【发布时间】：2020-05-18 11:46:33
【问题描述】：
我在 Whiskey Lake i7-8565U 上分析性能计数器和复制 512 KiB 数据的时间（是 L2 缓存大小的两倍），并且对 L2 HW 预取器的工作存在一些误解。
在Intel Manual Vol.4 MSR 中有 MSR 0x1A4 的位 0 用于控制 L2 HW 预取器（1 为禁用）。
考虑以下基准：
memcopy.h:
void *avx_memcpy_forward_lsls(void *restrict, const void *restrict, size_t);
memcopy.S:
avx_memcpy_forward_lsls:
shr rdx, 0x3
xor rcx, rcx
avx_memcpy_forward_loop_lsls:
vmovdqa ymm0, [rsi + 8*rcx]
vmovdqa [rdi + rcx*8], ymm0
vmovdqa ymm1, [rsi + 8*rcx + 0x20]
vmovdqa [rdi + rcx*8 + 0x20], ymm1
add rcx, 0x08
cmp rdx, rcx
ja avx_memcpy_forward_loop_lsls
ret
main.c:
#include <string.h>
#include <stdlib.h>
#include <inttypes.h>
#include <x86intrin.h>
#include <fcntl.h>
#include <unistd.h>
#include <stdio.h>
#include "memcopy.h"
#define ITERATIONS 1000
#define BUF_SIZE 512 * 1024
_Alignas(64) char src[BUF_SIZE];
_Alignas(64) char dest[BUF_SIZE];
static void __run_benchmark(unsigned runs, unsigned run_iterations,
void *(*fn)(void *, const void*, size_t), void *dest, const void* src, size_t sz);
#define run_benchmark(runs, run_iterations, fn, dest, src, sz) \
do{\
printf("Benchmarking " #fn "\n");\
__run_benchmark(runs, run_iterations, fn, dest, src, sz);\
}while(0)
int main(void){
int fd = open("/dev/urandom", O_RDONLY);
read(fd, src, sizeof src);
run_benchmark(20, ITERATIONS, avx_memcpy_forward_lsls, dest, src, BUF_SIZE);
}
static inline void benchmark_copy_function(unsigned iterations, void *(*fn)(void *, const void *, size_t),
void *restrict dest, const void *restrict src, size_t sz){
while(iterations --> 0){
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
fn(dest, src, sz);
}
}
static void __run_benchmark(unsigned runs, unsigned run_iterations,
void *(*fn)(void *, const void*, size_t), void *dest, const void* src, size_t sz){
unsigned current_run = 1;
while(current_run <= runs){
benchmark_copy_function(run_iterations, fn, dest, src, sz);
printf("Run %d finished\n", current_run);
current_run++;
}
}
考虑运行 2 次已编译的 main.c
我。
MSR:
$ sudo rdmsr -p 0 0x1A4
0
Run:
$ taskset -c 0 sudo ../profile.sh ./bin
Performance counter stats for './bin':
10 486 164 071 L1-dcache-loads (12,13%)
10 461 354 384 L1-dcache-load-misses # 99,76% of all L1-dcache hits (12,05%)
10 481 930 413 L1-dcache-stores (12,05%)
10 461 136 686 l1d.replacement (12,12%)
31 466 394 422 l1d_pend_miss.fb_full (12,11%)
211 853 643 294 l1d_pend_miss.pending (12,09%)
1 759 204 317 LLC-loads (12,16%)
31 007 LLC-load-misses # 0,00% of all LL-cache hits (12,16%)
3 154 901 630 LLC-stores (6,19%)
15 867 315 545 l2_rqsts.all_pf (9,22%)
0 sw_prefetch_access.t1_t2 (12,22%)
1 393 306 l2_lines_out.useless_hwpf (12,16%)
3 549 170 919 l2_rqsts.pf_hit (12,09%)
12 356 247 643 l2_rqsts.pf_miss (12,06%)
0 load_hit_pre.sw_pf (12,09%)
3 159 712 695 l2_rqsts.rfo_hit (12,06%)
1 207 642 335 l2_rqsts.rfo_miss (12,02%)
4 366 526 618 l2_rqsts.all_rfo (12,06%)
5 240 013 774 offcore_requests.all_data_rd (12,06%)
19 936 657 118 offcore_requests.all_requests (12,09%)
1 761 660 763 offcore_response.demand_data_rd.any_response (12,12%)
287 044 397 bus-cycles (12,15%)
36 816 767 779 resource_stalls.any (12,15%)
36 553 997 653 resource_stalls.sb (12,15%)
38 035 066 210 uops_retired.stall_cycles (12,12%)
24 766 225 119 uops_executed.stall_cycles (12,09%)
40 478 455 041 uops_issued.stall_cycles (12,05%)
24 497 256 548 cycle_activity.stalls_l1d_miss (12,02%)
12 611 038 018 cycle_activity.stalls_l2_miss (12,09%)
10 228 869 cycle_activity.stalls_l3_miss (12,12%)
24 707 614 483 cycle_activity.stalls_mem_any (12,22%)
24 776 110 104 cycle_activity.stalls_total (12,22%)
48 914 478 241 cycles (12,19%)
12,155774555 seconds time elapsed
11,984577000 seconds user
0,015984000 seconds sys
二。
MSR:
$ sudo rdmsr -p 0 0x1A4
1
Run:
$ taskset -c 0 sudo ../profile.sh ./bin
Performance counter stats for './bin':
10 508 027 832 L1-dcache-loads (12,05%)
10 463 643 206 L1-dcache-load-misses # 99,58% of all L1-dcache hits (12,09%)
10 481 296 605 L1-dcache-stores (12,12%)
10 444 854 468 l1d.replacement (12,15%)
29 287 445 744 l1d_pend_miss.fb_full (12,17%)
205 569 630 707 l1d_pend_miss.pending (12,17%)
5 103 444 329 LLC-loads (12,17%)
33 406 LLC-load-misses # 0,00% of all LL-cache hits (12,17%)
9 567 917 742 LLC-stores (6,08%)
1 157 237 980 l2_rqsts.all_pf (9,12%)
0 sw_prefetch_access.t1_t2 (12,17%)
301 471 l2_lines_out.useless_hwpf (12,17%)
218 528 985 l2_rqsts.pf_hit (12,17%)
938 735 722 l2_rqsts.pf_miss (12,17%)
0 load_hit_pre.sw_pf (12,17%)
4 096 281 l2_rqsts.rfo_hit (12,17%)
4 972 640 931 l2_rqsts.rfo_miss (12,17%)
4 976 006 805 l2_rqsts.all_rfo (12,17%)
5 175 544 191 offcore_requests.all_data_rd (12,17%)
15 772 124 082 offcore_requests.all_requests (12,17%)
5 120 635 892 offcore_response.demand_data_rd.any_response (12,17%)
292 980 395 bus-cycles (12,17%)
37 592 020 151 resource_stalls.any (12,14%)
37 317 091 982 resource_stalls.sb (12,11%)
38 121 826 730 uops_retired.stall_cycles (12,08%)
25 430 699 605 uops_executed.stall_cycles (12,04%)
41 416 190 037 uops_issued.stall_cycles (12,04%)
25 326 579 070 cycle_activity.stalls_l1d_miss (12,04%)
25 019 148 253 cycle_activity.stalls_l2_miss (12,03%)
7 384 770 cycle_activity.stalls_l3_miss (12,03%)
25 442 709 033 cycle_activity.stalls_mem_any (12,03%)
25 406 897 956 cycle_activity.stalls_total (12,03%)
49 877 044 086 cycles (12,03%)
12,231406658 seconds time elapsed
12,226386000 seconds user
0,004000000 seconds sys
我注意到了柜台：
12 611 038 018 cycle_activity.stalls_l2_missv/s25 019 148 253 cycle_activity.stalls_l2_miss
建议正在应用 MSR 禁用 L2 硬件预取器。其他 l2/LLC 相关的东西也有很大不同。 在不同的运行中可以重现差异。问题是total time 和周期几乎没有区别：
48 914 478 241 cyclesv/s49 877 044 086 cycles
12,155774555 seconds time elapsedv/s12,231406658 seconds time elapsed
问题：
L2 未命中是否被其他性能限制器隐藏？
如果是这样，您能否建议查看哪些计数器来理解它？
【问题讨论】：
-
根据经验：任何非深度实现的内存副本都是内存绑定的。即使它只命中 L1 缓存。任何内存访问的开销都远远高于 CPU 将两个和两个相加所需的开销。在您的情况下，您甚至使用 AVX 指令来减少每个复制字节的指令量。无论您的数据位于何处（L1、L2、LLC、内存），相关内存组件的吞吐量都会成为您的瓶颈。
标签： c performance assembly x86-64 avx