I'd like to do the following in CBLAS:
static float a[max_i][max_j]; static float b[max_i][max_j]; static float vec[max_i]; for (size_t i = 0; i < max_i; i++) { for (size_t j = 0; j < max_j; j++) { b[i][j] += vec[i] * a[i][j]; } }
Is there a single performant function that I can use to do this whole thing (assuming I alter the 2d arrays to be 1d arrays)? I know I can do this with a for loop of cblas_saxpy's.
Thanks!