AVX指令集矩阵乘向量算法

#include <stdio.h>
#include <time.h>
#include <x86intrin.h>


void matmul_avx(const float *x, const float **w,float *y,const int col,const int row){
    const int col_reduced_8 = col - col % 8;
    float scratchpad[8];
    __m256 op0, op1, tgt, tmp_vec;
    for (int i = 0; i < row; i++) {
        float res = 0;

        tgt = _mm256_setzero_ps();
        for (int j = 0; j < col_reduced_8; j += 8) {
            op0 = __builtin_ia32_loadups256(&x[j]);
            op1 = __builtin_ia32_loadups256(&w[i][j]);
            tmp_vec = __builtin_ia32_mulps256(op0, op1);
            tgt = __builtin_ia32_addps256(tmp_vec, tgt);
        }

        __builtin_ia32_storeups256(scratchpad, tgt);
        for (int k = 0; k < 8; k++)
            res += scratchpad[k];

        for (int l = col_reduced_8; l < col; l++) {
            res += w[i][l] *