gen()

#include 
#include 

#define         N1      5000
#define         N2      5000


void gen( int** a, int** b)
{
        int i, j;
        for (i = 0; i < N1; i++) {
                for (j = 0; j < N2; j++) {
                        srand( 0 );
                        a[i][j] = rand() % 5 + 1;
                        srand( 1 );
                        b[i][j] = rand() % 5 + 1;
                }
                //printf("i: %d\n", i);
        }
        pthread_exit(NULL);
}

void mul( int** a, int** b)
{
        int i, j, k;
        int c[N1][N2];

        for (i = 0; i < N1; i++) {
                for (j = 0;j < N2; j++) {
                        c[i][j] = 0;
                        for (k = 0; k < N1; k++)
                                c[i][j] += a[i][k] * b[k][j];
                        //printf("%d\t", c[i][j]);
                }
                //printf("\n");
        }
}

int main(int argc, char *argv[])
{
        int** a = NULL;
        int** b = NULL;
        int** c = NULL;

        a = (int**) malloc( sizeof(int) * N1 * N2);
        b = (int**) malloc( sizeof(int) * N1 * N2);
        c = (int**) malloc( sizeof(int) * N1 * N2);

        pthread_t* thread = NULL;
        thread = (pthread_t*) malloc( sizeof(pthread_t) * N1);
        int result;

        int i;
        for (i = 0; i < N1; i++) {
                a[i] = (int *) malloc( sizeof(int) * N2);
                b[i] = (int *) malloc( sizeof(int) * N2);
                c[i] = (int *) malloc( sizeof(int) * N2);
        }

        gen(a, b);

        return 0;
}

$ gcc m1.c && time ./a.out

real    3m55.660s
user    3m55.391s
sys     0m0.184s

This result without threading.