#ifndef HPC_GEMM_REFCOLMAJOR_H
#define HPC_GEMM_REFCOLMAJOR_H 1

#include "ulmblas.h"

namespace refColMajor {

template <typename T, typename Index>
void
gemm(Index m, Index n, Index k,
     T alpha,
     const T *A, Index incRowA, Index incColA,
     const T *B, Index incRowB, Index incColB,
     T beta,
     T *C, Index incRowC, Index incColC)
{
    ulmBLAS::gescal(m, n, beta, C, incRowC, incColC);
    for (Index j=0; j<n; ++j) {
        for (Index l=0; l<k; ++l) {
            for (Index i=0; i<m; ++i) {
                C[i*incRowC+j*incColC] += alpha*A[i*incRowA+l*incColA]
                                               *B[l*incRowB+j*incColB];
            }
        }
    }
}

} // namespace refColMajor

#endif // HPC_GEMM_REFCOLMAJOR_H