c - Nested loop in OpenMP -

i need run short outer loop , long inner loop. parallelize latter , not former. reason there array updated after inner loop has run. code using following

#pragma omp parallel{ for(j=0;j<3;j++){   s=0;   #pragma omp reduction(+:s)      for(i=0;i<10000;i++)         s+=1;    a[j]=s; } } 

this hangs. following works fine, i'd rather avoid overhead of starting new parallel region since preceded another.

for(j=0;j<3;j++){   s=0;   #pragma omp parallel reduction(+:s)      for(i=0;i<10000;i++)         s+=1;    a[j]=s;  } 

what correct (and fastest) way of doing this?

the following example should work expected:

#include<iostream>  using namespace std;  int main(){    int s;   int a[3];  #pragma omp parallel   { // note moved curly bracket     for(int j = 0; j < 3; j++) { #pragma omp single                s = 0; #pragma omp reduction(+:s)       for(int i=0;i<10000;i++) {         s+=1;       } // implicit barrier here     #pragma omp single       a[j]=s; // statement needs synchronization     } // end of outer loop   } // end of parallel region    (int jj = 0; jj < 3; jj++)     cout << a[jj] << endl;   return 0; } 

an example of compilation , execution is:

> g++ --version g++ (ubuntu/linaro 4.6.3-1ubuntu5) 4.6.3 copyright (c) 2011 free software foundation, inc. free software; see source copying conditions.  there no warranty; not merchantability or fitness particular purpose. > g++ -fopenmp -wall main.cpp > export omp_num_threads=169 > ./a.out  10000 10000 10000