summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorClement Courbet <courbet@google.com>2018-02-06 15:38:34 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-02-06 18:32:44 -0800
commit0ade34c37012ea5c516d9aa4d19a56e9f40a55ed (patch)
treee231c127d4a43927f49cf1a9323f9a52c81682ea /include
parent15ff67bf85c6c02ab7d850deea0199516e8f16a0 (diff)
downloadlinux-0ade34c37012ea5c516d9aa4d19a56e9f40a55ed.tar.bz2
lib: optimize cpumask_next_and()
We've measured that we spend ~0.6% of sys cpu time in cpumask_next_and(). It's essentially a joined iteration in search for a non-zero bit, which is currently implemented as a lookup join (find a nonzero bit on the lhs, lookup the rhs to see if it's set there). Implement a direct join (find a nonzero bit on the incrementally built join). Also add generic bitmap benchmarks in the new `test_find_bit` module for new function (see `find_next_and_bit` in [2] and [3] below). For cpumask_next_and, direct benchmarking shows that it's 1.17x to 14x faster with a geometric mean of 2.1 on 32 CPUs [1]. No impact on memory usage. Note that on Arm, the new pure-C implementation still outperforms the old one that uses a mix of C and asm (`find_next_bit`) [3]. [1] Approximate benchmark code: ``` unsigned long src1p[nr_cpumask_longs] = {pattern1}; unsigned long src2p[nr_cpumask_longs] = {pattern2}; for (/*a bunch of repetitions*/) { for (int n = -1; n <= nr_cpu_ids; ++n) { asm volatile("" : "+rm"(src1p)); // prevent any optimization asm volatile("" : "+rm"(src2p)); unsigned long result = cpumask_next_and(n, src1p, src2p); asm volatile("" : "+rm"(result)); } } ``` Results: pattern1 pattern2 time_before/time_after 0x0000ffff 0x0000ffff 1.65 0x0000ffff 0x00005555 2.24 0x0000ffff 0x00001111 2.94 0x0000ffff 0x00000000 14.0 0x00005555 0x0000ffff 1.67 0x00005555 0x00005555 1.71 0x00005555 0x00001111 1.90 0x00005555 0x00000000 6.58 0x00001111 0x0000ffff 1.46 0x00001111 0x00005555 1.49 0x00001111 0x00001111 1.45 0x00001111 0x00000000 3.10 0x00000000 0x0000ffff 1.18 0x00000000 0x00005555 1.18 0x00000000 0x00001111 1.17 0x00000000 0x00000000 1.25 ----------------------------- geo.mean 2.06 [2] test_find_next_bit, X86 (skylake) [ 3913.477422] Start testing find_bit() with random-filled bitmap [ 3913.477847] find_next_bit: 160868 cycles, 16484 iterations [ 3913.477933] find_next_zero_bit: 169542 cycles, 16285 iterations [ 3913.478036] find_last_bit: 201638 cycles, 16483 iterations [ 3913.480214] find_first_bit: 4353244 cycles, 16484 iterations [ 3913.480216] Start testing find_next_and_bit() with random-filled bitmap [ 3913.481074] find_next_and_bit: 89604 cycles, 8216 iterations [ 3913.481075] Start testing find_bit() with sparse bitmap [ 3913.481078] find_next_bit: 2536 cycles, 66 iterations [ 3913.481252] find_next_zero_bit: 344404 cycles, 32703 iterations [ 3913.481255] find_last_bit: 2006 cycles, 66 iterations [ 3913.481265] find_first_bit: 17488 cycles, 66 iterations [ 3913.481266] Start testing find_next_and_bit() with sparse bitmap [ 3913.481272] find_next_and_bit: 764 cycles, 1 iterations [3] test_find_next_bit, arm (v7 odroid XU3). [ 267.206928] Start testing find_bit() with random-filled bitmap [ 267.214752] find_next_bit: 4474 cycles, 16419 iterations [ 267.221850] find_next_zero_bit: 5976 cycles, 16350 iterations [ 267.229294] find_last_bit: 4209 cycles, 16419 iterations [ 267.279131] find_first_bit: 1032991 cycles, 16420 iterations [ 267.286265] Start testing find_next_and_bit() with random-filled bitmap [ 267.302386] find_next_and_bit: 2290 cycles, 8140 iterations [ 267.309422] Start testing find_bit() with sparse bitmap [ 267.316054] find_next_bit: 191 cycles, 66 iterations [ 267.322726] find_next_zero_bit: 8758 cycles, 32703 iterations [ 267.329803] find_last_bit: 84 cycles, 66 iterations [ 267.336169] find_first_bit: 4118 cycles, 66 iterations [ 267.342627] Start testing find_next_and_bit() with sparse bitmap [ 267.356919] find_next_and_bit: 91 cycles, 1 iterations [courbet@google.com: v6] Link: http://lkml.kernel.org/r/20171129095715.23430-1-courbet@google.com [geert@linux-m68k.org: m68k/bitops: always include <asm-generic/bitops/find.h>] Link: http://lkml.kernel.org/r/1512556816-28627-1-git-send-email-geert@linux-m68k.org Link: http://lkml.kernel.org/r/20171128131334.23491-1-courbet@google.com Signed-off-by: Clement Courbet <courbet@google.com> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Yury Norov <ynorov@caviumnetworks.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include')
-rw-r--r--include/asm-generic/bitops/find.h20
-rw-r--r--include/linux/bitmap.h6
2 files changed, 25 insertions, 1 deletions
diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h
index 1ba611e16fa0..8a1ee10014de 100644
--- a/include/asm-generic/bitops/find.h
+++ b/include/asm-generic/bitops/find.h
@@ -16,6 +16,22 @@ extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
size, unsigned long offset);
#endif
+#ifndef find_next_and_bit
+/**
+ * find_next_and_bit - find the next set bit in both memory regions
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the next set bit
+ * If no bits are set, returns @size.
+ */
+extern unsigned long find_next_and_bit(const unsigned long *addr1,
+ const unsigned long *addr2, unsigned long size,
+ unsigned long offset);
+#endif
+
#ifndef find_next_zero_bit
/**
* find_next_zero_bit - find the next cleared bit in a memory region
@@ -55,8 +71,12 @@ extern unsigned long find_first_zero_bit(const unsigned long *addr,
unsigned long size);
#else /* CONFIG_GENERIC_FIND_FIRST_BIT */
+#ifndef find_first_bit
#define find_first_bit(addr, size) find_next_bit((addr), (size), 0)
+#endif
+#ifndef find_first_zero_bit
#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0)
+#endif
#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index d9bf699e0e7a..5f11fbdc27f8 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -88,8 +88,12 @@
* test_and_change_bit(bit, addr) Change bit and return old value
* find_first_zero_bit(addr, nbits) Position first zero bit in *addr
* find_first_bit(addr, nbits) Position first set bit in *addr
- * find_next_zero_bit(addr, nbits, bit) Position next zero bit in *addr >= bit
+ * find_next_zero_bit(addr, nbits, bit)
+ * Position next zero bit in *addr >= bit
* find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit
+ * find_next_and_bit(addr1, addr2, nbits, bit)
+ * Same as find_next_bit, but in
+ * (*addr1 & *addr2)
*
*/