我刚刚开始使用我的矢量化代码。我的矩阵向量乘法代码没有被自动向量化gcc，我想知道为什么。此 pastebin 包含来自 -fopt-info-vec-missed.
我无法理解输出告诉我的内容以及它如何与我用代码编写的内容相匹配。
例如，我看到很多行说not enough data-refs in basic block，我无法通过谷歌搜索在网上找到很多关于此的详细信息。我还看到与内存对齐有关的问题，例如Unknown misalignment, naturally aligned和vector alignment may not be reachable. 我所有的内存分配都是针对double使用的类型malloc，我相信它可以保证与该类型对齐。
环境：gcc在 WSL2 上编译
gcc -v: gcc version 7.5.0 (Ubuntu 7.5.0-3ubuntu1~18.04)
#include <time.h>
#include <stdio.h>
#include <stdlib.h>
#include <omp.h>
#define N 4000 // Matrix size will be N x N
#define T 1
//gcc -fopenmp -g vectorisation.c -o main -O3 -march=native -fopt-info-vec-missed=missed.txt
void doParallelComputation(double *A, double *V, double *results, unsigned long matrixSize, int numThreads)
{
omp_set_num_threads(numThreads);
unsigned long i, j;
#pragma omp parallel for simd private(j)
for (i = 0; i < matrixSize; i++)
{
// double *AHead = &A[i * matrixSize];
// double tmp = 0;
for (j = 0; j < matrixSize; j++)
{
results[i] += A[i * matrixSize + j] * V[j];
// also tried tmp += A[i * matrixSize + j] * V[j];
}
// results[i] = tmp;
}
}
void genRandVector(double *S, unsigned long size)
{
srand(time(0));
unsigned long i;
for (i = 0; i < size; i++)
{
double n = rand() % 5;
S[i] = n;
}
}
void genRandMatrix(double *A, unsigned long size)
{
srand(time(0));
unsigned long i, j;
for (i = 0; i < size; i++)
{
for (j = 0; j < size; j++)
{
double n = rand() % 5;
A[i*size + j] = n;
}
}
}
int main(int argc, char *argv[])
{
double *V = (double *)malloc(N * sizeof(double)); // v in our A*v = parV computation
double *parV = (double *)malloc(N * sizeof(double)); // Parallel computed vector
double *A = (double *)malloc(N * N * sizeof(double)); // NxN Matrix to multiply by V
genRandVector(V, N);
doParallelComputation(A, V, parV, N, T);
free(parV);
free(A);
free(V);
return 0;
}