trying optimize doitgen

polybench-c-4.2.1-beta/linear-algebra/kernels/doitgen/doitgen_optimized.c

@@ -75,13 +75,16 @@ void kernel_doitgen(int nr, int nq, int np,
       #pragma omp ordered
     for (r = 0; r < _PB_NR; r++){
       
+  #pragma omp parallel for 
       for (p = 0; p < _PB_NP; p++)
       	sum[p] = SCALAR_VAL(0.0);
       
+  #pragma omp parallel for 
       for (s = 0; s < _PB_NP; s++)
         for (p = 0; p < _PB_NP; p++)
           sum[p] += A[r][q][s] * C4[s][p];
 
+  #pragma omp parallel for 
       for (p = 0; p < _PB_NP; p++)
 	      A[r][q][p] = sum[p];
     }