37
edits
Changes
→Serial
#include <stdlib.h>
#include <time.h>
/* Consider adjusting LOOP_COUNT based on the performance of your computer */
/* to make sure that total run time is at least 1 second */
#define LOOP_COUNT 220 //220 for more accurate statistics
int main()
{
double sum;
double s_initial, s_elapsed;
printf("\n This example demonstrates threading impact on computing real matrix product \n"
" C=alpha*A*B+beta*C using Intel(R) MKL function dgemm, where A, B, and C are \n"
" matrices and alpha and beta are double precision scalars \n\n");
m = 2000, p = 200, n = 1000;
printf(" Initializing data for matrix multiplication C=A*B for matrix \n"
" A(%ix%i) and matrix B(%ix%i)\n\n", m, p, p, n);
alpha = 1.0; beta = 0.0;
printf(" Allocating memory for matrices aligned on 64-byte boundary for better \n"
" performance \n\n");
return 1;
}
printf(" Intializing matrix data \n\n");
for (i = 0; i < (m * p); i++) {
A[i] = (double)(i + 1);
}
for (i = 0; i < (p * n); i++) {
B[i] = (double)(-i - 1);
}
for (i = 0; i < (m * n); i++) {
C[i] = 0.0;
} clock_t startTime = clock();
for (i = 0; i < m; i++) {
for (j = 0; j < n; j++) {
}
}
clock_t endTime = clock();
s_elapsed = (endTime - startTime) / LOOP_COUNT;
printf(" == Matrix multiplication using triple nested loop completed == \n"
" == at %.5f milliseconds == \n\n", (s_elapsed * 1000));
printf(" Deallocating memory \n\n");
free(A);
free(B);
free(C);
if (s_elapsed < 0.9 / LOOP_COUNT) {
s_elapsed = 1.0 / LOOP_COUNT / s_elapsed;
" of measurements\n\n", i);
}
printf(" Example completed. \n\n");
return 0;