diff options
author | Andi Kleen <ak@linux.intel.com> | 2018-01-18 04:44:03 -0800 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2018-01-25 06:36:36 -0300 |
commit | 97d00f2d10ddd6b3ca89641d4a2fe6922a535c3f (patch) | |
tree | b6bc488809e30b21ca3edc6caabeff26539a4a4d /tools | |
parent | b3ab8adc8b5a72c2cc60ea936a870143a9b8c100 (diff) | |
download | linux-97d00f2d10ddd6b3ca89641d4a2fe6922a535c3f.tar.bz2 |
perf vendor events intel: Update BroadwellX events to V13
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Link: https://lkml.kernel.org/r/20180118234518.GA27753@tassilo.jf.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools')
7 files changed, 1026 insertions, 969 deletions
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json index d1d043829b95..bf0c51272068 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json @@ -11,11 +11,28 @@ }, { "EventCode": "0x24", - "UMask": "0x41", - "BriefDescription": "Demand Data Read requests that hit L2 cache", + "UMask": "0x22", + "BriefDescription": "RFO requests that miss 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.", + "EventName": "L2_RQSTS.RFO_MISS", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x24", + "BriefDescription": "L2 cache misses when fetching instructions.", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x27", + "BriefDescription": "Demand requests that miss L2 cache.", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -31,6 +48,43 @@ }, { "EventCode": "0x24", + "UMask": "0x3f", + "BriefDescription": "All requests that miss L2 cache.", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.MISS", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x41", + "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.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x42", + "BriefDescription": "RFO requests that hit L2 cache.", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.RFO_HIT", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x44", + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", "UMask": "0x50", "BriefDescription": "L2 prefetch requests that hit L2 cache", "Counter": "0,1,2,3", @@ -71,6 +125,15 @@ }, { "EventCode": "0x24", + "UMask": "0xe7", + "BriefDescription": "Demand requests to L2 cache.", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", "UMask": "0xf8", "BriefDescription": "Requests from L2 hardware prefetchers", "Counter": "0,1,2,3", @@ -80,6 +143,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x24", + "UMask": "0xff", + "BriefDescription": "All L2 requests.", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.REFERENCES", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x27", "UMask": "0x50", "BriefDescription": "Not rejected writebacks that hit L2 cache", @@ -131,6 +203,27 @@ "CounterHTOff": "2" }, { + "EventCode": "0x48", + "UMask": "0x1", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "Counter": "2", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "AnyThread": "1", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "2" + }, + { + "EventCode": "0x48", + "UMask": "0x2", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "Counter": "0,1,2,3", + "EventName": "L1D_PEND_MISS.FB_FULL", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x51", "UMask": "0x1", "BriefDescription": "L1D data line replacements", @@ -153,12 +246,35 @@ }, { "EventCode": "0x60", + "UMask": "0x1", + "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.CYCLES_WITH_DEMAND_DATA_RD", + "CounterMask": "1", + "Errata": "BDM76", + "PublicDescription": "This event 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 with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "CounterMask": "6", + "Errata": "BDM76", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", "UMask": "0x2", "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle", "Counter": "0,1,2,3", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", "Errata": "BDM76", - "PublicDescription": "This event counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The \"Offcore outstanding\" state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "This event counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The Offcore outstanding state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -175,24 +291,24 @@ }, { "EventCode": "0x60", - "UMask": "0x8", - "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "UMask": "0x4", + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "CounterMask": "1", "Errata": "BDM76", - "PublicDescription": "This event 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.", + "PublicDescription": "This event counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The Offcore outstanding state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "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", + "UMask": "0x8", + "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_DEMAND_DATA_RD", - "CounterMask": "1", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", "Errata": "BDM76", - "PublicDescription": "This event 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).", + "PublicDescription": "This event 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" }, @@ -209,18 +325,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x60", - "UMask": "0x4", - "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "CounterMask": "1", - "Errata": "BDM76", - "PublicDescription": "This event counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The \"Offcore outstanding\" state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0x63", "UMask": "0x2", "BriefDescription": "Cycles when L1D is locked", @@ -266,7 +370,7 @@ "BriefDescription": "Demand and prefetch data reads", "Counter": "0,1,2,3", "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", - "PublicDescription": "This event counts the demand and prefetch data reads. All Core Data Reads include cacheable \"Demands\" and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "PublicDescription": "This event counts the demand and prefetch data reads. All Core Data Reads include cacheable Demands and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -281,26 +385,35 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { "EventCode": "0xD0", "UMask": "0x11", - "BriefDescription": "Retired load uops that miss the STLB.", + "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "This is a non-precise version (that is, does not use 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 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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x12", - "BriefDescription": "Retired store uops that miss the STLB.", + "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that 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.", + "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.", "SampleAfterValue": "100003", "L1_Hit_Indication": "1", "CounterHTOff": "0,1,2,3" @@ -308,37 +421,37 @@ { "EventCode": "0xD0", "UMask": "0x21", - "BriefDescription": "Retired load uops with locked access.", + "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "Errata": "BDM35", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts load uops with locked access retired to the architected path.", + "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.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x41", - "BriefDescription": "Retired load uops that split across a cacheline boundary.", + "BriefDescription": "Retired load uops that split across a cacheline boundary.(Precise Event - PEBS)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", - "PublicDescription": "This is a non-precise version (that is, does not use 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).", + "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" }, { "EventCode": "0xD0", "UMask": "0x42", - "BriefDescription": "Retired store uops that split across a cacheline boundary.", + "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", - "PublicDescription": "This is a non-precise version (that is, does not use 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).", + "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" @@ -346,24 +459,24 @@ { "EventCode": "0xD0", "UMask": "0x81", - "BriefDescription": "All retired load uops.", + "BriefDescription": "All retired load uops. (Precise Event - PEBS)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "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.", + "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.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x82", - "BriefDescription": "All retired store uops.", + "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "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.", + "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.", "SampleAfterValue": "2000003", "L1_Hit_Indication": "1", "CounterHTOff": "0,1,2,3" @@ -371,69 +484,69 @@ { "EventCode": "0xD1", "UMask": "0x1", - "BriefDescription": "Retired load uops with L1 cache hits as data sources.", + "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that 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.", + "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.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x2", - "BriefDescription": "Retired load uops with L2 cache hits as data sources.", + "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "Errata": "BDM35", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x4", - "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.", + "BriefDescription": "Hit in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", "Errata": "BDM100", - "PublicDescription": "This is a non-precise version (that is, does not use 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 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.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x8", - "BriefDescription": "Retired load uops misses in L1 cache as data sources.", + "BriefDescription": "Retired load uops misses in L1 cache as data sources. Uses PEBS.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", - "PublicDescription": "This is a non-precise version (that is, does not use 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 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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x10", - "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.", + "BriefDescription": "Retired load uops with L2 cache misses as data sources. Uses PEBS.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", - "PublicDescription": "This is a non-precise version (that is, does not use 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 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.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x20", - "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", + "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS).", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -445,84 +558,83 @@ { "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.", + "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)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", - "PublicDescription": "This is a non-precise version (that is, does not use 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 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.", "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.", + "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS)", "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 non-precise version (that is, does not use 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 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.", "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.", + "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS)", "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 non-precise version (that is, does not use 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 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.", "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. (Precise Event - PEBS)", "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 non-precise version (that is, does not use 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 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).", "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.", + "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required. (Precise Event - PEBS)", "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 non-precise version (that is, does not use 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 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.", "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": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI).", + "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.", "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)", + "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -534,7 +646,7 @@ { "EventCode": "0xD3", "UMask": "0x10", - "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM", + "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -546,7 +658,7 @@ { "EventCode": "0xD3", "UMask": "0x20", - "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache", + "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -695,119 +807,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x24", - "UMask": "0x42", - "BriefDescription": "RFO requests that hit L2 cache.", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.RFO_HIT", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0x22", - "BriefDescription": "RFO requests that miss L2 cache.", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.RFO_MISS", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0x44", - "BriefDescription": "L2 cache hits when fetching instructions, code reads.", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.CODE_RD_HIT", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0x24", - "BriefDescription": "L2 cache misses when fetching instructions.", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.CODE_RD_MISS", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0x27", - "BriefDescription": "Demand requests that miss L2 cache.", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0xe7", - "BriefDescription": "Demand requests to L2 cache.", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0x3f", - "BriefDescription": "All requests that miss L2 cache.", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.MISS", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0xff", - "BriefDescription": "All L2 requests.", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.REFERENCES", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0x60", - "UMask": "0x1", - "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", - "CounterMask": "6", - "Errata": "BDM76", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x48", - "UMask": "0x1", - "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", - "Counter": "2", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", - "AnyThread": "1", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "2" - }, - { - "EventCode": "0x48", - "UMask": "0x2", - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", - "Counter": "0,1,2,3", - "EventName": "L1D_PEND_MISS.FB_FULL", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", @@ -816,6 +815,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -828,6 +828,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -840,6 +841,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -852,6 +854,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -864,6 +867,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -876,6 +880,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -888,6 +893,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -900,6 +906,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -912,6 +919,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -924,6 +932,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -936,6 +945,20 @@ "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.", + "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", + "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.", "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 4ae1ea24f22f..d7b9d9c9c518 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json @@ -6,7 +6,7 @@ "Counter": "0,1,2,3", "EventName": "OTHER_ASSISTS.AVX_TO_SSE", "Errata": "BDM30", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.", + "PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -17,7 +17,7 @@ "Counter": "0,1,2,3", "EventName": "OTHER_ASSISTS.SSE_TO_AVX", "Errata": "BDM30", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.", + "PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -25,7 +25,6 @@ "EventCode": "0xC7", "UMask": "0x1", "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "PEBS": "1", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "SampleAfterValue": "2000003", @@ -35,7 +34,6 @@ "EventCode": "0xC7", "UMask": "0x2", "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "PEBS": "1", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "SampleAfterValue": "2000003", @@ -43,9 +41,17 @@ }, { "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.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", - "PEBS": "1", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", "SampleAfterValue": "2000003", @@ -55,7 +61,6 @@ "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.", - "PEBS": "1", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", "SampleAfterValue": "2000003", @@ -65,19 +70,54 @@ "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.", - "PEBS": "1", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { + "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. ?.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.DOUBLE", + "SampleAfterValue": "2000006", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "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. ?.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.SINGLE", + "SampleAfterValue": "2000005", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.PACKED", + "SampleAfterValue": "2000004", + "CounterHTOff": "0,1,2,3" + }, + { "EventCode": "0xCA", "UMask": "0x2", "BriefDescription": "Number of X87 assists due to output value.", "Counter": "0,1,2,3", "EventName": "FP_ASSIST.X87_OUTPUT", - "PublicDescription": "This is a non-precise version (that is, does not use 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.", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -87,7 +127,7 @@ "BriefDescription": "Number of X87 assists due to input value.", "Counter": "0,1,2,3", "EventName": "FP_ASSIST.X87_INPUT", - "PublicDescription": "This is a non-precise version (that is, does not use 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.", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -97,7 +137,7 @@ "BriefDescription": "Number of SIMD FP assists due to Output values", "Counter": "0,1,2,3", "EventName": "FP_ASSIST.SIMD_OUTPUT", - "PublicDescription": "This is a non-precise version (that is, does not use 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.", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -107,7 +147,7 @@ "BriefDescription": "Number of SIMD FP assists due to input values", "Counter": "0,1,2,3", "EventName": "FP_ASSIST.SIMD_INPUT", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that 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.", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -121,51 +161,5 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" - }, - { - "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.", - "PEBS": "1", - "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" - }, - { - "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.", - "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.SCALAR", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" - }, - { - "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.", - "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.PACKED", - "SampleAfterValue": "2000004", - "CounterHTOff": "0,1,2,3" - }, - { - "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. ?.", - "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.SINGLE", - "SampleAfterValue": "2000005", - "CounterHTOff": "0,1,2,3" - }, - { - "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. ?.", - "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.DOUBLE", - "SampleAfterValue": "2000006", - "CounterHTOff": "0,1,2,3" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json b/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json index 06bf0a40e568..72781e1e3362 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json @@ -15,80 +15,49 @@ "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "This event 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).", + "PublicDescription": "This event 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": "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": "This event 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": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "Counter": "0,1,2,3", - "EventName": "IDQ.MS_DSB_UOPS", - "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x79", - "UMask": "0x20", - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "Counter": "0,1,2,3", - "EventName": "IDQ.MS_MITE_UOPS", - "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x79", - "UMask": "0x30", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "UMask": "0x4", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_UOPS", - "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "EventName": "IDQ.MITE_CYCLES", + "CounterMask": "1", + "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", - "UMask": "0x30", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "UMask": "0x8", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_CYCLES", - "CounterMask": "1", - "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "This event 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": "0x4", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", + "UMask": "0x8", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", "Counter": "0,1,2,3", - "EventName": "IDQ.MITE_CYCLES", + "EventName": "IDQ.DSB_CYCLES", "CounterMask": "1", - "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ.", + "PublicDescription": "This event counts cycles during which uops are being 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": "0x8", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", + "UMask": "0x10", + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "EventName": "IDQ.DSB_CYCLES", - "CounterMask": "1", - "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.", + "EventName": "IDQ.MS_DSB_UOPS", + "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -99,7 +68,7 @@ "Counter": "0,1,2,3", "EventName": "IDQ.MS_DSB_CYCLES", "CounterMask": "1", - "PublicDescription": "This event counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.", + "PublicDescription": "This event counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -111,7 +80,7 @@ "Counter": "0,1,2,3", "EventName": "IDQ.MS_DSB_OCCUR", "CounterMask": "1", - "PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.", + "PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -122,7 +91,7 @@ "Counter": "0,1,2,3", "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", "CounterMask": "4", - "PublicDescription": "This event counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.", + "PublicDescription": "This event counts the number of cycles 4 uops were 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" }, @@ -133,7 +102,17 @@ "Counter": "0,1,2,3", "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", "CounterMask": "1", - "PublicDescription": "This event counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.", + "PublicDescription": "This event counts the number of cycles uops were 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": "0x20", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_MITE_UOPS", + "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -144,7 +123,7 @@ "Counter": "0,1,2,3", "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", "CounterMask": "4", - "PublicDescription": "This event counts the number of cycles 4 uops were 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).", + "PublicDescription": "This event counts the number of cycles 4 uops were 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" }, @@ -155,7 +134,39 @@ "Counter": "0,1,2,3", "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", "CounterMask": "1", - "PublicDescription": "This event counts the number of cycles uops were 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).", + "PublicDescription": "This event counts the number of cycles uops were 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": "0x30", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x30", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_CYCLES", + "CounterMask": "1", + "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "SampleAfterValue": "2000003", + "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.", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_SWITCHES", + "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -165,7 +176,7 @@ "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", "EventName": "IDQ.MITE_ALL_UOPS", - "PublicDescription": "This event 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).", + "PublicDescription": "This event 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" }, @@ -205,7 +216,7 @@ "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.CORE", - "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 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.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, @@ -268,18 +279,7 @@ "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", "Counter": "0,1,2,3", "EventName": "DSB2MITE_SWITCHES.PENALTY_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?2 cycles.", - "SampleAfterValue": "2000003", - "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.", - "Counter": "0,1,2,3", - "EventName": "IDQ.MS_SWITCHES", - "CounterMask": "1", + "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.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" } diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json index 1204ea8ff30d..d79a5cfea44b 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json @@ -95,7 +95,6 @@ "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", "Counter": "0,1,2,3", "EventName": "TX_EXEC.MISC1", - "PublicDescription": "Unfriendly TSX abort triggered by a flowmarker.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -171,11 +170,11 @@ { "EventCode": "0xc8", "UMask": "0x4", - "BriefDescription": "Number of times HLE abort was triggered", + "BriefDescription": "Number of times HLE abort was triggered (PEBS)", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "HLE_RETIRED.ABORTED", - "PublicDescription": "Number of times HLE abort was triggered.", + "PublicDescription": "Number of times HLE abort was triggered (PEBS).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -252,11 +251,11 @@ { "EventCode": "0xc9", "UMask": "0x4", - "BriefDescription": "Number of times RTM abort was triggered", + "BriefDescription": "Number of times RTM abort was triggered (PEBS)", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "RTM_RETIRED.ABORTED", - "PublicDescription": "Number of times RTM abort was triggered .", + "PublicDescription": "Number of times RTM abort was triggered (PEBS).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, @@ -439,6 +438,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -451,6 +451,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -463,6 +464,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -475,6 +477,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -487,6 +490,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -499,6 +503,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -511,6 +516,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -523,6 +529,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -535,6 +542,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -547,6 +555,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -559,6 +568,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -571,6 +581,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -583,6 +594,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -595,6 +607,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -607,6 +620,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -619,6 +633,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -631,6 +646,7 @@ "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -643,6 +659,20 @@ "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that 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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/other.json b/tools/perf/pmu-events/arch/x86/broadwellx/other.json index 718fcb1db2ee..4475249ea9da 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/other.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/other.json @@ -10,16 +10,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5C", - "UMask": "0x2", - "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3", - "Counter": "0,1,2,3", - "EventName": "CPL_CYCLES.RING123", - "PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EdgeDetect": "1", "EventCode": "0x5C", "UMask": "0x1", @@ -32,6 +22,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x5C", + "UMask": "0x2", + "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3", + "Counter": "0,1,2,3", + "EventName": "CPL_CYCLES.RING123", + "PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x63", "UMask": "0x1", "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock", diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json index 02b4e1035f2d..920c89da9111 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json @@ -3,31 +3,41 @@ "EventCode": "0x00", "UMask": "0x1", "BriefDescription": "Instructions retired from execution.", - "Counter": "Fixed counter 1", + "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", "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.", "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 1" + "CounterHTOff": "Fixed counter 0" }, { "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when the thread is not in halt state", - "Counter": "Fixed counter 2", + "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.THREAD", "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.", "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 2" + "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", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "Fixed counter 1" }, { "EventCode": "0x00", "UMask": "0x3", "BriefDescription": "Reference cycles when the core is not in halt state.", - "Counter": "Fixed counter 3", + "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", "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.", "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 3" + "CounterHTOff": "Fixed counter 2" }, { "EventCode": "0x03", @@ -60,22 +70,33 @@ }, { "EventCode": "0x0D", - "UMask": "0x8", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread", + "UMask": "0x3", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", "Counter": "0,1,2,3", - "EventName": "INT_MISC.RAT_STALL_CYCLES", - "PublicDescription": "This event counts the number of cycles during which Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the current thread. This also includes the cycles during which the Allocator is serving another thread.", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "CounterMask": "1", + "PublicDescription": "Cycles checkpoints in Resource Allocation Table (RAT) are recovering from JEClear or machine clear.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x0D", "UMask": "0x3", - "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...)", + "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).", "Counter": "0,1,2,3", - "EventName": "INT_MISC.RECOVERY_CYCLES", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "AnyThread": "1", "CounterMask": "1", - "PublicDescription": "Cycles checkpoints in Resource Allocation Table (RAT) are recovering from JEClear or machine clear.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0D", + "UMask": "0x8", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread", + "Counter": "0,1,2,3", + "EventName": "INT_MISC.RAT_STALL_CYCLES", + "PublicDescription": "This event counts the number of cycles during which Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the current thread. This also includes the cycles during which the Allocator is serving another thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -90,6 +111,18 @@ "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", + "Counter": "0,1,2,3", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "CounterMask": "1", + "PublicDescription": "This event 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" + }, + { "EventCode": "0x0E", "UMask": "0x10", "BriefDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive; added by GSR u-arch.", @@ -118,18 +151,6 @@ "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", - "Counter": "0,1,2,3", - "EventName": "UOPS_ISSUED.STALL_CYCLES", - "CounterMask": "1", - "PublicDescription": "This event 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" - }, - { "EventCode": "0x14", "UMask": "0x1", "BriefDescription": "Cycles when divider is busy executing divide operations", @@ -141,6 +162,26 @@ }, { "EventCode": "0x3C", + "UMask": "0x0", + "BriefDescription": "Thread cycles when thread is not in halt state", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "This is an architectural event that 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. For this reason, this event may have a changing ratio with regards to wall clock time.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x0", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", "UMask": "0x1", "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", "Counter": "0,1,2,3", @@ -150,6 +191,36 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x3C", + "UMask": "0x1", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x1", + "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x1", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x3c", "UMask": "0x2", "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", @@ -159,6 +230,15 @@ "CounterHTOff": "0,1,2,3" }, { + "EventCode": "0x3C", + "UMask": "0x2", + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x4c", "UMask": "0x1", "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch", @@ -225,6 +305,18 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EdgeDetect": "1", + "Invert": "1", + "EventCode": "0x5E", + "UMask": "0x1", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", + "Counter": "0,1,2,3", + "EventName": "RS_EVENTS.EMPTY_END", + "CounterMask": "1", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x87", "UMask": "0x1", "BriefDescription": "Stalls caused by changing prefix length of the instruction.", @@ -406,6 +498,15 @@ }, { "EventCode": "0x89", + "UMask": "0xa0", + "BriefDescription": "Taken speculative and retired mispredicted indirect calls.", + "Counter": "0,1,2,3", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x89", "UMask": "0xc1", "BriefDescription": "Speculative and retired mispredicted macro conditional branches", "Counter": "0,1,2,3", @@ -435,6 +536,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xA0", + "UMask": "0x3", + "BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports", + "Counter": "0,1,2,3", + "EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF", + "PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file. The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*. See the Broadwell Optimization Guide for more information.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { "EventCode": "0xA1", "UMask": "0x1", "BriefDescription": "Cycles per thread when uops are executed in port 0", @@ -446,6 +557,26 @@ }, { "EventCode": "0xA1", + "UMask": "0x1", + "BriefDescription": "Cycles per core when uops are exectuted in port 0.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x1", + "BriefDescription": "Cycles per thread when uops are executed in port 0", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_0", + "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 0.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", "UMask": "0x2", "BriefDescription": "Cycles per thread when uops are executed in port 1", "Counter": "0,1,2,3", @@ -456,6 +587,26 @@ }, { "EventCode": "0xA1", + "UMask": "0x2", + "BriefDescription": "Cycles per core when uops are exectuted in port 1.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x2", + "BriefDescription": "Cycles per thread when uops are executed in port 1", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_1", + "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 1.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", "UMask": "0x4", "BriefDescription": "Cycles per thread when uops are executed in port 2", "Counter": "0,1,2,3", @@ -466,6 +617,26 @@ }, { "EventCode": "0xA1", + "UMask": "0x4", + "BriefDescription": "Cycles per core when uops are dispatched to port 2.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x4", + "BriefDescription": "Cycles per thread when uops are executed in port 2", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_2", + "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 2.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", "UMask": "0x8", "BriefDescription": "Cycles per thread when uops are executed in port 3", "Counter": "0,1,2,3", @@ -476,6 +647,26 @@ }, { "EventCode": "0xA1", + "UMask": "0x8", + "BriefDescription": "Cycles per core when uops are dispatched to port 3.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x8", + "BriefDescription": "Cycles per thread when uops are executed in port 3", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_3", + "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 3.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", "UMask": "0x10", "BriefDescription": "Cycles per thread when uops are executed in port 4", "Counter": "0,1,2,3", @@ -486,6 +677,26 @@ }, { "EventCode": "0xA1", + "UMask": "0x10", + "BriefDescription": "Cycles per core when uops are exectuted in port 4.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x10", + "BriefDescription": "Cycles per thread when uops are executed in port 4", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_4", + "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 4.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", "UMask": "0x20", "BriefDescription": "Cycles per thread when uops are executed in port 5", "Counter": "0,1,2,3", @@ -496,6 +707,26 @@ }, { "EventCode": "0xA1", + "UMask": "0x20", + "BriefDescription": "Cycles per core when uops are exectuted in port 5.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x20", + "BriefDescription": "Cycles per thread when uops are executed in port 5", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_5", + "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 5.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", "UMask": "0x40", "BriefDescription": "Cycles per thread when uops are executed in port 6", "Counter": "0,1,2,3", @@ -506,6 +737,26 @@ }, { "EventCode": "0xA1", + "UMask": "0x40", + "BriefDescription": "Cycles per core when uops are exectuted in port 6.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x40", + "BriefDescription": "Cycles per thread when uops are executed in port 6", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_6", + "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 6.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", "UMask": "0x80", "BriefDescription": "Cycles per thread when uops are executed in port 7", "Counter": "0,1,2,3", @@ -515,6 +766,26 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xA1", + "UMask": "0x80", + "BriefDescription": "Cycles per core when uops are dispatched to port 7.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x80", + "BriefDescription": "Cycles per thread when uops are executed in port 7", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_7", + "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 7.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xA2", "UMask": "0x1", "BriefDescription": "Resource-related stall cycles", @@ -567,14 +838,13 @@ }, { "EventCode": "0xA3", - "UMask": "0x8", - "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", - "Counter": "2", - "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", - "CounterMask": "8", - "PublicDescription": "Counts number of cycles the CPU has at least one pending demand load request missing the L1 data cache.", + "UMask": "0x1", + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "CounterMask": "1", "SampleAfterValue": "2000003", - "CounterHTOff": "2" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA3", @@ -589,8 +859,18 @@ }, { "EventCode": "0xA3", + "UMask": "0x2", + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "CounterMask": "2", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xA3", "UMask": "0x4", - "BriefDescription": "Total execution stalls", + "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.", "Counter": "0,1,2,3", "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE", "CounterMask": "4", @@ -600,6 +880,16 @@ }, { "EventCode": "0xA3", + "UMask": "0x4", + "BriefDescription": "Total execution stalls.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "CounterMask": "4", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", "UMask": "0x5", "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", "Counter": "0,1,2,3", @@ -611,6 +901,16 @@ }, { "EventCode": "0xA3", + "UMask": "0x5", + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "CounterMask": "5", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", "UMask": "0x6", "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", "Counter": "0,1,2,3", @@ -622,6 +922,37 @@ }, { "EventCode": "0xA3", + "UMask": "0x6", + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", + "CounterMask": "6", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x8", + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "Counter": "2", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", + "CounterMask": "8", + "PublicDescription": "Counts number of cycles the CPU has at least one pending demand load request missing the L1 data cache.", + "SampleAfterValue": "2000003", + "CounterHTOff": "2" + }, + { + "EventCode": "0xA3", + "UMask": "0x8", + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "Counter": "2", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "CounterMask": "8", + "SampleAfterValue": "2000003", + "CounterHTOff": "2" + }, + { + "EventCode": "0xA3", "UMask": "0xc", "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", "Counter": "2", @@ -632,12 +963,41 @@ "CounterHTOff": "2" }, { + "EventCode": "0xA3", + "UMask": "0xc", + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "Counter": "2", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "CounterMask": "12", + "SampleAfterValue": "2000003", + "CounterHTOff": "2" + }, + { "EventCode": "0xA8", "UMask": "0x1", "BriefDescription": "Number of Uops delivered by the LSD.", "Counter": "0,1,2,3", "EventName": "LSD.UOPS", - "PublicDescription": "Number of Uops delivered by the LSD. ", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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", + "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", + "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -652,6 +1012,58 @@ "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.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "CounterMask": "1", + "PublicDescription": "This event counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Cycles where at least 1 uop was executed per-thread.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "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", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Cycles where at least 3 uops were executed per-thread.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "CounterMask": "3", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Cycles where at least 4 uops were executed per-thread.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "CounterMask": "4", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { "EventCode": "0xB1", "UMask": "0x2", "BriefDescription": "Number of uops executed on the core.", @@ -662,35 +1074,63 @@ "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.", + "EventCode": "0xb1", + "UMask": "0x2", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", "CounterMask": "1", - "PublicDescription": "This event counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC0", - "UMask": "0x0", - "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "EventCode": "0xb1", + "UMask": "0x2", + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "INST_RETIRED.ANY_P", - "Errata": "BDM61", - "PublicDescription": "This event counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "CounterMask": "2", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC0", + "EventCode": "0xb1", "UMask": "0x2", - "BriefDescription": "FP operations retired. X87 FP operations that have no exceptions:", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "INST_RETIRED.X87", - "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.", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "CounterMask": "3", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xb1", + "UMask": "0x2", + "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_4", + "CounterMask": "4", + "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.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC0", + "UMask": "0x0", + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3", + "EventName": "INST_RETIRED.ANY_P", + "Errata": "BDM61", + "PublicDescription": "This event counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -707,6 +1147,16 @@ "CounterHTOff": "1" }, { + "EventCode": "0xC0", + "UMask": "0x2", + "BriefDescription": "FP operations retired. X87 FP operations that have no exceptions:", + "Counter": "0,1,2,3", + "EventName": "INST_RETIRED.X87", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xC1", "UMask": "0x40", "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", @@ -718,23 +1168,12 @@ { "EventCode": "0xC2", "UMask": "0x1", - "BriefDescription": "Actually retired uops.", + "BriefDescription": "Actually retired uops. (Precise Event - PEBS)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "UOPS_RETIRED.ALL", - "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" - }, - { - "EventCode": "0xC2", - "UMask": "0x2", - "BriefDescription": "Retirement slots used.", - "PEBS": "1", - "Counter": "0,1,2,3", - "EventName": "UOPS_RETIRED.RETIRE_SLOTS", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of retirement slots used.", + "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.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -746,7 +1185,7 @@ "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" }, @@ -763,6 +1202,17 @@ "CounterHTOff": "0,1,2,3" }, { + "EventCode": "0xC2", + "UMask": "0x2", + "BriefDescription": "Retirement slots used. (Precise Event - PEBS)", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xC3", "UMask": "0x1", "BriefDescription": "Cycles there was a Nuke. Account for both thread-specific and All Thread Nukes.", @@ -773,6 +1223,17 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EdgeDetect": "1", + "EventCode": "0xC3", + "UMask": "0x1", + "BriefDescription": "Number of machine clears (nukes) of any type.", + "Counter": "0,1,2,3", + "EventName": "MACHINE_CLEARS.COUNT", + "CounterMask": "1", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xC3", "UMask": "0x4", "BriefDescription": "Self-modifying code (SMC) detected.", @@ -794,44 +1255,67 @@ }, { "EventCode": "0xC4", + "UMask": "0x0", + "BriefDescription": "All (macro) branch instructions retired.", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "This event counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", "UMask": "0x1", - "BriefDescription": "Conditional branch instructions retired.", + "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS)", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.CONDITIONAL", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts conditional branch instructions retired.", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that 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.", + "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS)", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts both direct and indirect near call instructions retired.", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC4", - "UMask": "0x0", - "BriefDescription": "All (macro) branch instructions retired.", + "UMask": "0x2", + "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS)", + "PEBS": "1", "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "This event counts all (macro) branch instructions retired.", - "SampleAfterValue": "400009", + "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).", + "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC4", + "UMask": "0x4", + "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS)", + "PEBS": "2", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "Errata": "BDW98", + "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC4", "UMask": "0x8", - "BriefDescription": "Return instructions retired.", + "BriefDescription": "Return instructions retired. (Precise Event - PEBS)", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts return instructions retired.", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -841,18 +1325,18 @@ "BriefDescription": "Not taken branch instructions retired.", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NOT_TAKEN", - "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 event counts not taken branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC4", "UMask": "0x20", - "BriefDescription": "Taken branch instructions retired.", + "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS)", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts taken branch instructions retired.", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -863,34 +1347,11 @@ "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "Errata": "BDW98", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts far branch instructions retired.", + "PublicDescription": "This event counts far branch instructions retired.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC4", - "UMask": "0x4", - "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS)", - "PEBS": "2", - "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", - "Errata": "BDW98", - "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", - "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0xC5", - "UMask": "0x1", - "BriefDescription": "Mispredicted conditional branch instructions retired.", - "PEBS": "1", - "Counter": "0,1,2,3", - "EventName": "BR_MISP_RETIRED.CONDITIONAL", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted conditional branch instructions retired.", - "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0xC5", "UMask": "0x0", "BriefDescription": "All mispredicted macro branch instructions retired.", @@ -902,13 +1363,13 @@ }, { "EventCode": "0xC5", - "UMask": "0x8", - "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", + "UMask": "0x1", + "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS)", "PEBS": "1", "Counter": "0,1,2,3", - "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", - "SampleAfterValue": "100007", + "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.", + "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -923,164 +1384,36 @@ "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xCC", - "UMask": "0x20", - "BriefDescription": "Count cases of saving new LBR", - "Counter": "0,1,2,3", - "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", - "PublicDescription": "This event counts cases of saving new LBR records by hardware. This assumes proper enabling of LBRs and takes into account LBR filtering done by the LBR_SELECT register.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x3C", - "UMask": "0x0", - "BriefDescription": "Thread cycles when thread is not in halt state", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "This is an architectural event that 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. For this reason, this event may have a changing ratio with regards to wall clock time.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x89", - "UMask": "0xa0", - "BriefDescription": "Taken speculative and retired mispredicted indirect calls.", - "Counter": "0,1,2,3", - "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x1", - "BriefDescription": "Cycles per core when uops are exectuted in port 0.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x2", - "BriefDescription": "Cycles per core when uops are exectuted in port 1.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x4", - "BriefDescription": "Cycles per core when uops are dispatched to port 2.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", + "EventCode": "0xC5", "UMask": "0x8", - "BriefDescription": "Cycles per core when uops are dispatched to port 3.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x10", - "BriefDescription": "Cycles per core when uops are exectuted in port 4.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x20", - "BriefDescription": "Cycles per core when uops are exectuted in port 5.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x40", - "BriefDescription": "Cycles per core when uops are exectuted in port 6.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x80", - "BriefDescription": "Cycles per core when uops are dispatched to port 7.", + "BriefDescription": "This event counts the number of mispredicted ret instructions retired.(Precise Event)", + "PEBS": "1", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", + "EventName": "BR_MISP_RETIRED.RET", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that 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.", + "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).", "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.", + "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 1 uop was executed per-thread.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" - }, - { - "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", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 3 uops were executed per-thread.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", - "CounterMask": "3", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 4 uops were executed per-thread.", + "EventCode": "0xCC", + "UMask": "0x20", + "BriefDescription": "Count cases of saving new LBR", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", - "CounterMask": "4", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "PublicDescription": "This event counts cases of saving new LBR records by hardware. This assumes proper enabling of LBRs and takes into account LBR filtering done by the LBR_SELECT register.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xe6", @@ -1090,328 +1423,5 @@ "EventName": "BACLEARS.ANY", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA3", - "UMask": "0x8", - "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", - "Counter": "2", - "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", - "CounterMask": "8", - "SampleAfterValue": "2000003", - "CounterHTOff": "2" - }, - { - "EventCode": "0xA3", - "UMask": "0x1", - "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", - "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA3", - "UMask": "0x2", - "BriefDescription": "Cycles while memory subsystem has an outstanding load.", - "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", - "CounterMask": "2", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0xA3", - "UMask": "0x4", - "BriefDescription": "Total execution stalls.", - "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", - "CounterMask": "4", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA3", - "UMask": "0xc", - "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", - "Counter": "2", - "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", - "CounterMask": "12", - "SampleAfterValue": "2000003", - "CounterHTOff": "2" - }, - { - "EventCode": "0xA3", - "UMask": "0x5", - "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", - "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", - "CounterMask": "5", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA3", - "UMask": "0x6", - "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", - "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", - "CounterMask": "6", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EdgeDetect": "1", - "EventCode": "0xC3", - "UMask": "0x1", - "BriefDescription": "Number of machine clears (nukes) of any type.", - "Counter": "0,1,2,3", - "EventName": "MACHINE_CLEARS.COUNT", - "CounterMask": "1", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "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", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EdgeDetect": "1", - "Invert": "1", - "EventCode": "0x5E", - "UMask": "0x1", - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", - "Counter": "0,1,2,3", - "EventName": "RS_EVENTS.EMPTY_END", - "CounterMask": "1", - "SampleAfterValue": "200003", - "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", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x1", - "BriefDescription": "Cycles per thread when uops are executed in port 0", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_0", - "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 0.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x2", - "BriefDescription": "Cycles per thread when uops are executed in port 1", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_1", - "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 1.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x4", - "BriefDescription": "Cycles per thread when uops are executed in port 2", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_2", - "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 2.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x8", - "BriefDescription": "Cycles per thread when uops are executed in port 3", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_3", - "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 3.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x10", - "BriefDescription": "Cycles per thread when uops are executed in port 4", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_4", - "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 4.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x20", - "BriefDescription": "Cycles per thread when uops are executed in port 5", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_5", - "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 5.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x40", - "BriefDescription": "Cycles per thread when uops are executed in port 6", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_6", - "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 6.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x80", - "BriefDescription": "Cycles per thread when uops are executed in port 7", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_7", - "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 7.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA0", - "UMask": "0x3", - "BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports", - "Counter": "0,1,2,3", - "EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF", - "PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file. The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*. See the Broadwell Optimization Guide for more information.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0x00", - "UMask": "0x2", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "Counter": "Fixed counter 2", - "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 2" - }, - { - "EventCode": "0x3C", - "UMask": "0x0", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x3C", - "UMask": "0x1", - "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x0D", - "UMask": "0x3", - "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).", - "Counter": "0,1,2,3", - "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", - "AnyThread": "1", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "UMask": "0x2", - "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_GE_1", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "UMask": "0x2", - "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_2", - "CounterMask": "2", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "UMask": "0x2", - "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "CounterMask": "3", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "UMask": "0x2", - "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_4", - "CounterMask": "4", - "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.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x3C", - "UMask": "0x1", - "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK", - "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x3C", - "UMask": "0x1", - "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x3C", - "UMask": "0x2", - "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/virtual-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/virtual-memory.json index 5ce8b67ba076..7d79c707c6d1 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/virtual-memory.json @@ -45,6 +45,16 @@ }, { "EventCode": "0x08", + "UMask": "0xe", + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "Errata": "BDM69", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", "UMask": "0x10", "BriefDescription": "Cycles when PMH is busy with page walks", "Counter": "0,1,2,3", @@ -73,6 +83,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x08", + "UMask": "0x60", + "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x49", "UMask": "0x1", "BriefDescription": "Store misses in all DTLB levels that cause page walks", @@ -118,6 +137,16 @@ }, { "EventCode": "0x49", + "UMask": "0xe", + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "Errata": "BDM69", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", "UMask": "0x10", "BriefDescription": "Cycles when PMH is busy with page walks", "Counter": "0,1,2,3", @@ -146,6 +175,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x49", + "UMask": "0x60", + "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x4F", "UMask": "0x10", "BriefDescription": "Cycle count for an Extended Page table walk.", @@ -201,6 +239,16 @@ }, { "EventCode": "0x85", + "UMask": "0xe", + "BriefDescription": "Misses in all ITLB levels that cause completed page walks.", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "Errata": "BDM69", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", "UMask": "0x10", "BriefDescription": "Cycles when PMH is busy with page walks", "Counter": "0,1,2,3", @@ -229,6 +277,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x85", + "UMask": "0x60", + "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.STLB_HIT", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xAE", "UMask": "0x1", "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", @@ -250,60 +307,60 @@ }, { "EventCode": "0xBC", - "UMask": "0x21", - "BriefDescription": "Number of ITLB page walker hits in the L1+FB.", + "UMask": "0x12", + "BriefDescription": "Number of DTLB page walker hits in the L2.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.ITLB_L1", + "EventName": "PAGE_WALKER_LOADS.DTLB_L2", "Errata": "BDM69, BDM98", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x12", - "BriefDescription": "Number of DTLB page walker hits in the L2.", + "UMask": "0x14", + "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.DTLB_L2", + "EventName": "PAGE_WALKER_LOADS.DTLB_L3", "Errata": "BDM69, BDM98", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x22", - "BriefDescription": "Number of ITLB page walker hits in the L2.", + "UMask": "0x18", + "BriefDescription": "Number of DTLB page walker hits in Memory.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.ITLB_L2", + "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY", "Errata": "BDM69, BDM98", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x14", - "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.", + "UMask": "0x21", + "BriefDescription": "Number of ITLB page walker hits in the L1+FB.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.DTLB_L3", + "EventName": "PAGE_WALKER_LOADS.ITLB_L1", "Errata": "BDM69, BDM98", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x24", - "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.", + "UMask": "0x22", + "BriefDescription": "Number of ITLB page walker hits in the L2.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.ITLB_L3", + "EventName": "PAGE_WALKER_LOADS.ITLB_L2", "Errata": "BDM69, BDM98", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x18", - "BriefDescription": "Number of DTLB page walker hits in Memory.", + "UMask": "0x24", + "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY", + "EventName": "PAGE_WALKER_LOADS.ITLB_L3", "Errata": "BDM69, BDM98", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" @@ -327,62 +384,5 @@ "PublicDescription": "This event counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, and so on).", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x08", - "UMask": "0xe", - "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.", - "Counter": "0,1,2,3", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "Errata": "BDM69", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x08", - "UMask": "0x60", - "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.", - "Counter": "0,1,2,3", - "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x49", - "UMask": "0xe", - "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.", - "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "Errata": "BDM69", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x49", - "UMask": "0x60", - "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", - "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x85", - "UMask": "0xe", - "BriefDescription": "Misses in all ITLB levels that cause completed page walks.", - "Counter": "0,1,2,3", - "EventName": "ITLB_MISSES.WALK_COMPLETED", - "Errata": "BDM69", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x85", - "UMask": "0x60", - "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.", - "Counter": "0,1,2,3", - "EventName": "ITLB_MISSES.STLB_HIT", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" } ]
\ No newline at end of file |