From 7c43b0c1d499c790cdb5623d27fdcef544ddb566 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 29 Jul 2020 15:00:34 -0700 Subject: perf bench: Add benchmark of find_next_bit for_each_set_bit, or similar functions like for_each_cpu, may be hot within the kernel. If many bits were set then one could imagine on Intel a "bt" instruction with every bit may be faster than the function call and word length find_next_bit logic. Add a benchmark to measure this. This benchmark on AMD rome and Intel skylakex shows "bt" is not a good option except for very small bitmaps. Committer testing: # perf bench Usage: perf bench [] [] # List of all available benchmark collections: sched: Scheduler and IPC benchmarks syscall: System call benchmarks mem: Memory access benchmarks numa: NUMA scheduling and MM benchmarks futex: Futex stressing benchmarks epoll: Epoll stressing benchmarks internals: Perf-internals benchmarks all: All benchmarks # perf bench mem # List of available benchmarks for collection 'mem': memcpy: Benchmark for memcpy() functions memset: Benchmark for memset() functions find_bit: Benchmark for find_bit() functions all: Run all memory access benchmarks # perf bench mem find_bit # Running 'mem/find_bit' benchmark: 100000 operations 1 bits set of 1 bits Average for_each_set_bit took: 730.200 usec (+- 6.468 usec) Average test_bit loop took: 366.200 usec (+- 4.652 usec) 100000 operations 1 bits set of 2 bits Average for_each_set_bit took: 781.000 usec (+- 24.247 usec) Average test_bit loop took: 550.200 usec (+- 4.152 usec) 100000 operations 2 bits set of 2 bits Average for_each_set_bit took: 1113.400 usec (+- 112.340 usec) Average test_bit loop took: 1098.500 usec (+- 182.834 usec) 100000 operations 1 bits set of 4 bits Average for_each_set_bit took: 843.800 usec (+- 8.772 usec) Average test_bit loop took: 948.800 usec (+- 10.278 usec) 100000 operations 2 bits set of 4 bits Average for_each_set_bit took: 1185.800 usec (+- 114.345 usec) Average test_bit loop took: 1473.200 usec (+- 175.498 usec) 100000 operations 4 bits set of 4 bits Average for_each_set_bit took: 1769.667 usec (+- 233.177 usec) Average test_bit loop took: 1864.933 usec (+- 187.470 usec) 100000 operations 1 bits set of 8 bits Average for_each_set_bit took: 898.000 usec (+- 21.755 usec) Average test_bit loop took: 1768.400 usec (+- 23.672 usec) 100000 operations 2 bits set of 8 bits Average for_each_set_bit took: 1244.900 usec (+- 116.396 usec) Average test_bit loop took: 2201.800 usec (+- 145.398 usec) 100000 operations 4 bits set of 8 bits Average for_each_set_bit took: 1822.533 usec (+- 231.554 usec) Average test_bit loop took: 2569.467 usec (+- 168.453 usec) 100000 operations 8 bits set of 8 bits Average for_each_set_bit took: 2845.100 usec (+- 441.365 usec) Average test_bit loop took: 3023.300 usec (+- 219.575 usec) 100000 operations 1 bits set of 16 bits Average for_each_set_bit took: 923.400 usec (+- 17.560 usec) Average test_bit loop took: 3240.000 usec (+- 16.492 usec) 100000 operations 2 bits set of 16 bits Average for_each_set_bit took: 1264.300 usec (+- 114.034 usec) Average test_bit loop took: 3714.400 usec (+- 158.898 usec) 100000 operations 4 bits set of 16 bits Average for_each_set_bit took: 1817.867 usec (+- 222.199 usec) Average test_bit loop took: 4015.333 usec (+- 154.162 usec) 100000 operations 8 bits set of 16 bits Average for_each_set_bit took: 2826.350 usec (+- 433.457 usec) Average test_bit loop took: 4460.350 usec (+- 210.762 usec) 100000 operations 16 bits set of 16 bits Average for_each_set_bit took: 4615.600 usec (+- 809.350 usec) Average test_bit loop took: 5129.960 usec (+- 320.821 usec) 100000 operations 1 bits set of 32 bits Average for_each_set_bit took: 904.400 usec (+- 14.250 usec) Average test_bit loop took: 6194.000 usec (+- 29.254 usec) 100000 operations 2 bits set of 32 bits Average for_each_set_bit took: 1252.700 usec (+- 116.432 usec) Average test_bit loop took: 6652.400 usec (+- 154.352 usec) 100000 operations 4 bits set of 32 bits Average for_each_set_bit took: 1824.200 usec (+- 229.133 usec) Average test_bit loop took: 6961.733 usec (+- 154.682 usec) 100000 operations 8 bits set of 32 bits Average for_each_set_bit took: 2823.950 usec (+- 432.296 usec) Average test_bit loop took: 7351.900 usec (+- 193.626 usec) 100000 operations 16 bits set of 32 bits Average for_each_set_bit took: 4552.560 usec (+- 785.141 usec) Average test_bit loop took: 7998.360 usec (+- 305.629 usec) 100000 operations 32 bits set of 32 bits Average for_each_set_bit took: 7557.067 usec (+- 1407.702 usec) Average test_bit loop took: 9072.400 usec (+- 513.209 usec) 100000 operations 1 bits set of 64 bits Average for_each_set_bit took: 896.800 usec (+- 14.389 usec) Average test_bit loop took: 11927.200 usec (+- 68.862 usec) 100000 operations 2 bits set of 64 bits Average for_each_set_bit took: 1230.400 usec (+- 111.731 usec) Average test_bit loop took: 12478.600 usec (+- 189.382 usec) 100000 operations 4 bits set of 64 bits Average for_each_set_bit took: 1844.733 usec (+- 244.826 usec) Average test_bit loop took: 12911.467 usec (+- 206.246 usec) 100000 operations 8 bits set of 64 bits Average for_each_set_bit took: 2779.300 usec (+- 413.612 usec) Average test_bit loop took: 13372.650 usec (+- 239.623 usec) 100000 operations 16 bits set of 64 bits Average for_each_set_bit took: 4423.920 usec (+- 748.240 usec) Average test_bit loop took: 13995.800 usec (+- 318.427 usec) 100000 operations 32 bits set of 64 bits Average for_each_set_bit took: 7580.600 usec (+- 1462.407 usec) Average test_bit loop took: 15063.067 usec (+- 516.477 usec) 100000 operations 64 bits set of 64 bits Average for_each_set_bit took: 13391.514 usec (+- 2765.371 usec) Average test_bit loop took: 16974.914 usec (+- 916.936 usec) 100000 operations 1 bits set of 128 bits Average for_each_set_bit took: 1153.800 usec (+- 124.245 usec) Average test_bit loop took: 26959.000 usec (+- 714.047 usec) 100000 operations 2 bits set of 128 bits Average for_each_set_bit took: 1445.200 usec (+- 113.587 usec) Average test_bit loop took: 25798.800 usec (+- 512.908 usec) 100000 operations 4 bits set of 128 bits Average for_each_set_bit took: 1990.933 usec (+- 219.362 usec) Average test_bit loop took: 25589.400 usec (+- 348.288 usec) 100000 operations 8 bits set of 128 bits Average for_each_set_bit took: 2963.000 usec (+- 419.487 usec) Average test_bit loop took: 25690.050 usec (+- 262.025 usec) 100000 operations 16 bits set of 128 bits Average for_each_set_bit took: 4585.200 usec (+- 741.734 usec) Average test_bit loop took: 26125.040 usec (+- 274.127 usec) 100000 operations 32 bits set of 128 bits Average for_each_set_bit took: 7626.200 usec (+- 1404.950 usec) Average test_bit loop took: 27038.867 usec (+- 442.554 usec) 100000 operations 64 bits set of 128 bits Average for_each_set_bit took: 13343.371 usec (+- 2686.460 usec) Average test_bit loop took: 28936.543 usec (+- 883.257 usec) 100000 operations 128 bits set of 128 bits Average for_each_set_bit took: 23442.950 usec (+- 4880.541 usec) Average test_bit loop took: 32484.125 usec (+- 1691.931 usec) 100000 operations 1 bits set of 256 bits Average for_each_set_bit took: 1183.000 usec (+- 32.073 usec) Average test_bit loop took: 50114.600 usec (+- 198.880 usec) 100000 operations 2 bits set of 256 bits Average for_each_set_bit took: 1550.000 usec (+- 124.550 usec) Average test_bit loop took: 50334.200 usec (+- 128.425 usec) 100000 operations 4 bits set of 256 bits Average for_each_set_bit took: 2164.333 usec (+- 246.359 usec) Average test_bit loop took: 49959.867 usec (+- 188.035 usec) 100000 operations 8 bits set of 256 bits Average for_each_set_bit took: 3211.200 usec (+- 454.829 usec) Average test_bit loop took: 50140.850 usec (+- 176.046 usec) 100000 operations 16 bits set of 256 bits Average for_each_set_bit took: 5181.640 usec (+- 882.726 usec) Average test_bit loop took: 51003.160 usec (+- 419.601 usec) 100000 operations 32 bits set of 256 bits Average for_each_set_bit took: 8369.333 usec (+- 1513.150 usec) Average test_bit loop took: 52096.700 usec (+- 573.022 usec) 100000 operations 64 bits set of 256 bits Average for_each_set_bit took: 13866.857 usec (+- 2649.393 usec) Average test_bit loop took: 53989.600 usec (+- 938.808 usec) 100000 operations 128 bits set of 256 bits Average for_each_set_bit took: 23588.350 usec (+- 4724.222 usec) Average test_bit loop took: 57300.625 usec (+- 1625.962 usec) 100000 operations 256 bits set of 256 bits Average for_each_set_bit took: 42752.200 usec (+- 9202.084 usec) Average test_bit loop took: 64426.933 usec (+- 3402.326 usec) 100000 operations 1 bits set of 512 bits Average for_each_set_bit took: 1632.000 usec (+- 229.954 usec) Average test_bit loop took: 98090.000 usec (+- 1120.435 usec) 100000 operations 2 bits set of 512 bits Average for_each_set_bit took: 1937.700 usec (+- 148.902 usec) Average test_bit loop took: 100364.100 usec (+- 1433.219 usec) 100000 operations 4 bits set of 512 bits Average for_each_set_bit took: 2528.000 usec (+- 243.654 usec) Average test_bit loop took: 99932.067 usec (+- 955.868 usec) 100000 operations 8 bits set of 512 bits Average for_each_set_bit took: 3734.100 usec (+- 512.359 usec) Average test_bit loop took: 98944.750 usec (+- 812.070 usec) 100000 operations 16 bits set of 512 bits Average for_each_set_bit took: 5551.400 usec (+- 846.605 usec) Average test_bit loop took: 98691.600 usec (+- 654.753 usec) 100000 operations 32 bits set of 512 bits Average for_each_set_bit took: 8594.500 usec (+- 1446.072 usec) Average test_bit loop took: 99176.867 usec (+- 579.990 usec) 100000 operations 64 bits set of 512 bits Average for_each_set_bit took: 13840.743 usec (+- 2527.055 usec) Average test_bit loop took: 100758.743 usec (+- 833.865 usec) 100000 operations 128 bits set of 512 bits Average for_each_set_bit took: 23185.925 usec (+- 4532.910 usec) Average test_bit loop took: 103786.700 usec (+- 1475.276 usec) 100000 operations 256 bits set of 512 bits Average for_each_set_bit took: 40322.400 usec (+- 8341.802 usec) Average test_bit loop took: 109433.378 usec (+- 2742.615 usec) 100000 operations 512 bits set of 512 bits Average for_each_set_bit took: 71804.540 usec (+- 15436.546 usec) Average test_bit loop took: 120255.440 usec (+- 5252.777 usec) 100000 operations 1 bits set of 1024 bits Average for_each_set_bit took: 1859.600 usec (+- 27.969 usec) Average test_bit loop took: 187676.000 usec (+- 1337.770 usec) 100000 operations 2 bits set of 1024 bits Average for_each_set_bit took: 2273.600 usec (+- 139.420 usec) Average test_bit loop took: 188176.000 usec (+- 684.357 usec) 100000 operations 4 bits set of 1024 bits Average for_each_set_bit took: 2940.400 usec (+- 268.213 usec) Average test_bit loop took: 189172.600 usec (+- 593.295 usec) 100000 operations 8 bits set of 1024 bits Average for_each_set_bit took: 4224.200 usec (+- 547.933 usec) Average test_bit loop took: 190257.250 usec (+- 621.021 usec) 100000 operations 16 bits set of 1024 bits Average for_each_set_bit took: 6090.560 usec (+- 877.975 usec) Average test_bit loop took: 190143.880 usec (+- 503.753 usec) 100000 operations 32 bits set of 1024 bits Average for_each_set_bit took: 9178.800 usec (+- 1475.136 usec) Average test_bit loop took: 190757.100 usec (+- 494.757 usec) 100000 operations 64 bits set of 1024 bits Average for_each_set_bit took: 14441.457 usec (+- 2545.497 usec) Average test_bit loop took: 192299.486 usec (+- 795.251 usec) 100000 operations 128 bits set of 1024 bits Average for_each_set_bit took: 23623.825 usec (+- 4481.182 usec) Average test_bit loop took: 194885.550 usec (+- 1300.817 usec) 100000 operations 256 bits set of 1024 bits Average for_each_set_bit took: 40194.956 usec (+- 8109.056 usec) Average test_bit loop took: 200259.311 usec (+- 2566.085 usec) 100000 operations 512 bits set of 1024 bits Average for_each_set_bit took: 70983.560 usec (+- 15074.982 usec) Average test_bit loop took: 210527.460 usec (+- 4968.980 usec) 100000 operations 1024 bits set of 1024 bits Average for_each_set_bit took: 136530.345 usec (+- 31584.400 usec) Average test_bit loop took: 233329.691 usec (+- 10814.036 usec) 100000 operations 1 bits set of 2048 bits Average for_each_set_bit took: 3077.600 usec (+- 76.376 usec) Average test_bit loop took: 402154.400 usec (+- 518.571 usec) 100000 operations 2 bits set of 2048 bits Average for_each_set_bit took: 3508.600 usec (+- 148.350 usec) Average test_bit loop took: 403814.500 usec (+- 1133.027 usec) 100000 operations 4 bits set of 2048 bits Average for_each_set_bit took: 4219.333 usec (+- 285.844 usec) Average test_bit loop took: 404312.533 usec (+- 985.751 usec) 100000 operations 8 bits set of 2048 bits Average for_each_set_bit took: 5670.550 usec (+- 615.238 usec) Average test_bit loop took: 405321.800 usec (+- 1038.487 usec) 100000 operations 16 bits set of 2048 bits Average for_each_set_bit took: 7785.080 usec (+- 992.522 usec) Average test_bit loop took: 406746.160 usec (+- 1015.478 usec) 100000 operations 32 bits set of 2048 bits Average for_each_set_bit took: 11163.800 usec (+- 1627.320 usec) Average test_bit loop took: 406124.267 usec (+- 898.785 usec) 100000 operations 64 bits set of 2048 bits Average for_each_set_bit took: 16964.629 usec (+- 2806.130 usec) Average test_bit loop took: 406618.514 usec (+- 798.356 usec) 100000 operations 128 bits set of 2048 bits Average for_each_set_bit took: 27219.625 usec (+- 4988.458 usec) Average test_bit loop took: 410149.325 usec (+- 1705.641 usec) 100000 operations 256 bits set of 2048 bits Average for_each_set_bit took: 45138.578 usec (+- 8831.021 usec) Average test_bit loop took: 415462.467 usec (+- 2725.418 usec) 100000 operations 512 bits set of 2048 bits Average for_each_set_bit took: 77450.540 usec (+- 15962.238 usec) Average test_bit loop took: 426089.180 usec (+- 5171.788 usec) 100000 operations 1024 bits set of 2048 bits Average for_each_set_bit took: 138023.636 usec (+- 29826.959 usec) Average test_bit loop took: 446346.636 usec (+- 9904.417 usec) 100000 operations 2048 bits set of 2048 bits Average for_each_set_bit took: 251072.600 usec (+- 55947.692 usec) Average test_bit loop took: 484855.983 usec (+- 18970.431 usec) # Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Link: http://lore.kernel.org/lkml/20200729220034.1337168-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/Build | 1 + tools/perf/bench/bench.h | 1 + tools/perf/bench/find-bit-bench.c | 135 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 137 insertions(+) create mode 100644 tools/perf/bench/find-bit-bench.c (limited to 'tools/perf/bench') diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index 560eb9711ea2..dd68a40a790c 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -11,6 +11,7 @@ perf-y += epoll-wait.o perf-y += epoll-ctl.o perf-y += synthesize.o perf-y += kallsyms-parse.o +perf-y += find-bit-bench.o perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index 49bc8ed3042a..2804812d4154 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -36,6 +36,7 @@ int bench_sched_pipe(int argc, const char **argv); int bench_syscall_basic(int argc, const char **argv); int bench_mem_memcpy(int argc, const char **argv); int bench_mem_memset(int argc, const char **argv); +int bench_mem_find_bit(int argc, const char **argv); int bench_futex_hash(int argc, const char **argv); int bench_futex_wake(int argc, const char **argv); int bench_futex_wake_parallel(int argc, const char **argv); diff --git a/tools/perf/bench/find-bit-bench.c b/tools/perf/bench/find-bit-bench.c new file mode 100644 index 000000000000..fa90f3e9d368 --- /dev/null +++ b/tools/perf/bench/find-bit-bench.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Benchmark find_next_bit and related bit operations. + * + * Copyright 2020 Google LLC. + */ +#include +#include "bench.h" +#include "../util/stat.h" +#include +#include +#include +#include + +static unsigned int outer_iterations = 5; +static unsigned int inner_iterations = 100000; + +static const struct option options[] = { + OPT_UINTEGER('i', "outer-iterations", &outer_iterations, + "Number of outerer iterations used"), + OPT_UINTEGER('j', "inner-iterations", &inner_iterations, + "Number of outerer iterations used"), + OPT_END() +}; + +static const char *const bench_usage[] = { + "perf bench mem find_bit ", + NULL +}; + +static unsigned int accumulator; +static unsigned int use_of_val; + +static noinline void workload(int val) +{ + use_of_val += val; + accumulator++; +} + +#if (defined(__i386__) || defined(__x86_64__)) && defined(__GCC_ASM_FLAG_OUTPUTS__) +static bool asm_test_bit(long nr, const unsigned long *addr) +{ + bool oldbit; + + asm volatile("bt %2,%1" + : "=@ccc" (oldbit) + : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory"); + + return oldbit; +} +#else +#define asm_test_bit test_bit +#endif + +static int do_for_each_set_bit(unsigned int num_bits) +{ + unsigned long *to_test = bitmap_alloc(num_bits); + struct timeval start, end, diff; + u64 runtime_us; + struct stats fb_time_stats, tb_time_stats; + double time_average, time_stddev; + unsigned int bit, i, j; + unsigned int set_bits, skip; + unsigned int old; + + init_stats(&fb_time_stats); + init_stats(&tb_time_stats); + + for (set_bits = 1; set_bits <= num_bits; set_bits <<= 1) { + bitmap_zero(to_test, num_bits); + skip = num_bits / set_bits; + for (i = 0; i < num_bits; i += skip) + set_bit(i, to_test); + + for (i = 0; i < outer_iterations; i++) { + old = accumulator; + gettimeofday(&start, NULL); + for (j = 0; j < inner_iterations; j++) { + for_each_set_bit(bit, to_test, num_bits) + workload(bit); + } + gettimeofday(&end, NULL); + assert(old + (inner_iterations * set_bits) == accumulator); + timersub(&end, &start, &diff); + runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; + update_stats(&fb_time_stats, runtime_us); + + old = accumulator; + gettimeofday(&start, NULL); + for (j = 0; j < inner_iterations; j++) { + for (bit = 0; bit < num_bits; bit++) { + if (asm_test_bit(bit, to_test)) + workload(bit); + } + } + gettimeofday(&end, NULL); + assert(old + (inner_iterations * set_bits) == accumulator); + timersub(&end, &start, &diff); + runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; + update_stats(&tb_time_stats, runtime_us); + } + + printf("%d operations %d bits set of %d bits\n", + inner_iterations, set_bits, num_bits); + time_average = avg_stats(&fb_time_stats); + time_stddev = stddev_stats(&fb_time_stats); + printf(" Average for_each_set_bit took: %.3f usec (+- %.3f usec)\n", + time_average, time_stddev); + time_average = avg_stats(&tb_time_stats); + time_stddev = stddev_stats(&tb_time_stats); + printf(" Average test_bit loop took: %.3f usec (+- %.3f usec)\n", + time_average, time_stddev); + + if (use_of_val == accumulator) /* Try to avoid compiler tricks. */ + printf("\n"); + } + bitmap_free(to_test); + return 0; +} + +int bench_mem_find_bit(int argc, const char **argv) +{ + int err = 0, i; + + argc = parse_options(argc, argv, options, bench_usage, 0); + if (argc) { + usage_with_options(bench_usage, options); + exit(EXIT_FAILURE); + } + + for (i = 1; i <= 2048; i <<= 1) + do_for_each_set_bit(i); + + return err; +} -- cgit v1.2.3