我目前正在尝试使用内在函数和循环展开来优化矩阵运算。有分段错误,我无法弄清楚。这是我所做的更改代码:
const int UNROLL = 4;
void outer_product(matrix *vec1, matrix *vec2, matrix *dst) {
assert(vec1->dim.cols == 1 && vec2->dim.cols == 1 && vec1->dim.rows == dst->dim.rows && vec2->dim.rows == dst->dim.cols);
__m256 tmp[4];
for (int x = 0; x < UNROLL; x++) {
tmp[x] = _mm256_setzero_ps();
}
for (int i = 0; i < vec1->dim.rows; i+=UNROLL*8) {
for (int j = 0; j < vec2->dim.rows; j++) {
__m256 row2 = _mm256_broadcast_ss(&vec2->data[j][0]);
for (int x = 0; x<UNROLL; x++) {
tmp[x] = _mm256_mul_ps(_mm256_load_ps(&vec1->data[i+x*8][0]), row2);
_mm256_store_ps(&dst->data[i+x*8][j], tmp[x]);
}
}
}
}
void matrix_multiply(matrix *mat1, matrix *mat2, matrix *dst) {
assert (mat1->dim.cols == mat2->dim.rows && dst->dim.rows == mat1->dim.rows && dst->dim.cols == mat2->dim.cols);
for (int i = 0; i < mat1->dim.rows; i+=UNROLL*8) {
for (int j = 0; j < mat2->dim.cols; j++) {
__m256 tmp[4];
for (int x = 0; x < UNROLL; x++) {
tmp[x] = _mm256_setzero_ps();
}
for (int k = 0; k < mat1->dim.cols; k++) {
__m256 mat2_s = _mm256_broadcast_ss(&mat2->data[k][j]);
for (int x = 0; x < UNROLL; x++) {
tmp[x] = _mm256_add_ps(tmp[x], _mm256_mul_ps(_mm256_load_ps(&mat1->data[i+x*8][k]), mat2_s));
}
}
for (int x = 0; x < UNROLL; x++) {
_mm256_store_ps(&dst->data[i+x*8][j], tmp[x]);
}
}
}
}
编辑: 这里是矩阵的结构。我没有修改它。
typedef struct shape {
int rows;
int cols;
} shape;
typedef struct matrix {
shape dim;
float** data;
} matrix;
编辑:我尝试使用 gdb 来确定是哪一行导致了分段错误,并且看起来确实如此_mm256_load_ps()
。我是否以错误的方式索引到矩阵,以至于它无法从正确的地址加载?还是对齐内存的问题?