blas-l1-mm.cpp

void blasL1(Matrix1D *A, Matrix1D *B, Matrix1D *C, int n) {
    double *Cmat = C->matrix;
    double *Amat = A->matrix;
    double *Bmat = B->matrix;

    double *Arv, *Crv;

    omp_set_num_threads(4);
    #pragma omp parallel for
    for (int i = 0; i < n; ++i) {
        Arv = Amat + i * n;
        Crv = Cmat + i * n;

        for (int j = 0; j < n; j++)
            *(Crv + j) = cblas_ddot(n, Arv, 1, &Bmat[j * n], 1);
    }
}