【发布时间】：2019-12-31 09:41:44
【问题描述】：
我们一直在使用两台相同的 Skylake 服务器，它们的软件、Centos 7 操作系统和 BIOS 设置完全相同。一切都是一样的，除了延迟性能。我们的软件使用的是 AVX512。
在测试中，我注意到 AVX512 每次都会降低其中一个系统的性能（增加延迟）。存在显着的性能差异。我检查了一切，都是一样的。
我应该怎么做才能解决这个问题？哪个工具可以提供帮助？
提前谢谢..
sudo lshw -class cpu
*-cpu:0
description: CPU
product: Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
vendor: Intel Corp.
vendor_id: GenuineIntel
physical id: 400
bus info: cpu@0
version: Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
slot: CPU1
size: 3GHz
capacity: 4GHz
width: 64 bits
clock: 1010MHz
capabilities: lm fpu fpu_exception wp vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp x86-64 constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch epb cat_l3 cdp_l3 intel_ppin intel_pt ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts pku ospke md_clear spec_ctrl intel_stibp flush_l1d
configuration: cores=18 enabledcores=18 threads=18
*-cpu:1 DISABLED
description: CPU [empty]
physical id: 401
slot: CPU2
更新：在彼得的评论之后，我添加了以下示例代码作为示例。
#include <emmintrin.h>
#include <pthread.h>
#include <immintrin.h>
#include <unistd.h>
#include <inttypes.h>
#include <string.h>
#include <stdbool.h>
#include <stdio.h>
#define CACHE_LINE_SIZE 64
/**
* Copy 64 bytes from one location to another,
* locations should not overlap.
*/
static inline __attribute__((always_inline)) void
mov64(uint8_t *dst, const uint8_t *src)
{
__m512i zmm0;
zmm0 = _mm512_load_si512((const void *)src);
_mm512_store_si512((void *)dst, zmm0);
}
#define likely(x) __builtin_expect((x), 1)
#define unlikely(x) __builtin_expect((x), 0)
static inline uint64_t rdtsc(void)
{
union {
uint64_t tsc_64;
__extension__
struct {
uint32_t lo_32;
uint32_t hi_32;
};
} tsc;
__asm__ volatile("rdtsc" :
"=a" (tsc.lo_32),
"=d" (tsc.hi_32));
return tsc.tsc_64;
}
union levels {
__m512i zmm0;
struct {
uint32_t x1;
uint64_t x2;
uint64_t x3;
uint32_t x4;
uint32_t x5;
uint32_t x6;
uint32_t x7;
};
} __attribute__((aligned(CACHE_LINE_SIZE)));
union levels g_shared;
void *worker_loop(void *param)
{
cpu_set_t cpuset;
CPU_ZERO(&cpuset);
CPU_SET(16, &cpuset);
pthread_t thread = pthread_self();
pthread_setaffinity_np(thread, sizeof(cpu_set_t), &cpuset);
union levels lshared;
uint32_t old_x1 = 0;
lshared.x1 = 0;
while (1) {
__asm__ ("" ::: "memory");
lshared.zmm0 = _mm512_load_si512((const void *)&g_shared);
if (unlikely(lshared.x1 <= old_x1)) {
continue;
} else if (unlikely(lshared.x1 != lshared.x7)) {
// printf("%u %u %u %u %u %u\n", lshared.x1, lshared.x3, lshared.x4, lshared.x5, lshared.x6, lshared.x7);
exit(EXIT_FAILURE);
} else {
uint64_t val = rdtsc();
if (val > lshared.x2) {
printf("> (%u) %lu - %lu = %lu\n", lshared.x1, val, lshared.x2, val - lshared.x2);
} else {
printf("< (%u) %lu - %lu = %lu\n", lshared.x1, lshared.x2, val, lshared.x2 - val);
}
}
old_x1 = lshared.x1;
_mm_pause();
}
return NULL;
}
int main(int argc, char *argv[])
{
cpu_set_t cpuset;
CPU_ZERO(&cpuset);
CPU_SET(15, &cpuset);
pthread_t thread = pthread_self();
memset(&g_shared, 0, sizeof(g_shared));
pthread_setaffinity_np(thread, sizeof(cpu_set_t), &cpuset);
pthread_t worker;
pthread_create(&worker, NULL, worker_loop, NULL);
uint32_t val = 1;
union levels lshared;
while (1) {
lshared.x1 = val;
lshared.x2 = rdtsc();
lshared.x3 = val;
lshared.x4 = val;
lshared.x5 = val;
lshared.x6 = val;
lshared.x7 = val;
_mm512_store_si512((void *)&g_shared, lshared.zmm0);
__asm__ ("" ::: "memory");
usleep(100000);
val++;
_mm_pause();
}
return EXIT_SUCCESS;
}
较慢的系统输出：
> (1) 4582365777844442 - 4582365777792564 = 51878
> (2) 4582366077239290 - 4582366077238806 = 484
> (3) 4582366376674782 - 4582366376674346 = 436
> (4) 4582366676044526 - 4582366676041890 = 2636
> (5) 4582366975470562 - 4582366975470134 = 428
> (6) 4582367274899258 - 4582367274898828 = 430
> (7) 4582367574328446 - 4582367574328022 = 424
> (8) 4582367873757956 - 4582367873757532 = 424
> (9) 4582368173187886 - 4582368173187466 = 420
> (10) 4582368472618418 - 4582368472617958 = 460
> (11) 4582368772049720 - 4582368772049236 = 484
> (12) 4582369071481018 - 4582369071480594 = 424
> (13) 4582369370912760 - 4582369370912284 = 476
> (14) 4582369670344890 - 4582369670344212 = 678
> (15) 4582369969776826 - 4582369969776400 = 426
> (16) 4582370269209462 - 4582370269209024 = 438
> (17) 4582370568642626 - 4582370568642172 = 454
> (18) 4582370868076202 - 4582370868075764 = 438
> (19) 4582371167510016 - 4582371167509594 = 422
> (20) 4582371466944326 - 4582371466943892 = 434
> (21) 4582371766379206 - 4582371766378734 = 472
> (22) 4582372065814804 - 4582372065814344 = 460
> (23) 4582372365225608 - 4582372365223068 = 2540
> (24) 4582372664652112 - 4582372664651668 = 444
> (25) 4582372964080746 - 4582372964080314 = 432
> (26) 4582373263510732 - 4582373263510308 = 424
> (27) 4582373562940116 - 4582373562939676 = 440
> (28) 4582373862370284 - 4582373862369860 = 424
> (29) 4582374161800632 - 4582374161800182 = 450
更快的系统输出：
> (1) 9222001841102298 - 9222001841045386 = 56912
> (2) 9222002140513228 - 9222002140512908 = 320
> (3) 9222002439970702 - 9222002439970330 = 372
> (4) 9222002739428448 - 9222002739428114 = 334
> (5) 9222003038886492 - 9222003038886152 = 340
> (6) 9222003338344884 - 9222003338344516 = 368
> (7) 9222003637803702 - 9222003637803332 = 370
> (8) 9222003937262776 - 9222003937262404 = 372
> (9) 9222004236649320 - 9222004236648932 = 388
> (10) 9222004536101876 - 9222004536101510 = 366
> (11) 9222004835554776 - 9222004835554378 = 398
> (12) 9222005135008064 - 9222005135007686 = 378
> (13) 9222005434461868 - 9222005434461526 = 342
> (14) 9222005733916416 - 9222005733916026 = 390
> (15) 9222006033370968 - 9222006033370640 = 328
> (16) 9222006332825872 - 9222006332825484 = 388
> (17) 9222006632280956 - 9222006632280570 = 386
> (18) 9222006931736548 - 9222006931736178 = 370
> (19) 9222007231192376 - 9222007231191986 = 390
> (20) 9222007530648868 - 9222007530648486 = 382
> (21) 9222007830105642 - 9222007830105270 = 372
> (22) 9222008129562750 - 9222008129562382 = 368
> (23) 9222008429020310 - 9222008429019944 = 366
> (24) 9222008728478336 - 9222008728477970 = 366
> (25) 9222009027936696 - 9222009027936298 = 398
> (26) 9222009327395716 - 9222009327395342 = 374
> (27) 9222009626854876 - 9222009626854506 = 370
> (28) 9222009926282324 - 9222009926281936 = 388
> (29) 9222010225734832 - 9222010225734442 = 390
> (30) 9222010525187748 - 9222010525187366 = 382
更新2：在彼得的回答之后，我添加了以下示例代码作为示例，以测量同一裸片上不同网状网络路径的延迟，并且答案的内容是正确的，不同的cpu有不同的cpu间延迟。但在所有情况下，相同系统中的一个仍然比另一个慢 25%。
我也不知道会不会影响它，但我刚刚意识到慢速 CPU 有额外的 md_clear 标志。
总之，我应该怎么做才能解决这个问题？哪个工具可以提供帮助？如何理解性能差异？
#include <emmintrin.h>
#include <pthread.h>
#include <immintrin.h>
#include <unistd.h>
#include <inttypes.h>
#include <string.h>
#include <stdbool.h>
#include <stdio.h>
#define CACHE_LINE_SIZE 64
/**
* Copy 64 bytes from one location to another,
* locations should not overlap.
*/
static inline __attribute__((always_inline)) void
mov64(uint8_t *dst, const uint8_t *src)
{
__m512i zmm0;
zmm0 = _mm512_load_si512((const void *)src);
_mm512_store_si512((void *)dst, zmm0);
}
#define likely(x) __builtin_expect((x), 1)
#define unlikely(x) __builtin_expect((x), 0)
static inline uint64_t rdtsc(void)
{
union {
uint64_t tsc_64;
__extension__
struct {
uint32_t lo_32;
uint32_t hi_32;
};
} tsc;
__asm__ volatile("rdtsc" :
"=a" (tsc.lo_32),
"=d" (tsc.hi_32));
return tsc.tsc_64;
}
union levels {
__m512i zmm0;
struct {
uint32_t x1;
uint64_t x2;
uint64_t x3;
uint32_t x4;
uint32_t x5;
uint32_t x6;
uint32_t x7;
};
} __attribute__((aligned(CACHE_LINE_SIZE)));
union levels g_shared;
uint32_t g_main_cpu;
uint32_t g_worker_cpu;
void *worker_loop(void *param)
{
_mm_mfence();
cpu_set_t cpuset;
CPU_ZERO(&cpuset);
CPU_SET(g_worker_cpu, &cpuset);
pthread_t thread = pthread_self();
pthread_setaffinity_np(thread, sizeof(cpu_set_t), &cpuset);
union levels lshared;
uint32_t old_x1 = 1;
uint64_t min = 10000, max = 0, sum = 0;
int i = 0;
while (i < 300) {
__asm__ ("" ::: "memory");
lshared.zmm0 = _mm512_load_si512((const void *)&g_shared);
if (unlikely(lshared.x1 <= old_x1)) {
continue;
} else if (unlikely(lshared.x1 != lshared.x7)) {
exit(EXIT_FAILURE);
} else {
uint64_t val = rdtsc();
uint64_t diff = val - lshared.x2;
sum += diff;
if (min > diff)
min = diff;
if (diff > max)
max = diff;
i++;
}
old_x1 = lshared.x1;
_mm_pause();
}
printf("(M=%u-W=%u) min=%lu max=%lu mean=%lu\n", g_main_cpu, g_worker_cpu, min, max, sum / 300);
return NULL;
}
int main(int argc, char *argv[])
{
for (int main_cpu = 2; main_cpu <= 17; ++main_cpu) {
for (int worker_cpu = 2; worker_cpu <= 17; ++worker_cpu) {
if (main_cpu == worker_cpu) {
continue;
}
_mm_mfence();
g_main_cpu = main_cpu;
g_worker_cpu = worker_cpu;
cpu_set_t cpuset;
CPU_ZERO(&cpuset);
CPU_SET(g_main_cpu, &cpuset);
pthread_t thread = pthread_self();
memset(&g_shared, 0, sizeof(g_shared));
pthread_setaffinity_np(thread, sizeof(cpu_set_t), &cpuset);
pthread_t worker;
pthread_create(&worker, NULL, worker_loop, NULL);
uint32_t val = 0;
union levels lshared;
for (int i = 0; i < 350; ++i) {
lshared.x1 = val;
lshared.x2 = rdtsc();
lshared.x3 = val;
lshared.x4 = val;
lshared.x5 = val;
lshared.x6 = val;
lshared.x7 = val;
_mm512_store_si512((void *)&g_shared, lshared.zmm0);
__asm__ ("" ::: "memory");
usleep(100000);
val++;
_mm_pause();
}
pthread_join(worker, NULL);
}
}
return EXIT_SUCCESS;
}
两个系统的输出：（2-17是隔离cpu）
slow cpu fast cpu
------------------------------------
(M=2-W=3) mean=580 mean=374
(M=2-W=4) mean=463 mean=365
(M=2-W=5) mean=449 mean=391
(M=2-W=6) mean=484 mean=345
(M=2-W=7) mean=430 mean=386
(M=2-W=8) mean=439 mean=369
(M=2-W=9) mean=445 mean=376
(M=2-W=10) mean=480 mean=354
(M=2-W=11) mean=440 mean=392
(M=2-W=12) mean=475 mean=324
(M=2-W=13) mean=453 mean=373
(M=2-W=14) mean=474 mean=344
(M=2-W=15) mean=445 mean=384
(M=2-W=16) mean=468 mean=372
(M=2-W=17) mean=462 mean=373
(M=3-W=2) mean=447 mean=392
(M=3-W=4) mean=556 mean=386
(M=3-W=5) mean=418 mean=409
(M=3-W=6) mean=473 mean=372
(M=3-W=7) mean=397 mean=400
(M=3-W=8) mean=408 mean=403
(M=3-W=9) mean=412 mean=413
(M=3-W=10) mean=447 mean=389
(M=3-W=11) mean=412 mean=423
(M=3-W=12) mean=446 mean=399
(M=3-W=13) mean=427 mean=407
(M=3-W=14) mean=445 mean=390
(M=3-W=15) mean=417 mean=448
(M=3-W=16) mean=438 mean=386
(M=3-W=17) mean=435 mean=396
(M=4-W=2) mean=463 mean=368
(M=4-W=3) mean=433 mean=401
(M=4-W=5) mean=561 mean=406
(M=4-W=6) mean=468 mean=378
(M=4-W=7) mean=416 mean=387
(M=4-W=8) mean=425 mean=386
(M=4-W=9) mean=425 mean=415
(M=4-W=10) mean=464 mean=379
(M=4-W=11) mean=424 mean=404
(M=4-W=12) mean=456 mean=369
(M=4-W=13) mean=441 mean=395
(M=4-W=14) mean=460 mean=378
(M=4-W=15) mean=427 mean=405
(M=4-W=16) mean=446 mean=369
(M=4-W=17) mean=448 mean=391
(M=5-W=2) mean=447 mean=382
(M=5-W=3) mean=418 mean=406
(M=5-W=4) mean=430 mean=397
(M=5-W=6) mean=584 mean=386
(M=5-W=7) mean=399 mean=399
(M=5-W=8) mean=404 mean=386
(M=5-W=9) mean=408 mean=408
(M=5-W=10) mean=446 mean=378
(M=5-W=11) mean=411 mean=407
(M=5-W=12) mean=440 mean=385
(M=5-W=13) mean=424 mean=402
(M=5-W=14) mean=442 mean=381
(M=5-W=15) mean=411 mean=411
(M=5-W=16) mean=433 mean=398
(M=5-W=17) mean=429 mean=395
(M=6-W=2) mean=486 mean=356
(M=6-W=3) mean=453 mean=388
(M=6-W=4) mean=471 mean=353
(M=6-W=5) mean=452 mean=388
(M=6-W=7) mean=570 mean=360
(M=6-W=8) mean=444 mean=377
(M=6-W=9) mean=450 mean=376
(M=6-W=10) mean=485 mean=335
(M=6-W=11) mean=451 mean=410
(M=6-W=12) mean=479 mean=353
(M=6-W=13) mean=463 mean=363
(M=6-W=14) mean=479 mean=359
(M=6-W=15) mean=450 mean=394
(M=6-W=16) mean=473 mean=364
(M=6-W=17) mean=469 mean=373
(M=7-W=2) mean=454 mean=365
(M=7-W=3) mean=418 mean=410
(M=7-W=4) mean=443 mean=370
(M=7-W=5) mean=421 mean=407
(M=7-W=6) mean=456 mean=363
(M=7-W=8) mean=527 mean=380
(M=7-W=9) mean=417 mean=392
(M=7-W=10) mean=460 mean=361
(M=7-W=11) mean=421 mean=402
(M=7-W=12) mean=447 mean=354
(M=7-W=13) mean=430 mean=381
(M=7-W=14) mean=449 mean=375
(M=7-W=15) mean=420 mean=393
(M=7-W=16) mean=442 mean=352
(M=7-W=17) mean=438 mean=367
(M=8-W=2) mean=463 mean=382
(M=8-W=3) mean=434 mean=411
(M=8-W=4) mean=452 mean=372
(M=8-W=5) mean=429 mean=402
(M=8-W=6) mean=469 mean=368
(M=8-W=7) mean=416 mean=418
(M=8-W=9) mean=560 mean=418
(M=8-W=10) mean=468 mean=385
(M=8-W=11) mean=429 mean=394
(M=8-W=12) mean=460 mean=378
(M=8-W=13) mean=439 mean=392
(M=8-W=14) mean=459 mean=373
(M=8-W=15) mean=429 mean=383
(M=8-W=16) mean=452 mean=376
(M=8-W=17) mean=449 mean=401
(M=9-W=2) mean=440 mean=368
(M=9-W=3) mean=410 mean=398
(M=9-W=4) mean=426 mean=385
(M=9-W=5) mean=406 mean=403
(M=9-W=6) mean=447 mean=378
(M=9-W=7) mean=393 mean=427
(M=9-W=8) mean=408 mean=368
(M=9-W=10) mean=580 mean=392
(M=9-W=11) mean=408 mean=387
(M=9-W=12) mean=433 mean=381
(M=9-W=13) mean=418 mean=444
(M=9-W=14) mean=441 mean=407
(M=9-W=15) mean=408 mean=401
(M=9-W=16) mean=427 mean=376
(M=9-W=17) mean=426 mean=383
(M=10-W=2) mean=478 mean=361
(M=10-W=3) mean=446 mean=379
(M=10-W=4) mean=461 mean=350
(M=10-W=5) mean=445 mean=373
(M=10-W=6) mean=483 mean=354
(M=10-W=7) mean=428 mean=370
(M=10-W=8) mean=436 mean=355
(M=10-W=9) mean=448 mean=390
(M=10-W=11) mean=569 mean=350
(M=10-W=12) mean=473 mean=337
(M=10-W=13) mean=454 mean=370
(M=10-W=14) mean=474 mean=360
(M=10-W=15) mean=441 mean=370
(M=10-W=16) mean=463 mean=354
(M=10-W=17) mean=462 mean=358
(M=11-W=2) mean=447 mean=384
(M=11-W=3) mean=411 mean=408
(M=11-W=4) mean=433 mean=394
(M=11-W=5) mean=413 mean=428
(M=11-W=6) mean=455 mean=383
(M=11-W=7) mean=402 mean=395
(M=11-W=8) mean=407 mean=418
(M=11-W=9) mean=417 mean=424
(M=11-W=10) mean=452 mean=395
(M=11-W=12) mean=577 mean=406
(M=11-W=13) mean=426 mean=402
(M=11-W=14) mean=442 mean=412
(M=11-W=15) mean=408 mean=411
(M=11-W=16) mean=435 mean=400
(M=11-W=17) mean=431 mean=415
(M=12-W=2) mean=473 mean=352
(M=12-W=3) mean=447 mean=381
(M=12-W=4) mean=461 mean=361
(M=12-W=5) mean=445 mean=366
(M=12-W=6) mean=483 mean=322
(M=12-W=7) mean=431 mean=358
(M=12-W=8) mean=438 mean=340
(M=12-W=9) mean=448 mean=409
(M=12-W=10) mean=481 mean=334
(M=12-W=11) mean=447 mean=351
(M=12-W=13) mean=580 mean=383
(M=12-W=14) mean=473 mean=359
(M=12-W=15) mean=441 mean=385
(M=12-W=16) mean=463 mean=355
(M=12-W=17) mean=462 mean=358
(M=13-W=2) mean=450 mean=385
(M=13-W=3) mean=420 mean=410
(M=13-W=4) mean=440 mean=396
(M=13-W=5) mean=418 mean=402
(M=13-W=6) mean=461 mean=385
(M=13-W=7) mean=406 mean=391
(M=13-W=8) mean=415 mean=382
(M=13-W=9) mean=421 mean=402
(M=13-W=10) mean=457 mean=376
(M=13-W=11) mean=422 mean=409
(M=13-W=12) mean=451 mean=381
(M=13-W=14) mean=579 mean=375
(M=13-W=15) mean=430 mean=402
(M=13-W=16) mean=440 mean=408
(M=13-W=17) mean=439 mean=394
(M=14-W=2) mean=477 mean=330
(M=14-W=3) mean=449 mean=406
(M=14-W=4) mean=464 mean=355
(M=14-W=5) mean=450 mean=389
(M=14-W=6) mean=487 mean=342
(M=14-W=7) mean=432 mean=380
(M=14-W=8) mean=439 mean=360
(M=14-W=9) mean=451 mean=405
(M=14-W=10) mean=485 mean=356
(M=14-W=11) mean=447 mean=398
(M=14-W=12) mean=479 mean=338
(M=14-W=13) mean=455 mean=382
(M=14-W=15) mean=564 mean=383
(M=14-W=16) mean=481 mean=361
(M=14-W=17) mean=465 mean=351
(M=15-W=2) mean=426 mean=409
(M=15-W=3) mean=395 mean=424
(M=15-W=4) mean=412 mean=427
(M=15-W=5) mean=395 mean=425
(M=15-W=6) mean=435 mean=391
(M=15-W=7) mean=379 mean=405
(M=15-W=8) mean=388 mean=412
(M=15-W=9) mean=399 mean=432
(M=15-W=10) mean=432 mean=389
(M=15-W=11) mean=397 mean=432
(M=15-W=12) mean=426 mean=393
(M=15-W=13) mean=404 mean=407
(M=15-W=14) mean=429 mean=412
(M=15-W=16) mean=539 mean=391
(M=15-W=17) mean=414 mean=397
(M=16-W=2) mean=456 mean=368
(M=16-W=3) mean=422 mean=406
(M=16-W=4) mean=445 mean=384
(M=16-W=5) mean=427 mean=397
(M=16-W=6) mean=462 mean=348
(M=16-W=7) mean=413 mean=408
(M=16-W=8) mean=419 mean=361
(M=16-W=9) mean=429 mean=385
(M=16-W=10) mean=463 mean=369
(M=16-W=11) mean=426 mean=404
(M=16-W=12) mean=454 mean=391
(M=16-W=13) mean=434 mean=378
(M=16-W=14) mean=454 mean=412
(M=16-W=15) mean=424 mean=416
(M=16-W=17) mean=578 mean=378
(M=17-W=2) mean=460 mean=402
(M=17-W=3) mean=419 mean=381
(M=17-W=4) mean=446 mean=394
(M=17-W=5) mean=424 mean=422
(M=17-W=6) mean=468 mean=369
(M=17-W=7) mean=409 mean=401
(M=17-W=8) mean=418 mean=405
(M=17-W=9) mean=428 mean=414
(M=17-W=10) mean=459 mean=369
(M=17-W=11) mean=424 mean=387
(M=17-W=12) mean=451 mean=372
(M=17-W=13) mean=435 mean=382
(M=17-W=14) mean=459 mean=369
(M=17-W=15) mean=426 mean=401
(M=17-W=16) mean=446 mean=371
【问题讨论】：
-
你能用文字解释一下你的微基准测量的是什么吗？我认为线程间延迟，但是您要固定到某些特定的内核？您似乎在负载和分支上旋转，没有
_mm_pause()？我猜barrier()类似于asm("":::"memory")，但您没有显示定义。 -
@PeterCordes 对于此示例，我正在尝试测量 CPU 间延迟。即使这向我展示了缓慢的证据，系统完全相同在实际代码中，我也使用 SIMD/AVX512 进行数学运算，在现场工作应用程序中，相同系统存在令人难以置信的差异。这怎么可能发生？障碍是 asm("":::"memory")。
-
这两件事都可以很好地解决这个问题。
-
好吧，
_mm_pause()只是让两个版本的速度差不多，我想。这很好，我猜。读者中的continue;是否曾经到达过？跳过pause。但我认为这不是它花费大部分时间等待的地方。我没有花时间完全理清那个逻辑，也没有 cmets。 -
IMO 你应该显示 median，而不是意思。您的结果在第一次迭代（冷缓存，线程启动？）中都有巨大的峰值，您不应该计算在内。以及偶尔出现的其他峰值，可能来自中断或其他争用。
标签： c performance x86-64 intel avx512