Using mkl_?csrmm

Bounrajbanditt_K_ — Fri, 10 Feb 2017 05:33:57 GMT

Hello,

I have trouble getting mkl_?csrmm to output the correct answer to my program. I am wondering if I am using or inputting the correct parameters for what I want to do for the sparse routine. Any assistance would be greatly appreciated.

#include <stdio.h>
#include <stdlib.h>
#include "mkl.h"

#define NNZ 8
#define M 6
#define N 2
#define K 3
/*
	This program tries to multiply :

	 [5.0  0.0  1.0]
	 [0.0  2.0  0.0]   x       [5.0  1.0]
	 [0.0  3.0  0.0]	   [2.0  2.0]
	 [0.0  0.0  1.0]	   [6.0  6.0]
	 [1.0  0.0  0.0]
	 [2.0  0.0  5.0]

*/
int main() {
	char transa = 'n';
	MKL_INT m = M;
	MKL_INT n = N;
	MKL_INT k = K;

	float alpha = 1.0;
	char matdescra[5];
	matdescra[0] = 'g';
	matdescra[3] = 'f';

	float    val[NNZ] = { 5.0, 1.0, 2.0, 3.0, 1.0, 1.0, 2.0, 5.0 };
	MKL_INT  col[NNZ] = { 1, 3, 2, 2, 3, 1, 1, 3 };
	MKL_INT  ind[7] = { 1, 3, 4, 5, 6, 7, 9 };

	float 	b = { { 5.0 , 1.0 },{ 2.0 , 2.0 },{ 6.0 , 6.0 } };
	MKL_INT ldb = K;
	float 	beta = 0.0;

	float  c = { { 0.0, 0.0 },{ 0.0, 0.0 },{ 0.0, 0.0 },{ 0.0, 0.0 },{ 0.0, 0.0 },{ 0.0, 0.0 } };
	MKL_INT ldc = M;

	mkl_scsrmm(&transa, &m, &n, &k, &alpha, matdescra, val, col, ind, &(ind[1]), &(b[0][0]), &ldb, &beta, &(c[0][0]), &ldc);

	int i, j;


	for (i = 0; i < m; i++) {
		for (j = 0; j < n; j++) {
			printf("\n c[%d][%d] = %7.1f", i, j, c);
		}
	}

	getchar();

	return 0;
}

Hello,

MariaZh — Fri, 10 Feb 2017 06:35:17 GMT

Hello,

I can see that problem here is in mix of parameters for 0-based and 1-based indexing.
If you're going to use 1-based indexing then you should change matrix layout to Column major, anyway I slightly modified your example to show correct usage for both cases.

Best regards,
Maria

Thank you so much Maria!

Bounrajbanditt_K_ — Sun, 12 Feb 2017 23:59:06 GMT

Thank you so much Maria! These forums are very responsive and I appreciate the help that it gives.

topic Using mkl_?csrmm in Intel® oneAPI Math Kernel Library

Using mkl_?csrmm

Hello,

Thank you so much Maria!