "EdgeDetect": "1", + "EventName": "INT_MISC.RECOVERY_STALLS_COUNT", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x0D", "Counter": "0,1,2,3", - "UMask": "0xc4", - "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.", + "UMask": "0x3", + "AnyThread": "1", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x0D", "Counter": "0,1,2,3", - "UMask": "0xc8", - "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired indirect return branches.", + "UMask": "0x40", + "EventName": "INT_MISC.RAT_STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "PublicDescription": "This event counts the number of Uops issued by the front-end of the pipeilne to the back-end.", + "EventCode": "0x0E", "Counter": "0,1,2,3", - "UMask": "0xd0", - "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired direct near calls.", + "UMask": "0x1", + "EventName": "UOPS_ISSUED.ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "EventCode": "0x0E", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0x41", - "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x89", + "EventCode": "0x0E", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0x81", - "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1", + "AnyThread": "1", + "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x89", + "EventCode": "0x14", "Counter": "0,1,2,3", - "UMask": "0x84", - "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.", + "UMask": "0x1", + "EventName": "ARITH.FPU_DIV_ACTIVE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when divider is busy executing divide operations.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "PublicDescription": "This event counts the number of the divide operations executed.", + "EventCode": "0x14", "Counter": "0,1,2,3", - "UMask": "0x88", - "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.", + "UMask": "0x1", + "EdgeDetect": "1", + "EventName": "ARITH.FPU_DIV", + "SampleAfterValue": "100003", + "BriefDescription": "Divide operations executed.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0x90", - "EventName": "BR_MISP_EXEC.TAKEN_DIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired mispredicted direct near calls.", + "UMask": "0x0", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "SampleAfterValue": "2000003", + "BriefDescription": "Thread cycles when thread is not in halt state.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0xa0", - "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired mispredicted indirect calls.", + "UMask": "0x0", + "AnyThread": "1", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0xc1", - "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", + "UMask": "0x1", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0xc4", - "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", - "SampleAfterValue": "200003", - "BriefDescription": "Mispredicted indirect branches excluding calls and returns.", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0xd0", - "EventName": "BR_MISP_EXEC.ALL_DIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired mispredicted direct near calls.", + "UMask": "0x1", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", "SampleAfterValue": "2000003", - "BriefDescription": "Thread cycles when thread is not in halt state.", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA8", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.UOPS", + "UMask": "0x2", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of Uops delivered by the LSD.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xA8", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.CYCLES_ACTIVE", + "UMask": "0x2", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", - "CounterMask": "1", + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x87", + "EventCode": "0x4C", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "ILD_STALL.LCP", - "SampleAfterValue": "2000003", - "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "EventName": "LOAD_HIT_PRE.SW_PF", + "SampleAfterValue": "100003", + "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x87", + "EventCode": "0x4C", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "ILD_STALL.IQ_FULL", - "SampleAfterValue": "2000003", - "BriefDescription": "Stall cycles because IQ is full.", + "UMask": "0x2", + "EventName": "LOAD_HIT_PRE.HW_PF", + "SampleAfterValue": "100003", + "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0D", + "EventCode": "0x59", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "INT_MISC.RAT_STALL_CYCLES", + "UMask": "0x20", + "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread.", + "BriefDescription": "Increments the number of flags-merge uops in flight each cycle.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual.", "EventCode": "0x59", "Counter": "0,1,2,3", "UMask": "0x20", - "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP", + "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Increments the number of flags-merge uops in flight each cycle.", + "BriefDescription": "Performance sensitive flags-merging uops added by Sandy Bridge u-arch.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.", + "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.", "EventCode": "0x59", "Counter": "0,1,2,3", "UMask": "0x40", @@ -302,48 +320,21 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "RESOURCE_STALLS.ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Resource-related stall cycles.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA2", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "RESOURCE_STALLS.LB", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts the cycles of stall due to lack of load buffers.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA2", - "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "RESOURCE_STALLS.RS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles stalled due to no eligible RS entry available.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA2", + "EventCode": "0x5B", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "RESOURCE_STALLS.SB", + "UMask": "0xc", + "EventName": "RESOURCE_STALLS2.ALL_FL_EMPTY", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "BriefDescription": "Cycles with either free list is empty.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0x5B", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "RESOURCE_STALLS.ROB", + "UMask": "0xf", + "EventName": "RESOURCE_STALLS2.ALL_PRF_CONTROL", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles stalled due to re-order buffer full.", + "BriefDescription": "Resource stalls2 control structures full for physical registers.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -356,702 +347,663 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of Uops issued by the front-end of the pipeilne to the back-end.", - "EventCode": "0x0E", + "EventCode": "0x5B", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_ISSUED.ANY", + "UMask": "0x4f", + "EventName": "RESOURCE_STALLS2.OOO_RSRC", "SampleAfterValue": "2000003", - "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS).", + "BriefDescription": "Resource stalls out of order resources full.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0E", - "Invert": "1", + "EventCode": "0x5E", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "UOPS_ISSUED.STALL_CYCLES", + "EventName": "RS_EVENTS.EMPTY_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0E", + "EventCode": "0x5E", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", - "AnyThread": "1", - "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES", + "EdgeDetect": "1", + "EventName": "RS_EVENTS.EMPTY_END", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", "CounterMask": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5E", + "EventCode": "0x87", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "RS_EVENTS.EMPTY_CYCLES", + "EventName": "ILD_STALL.LCP", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xCC", + "EventCode": "0x87", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "UMask": "0x4", + "EventName": "ILD_STALL.IQ_FULL", "SampleAfterValue": "2000003", - "BriefDescription": "Count cases of saving new LBR.", + "BriefDescription": "Stall cycles because IQ is full.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear. Machine clears can have a significant performance impact if they are happening frequently.", - "EventCode": "0xC3", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MACHINE_CLEARS.SMC", - "SampleAfterValue": "100003", - "BriefDescription": "Self-modifying code (SMC) detected.", + "UMask": "0x41", + "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Not taken macro-conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Maskmov false fault - counts number of time ucode passes through Maskmov flow due to instruction's mask being 0 while the flow was completed without raising a fault.", - "EventCode": "0xC3", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "MACHINE_CLEARS.MASKMOV", - "SampleAfterValue": "100003", - "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.", + "UMask": "0x81", + "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired macro-conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC0", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "INST_RETIRED.ANY_P", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of instructions retired. General Counter - architectural event.", + "UMask": "0x82", + "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts the number of micro-ops retired.", - "EventCode": "0xC2", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_RETIRED.ALL", - "SampleAfterValue": "2000003", - "BriefDescription": "Actually retired uops.", + "UMask": "0x84", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts the number of retirement slots used each cycle. There are potentially 4 slots that can be used each cycle - meaning, 4 micro-ops or 4 instructions could retire each cycle. This event is used in determining the 'Retiring' category of the Top-Down pipeline slots characterization.", - "EventCode": "0xC2", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_RETIRED.RETIRE_SLOTS", - "SampleAfterValue": "2000003", - "BriefDescription": "Retirement slots used.", + "UMask": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC2", - "Invert": "1", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_RETIRED.STALL_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x90", + "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired direct near calls.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC2", - "Invert": "1", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_RETIRED.TOTAL_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 10 actually retired uops.", - "CounterMask": "10", - "CounterHTOff": "0,1,2,3" + "UMask": "0xa0", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired indirect calls.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "BR_INST_RETIRED.CONDITIONAL", - "SampleAfterValue": "400009", - "BriefDescription": "Conditional branch instructions retired.", + "UMask": "0xc1", + "EventName": "BR_INST_EXEC.ALL_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired macro-conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "BR_INST_RETIRED.NEAR_CALL", - "SampleAfterValue": "100007", - "BriefDescription": "Direct and indirect near call instructions retired.", + "UMask": "0xc2", + "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "SampleAfterValue": "400009", - "BriefDescription": "All (macro) branch instructions retired.", + "UMask": "0xc4", + "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "SampleAfterValue": "100007", - "BriefDescription": "Return instructions retired.", + "UMask": "0xc8", + "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired indirect return branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "BR_INST_RETIRED.NOT_TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Not taken branch instructions retired.", + "UMask": "0xd0", + "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired direct near calls.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Taken branch instructions retired.", + "UMask": "0xff", + "EventName": "BR_INST_EXEC.ALL_BRANCHES", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC4", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "SampleAfterValue": "100007", - "BriefDescription": "Far branch instructions retired.", + "UMask": "0x41", + "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "2", - "EventCode": "0xC4", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", - "SampleAfterValue": "400009", - "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS).", - "CounterHTOff": "0,1,2,3" + "UMask": "0x81", + "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "BR_MISP_RETIRED.CONDITIONAL", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted conditional branch instructions retired.", + "UMask": "0x84", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "BR_MISP_RETIRED.NEAR_CALL", - "SampleAfterValue": "100007", - "BriefDescription": "Direct and indirect mispredicted near call instructions retired.", + "UMask": "0x88", + "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "SampleAfterValue": "400009", - "BriefDescription": "All mispredicted macro branch instructions retired.", + "UMask": "0x90", + "EventName": "BR_MISP_EXEC.TAKEN_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted direct near calls.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "BR_MISP_RETIRED.NOT_TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted not taken branch instructions retired.", + "UMask": "0xa0", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted indirect calls.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "BR_MISP_RETIRED.TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted taken branch instructions retired.", + "UMask": "0xc1", + "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "2", - "PublicDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS)", - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS).", - "CounterHTOff": "0,1,2,3" + "UMask": "0xc4", + "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Mispredicted indirect branches excluding calls and returns.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC1", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "OTHER_ASSISTS.ITLB_MISS_RETIRED", - "SampleAfterValue": "100003", - "BriefDescription": "Retired instructions experiencing ITLB misses.", + "UMask": "0xd0", + "EventName": "BR_MISP_EXEC.ALL_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired mispredicted direct near calls.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x14", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ARITH.FPU_DIV_ACTIVE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when divider is busy executing divide operations.", + "UMask": "0xff", + "EventName": "BR_MISP_EXEC.ALL_BRANCHES", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of the divide operations executed.", - "EventCode": "0x14", + "EventCode": "0xA1", "Counter": "0,1,2,3", "UMask": "0x1", - "EdgeDetect": "1", - "EventName": "ARITH.FPU_DIV", - "SampleAfterValue": "100003", - "BriefDescription": "Divide operations executed.", - "CounterMask": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are dispatched to port 0.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "EventCode": "0xA1", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "UOPS_DISPATCHED.THREAD", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Uops dispatched per thread.", + "BriefDescription": "Cycles per core when uops are dispatched to port 0.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "EventCode": "0xA1", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "UOPS_DISPATCHED.CORE", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1", "SampleAfterValue": "2000003", - "BriefDescription": "Uops dispatched from any thread.", + "BriefDescription": "Cycles per thread when uops are dispatched to port 1.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "UMask": "0x2", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are dispatched to port 0.", + "BriefDescription": "Cycles per core when uops are dispatched to port 1.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_DISPATCHED_PORT.PORT_1", + "UMask": "0xc", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are dispatched to port 1.", + "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "UMask": "0xc", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are dispatched to port 4.", + "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 2.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "UMask": "0x30", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are dispatched to port 5.", + "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", + "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "CYCLE_ACTIVITY.CYCLES_NO_DISPATCH", + "UMask": "0x30", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Each cycle there was no dispatch for this thread, increment by 1. Note this is connect to Umask 2. No dispatch can be deduced from the UOPS_EXECUTED event.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", - "Counter": "2", - "UMask": "0x2", - "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4", "SampleAfterValue": "2000003", - "BriefDescription": "Each cycle there was a miss-pending demand load this thread, increment by 1. Note this is in DCU and connected to Umask 1. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.", - "CounterMask": "2", - "CounterHTOff": "2" + "BriefDescription": "Cycles per thread when uops are dispatched to port 4.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", + "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING", + "UMask": "0x40", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Each cycle there was a MLC-miss pending demand load this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0.", - "CounterMask": "1", + "BriefDescription": "Cycles per core when uops are dispatched to port 4.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", - "Counter": "2", - "UMask": "0x6", - "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING", + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x80", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5", "SampleAfterValue": "2000003", - "BriefDescription": "Each cycle there was a miss-pending demand load this thread and no uops dispatched, increment by 1. Note this is in DCU and connected to Umask 1 and 2. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.", - "CounterMask": "6", - "CounterHTOff": "2" + "BriefDescription": "Cycles per thread when uops are dispatched to port 5.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", + "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x5", - "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING", + "UMask": "0x80", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Each cycle there was a MLC-miss pending demand load and no uops dispatched on this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0 and 2.", - "CounterMask": "5", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Cycles per core when uops are dispatched to port 5.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x4C", + "EventCode": "0xA2", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "LOAD_HIT_PRE.SW_PF", - "SampleAfterValue": "100003", - "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch.", + "EventName": "RESOURCE_STALLS.ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource-related stall cycles.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x4C", + "EventCode": "0xA2", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "LOAD_HIT_PRE.HW_PF", - "SampleAfterValue": "100003", - "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x03", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LD_BLOCKS.DATA_UNKNOWN", - "SampleAfterValue": "100003", - "BriefDescription": "Loads delayed due to SB blocks, preceding store operations with known addresses but unknown data.", + "EventName": "RESOURCE_STALLS.LB", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the cycles of stall due to lack of load buffers.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", - "EventCode": "0x03", + "EventCode": "0xA2", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "LD_BLOCKS.STORE_FORWARD", - "SampleAfterValue": "100003", - "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.", + "UMask": "0x4", + "EventName": "RESOURCE_STALLS.RS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles stalled due to no eligible RS entry available.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x03", + "EventCode": "0xA2", "Counter": "0,1,2,3", "UMask": "0x8", - "EventName": "LD_BLOCKS.NO_SR", - "SampleAfterValue": "100003", - "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "EventName": "RESOURCE_STALLS.SB", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x03", + "EventCode": "0xA2", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "LD_BLOCKS.ALL_BLOCK", - "SampleAfterValue": "100003", - "BriefDescription": "Number of cases where any load ends up with a valid block-code written to the load buffer (including blocks due to Memory Order Buffer (MOB), Data Cache Unit (DCU), TLB, but load has no DCU miss).", + "UMask": "0xa", + "EventName": "RESOURCE_STALLS.LB_SB", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource stalls due to load or store buffers all being in use.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Aliasing occurs when a load is issued after a store and their memory addresses are offset by 4K. This event counts the number of loads that aliased with a preceding store, resulting in an extended address check in the pipeline. The enhanced address check typically has a performance penalty of 5 cycles.", - "EventCode": "0x07", + "EventCode": "0xA2", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", - "SampleAfterValue": "100003", - "BriefDescription": "False dependencies in MOB due to partial compare.", + "UMask": "0xe", + "EventName": "RESOURCE_STALLS.MEM_RS", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource stalls due to memory buffers or Reservation Station (RS) being fully utilized.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x07", + "EventCode": "0xA2", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "LD_BLOCKS_PARTIAL.ALL_STA_BLOCK", - "SampleAfterValue": "100003", - "BriefDescription": "This event counts the number of times that load operations are temporarily blocked because of older stores, with addresses that are not yet known. A load operation may incur more than one block of this type.", + "UMask": "0x10", + "EventName": "RESOURCE_STALLS.ROB", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles stalled due to re-order buffer full.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB6", + "EventCode": "0xA2", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "AGU_BYPASS_CANCEL.COUNT", - "SampleAfterValue": "100003", - "BriefDescription": "This event counts executed load operations with all the following traits: 1. addressing of the format [base + offset], 2. the offset is between 1 and 2047, 3. the address specified in the base register is in one page and the address [base+offset] is in an.", + "UMask": "0xf0", + "EventName": "RESOURCE_STALLS.OOO_RSRC", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource stalls due to Rob being full, FCSW, MXCSR and OTHER.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", + "EventCode": "0xA3", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING", "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).", + "BriefDescription": "Each cycle there was a MLC-miss pending demand load this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", - "Counter": "0,1,2,3", + "EventCode": "0xA3", + "Counter": "2", "UMask": "0x2", - "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", "SampleAfterValue": "2000003", - "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Each cycle there was a miss-pending demand load this thread, increment by 1. Note this is in DCU and connected to Umask 1. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.", + "CounterMask": "2", + "CounterHTOff": "2" }, { - "EventCode": "0xA1", + "EventCode": "0xA3", "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE", + "UMask": "0x4", + "EventName": "CYCLE_ACTIVITY.CYCLES_NO_DISPATCH", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are dispatched to port 0.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Each cycle there was no dispatch for this thread, increment by 1. Note this is connect to Umask 2. No dispatch can be deduced from the UOPS_EXECUTED event.", + "CounterMask": "4", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xA1", + "EventCode": "0xA3", "Counter": "0,1,2,3", - "UMask": "0x2", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE", + "UMask": "0x5", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are dispatched to port 1.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Each cycle there was a MLC-miss pending demand load and no uops dispatched on this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0 and 2.", + "CounterMask": "5", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x40", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE", + "EventCode": "0xA3", + "Counter": "2", + "UMask": "0x6", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are dispatched to port 4.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Each cycle there was a miss-pending demand load this thread and no uops dispatched, increment by 1. Note this is in DCU and connected to Umask 1 and 2. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.", + "CounterMask": "6", + "CounterHTOff": "2" }, { - "EventCode": "0xA1", + "EventCode": "0xA8", "Counter": "0,1,2,3", - "UMask": "0x80", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE", + "UMask": "0x1", + "EventName": "LSD.UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are dispatched to port 5.", + "BriefDescription": "Number of Uops delivered by the LSD.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", + "EventCode": "0xA8", "Counter": "0,1,2,3", - "UMask": "0xc", - "EventName": "UOPS_DISPATCHED_PORT.PORT_2", + "UMask": "0x1", + "EventName": "LSD.CYCLES_ACTIVE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2.", + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", + "EventCode": "0xA8", "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "UMask": "0x1", + "EventName": "LSD.CYCLES_4_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3.", + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "CounterMask": "4", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0xc", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE", + "UMask": "0x1", + "EventName": "UOPS_DISPATCHED.THREAD", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 2.", + "BriefDescription": "Uops dispatched per thread.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0x30", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE", + "UMask": "0x2", + "EventName": "UOPS_DISPATCHED.CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3.", + "BriefDescription": "Uops dispatched from any thread.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "2", - "EventCode": "0xC0", - "Counter": "1", - "UMask": "0x1", - "EventName": "INST_RETIRED.PREC_DIST", - "SampleAfterValue": "2000003", - "BriefDescription": "Instructions retired. (Precise Event - PEBS).", - "TakenAlone": "1", - "CounterHTOff": "1" - }, - { - "EventCode": "0x5B", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0xf", - "EventName": "RESOURCE_STALLS2.ALL_PRF_CONTROL", + "UMask": "0x2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", "SampleAfterValue": "2000003", - "BriefDescription": "Resource stalls2 control structures full for physical registers.", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5B", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0xc", - "EventName": "RESOURCE_STALLS2.ALL_FL_EMPTY", + "UMask": "0x2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with either free list is empty.", + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "CounterMask": "2", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0xe", - "EventName": "RESOURCE_STALLS.MEM_RS", + "UMask": "0x2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", "SampleAfterValue": "2000003", - "BriefDescription": "Resource stalls due to memory buffers or Reservation Station (RS) being fully utilized.", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "CounterMask": "3", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0xf0", - "EventName": "RESOURCE_STALLS.OOO_RSRC", + "UMask": "0x2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", "SampleAfterValue": "2000003", - "BriefDescription": "Resource stalls due to Rob being full, FCSW, MXCSR and OTHER.", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "CounterMask": "4", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5B", + "EventCode": "0xB1", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0x4f", - "EventName": "RESOURCE_STALLS2.OOO_RSRC", + "UMask": "0x2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", "SampleAfterValue": "2000003", - "BriefDescription": "Resource stalls out of order resources full.", + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xB6", "Counter": "0,1,2,3", - "UMask": "0xa", - "EventName": "RESOURCE_STALLS.LB_SB", - "SampleAfterValue": "2000003", - "BriefDescription": "Resource stalls due to load or store buffers all being in use.", + "UMask": "0x1", + "EventName": "AGU_BYPASS_CANCEL.COUNT", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts executed load operations with all the following traits: 1. addressing of the format [base + offset], 2. the offset is between 1 and 2047, 3. the address specified in the base register is in one page and the address [base+offset] is in an.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0D", + "EventCode": "0xC0", "Counter": "0,1,2,3", - "UMask": "0x3", - "EventName": "INT_MISC.RECOVERY_CYCLES", + "UMask": "0x0", + "EventName": "INST_RETIRED.ANY_P", "SampleAfterValue": "2000003", - "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).", - "CounterMask": "1", + "BriefDescription": "Number of instructions retired. General Counter - architectural event.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel? 64 and IA-32 Architectures Optimization Reference Manual.", - "EventCode": "0x59", - "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES", + "PEBS": "2", + "EventCode": "0xC0", + "Counter": "1", + "UMask": "0x1", + "EventName": "INST_RETIRED.PREC_DIST", "SampleAfterValue": "2000003", - "BriefDescription": "Performance sensitive flags-merging uops added by Sandy Bridge u-arch.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Instructions retired. (Precise Event - PEBS).", + "TakenAlone": "1", + "CounterHTOff": "1" }, { - "EventCode": "0x0D", + "EventCode": "0xC1", "Counter": "0,1,2,3", - "UMask": "0x3", - "EdgeDetect": "1", - "EventName": "INT_MISC.RECOVERY_STALLS_COUNT", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).", - "CounterMask": "1", + "UMask": "0x2", + "EventName": "OTHER_ASSISTS.ITLB_MISS_RETIRED", + "SampleAfterValue": "100003", + "BriefDescription": "Retired instructions experiencing ITLB misses.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xE6", + "PEBS": "1", + "PublicDescription": "This event counts the number of micro-ops retired. (Precise Event)", + "EventCode": "0xC2", "Counter": "0,1,2,3", - "UMask": "0x1f", - "EventName": "BACLEARS.ANY", - "SampleAfterValue": "100003", - "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "UMask": "0x1", + "EventName": "UOPS_RETIRED.ALL", + "SampleAfterValue": "2000003", + "BriefDescription": "Actually retired uops. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0xC2", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0xff", - "EventName": "BR_INST_EXEC.ALL_BRANCHES", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired branches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles without actually retired uops.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x89", + "EventCode": "0xC2", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0xff", - "EventName": "BR_MISP_EXEC.ALL_BRANCHES", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with less than 10 actually retired uops.", + "CounterMask": "10", + "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xC2", @@ -1065,13 +1017,14 @@ "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xA8", + "PEBS": "1", + "PublicDescription": "This event counts the number of retirement slots used each cycle. There are potentially 4 slots that can be used each cycle - meaning, 4 micro-ops or 4 instructions could retire each cycle. This event is used in determining the 'Retiring' category of the Top-Down pipeline slots characterization. (Precise Event - PEBS)", + "EventCode": "0xC2", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.CYCLES_4_UOPS", + "UMask": "0x2", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", - "CounterMask": "4", + "BriefDescription": "Retirement slots used. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1086,135 +1039,188 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5E", - "Invert": "1", + "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear. Machine clears can have a significant performance impact if they are happening frequently.", + "EventCode": "0xC3", "Counter": "0,1,2,3", - "UMask": "0x1", - "EdgeDetect": "1", - "EventName": "RS_EVENTS.EMPTY_END", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", - "CounterMask": "1", + "UMask": "0x4", + "EventName": "MACHINE_CLEARS.SMC", + "SampleAfterValue": "100003", + "BriefDescription": "Self-modifying code (SMC) detected.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x00", - "Counter": "Fixed counter 2", - "UMask": "0x2", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "CounterHTOff": "Fixed counter 2" + "PublicDescription": "Maskmov false fault - counts number of time ucode passes through Maskmov flow due to instruction's mask being 0 while the flow was completed without raising a fault.", + "EventCode": "0xC3", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "MACHINE_CLEARS.MASKMOV", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", + "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x0", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "SampleAfterValue": "400009", + "BriefDescription": "All (macro) branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", + "PEBS": "1", + "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x1", - "AnyThread": "1", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "SampleAfterValue": "400009", + "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0D", + "PEBS": "1", + "EventCode": "0xC4", "Counter": "0,1,2,3", - "UMask": "0x3", - "AnyThread": "1", - "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", - "CounterMask": "1", + "UMask": "0x2", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "SampleAfterValue": "100007", + "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "PEBS": "1", + "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", - "CounterMask": "1", + "EventName": "BR_INST_RETIRED.NEAR_CALL_R3", + "SampleAfterValue": "100007", + "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "PEBS": "2", + "EventCode": "0xC4", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", - "CounterMask": "2", + "UMask": "0x4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "SampleAfterValue": "400009", + "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xC4", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "SampleAfterValue": "100007", + "BriefDescription": "Return instructions retired. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "EventCode": "0xC4", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", - "CounterMask": "3", + "UMask": "0x10", + "EventName": "BR_INST_RETIRED.NOT_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Not taken branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "PEBS": "1", + "EventCode": "0xC4", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", - "CounterMask": "4", + "UMask": "0x20", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", - "Invert": "1", + "EventCode": "0xC4", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "UMask": "0x40", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "SampleAfterValue": "100007", + "BriefDescription": "Far branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", - "EventCode": "0x3C", + "EventCode": "0xC5", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK", - "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).", + "UMask": "0x0", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "SampleAfterValue": "400009", + "BriefDescription": "All mispredicted macro branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", + "PEBS": "1", + "EventCode": "0xC5", "Counter": "0,1,2,3", "UMask": "0x1", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "EventName": "BR_MISP_RETIRED.CONDITIONAL", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", + "PEBS": "1", + "EventCode": "0xC5", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "EventName": "BR_MISP_RETIRED.NEAR_CALL", + "SampleAfterValue": "100007", + "BriefDescription": "Direct and indirect mispredicted near call instructions retired. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "2", + "PublicDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS)", + "EventCode": "0xC5", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xC5", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "BR_MISP_RETIRED.NOT_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted not taken branch instructions retired.(Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "1", + "EventCode": "0xC5", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "BR_MISP_RETIRED.TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted taken branch instructions retired. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCC", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", "SampleAfterValue": "2000003", - "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", + "BriefDescription": "Count cases of saving new LBR.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xE6", + "Counter": "0,1,2,3", + "UMask": "0x1f", + "EventName": "BACLEARS.ANY", + "SampleAfterValue": "100003", + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", "CounterHTOff": "0,1,2,3,4,5,6,7" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index fd7d7c438226..cfeba5067bab 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -1,140 +1,226 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", - "MetricGroup": "Frontend", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Average CPU Utilization", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json b/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json index a654ab771fce..b8eccce5d75d 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json @@ -1,131 +1,131 @@ [ { - "EventCode": "0xAE", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ITLB.ITLB_FLUSH", - "SampleAfterValue": "100007", - "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x4F", - "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "EPT.WALK_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycle count for an Extended Page table walk. The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x85", + "EventCode": "0x08", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", "SampleAfterValue": "100003", - "BriefDescription": "Misses at all ITLB levels that cause page walks.", + "BriefDescription": "Load misses in all DTLB levels that cause page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x85", + "EventCode": "0x08", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "ITLB_MISSES.WALK_COMPLETED", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", "SampleAfterValue": "100003", - "BriefDescription": "Misses in all ITLB levels that cause completed page walks.", + "BriefDescription": "Load misses at all DTLB levels that cause completed page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event count cycles when Page Miss Handler (PMH) is servicing page walks caused by ITLB misses.", - "EventCode": "0x85", + "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.", + "EventCode": "0x08", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "ITLB_MISSES.WALK_DURATION", + "EventName": "DTLB_LOAD_MISSES.WALK_DURATION", "SampleAfterValue": "2000003", "BriefDescription": "Cycles when PMH is busy with page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x85", + "PublicDescription": "This event counts load operations that miss the first DTLB level but hit the second and do not cause any page walks. The penalty in this case is approximately 7 cycles.", + "EventCode": "0x08", "Counter": "0,1,2,3", "UMask": "0x10", - "EventName": "ITLB_MISSES.STLB_HIT", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", "SampleAfterValue": "100003", - "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.", + "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x08", + "EventCode": "0x49", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", "SampleAfterValue": "100003", - "BriefDescription": "Load misses in all DTLB levels that cause page walks.", + "BriefDescription": "Store misses in all DTLB levels that cause page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x08", + "EventCode": "0x49", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", "SampleAfterValue": "100003", - "BriefDescription": "Load misses at all DTLB levels that cause completed page walks.", + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.", - "EventCode": "0x08", + "EventCode": "0x49", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "DTLB_LOAD_MISSES.WALK_DURATION", + "EventName": "DTLB_STORE_MISSES.WALK_DURATION", "SampleAfterValue": "2000003", "BriefDescription": "Cycles when PMH is busy with page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts load operations that miss the first DTLB level but hit the second and do not cause any page walks. The penalty in this case is approximately 7 cycles.", - "EventCode": "0x08", + "EventCode": "0x49", "Counter": "0,1,2,3", "UMask": "0x10", - "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", "SampleAfterValue": "100003", - "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.", + "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x49", + "EventCode": "0x4F", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "EPT.WALK_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycle count for an Extended Page table walk. The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", "SampleAfterValue": "100003", - "BriefDescription": "Store misses in all DTLB levels that cause page walks.", + "BriefDescription": "Misses at all ITLB levels that cause page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x49", + "EventCode": "0x85", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "EventName": "ITLB_MISSES.WALK_COMPLETED", "SampleAfterValue": "100003", - "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.", + "BriefDescription": "Misses in all ITLB levels that cause completed page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x49", + "PublicDescription": "This event count cycles when Page Miss Handler (PMH) is servicing page walks caused by ITLB misses.", + "EventCode": "0x85", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "DTLB_STORE_MISSES.WALK_DURATION", + "EventName": "ITLB_MISSES.WALK_DURATION", "SampleAfterValue": "2000003", "BriefDescription": "Cycles when PMH is busy with page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x49", + "EventCode": "0x85", "Counter": "0,1,2,3", "UMask": "0x10", - "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "EventName": "ITLB_MISSES.STLB_HIT", "SampleAfterValue": "100003", - "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", + "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xAE", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "ITLB.ITLB_FLUSH", + "SampleAfterValue": "100007", + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { diff --git a/tools/perf/pmu-events/arch/x86/silvermont/cache.json b/tools/perf/pmu-events/arch/x86/silvermont/cache.json index 82be7d1b8b81..805ef1436539 100644 --- a/tools/perf/pmu-events/arch/x86/silvermont/cache.json +++ b/tools/perf/pmu-events/arch/x86/silvermont/cache.json @@ -36,7 +36,7 @@ "BriefDescription": "L2 cache request misses" }, { - "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss. Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.\r\nCounts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events. \r\n", + "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss. Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.\r\nCounts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events.", "EventCode": "0x86", "Counter": "0,1", "UMask": "0x4", diff --git a/tools/perf/pmu-events/arch/x86/silvermont/other.json b/tools/perf/pmu-events/arch/x86/silvermont/other.json new file mode 100644 index 000000000000..47814046fa9d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/silvermont/other.json @@ -0,0 +1,20 @@ +[ + { + "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss. Note: this event is not the same as page walk cycles to retrieve an instruction translation.", + "EventCode": "0x86", + "Counter": "0,1", + "UMask": "0x2", + "EventName": "FETCH_STALL.ITLB_FILL_PENDING_CYCLES", + "SampleAfterValue": "200003", + "BriefDescription": "Cycles code-fetch stalled due to an outstanding ITLB miss." + }, + { + "PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events.", + "EventCode": "0x86", + "Counter": "0,1", + "UMask": "0x3f", + "EventName": "FETCH_STALL.ALL", + "SampleAfterValue": "200003", + "BriefDescription": "Cycles code-fetch stalled due to any reason." + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json b/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json index 7468af99190a..1ed62ad4cf77 100644 --- a/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json @@ -210,7 +210,7 @@ "UMask": "0x4", "EventName": "NO_ALLOC_CYCLES.MISPREDICTS", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of cycles when no uops are allocated and the alloc pipe is stalled waiting for a mispredicted jump to retire. After the misprediction is detected, the front end will start immediately but the allocate pipe stalls until the mispredicted " + "BriefDescription": "Counts the number of cycles when no uops are allocated and the alloc pipe is stalled waiting for a mispredicted jump to retire. After the misprediction is detected, the front end will start immediately but the allocate pipe stalls until the mispredicted" }, { "EventCode": "0xCA", @@ -275,7 +275,6 @@ }, { "PublicDescription": "This event counts the number of instructions that retire. For instructions that consist of multiple micro-ops, this event counts exactly once, as the last micro-op of the instruction retires. The event continues counting while instructions retire, including during interrupt service routines caused by hardware interrupts, faults or traps. Background: Modern microprocessors employ extensive pipelining and speculative techniques. Since sometimes an instruction is started but never completed, the notion of \"retirement\" is introduced. A retired instruction is one that commits its states. Or stated differently, an instruction might be abandoned at some point. No instruction is truly finished until it retires. This counter measures the number of completed instructions. The fixed event is INST_RETIRED.ANY and the programmable event is INST_RETIRED.ANY_P.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -284,7 +283,6 @@ }, { "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. In systems with a constant core frequency, this event can give you a measurement of the elapsed time while the core was not in halt state by dividing the event count by the core frequency. This event is architecturally defined and is a designated fixed counter. CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.CORE_P use the core frequency which may change from time to time. CPU_CLK_UNHALTE.REF_TSC and CPU_CLK_UNHALTED.REF are not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. The fixed events are CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.REF_TSC and the programmable events are CPU_CLK_UNHALTED.CORE_P and CPU_CLK_UNHALTED.REF.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.CORE", @@ -293,7 +291,6 @@ }, { "PublicDescription": "Counts the number of reference cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. Divide this event count by core frequency to determine the elapsed time while the core was not in halt state. Divide this event count by core frequency to determine the elapsed time while the core was not in halt state. This event is architecturally defined and is a designated fixed counter. CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.CORE_P use the core frequency which may change from time to time. CPU_CLK_UNHALTE.REF_TSC and CPU_CLK_UNHALTED.REF are not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. The fixed events are CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.REF_TSC and the programmable events are CPU_CLK_UNHALTED.CORE_P and CPU_CLK_UNHALTED.REF.", - "EventCode": "0x00", "Counter": "Fixed counter 3", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", diff --git a/tools/perf/pmu-events/arch/x86/skylake/cache.json b/tools/perf/pmu-events/arch/x86/skylake/cache.json index 54bfe9e4045c..720458139049 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylake/cache.json @@ -60,10 +60,10 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x41", + "UMask": "0xc1", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "SampleAfterValue": "200003", "BriefDescription": "Demand Data Read requests that hit L2 cache", @@ -73,7 +73,7 @@ "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x42", + "UMask": "0xc2", "EventName": "L2_RQSTS.RFO_HIT", "SampleAfterValue": "200003", "BriefDescription": "RFO requests that hit L2 cache", @@ -83,7 +83,7 @@ "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x44", + "UMask": "0xc4", "EventName": "L2_RQSTS.CODE_RD_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", @@ -482,7 +482,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "EventCode": "0xD1", "Counter": "0,1,2,3", "UMask": "0x1", @@ -554,7 +554,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "EventCode": "0xD1", "Counter": "0,1,2,3", "UMask": "0x40", @@ -661,13 +661,13 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.", + "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", "EventCode": "0xF2", "Counter": "0,1,2,3", "UMask": "0x4", "EventName": "L2_LINES_OUT.USELESS_PREF", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", + "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -690,249 +690,2238 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC01C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10001C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x04001C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x02001C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x01001C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00801C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00401C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fc0400001 ", + "MSRValue": "0x0200028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests have any response type.", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0000018000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests have any response type.", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC01C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10001C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x04001C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x02001C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x01001C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00801C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00401C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0000010004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC01C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10001C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x04001C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x02001C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x01001C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00801C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00401C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs) have any response type.", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0000010002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000400001 ", + "MSRValue": "0x1000400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400400001 ", + "MSRValue": "0x0400400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200400001 ", + "MSRValue": "0x0200400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100400001 ", + "MSRValue": "0x0100400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080400001 ", + "MSRValue": "0x0080400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040400001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fc01c0001 ", + "MSRValue": "0x3FC01C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_HIT & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10001c0001 ", + "MSRValue": "0x10001C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04001c0001 ", + "MSRValue": "0x04001C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops sent to sibling cores return clean response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02001c0001 ", + "MSRValue": "0x02001C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops sent to sibling cores return clean response.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01001c0001 ", + "MSRValue": "0x01001C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00801c0001 ", + "MSRValue": "0x00801C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00401C0001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fc0020001 ", + "MSRValue": "0x0080100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020001 ", + "MSRValue": "0x1000020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020001 ", + "MSRValue": "0x0400020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020001 ", + "MSRValue": "0x0200020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020001 ", + "MSRValue": "0x0100020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020001 ", + "MSRValue": "0x0080020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040020001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010001 ", + "MSRValue": "0x0000010001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that have any response type.", + "BriefDescription": "Counts demand data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/skylake/frontend.json b/tools/perf/pmu-events/arch/x86/skylake/frontend.json index 578dff5bd823..7fa95a35e3ca 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/skylake/frontend.json @@ -177,7 +177,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", + "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", "EventCode": "0x9C", "Counter": "0,1,2,3", "UMask": "0x1", @@ -242,7 +242,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.", "EventCode": "0xAB", "Counter": "0,1,2,3", "UMask": "0x2", @@ -253,7 +253,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "EventCode": "0xC6", "MSRValue": "0x11", "Counter": "0,1,2,3", @@ -360,7 +360,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "EventCode": "0xC6", "MSRValue": "0x400806", "Counter": "0,1,2,3", @@ -374,7 +374,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "EventCode": "0xC6", "MSRValue": "0x401006", "Counter": "0,1,2,3", @@ -388,7 +388,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "EventCode": "0xC6", "MSRValue": "0x402006", "Counter": "0,1,2,3", @@ -454,7 +454,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "EventCode": "0xC6", "MSRValue": "0x100206", "Counter": "0,1,2,3", diff --git a/tools/perf/pmu-events/arch/x86/skylake/memory.json b/tools/perf/pmu-events/arch/x86/skylake/memory.json index 3bd8b712c889..f197b4c7695b 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/memory.json +++ b/tools/perf/pmu-events/arch/x86/skylake/memory.json @@ -215,7 +215,7 @@ "UMask": "0x4", "EventName": "HLE_RETIRED.ABORTED", "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ", + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -237,6 +237,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", "EventCode": "0xC8", "Counter": "0,1,2,3", "UMask": "0x20", @@ -292,7 +293,7 @@ "UMask": "0x4", "EventName": "RTM_RETIRED.ABORTED", "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ", + "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -346,7 +347,7 @@ }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x4", "Counter": "0,1,2,3", @@ -354,13 +355,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "SampleAfterValue": "100003", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x8", "Counter": "0,1,2,3", @@ -368,13 +369,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "SampleAfterValue": "50021", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x10", "Counter": "0,1,2,3", @@ -382,13 +383,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "SampleAfterValue": "20011", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x20", "Counter": "0,1,2,3", @@ -396,13 +397,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "SampleAfterValue": "100007", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x40", "Counter": "0,1,2,3", @@ -410,13 +411,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "SampleAfterValue": "2003", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x80", "Counter": "0,1,2,3", @@ -424,13 +425,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "SampleAfterValue": "1009", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x100", "Counter": "0,1,2,3", @@ -438,13 +439,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "SampleAfterValue": "503", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x200", "Counter": "0,1,2,3", @@ -452,163 +453,1151 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "SampleAfterValue": "101", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3ffc000001 ", + "MSRValue": "0x3FFC408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x203C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x103C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x043C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x023C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x013C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00BC408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x007C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC4008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2004008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1004008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0404008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0204008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0104008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0084008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0044008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x20001C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FFC400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x203C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x103C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x043C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x023C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x013C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00BC400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x007C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC4000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2004000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1004000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0404000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0204000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0104000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0084000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0044000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x20001C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FFC400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x203C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x103C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x043C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x023C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x013C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00BC400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x007C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC4000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2004000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1004000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0404000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0204000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0104000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0084000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0044000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x20001C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FFC400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x203C400001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x103c000001 ", + "MSRValue": "0x103C400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000001 ", + "MSRValue": "0x043C400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000001 ", + "MSRValue": "0x023C400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000001 ", + "MSRValue": "0x013C400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000001 ", + "MSRValue": "0x00BC400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fc4000001 ", + "MSRValue": "0x007C400001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC4000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2004000001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000001 ", + "MSRValue": "0x1004000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000001 ", + "MSRValue": "0x0404000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000001 ", + "MSRValue": "0x0204000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000001 ", + "MSRValue": "0x0104000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000001 ", + "MSRValue": "0x0084000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0044000001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000400001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x20001C0001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000020001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json index bc6d2afbcd8a..4a891fbbc4bb 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json @@ -1,7 +1,6 @@ [ { "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -11,7 +10,6 @@ }, { "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -20,7 +18,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "AnyThread": "1", @@ -31,7 +28,6 @@ }, { "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -121,7 +117,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.", "EventCode": "0x0E", "Counter": "0,1,2,3", "UMask": "0x2", @@ -248,6 +244,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", + "EventCode": "0x59", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", "EventCode": "0x5E", "Counter": "0,1,2,3", @@ -361,8 +367,8 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", - "EventCode": "0xA2", + "PublicDescription": "Counts resource-related stall cycles.", + "EventCode": "0xa2", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "RESOURCE_STALLS.ANY", @@ -735,7 +741,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.", + "PublicDescription": "This event counts cycles without actually retired uops.", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", @@ -759,6 +765,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Number of machine clears (nukes) of any type.", "EventCode": "0xC3", "Counter": "0,1,2,3", "UMask": "0x1", @@ -839,14 +846,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x10", "Errata": "SKL091", "EventName": "BR_INST_RETIRED.NOT_TAKEN", "SampleAfterValue": "400009", - "BriefDescription": "Not taken branch instructions retired.", + "BriefDescription": "Counts all not taken macro branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -924,7 +932,7 @@ "UMask": "0x20", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", "SampleAfterValue": "400009", - "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ", + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -938,6 +946,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xCC", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "ROB_MISC_EVENTS.PAUSE_INST", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", "EventCode": "0xE6", "Counter": "0,1,2,3", diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 71e9737f4614..2c95417a4dae 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -1,164 +1,364 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )", - "MetricGroup": "Frontend", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "Branch_Misprediction_Cost" }, { + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" + }, + { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Access_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "arb@event\\=0x80\\,umask\\=0x2@ / arb@event\\=0x80\\,umask\\=0x2\\,thresh\\=1@", + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_Parallel_Reads" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json index 5c9940866acd..24df183693fa 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json @@ -61,17 +61,17 @@ }, { "EventCode": "0x24", - "UMask": "0x41", + "UMask": "0xc1", "BriefDescription": "Demand Data Read requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x24", - "UMask": "0x42", + "UMask": "0xc2", "BriefDescription": "RFO requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.RFO_HIT", @@ -81,7 +81,7 @@ }, { "EventCode": "0x24", - "UMask": "0x44", + "UMask": "0xc4", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.CODE_RD_HIT", @@ -165,6 +165,7 @@ "BriefDescription": "Core-originated cacheable demand requests missed L3", "Counter": "0,1,2,3", "EventName": "LONGEST_LAT_CACHE.MISS", + "Errata": "SKL057", "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" @@ -175,28 +176,29 @@ "BriefDescription": "Core-originated cacheable demand requests that refer to L3", "Counter": "0,1,2,3", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", + "Errata": "SKL057", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x48", "UMask": "0x1", - "BriefDescription": "L1D miss outstandings duration in cycles", + "BriefDescription": "Cycles with L1D load Misses outstanding.", "Counter": "0,1,2,3", - "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x48", "UMask": "0x1", - "BriefDescription": "Cycles with L1D load Misses outstanding.", + "BriefDescription": "L1D miss outstandings duration in cycles", "Counter": "0,1,2,3", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "CounterMask": "1", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -234,21 +236,21 @@ { "EventCode": "0x60", "UMask": "0x1", - "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "CounterMask": "1", + "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x60", "UMask": "0x1", - "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "CounterMask": "1", - "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -307,21 +309,21 @@ { "EventCode": "0x60", "UMask": "0x8", - "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", - "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "CounterMask": "1", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x60", "UMask": "0x8", - "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "CounterMask": "1", - "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -486,7 +488,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, @@ -558,7 +560,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" }, @@ -690,6 +692,7 @@ "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared state. A non-threaded event.", "Counter": "0,1,2,3", "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -699,17 +702,18 @@ "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped", "Counter": "0,1,2,3", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped.", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xF2", "UMask": "0x4", - "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", + "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", + "Deprecated": "1", "Counter": "0,1,2,3", "EventName": "L2_LINES_OUT.USELESS_PREF", - "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.", + "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -736,12 +740,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that have any response type.", - "MSRValue": "0x0000010001 ", + "BriefDescription": "Counts demand data reads have any response type.", + "MSRValue": "0x0000010001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -749,12 +753,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0001 ", + "BriefDescription": "Counts demand data reads TBD TBD", + "MSRValue": "0x01003C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -762,25 +766,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0001 ", + "BriefDescription": "Counts demand data reads TBD TBD", + "MSRValue": "0x04003C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0001 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -788,12 +779,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0001 ", + "BriefDescription": "Counts demand data reads TBD TBD", + "MSRValue": "0x10003C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -801,12 +792,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3.", - "MSRValue": "0x3f803c0001 ", + "BriefDescription": "Counts demand data reads TBD TBD", + "MSRValue": "0x3F803C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -814,12 +805,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.", - "MSRValue": "0x0000010002 ", + "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", + "MSRValue": "0x0000010002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -827,12 +818,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", + "MSRValue": "0x01003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -840,12 +831,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", + "MSRValue": "0x04003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -853,25 +844,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0002 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", + "MSRValue": "0x10003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -879,12 +857,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.", - "MSRValue": "0x3f803c0002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", + "MSRValue": "0x3F803C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -892,12 +870,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that have any response type.", - "MSRValue": "0x0000010004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", + "MSRValue": "0x0000010004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -905,12 +883,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "MSRValue": "0x01003C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -918,12 +896,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "MSRValue": "0x04003C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -931,25 +909,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0004 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "MSRValue": "0x10003C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -957,12 +922,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3.", - "MSRValue": "0x3f803c0004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "MSRValue": "0x3F803C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -970,12 +935,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.", - "MSRValue": "0x0000010010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads have any response type.", + "MSRValue": "0x0000010010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -983,12 +948,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "MSRValue": "0x01003C0010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -996,12 +961,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "MSRValue": "0x04003C0010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1009,25 +974,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0010 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "MSRValue": "0x10003C0010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1035,12 +987,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.", - "MSRValue": "0x3f803c0010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "MSRValue": "0x3F803C0010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1048,12 +1000,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.", - "MSRValue": "0x0000010020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.", + "MSRValue": "0x0000010020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1061,12 +1013,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "MSRValue": "0x01003C0020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1074,12 +1026,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "MSRValue": "0x04003C0020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1087,25 +1039,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0020 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "MSRValue": "0x10003C0020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1113,12 +1052,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.", - "MSRValue": "0x3f803c0020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "MSRValue": "0x3F803C0020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1126,12 +1065,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.", - "MSRValue": "0x0000010080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.", + "MSRValue": "0x0000010080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1139,12 +1078,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "MSRValue": "0x01003C0080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1152,25 +1091,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "MSRValue": "0x04003C0080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0080 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1178,12 +1104,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "MSRValue": "0x10003C0080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1191,12 +1117,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.", - "MSRValue": "0x3f803c0080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "MSRValue": "0x3F803C0080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1204,12 +1130,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.", - "MSRValue": "0x0000010100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.", + "MSRValue": "0x0000010100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1217,12 +1143,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "MSRValue": "0x01003C0100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1230,12 +1156,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "MSRValue": "0x04003C0100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1243,12 +1169,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "MSRValue": "0x10003C0100", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1256,12 +1182,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "MSRValue": "0x3F803C0100", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1269,12 +1195,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.", - "MSRValue": "0x3f803c0100 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.", + "MSRValue": "0x0000010400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1282,12 +1208,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.", - "MSRValue": "0x0000010400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "MSRValue": "0x01003C0400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1295,12 +1221,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "MSRValue": "0x04003C0400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1308,12 +1234,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "MSRValue": "0x10003C0400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1321,12 +1247,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "PF_L1D_AND_SW & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "MSRValue": "0x3F803C0400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1334,12 +1260,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0400 ", + "BriefDescription": "TBD have any response type.", + "MSRValue": "0x0000010490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1347,12 +1273,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.", - "MSRValue": "0x3f803c0400 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x01003C0490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1360,12 +1286,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts any other requests that have any response type.", - "MSRValue": "0x0000018000 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x04003C0490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1373,12 +1299,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c8000 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x10003C0490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1386,12 +1312,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c8000 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3F803C0490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1399,12 +1325,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "OTHER & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c8000 ", + "BriefDescription": "TBD have any response type.", + "MSRValue": "0x0000010120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1412,12 +1338,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c8000 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x01003C0120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1425,12 +1351,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts any other requests that hit in the L3.", - "MSRValue": "0x3f803c8000 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x04003C0120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1438,12 +1364,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that have any response type.", - "MSRValue": "0x0000010490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x10003C0120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1451,12 +1377,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3F803C0120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1464,12 +1390,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0490 ", + "BriefDescription": "TBD have any response type.", + "MSRValue": "0x0000010491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1477,12 +1403,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x01003C0491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1490,12 +1416,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x04003C0491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1503,12 +1429,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that hit in the L3.", - "MSRValue": "0x3f803c0490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x10003C0491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1516,12 +1442,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that have any response type.", - "MSRValue": "0x0000010120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3F803C0491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1529,12 +1455,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0120 ", + "BriefDescription": "TBD have any response type.", + "MSRValue": "0x0000010122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1542,12 +1468,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x01003C0122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1555,12 +1481,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x04003C0122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1568,12 +1494,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x10003C0122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1581,12 +1507,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that hit in the L3.", - "MSRValue": "0x3f803c0120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3F803C0122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1594,12 +1520,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that have any response type.", - "MSRValue": "0x0000010491 ", + "BriefDescription": "Counts demand data reads", + "MSRValue": "0x08007C0001", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts demand data reads", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1607,12 +1532,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0491 ", + "BriefDescription": "Counts all demand data writes (RFOs)", + "MSRValue": "0x08007C0002", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1620,12 +1544,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0491 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "MSRValue": "0x08007C0004", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1633,12 +1556,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0491 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", + "MSRValue": "0x08007C0010", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1646,12 +1568,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0491 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", + "MSRValue": "0x08007C0020", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1659,12 +1580,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.", - "MSRValue": "0x3f803c0491 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", + "MSRValue": "0x08007C0080", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1672,12 +1592,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.", - "MSRValue": "0x0000010122 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", + "MSRValue": "0x08007C0100", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1685,12 +1604,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0122 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests", + "MSRValue": "0x08007C0400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1698,12 +1616,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0122 ", + "BriefDescription": "TBD", + "MSRValue": "0x08007C0490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1711,12 +1628,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0122 ", + "BriefDescription": "TBD", + "MSRValue": "0x08007C0120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1724,12 +1640,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0122 ", + "BriefDescription": "TBD", + "MSRValue": "0x08007C0491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1737,12 +1652,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.", - "MSRValue": "0x3f803c0122 ", + "BriefDescription": "TBD", + "MSRValue": "0x08007C0122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json index 286ed1a37ec9..c5d0babe89fc 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json @@ -59,7 +59,6 @@ "BriefDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8)", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", - "PublicDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -69,7 +68,6 @@ "BriefDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16)", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", - "PublicDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json index 403a4f89e9b2..4dc583cfb545 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json @@ -2,16 +2,6 @@ { "EventCode": "0x79", "UMask": "0x4", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", - "Counter": "0,1,2,3", - "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x79", - "UMask": "0x4", "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", "EventName": "IDQ.MITE_CYCLES", @@ -22,11 +12,11 @@ }, { "EventCode": "0x79", - "UMask": "0x8", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "UMask": "0x4", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", - "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -43,6 +33,16 @@ }, { "EventCode": "0x79", + "UMask": "0x8", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", "UMask": "0x10", "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", @@ -55,22 +55,22 @@ { "EventCode": "0x79", "UMask": "0x18", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", - "CounterMask": "4", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "CounterMask": "1", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "UMask": "0x18", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", - "CounterMask": "1", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "CounterMask": "4", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -87,22 +87,22 @@ { "EventCode": "0x79", "UMask": "0x24", - "BriefDescription": "Cycles MITE is delivering 4 Uops", + "BriefDescription": "Cycles MITE is delivering any Uop", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", - "CounterMask": "4", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "CounterMask": "1", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "UMask": "0x24", - "BriefDescription": "Cycles MITE is delivering any Uop", + "BriefDescription": "Cycles MITE is delivering 4 Uops", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", - "CounterMask": "1", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "CounterMask": "4", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -118,24 +118,24 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EdgeDetect": "1", "EventCode": "0x79", "UMask": "0x30", - "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_SWITCHES", - "CounterMask": "1", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EdgeDetect": "1", "EventCode": "0x79", "UMask": "0x30", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", + "EventName": "IDQ.MS_SWITCHES", + "CounterMask": "1", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -177,67 +177,67 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "Invert": "1", "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", + "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "CounterMask": "4", - "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", + "CounterMask": "1", + "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", + "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", - "CounterMask": "3", - "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "CounterMask": "2", + "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", - "CounterMask": "2", - "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "CounterMask": "3", + "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", - "CounterMask": "1", - "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "CounterMask": "4", + "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", - "CounterMask": "1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -247,20 +247,19 @@ "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", "Counter": "0,1,2,3", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x11", + "MSRValue": "0x400406", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.DSB_MISS", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -268,11 +267,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x12", + "MSRValue": "0x200206", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.L1I_MISS", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -281,11 +280,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x13", + "MSRValue": "0x400206", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.L2_MISS", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -294,13 +293,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.", + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.", "PEBS": "1", - "MSRValue": "0x14", + "MSRValue": "0x15", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -308,13 +307,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.", + "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.", "PEBS": "1", - "MSRValue": "0x15", + "MSRValue": "0x14", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.STLB_MISS", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -322,11 +321,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.", "PEBS": "1", - "MSRValue": "0x400206", + "MSRValue": "0x13", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -335,11 +334,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.", "PEBS": "1", - "MSRValue": "0x200206", + "MSRValue": "0x12", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", + "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -348,12 +347,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.", "PEBS": "1", - "MSRValue": "0x400406", + "MSRValue": "0x11", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -361,13 +361,12 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x400806", + "MSRValue": "0x300206", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -375,13 +374,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x401006", + "MSRValue": "0x100206", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -389,13 +388,12 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x402006", + "MSRValue": "0x420006", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -403,11 +401,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x404006", + "MSRValue": "0x410006", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -429,11 +427,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x410006", + "MSRValue": "0x404006", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -442,12 +440,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x420006", + "MSRValue": "0x402006", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -455,13 +454,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x100206", + "MSRValue": "0x401006", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -469,12 +468,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", "PEBS": "1", - "MSRValue": "0x300206", + "MSRValue": "0x400806", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json index e7f1aa31226d..48a9cdf81307 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/memory.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json @@ -129,20 +129,20 @@ { "EventCode": "0x60", "UMask": "0x10", - "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", - "CounterMask": "1", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", + "CounterMask": "6", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x60", "UMask": "0x10", - "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", + "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", - "CounterMask": "6", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -210,7 +210,7 @@ { "EventCode": "0xC8", "UMask": "0x4", - "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ", + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "HLE_RETIRED.ABORTED", @@ -242,6 +242,7 @@ "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", "Counter": "0,1,2,3", "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -287,7 +288,7 @@ { "EventCode": "0xC9", "UMask": "0x4", - "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ", + "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "RTM_RETIRED.ABORTED", @@ -347,125 +348,125 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", "PEBS": "2", - "MSRValue": "0x4", + "MSRValue": "0x200", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "100003", + "SampleAfterValue": "101", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", "PEBS": "2", - "MSRValue": "0x8", + "MSRValue": "0x100", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "50021", + "SampleAfterValue": "503", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", "PEBS": "2", - "MSRValue": "0x10", + "MSRValue": "0x80", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "20011", + "SampleAfterValue": "1009", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", "PEBS": "2", - "MSRValue": "0x20", + "MSRValue": "0x40", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "100007", + "SampleAfterValue": "2003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", "PEBS": "2", - "MSRValue": "0x40", + "MSRValue": "0x20", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "2003", + "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", "PEBS": "2", - "MSRValue": "0x80", + "MSRValue": "0x10", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "1009", + "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", "PEBS": "2", - "MSRValue": "0x100", + "MSRValue": "0x8", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "503", + "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", "PEBS": "2", - "MSRValue": "0x200", + "MSRValue": "0x4", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "101", + "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss in the L3.", - "MSRValue": "0x3fbc000001 ", + "BriefDescription": "Counts demand data reads TBD TBD", + "MSRValue": "0x3FBC000001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -473,12 +474,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00001 ", + "BriefDescription": "Counts demand data reads TBD", + "MSRValue": "0x083FC00001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -486,12 +487,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00001 ", + "BriefDescription": "Counts demand data reads TBD", + "MSRValue": "0x103FC00001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -499,12 +500,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00001 ", + "BriefDescription": "Counts demand data reads TBD", + "MSRValue": "0x063FC00001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -512,12 +513,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800001 ", + "BriefDescription": "Counts demand data reads TBD", + "MSRValue": "0x063B800001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -525,12 +526,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000001 ", + "BriefDescription": "Counts demand data reads TBD", + "MSRValue": "0x0604000001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -538,12 +539,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.", - "MSRValue": "0x3fbc000002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", + "MSRValue": "0x3FBC000002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -551,12 +552,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD", + "MSRValue": "0x083FC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -564,12 +565,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD", + "MSRValue": "0x103FC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -577,12 +578,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD", + "MSRValue": "0x063FC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -590,12 +591,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD", + "MSRValue": "0x063B800002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -603,12 +604,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD", + "MSRValue": "0x0604000002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -616,12 +617,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss in the L3.", - "MSRValue": "0x3fbc000004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "MSRValue": "0x3FBC000004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -629,12 +630,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "MSRValue": "0x083FC00004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -642,12 +643,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "MSRValue": "0x103FC00004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -655,12 +656,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "MSRValue": "0x063FC00004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -668,12 +669,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "MSRValue": "0x063B800004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -681,12 +682,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "MSRValue": "0x0604000004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -694,12 +695,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.", - "MSRValue": "0x3fbc000010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "MSRValue": "0x3FBC000010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -707,12 +708,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "MSRValue": "0x083FC00010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -720,12 +721,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "MSRValue": "0x103FC00010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -733,12 +734,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "MSRValue": "0x063FC00010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -746,12 +747,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "MSRValue": "0x063B800010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -759,12 +760,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "MSRValue": "0x0604000010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -772,12 +773,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.", - "MSRValue": "0x3fbc000020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "MSRValue": "0x3FBC000020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -785,12 +786,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "MSRValue": "0x083FC00020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -798,12 +799,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "MSRValue": "0x103FC00020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -811,12 +812,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "MSRValue": "0x063FC00020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -824,12 +825,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "MSRValue": "0x063B800020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -837,12 +838,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "MSRValue": "0x0604000020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -850,12 +851,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.", - "MSRValue": "0x3fbc000080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "MSRValue": "0x3FBC000080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -863,12 +864,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "MSRValue": "0x083FC00080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -876,12 +877,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "MSRValue": "0x103FC00080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -889,12 +890,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "MSRValue": "0x063FC00080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -902,12 +903,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "MSRValue": "0x063B800080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -915,12 +916,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "MSRValue": "0x0604000080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -928,12 +929,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.", - "MSRValue": "0x3fbc000100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "MSRValue": "0x3FBC000100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -941,12 +942,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "MSRValue": "0x083FC00100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -954,12 +955,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "MSRValue": "0x103FC00100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -967,12 +968,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "MSRValue": "0x063FC00100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -980,12 +981,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "MSRValue": "0x063B800100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -993,12 +994,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "MSRValue": "0x0604000100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1006,12 +1007,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.", - "MSRValue": "0x3fbc000400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "MSRValue": "0x3FBC000400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1019,12 +1020,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "MSRValue": "0x083FC00400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1032,12 +1033,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "MSRValue": "0x103FC00400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1045,12 +1046,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "MSRValue": "0x063FC00400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1058,12 +1059,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "MSRValue": "0x063B800400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1071,90 +1072,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "MSRValue": "0x0604000400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss in the L3.", - "MSRValue": "0x3fbc008000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc08000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc08000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc08000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b808000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604008000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1162,12 +1085,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss in the L3.", - "MSRValue": "0x3fbc000490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3FBC000490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1175,12 +1098,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00490 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x083FC00490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1188,12 +1111,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00490 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x103FC00490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1201,12 +1124,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00490 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063FC00490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1214,12 +1137,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800490 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063B800490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1227,12 +1150,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000490 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x0604000490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1240,12 +1163,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss in the L3.", - "MSRValue": "0x3fbc000120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3FBC000120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1253,12 +1176,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00120 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x083FC00120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1266,12 +1189,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00120 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x103FC00120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1279,12 +1202,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00120 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063FC00120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1292,12 +1215,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800120 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063B800120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1305,12 +1228,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000120 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x0604000120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1318,12 +1241,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.", - "MSRValue": "0x3fbc000491 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3FBC000491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1331,12 +1254,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00491 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x083FC00491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1344,12 +1267,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00491 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x103FC00491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1357,12 +1280,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00491 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063FC00491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1370,12 +1293,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800491 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063B800491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1383,12 +1306,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000491 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x0604000491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1396,12 +1319,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.", - "MSRValue": "0x3fbc000122 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3FBC000122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1409,12 +1332,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00122 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x083FC00122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1422,12 +1345,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00122 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x103FC00122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1435,12 +1358,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00122 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063FC00122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1448,12 +1371,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800122 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063B800122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1461,12 +1384,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000122 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x0604000122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json index f99f7ae27820..369f56c1d1b5 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "UMask": "0x1", "BriefDescription": "Instructions retired from execution.", "Counter": "Fixed counter 0", @@ -10,7 +9,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when the thread is not in halt state", "Counter": "Fixed counter 1", @@ -20,7 +18,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "Fixed counter 1", @@ -30,7 +27,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x3", "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", @@ -99,24 +95,24 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "Invert": "1", "EventCode": "0x0E", "UMask": "0x1", - "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", "Counter": "0,1,2,3", - "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", "EventCode": "0x0E", "UMask": "0x1", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", "Counter": "0,1,2,3", - "EventName": "UOPS_ISSUED.STALL_CYCLES", - "CounterMask": "1", - "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -126,7 +122,7 @@ "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", "Counter": "0,1,2,3", "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", - "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -203,19 +199,19 @@ { "EventCode": "0x3C", "UMask": "0x1", - "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "AnyThread": "1", "SampleAfterValue": "2503", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x3C", "UMask": "0x1", - "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", - "AnyThread": "1", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", "SampleAfterValue": "2503", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -248,12 +244,12 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5E", + "EventCode": "0x59", "UMask": "0x1", - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", + "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", "Counter": "0,1,2,3", - "EventName": "RS_EVENTS.EMPTY_CYCLES", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", + "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -271,6 +267,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x5E", + "UMask": "0x1", + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", + "Counter": "0,1,2,3", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x87", "UMask": "0x1", "BriefDescription": "Stalls caused by changing prefix length of the instruction.", @@ -361,12 +367,12 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xa2", "UMask": "0x1", "BriefDescription": "Resource-related stall cycles", "Counter": "0,1,2,3", "EventName": "RESOURCE_STALLS.ANY", - "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "PublicDescription": "Counts resource-related stall cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -522,6 +528,17 @@ { "EventCode": "0xA8", "UMask": "0x1", + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "Counter": "0,1,2,3", + "EventName": "LSD.CYCLES_4_UOPS", + "CounterMask": "4", + "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA8", + "UMask": "0x1", "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", "Counter": "0,1,2,3", "EventName": "LSD.CYCLES_ACTIVE", @@ -531,35 +548,35 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA8", + "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", "Counter": "0,1,2,3", - "EventName": "LSD.CYCLES_4_UOPS", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", "CounterMask": "4", - "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.THREAD", - "PublicDescription": "Number of uops to be executed per-thread each cycle.", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "CounterMask": "3", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.STALL_CYCLES", - "CounterMask": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", + "CounterMask": "2", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -575,35 +592,24 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "Invert": "1", "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Cycles where at least 2 uops were executed per-thread", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", - "CounterMask": "2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", - "CounterMask": "3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", - "CounterMask": "4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Number of uops to be executed per-thread each cycle.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -618,11 +624,12 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "Invert": "1", "EventCode": "0xB1", "UMask": "0x2", - "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" @@ -630,10 +637,10 @@ { "EventCode": "0xB1", "UMask": "0x2", - "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "CounterMask": "2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "CounterMask": "4", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -650,20 +657,19 @@ { "EventCode": "0xB1", "UMask": "0x2", - "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "CounterMask": "4", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "CounterMask": "2", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", "EventCode": "0xB1", "UMask": "0x2", - "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" @@ -725,12 +731,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "Invert": "1", "EventCode": "0xC2", "UMask": "0x2", - "BriefDescription": "Retirement slots used.", + "BriefDescription": "Cycles with less than 10 actually retired uops.", "Counter": "0,1,2,3", - "EventName": "UOPS_RETIRED.RETIRE_SLOTS", - "PublicDescription": "Counts the retirement slots used.", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "CounterMask": "10", + "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -742,19 +750,17 @@ "Counter": "0,1,2,3", "EventName": "UOPS_RETIRED.STALL_CYCLES", "CounterMask": "1", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.", + "PublicDescription": "This event counts cycles without actually retired uops.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", "EventCode": "0xC2", "UMask": "0x2", - "BriefDescription": "Cycles with less than 10 actually retired uops.", + "BriefDescription": "Retirement slots used.", "Counter": "0,1,2,3", - "EventName": "UOPS_RETIRED.TOTAL_CYCLES", - "CounterMask": "10", - "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PublicDescription": "Counts the retirement slots used.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -766,6 +772,7 @@ "Counter": "0,1,2,3", "EventName": "MACHINE_CLEARS.COUNT", "CounterMask": "1", + "PublicDescription": "Number of machine clears (nukes) of any type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -841,11 +848,12 @@ { "EventCode": "0xC4", "UMask": "0x10", - "BriefDescription": "Not taken branch instructions retired.", + "BriefDescription": "Counts all not taken macro branch instructions retired.", + "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NOT_TAKEN", "Errata": "SKL091", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -919,7 +927,7 @@ { "EventCode": "0xC5", "UMask": "0x20", - "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ", + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", @@ -938,6 +946,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xCC", + "UMask": "0x40", + "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", + "Counter": "0,1,2,3", + "EventName": "ROB_MISC_EVENTS.PAUSE_INST", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xE6", "UMask": "0x1", "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index 71e9737f4614..56e03ba771f4 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -1,164 +1,394 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )", - "MetricGroup": "Frontend", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "Branch_Misprediction_Cost" + }, + { + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" }, { + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" + }, + { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Access_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )", + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "DRAM_Read_Latency" + }, + { + "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@", + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_Parallel_Reads" + }, + { + "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 0 == 1 else 0 else 0", + "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "MEM_PMM_Read_Latency" + }, + { + "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0", + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "PMM_Read_BW" + }, + { + "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0", + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "PMM_Write_BW" + }, + { + "MetricExpr": "cha_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/trace/beauty/renameat.c b/tools/perf/trace/beauty/renameat.c index 6dab340cc506..852d2e271833 100644 --- a/tools/perf/trace/beauty/renameat.c +++ b/tools/perf/trace/beauty/renameat.c @@ -2,7 +2,6 @@ // Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> #include "trace/beauty/beauty.h" -#include <uapi/linux/fs.h> static size_t renameat2__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix) { diff --git a/tools/perf/trace/strace/groups/string b/tools/perf/trace/strace/groups/string new file mode 100644 index 000000000000..c87129a3e3c4 --- /dev/null +++ b/tools/perf/trace/strace/groups/string @@ -0,0 +1,65 @@ +access +acct +add_key +chdir +chmod +chown +chroot +creat +delete_module +execve +execveat +faccessat +fchmodat +fchownat +fgetxattr +finit_module +fremovexattr +fsetxattr +futimesat +getxattr +inotify_add_watch +lchown +lgetxattr +link +linkat +listxattr +llistxattr +lremovexattr +lsetxattr +lstat +memfd_create +mkdir +mkdirat +mknod +mknodat +mq_open +mq_timedsend +mq_unlink +name_to_handle_at +newfstatat +open +openat +pivot_root +pwrite64 +quotactl +readlink +readlinkat +removexattr +rename +renameat +renameat2 +request_key +rmdir +setxattr +stat +statfs +statx +swapoff +swapon +symlink +symlinkat +truncate +unlink +unlinkat +utimensat diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 26af43ad9ddd..e0311c9750ad 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -310,7 +310,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, if (flags & TEP_FIELD_IS_DYNAMIC) { unsigned long long tmp_val; - tmp_val = tep_read_number(fmtf->event->pevent, + tmp_val = tep_read_number(fmtf->event->tep, data + offset, len); offset = tmp_val; len = offset >> 16; @@ -354,7 +354,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, unsigned long long value_int; value_int = tep_read_number( - fmtf->event->pevent, + fmtf->event->tep, data + offset + i * len, len); if (!(flags & TEP_FIELD_IS_SIGNED)) diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 36ae7e92dab1..4e908ec1ef64 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -6,6 +6,7 @@ #include <stdio.h> #include <linux/kernel.h> #include <linux/bpf.h> +#include <linux/perf_event.h> #include "../perf.h" #include "build-id.h" diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 51ead577533f..4b6783ff5813 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1009,7 +1009,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, */ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, unsigned int auxtrace_pages, - bool auxtrace_overwrite, int nr_cblocks, int affinity) + bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush) { struct perf_evsel *evsel; const struct cpu_map *cpus = evlist->cpus; @@ -1019,7 +1019,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, * Its value is decided by evsel's write_backward. * So &mp should not be passed through const pointer. */ - struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity }; + struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush }; if (!evlist->mmap) evlist->mmap = perf_evlist__alloc_mmap(evlist, false); @@ -1051,7 +1051,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages) { - return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS); + return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1); } int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 6a94785b9100..c9a0f72677fd 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -177,7 +177,8 @@ unsigned long perf_event_mlock_kb_in_pages(void); int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, unsigned int auxtrace_pages, - bool auxtrace_overwrite, int nr_cblocks, int affinity); + bool auxtrace_overwrite, int nr_cblocks, + int affinity, int flush); int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages); void perf_evlist__munmap(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 966360844fff..a10cf4cde920 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -580,6 +580,12 @@ static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size) return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); } +static int perf_evsel__tool_name(char *bf, size_t size) +{ + int ret = scnprintf(bf, size, "duration_time"); + return ret; +} + const char *perf_evsel__name(struct perf_evsel *evsel) { char bf[128]; @@ -601,7 +607,10 @@ const char *perf_evsel__name(struct perf_evsel *evsel) break; case PERF_TYPE_SOFTWARE: - perf_evsel__sw_name(evsel, bf, sizeof(bf)); + if (evsel->tool_event) + perf_evsel__tool_name(bf, sizeof(bf)); + else + perf_evsel__sw_name(evsel, bf, sizeof(bf)); break; case PERF_TYPE_TRACEPOINT: diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 0f2c6c93d721..6d190cbf1070 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -75,6 +75,11 @@ struct perf_stat_evsel; typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data); +enum perf_tool_event { + PERF_TOOL_NONE = 0, + PERF_TOOL_DURATION_TIME = 1, +}; + /** struct perf_evsel - event selector * * @evlist - evlist this evsel is in, if it is in one. @@ -121,6 +126,7 @@ struct perf_evsel { unsigned int sample_size; int id_pos; int is_pos; + enum perf_tool_event tool_event; bool uniquified_name; bool snapshot; bool supported; diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index cdc7740fc181..ef3d79b2c90b 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -440,6 +440,8 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c perf_mmap__setup_affinity_mask(map, mp); + map->flush = mp->flush; + if (auxtrace_mmap__mmap(&map->auxtrace_mmap, &mp->auxtrace_mp, map->base, fd)) return -1; @@ -492,7 +494,7 @@ static int __perf_mmap__read_init(struct perf_mmap *md) md->start = md->overwrite ? head : old; md->end = md->overwrite ? old : head; - if (md->start == md->end) + if ((md->end - md->start) < md->flush) return -EAGAIN; size = md->end - md->start; diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index e566c19b242b..b82f8c2d55c4 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -39,6 +39,7 @@ struct perf_mmap { } aio; #endif cpu_set_t affinity_mask; + u64 flush; }; /* @@ -70,7 +71,7 @@ enum bkw_mmap_state { }; struct mmap_params { - int prot, mask, nr_cblocks, affinity; + int prot, mask, nr_cblocks, affinity, flush; struct auxtrace_mmap_params auxtrace_mp; }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 5ef4939408f2..4432bfe039fd 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -317,10 +317,12 @@ static struct perf_evsel * __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name, struct perf_pmu *pmu, - struct list_head *config_terms, bool auto_merge_stats) + struct list_head *config_terms, bool auto_merge_stats, + const char *cpu_list) { struct perf_evsel *evsel; - struct cpu_map *cpus = pmu ? pmu->cpus : NULL; + struct cpu_map *cpus = pmu ? pmu->cpus : + cpu_list ? cpu_map__new(cpu_list) : NULL; event_attr_init(attr); @@ -348,7 +350,25 @@ static int add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name, struct list_head *config_terms) { - return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM; + return __add_event(list, idx, attr, name, NULL, config_terms, false, NULL) ? 0 : -ENOMEM; +} + +static int add_event_tool(struct list_head *list, int *idx, + enum perf_tool_event tool_event) +{ + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_DUMMY, + }; + + evsel = __add_event(list, idx, &attr, NULL, NULL, NULL, false, "0"); + if (!evsel) + return -ENOMEM; + evsel->tool_event = tool_event; + if (tool_event == PERF_TOOL_DURATION_TIME) + evsel->unit = strdup("ns"); + return 0; } static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size) @@ -1233,6 +1253,13 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, get_config_name(head_config), &config_terms); } +int parse_events_add_tool(struct parse_events_state *parse_state, + struct list_head *list, + enum perf_tool_event tool_event) +{ + return add_event_tool(list, &parse_state->idx, tool_event); +} + int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config, @@ -1267,7 +1294,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (!head_config) { attr.type = pmu->type; - evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats); + evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, + auto_merge_stats, NULL); if (evsel) { evsel->pmu_name = name; evsel->use_uncore_alias = use_uncore_alias; @@ -1295,7 +1323,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel = __add_event(list, &parse_state->idx, &attr, get_config_name(head_config), pmu, - &config_terms, auto_merge_stats); + &config_terms, auto_merge_stats, NULL); if (evsel) { evsel->unit = info.unit; evsel->scale = info.scale; @@ -2429,6 +2457,25 @@ out_enomem: return evt_num; } +static void print_tool_event(const char *name, const char *event_glob, + bool name_only) +{ + if (event_glob && !strglobmatch(name, event_glob)) + return; + if (name_only) + printf("%s ", name); + else + printf(" %-50s [%s]\n", name, "Tool event"); + +} + +void print_tool_events(const char *event_glob, bool name_only) +{ + print_tool_event("duration_time", event_glob, name_only); + if (pager_in_use()) + printf("\n"); +} + void print_symbol_events(const char *event_glob, unsigned type, struct event_symbol *syms, unsigned max, bool name_only) @@ -2512,6 +2559,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag, print_symbol_events(event_glob, PERF_TYPE_SOFTWARE, event_symbols_sw, PERF_COUNT_SW_MAX, name_only); + print_tool_events(event_glob, name_only); print_hwcache_events(event_glob, name_only); diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 5ed035cbcbb7..a052cd6ac63e 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -160,6 +160,10 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, struct list_head *head_config); +enum perf_tool_event; +int parse_events_add_tool(struct parse_events_state *parse_state, + struct list_head *list, + enum perf_tool_event tool_event); int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2, struct parse_events_error *error, @@ -200,6 +204,7 @@ extern struct event_symbol event_symbols_sw[]; void print_symbol_events(const char *event_glob, unsigned type, struct event_symbol *syms, unsigned max, bool name_only); +void print_tool_events(const char *event_glob, bool name_only); void print_tracepoint_events(const char *subsys_glob, const char *event_glob, bool name_only); int print_hwcache_events(const char *event_glob, bool name_only); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 7805c71aaae2..c54bfe88626c 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -15,6 +15,7 @@ #include "../perf.h" #include "parse-events.h" #include "parse-events-bison.h" +#include "evsel.h" char *parse_events_get_text(yyscan_t yyscanner); YYSTYPE *parse_events_get_lval(yyscan_t yyscanner); @@ -154,6 +155,14 @@ static int sym(yyscan_t scanner, int type, int config) return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW; } +static int tool(yyscan_t scanner, enum perf_tool_event event) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + + yylval->num = event; + return PE_VALUE_SYM_TOOL; +} + static int term(yyscan_t scanner, int type) { YYSTYPE *yylval = parse_events_get_lval(scanner); @@ -322,7 +331,7 @@ cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } -duration_time { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } +duration_time { return tool(yyscanner, PERF_TOOL_DURATION_TIME); } bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); } /* diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 44819bdb037d..6ad8d4914969 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -14,6 +14,7 @@ #include <linux/types.h> #include "util.h" #include "pmu.h" +#include "evsel.h" #include "debug.h" #include "parse-events.h" #include "parse-events-bison.h" @@ -45,6 +46,7 @@ static void inc_group_count(struct list_head *list, %token PE_START_EVENTS PE_START_TERMS %token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM +%token PE_VALUE_SYM_TOOL %token PE_EVENT_NAME %token PE_NAME %token PE_BPF_OBJECT PE_BPF_SOURCE @@ -58,6 +60,7 @@ static void inc_group_count(struct list_head *list, %type <num> PE_VALUE %type <num> PE_VALUE_SYM_HW %type <num> PE_VALUE_SYM_SW +%type <num> PE_VALUE_SYM_TOOL %type <num> PE_RAW %type <num> PE_TERM %type <str> PE_NAME @@ -321,6 +324,15 @@ value_sym sep_slash_slash_dc ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL)); $$ = list; } +| +PE_VALUE_SYM_TOOL sep_slash_slash_dc +{ + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_tool(_parse_state, list, $1)); + $$ = list; +} event_legacy_cache: PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index dda0ac978b1e..6aa7e2352e16 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -342,7 +342,7 @@ static bool is_tracepoint(struct pyrf_event *pevent) static PyObject* tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field) { - struct tep_handle *pevent = field->event->pevent; + struct tep_handle *pevent = field->event->tep; void *data = pe->sample.raw_data; PyObject *ret = NULL; unsigned long long val; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 5f06378a482b..61aa7f3df915 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -372,7 +372,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, ns = nsecs - s * NSEC_PER_SEC; scripting_context->event_data = data; - scripting_context->pevent = evsel->tp_format->pevent; + scripting_context->pevent = evsel->tp_format->tep; ENTER; SAVETMPS; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 09604c6508f0..22f52b669871 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -837,7 +837,7 @@ static void python_process_tracepoint(struct perf_sample *sample, ns = nsecs - s * NSEC_PER_SEC; scripting_context->event_data = data; - scripting_context->pevent = evsel->tp_format->pevent; + scripting_context->pevent = evsel->tp_format->tep; context = _PyCapsule_New(scripting_context, NULL, NULL); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 6d043c78f3c2..3324f23c7efc 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -18,11 +18,6 @@ #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" -static bool is_duration_time(struct perf_evsel *evsel) -{ - return !strcmp(evsel->name, "duration_time"); -} - static void print_running(struct perf_stat_config *config, u64 run, u64 ena) { @@ -628,9 +623,6 @@ static void print_aggr(struct perf_stat_config *config, ad.id = id = config->aggr_map->map[s]; first = true; evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; - ad.val = ad.ena = ad.run = 0; ad.nr = 0; if (!collect_data(config, counter, aggr_cb, &ad)) @@ -848,8 +840,6 @@ static void print_no_aggr_metric(struct perf_stat_config *config, if (prefix) fputs(prefix, config->output); evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; if (first) { aggr_printout(config, counter, cpu, 0); first = false; @@ -906,8 +896,6 @@ static void print_metric_headers(struct perf_stat_config *config, /* Print metrics headers only */ evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; os.evsel = counter; out.ctx = &os; out.print_metric = print_metric_header; @@ -1136,15 +1124,11 @@ perf_evlist__print_counters(struct perf_evlist *evlist, break; case AGGR_THREAD: evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; print_aggr_thread(config, _target, counter, prefix); } break; case AGGR_GLOBAL: evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; print_counter_aggr(config, counter, prefix); } if (metric_only) @@ -1155,8 +1139,6 @@ perf_evlist__print_counters(struct perf_evlist *evlist, print_no_aggr_metric(config, evlist, prefix); else { evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; print_counter(config, counter, prefix); } } diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index ad74be1f0e42..863955e4094e 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -111,7 +111,7 @@ raw_field_value(struct tep_event *event, const char *name, void *data) unsigned long long read_size(struct tep_event *event, void *ptr, int size) { - return tep_read_number(event->pevent, ptr, size); + return tep_read_number(event->tep, ptr, size); } void event_format__fprintf(struct tep_event *event, diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index efe2f58cff4e..48d53d8e3e16 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -442,7 +442,7 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) tep_set_flag(pevent, TEP_NSEC_OUTPUT); tep_set_file_bigendian(pevent, file_bigendian); - tep_set_host_bigendian(pevent, host_bigendian); + tep_set_local_bigendian(pevent, host_bigendian); if (do_read(buf, 1) < 0) goto out; diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c index cbe0dd758e3a..01b9d89bf5bf 100644 --- a/tools/perf/util/trace-event.c +++ b/tools/perf/util/trace-event.c @@ -40,7 +40,7 @@ int trace_event__init(struct trace_event *t) static int trace_event__init2(void) { - int be = tep_host_bigendian(); + int be = tep_is_bigendian(); struct tep_handle *pevent; if (trace_event__init(&tevent)) @@ -49,7 +49,7 @@ static int trace_event__init2(void) pevent = tevent.pevent; tep_set_flag(pevent, TEP_NSEC_OUTPUT); tep_set_file_bigendian(pevent, be); - tep_set_host_bigendian(pevent, be); + tep_set_local_bigendian(pevent, be); tevent_initialized = true; return 0; } |