void aThreadPerElement(int rowA, int colA, int rowB, int colB, int** a, int** b){
    if (colA != rowB) {
        printf("Matrices cannot be multiplied: Incompatible dimensions.\n");
        return;
    }
    struct timeval stop, start;
    int** c = malloc(rowA * sizeof(int*));
    for(int i = 0; i < rowA; i++){
        c[i] = malloc(colB * sizeof(int));
    }
    pthread_t threads[rowA][colB];
    int rc;
    gettimeofday(&start, NULL);
    for (int i = 0; i < rowA; i++) {
        for (int j = 0; j < colB; j++) {
            c[i][j] = 0;
            struct thread_data *tdata = malloc(sizeof(struct thread_data));
            tdata->a =  a;
            tdata->b =  b;
            tdata->c =  c;
            tdata->colA = colA;
            tdata->colB = colB;
            tdata->rowA = rowA;
            tdata->rowB = rowB;
            tdata->i = i;
            tdata->j = j;
            rc = pthread_create(&threads[i][j], NULL,  n, (void*)tdata);
            if(rc){
                printf("ERROR; return code from pthread_create() is %d\n", rc);
                exit(-1);
            }
        }
    }
    gettimeofday(&stop, NULL);
    for(int i = 0 ; i < rowA ; ++i){
        for(int j = 0 ; j < colB ; ++j) {
            pthread_join(threads[i][j], NULL);
        }
    }
    printf(RED "Multiplication Finished you can see results in c.txt\n" );
    printf("Seconds taken %lu\n", stop.tv_sec - start.tv_sec);
    printf("Microseconds taken: %lu\n", stop.tv_usec - start.tv_usec);
    printf(RESET);
    FILE *fp;
    fp = fopen("c.txt", "w");
    if (fp == NULL) {
        printf("File not found\n");
        return;
    }
    fprintf(fp, "row=%d col=%d\n", rowA, colB);
    for (int i = 0; i < rowA; i++) {
        for (int j = 0; j < colB; j++) {
            fprintf(fp, "%d ", c[i][j]);
        }
        fprintf(fp, "\n");
    }
    fclose(fp);
    free(c);
}