trying optimize 2mm

polybench-c-4.2.1-beta/linear-algebra/kernels/2mm/2mm_optimized.c

@@ -86,19 +86,23 @@ void kernel_2mm(int ni, int nj, int nk, int nl,
 
 #pragma scop
   /* D := alpha*A*B*C + beta*D */
+#pragma omp for schedule(dynamic)
   for (i = 0; i < _PB_NI; i++)
     for (j = 0; j < _PB_NJ; j++)
 	    tmp[i][j] = SCALAR_VAL(0.0);
 
+#pragma omp for schedule(dynamic)
   for (i = 0; i < _PB_NI; i++)
     for (k = 0; k < _PB_NK; ++k)
       for (j = 0; j < _PB_NJ; j++)
 	      tmp[i][j] += alpha * A[i][k] * B[k][j];
 
+#pragma omp for schedule(dynamic)
   for (i = 0; i < _PB_NI; i++)
     for (j = 0; j < _PB_NL; j++)
 	    D[i][j] *= beta;
 
+#pragma omp for schedule(dynamic)
   for (i = 0; i < _PB_NI; i++)
     for (k = 0; k < _PB_NJ; ++k)
       for (j = 0; j < _PB_NL; j++)