我正在尝试使用 GCC 内置 simd 支持编写几个内核。我有这段代码对 AVX 点积内核进行基准测试:
#include <time.h>
#include <stdio.h>
#include <assert.h>
#include <stdint.h>
#include <stdlib.h>
#include <unistd.h>
// define rtdsc instruction
static __inline__ uint64_t tick(void) {
uint32_t hi, lo;
__asm__ __volatile__ ("rdtsc" : "=a"(lo), "=d"(hi));
return ( (uint64_t)lo)|( ((uint64_t)hi)<<32 );
}
// AVX dot product
float avx_dot(float* __restrict__ ans, float* __restrict__ A, float* __restrict__ B, int N, ssize_t nprod, ssize_t shift) {
assert(N % 32 == 0 && "N not divisible by 32");
const int VECTOR_SIZE = 8;
typedef float vec
__attribute__ ((vector_size (sizeof(float) * VECTOR_SIZE)));
N /= VECTOR_SIZE;
for (ssize_t ii=0; ii < nprod; ii++) {
vec *Av = (vec*)A;
vec *Bv = (vec*)(B + ii*shift);
vec temp[4] = {0,0,0,0};
for(int jj = 0; jj < N; jj += 4) {
temp[0] += Av[jj+0] * Bv[jj+0];
temp[1] += Av[jj+1] * Bv[jj+1];
temp[2] += Av[jj+2] * Bv[jj+2];
temp[3] += Av[jj+3] * Bv[jj+3];
}
union {
vec tempv;
float tempf[VECTOR_SIZE];
};
tempv = temp[0] + temp[1] + temp[2] + temp[3];
ans[ii] = 0;
for(int jj = 0; jj < VECTOR_SIZE; ++jj) {
ans[ii] += tempf[jj];
}
}
}
int main(int argc, const char *argv[]) {
const ssize_t NITER = 1000;
const ssize_t DECIM = atoi(argv[2]);
const ssize_t DOTPROD = atoi(argv[3]);
ssize_t size = atoi(argv[1]);
float* A; posix_memalign((void**)&A, 128, size*sizeof(float));
float* B; posix_memalign((void**)&B, 128, (size+(DOTPROD-1)*DECIM)*sizeof(float));
srand(time(NULL));
for (ssize_t ii=0; ii < size; ii++) A[ii] = rand();
for (ssize_t ii=0; ii < size+(DOTPROD-1)*DECIM; ii++) B[ii] = rand();
printf("# size: %i nproducts: %i shift: %i\n", size, DOTPROD, DECIM);
printf("# iter answer cycles seconds samprate\n");
float results[DOTPROD];
for (ssize_t ii=0; ii < NITER; ii++) {
uint64_t beg = tick();
avx_dot(results, A, B, size, DOTPROD, DECIM);
uint64_t end = tick();
float ans = 0;
for (ssize_t jj=0; jj < DOTPROD; jj++) {
ans += results[jj];
}
double CLOCK = 3300e6;
uint64_t cycles = end-beg;
double seconds = (double)cycles/CLOCK;
double samprate = (size*DOTPROD)/seconds;
printf("%-5zd %f %lli %.3e %e\n", ii, ans, (unsigned long long)cycles, seconds, samprate);
}
return 0;
}
奇怪的是,当编译时:
g++ -O3 -march=corei7-avx dotprod.cc -ffast-math -o dotprod
第一次访问 avx_dot 中的 temp 时出现段错误。但是,当编译时:
g++ -O3 -march=corei7-avx dotprod.cc -o dotprod
IE,没有 -ffast-math ,它运行良好。我很困惑,因为我相信快速数学不应该影响内存访问,所以我不知道段错误来自哪里。
我正在运行:
CentOS Linux release 7.2.1511
gcc version 4.8.5 20150623 (Red Hat 4.8.5-4) (GCC)
任何人都可以在他们的机器上确认这种行为并阐明正在发生的事情吗?