#include <omp.h>
#include <stdio.h>

// OpenMP example:  finds mean number of mutual outlinks, among all
// pairs of Web sites in our set

int n,  // number of sites (will assume n is even)
    nth,  // number of threads (will assume n/2 divisible by nth)
    *m, // link matrix
    tot = 0; // grand total of matches

// processes row pairs (i,i+1), (i,i+2), ...
int procpairs(int i)
{  int j,k,sum=0;
   for (j = i+1; j < n; j++) {
      for (k = 0; k < n; k++) 
         sum += m[n*i+k] * m[n*j+k];
   }
   return sum;
}

float dowork()
{ 
   #pragma omp parallel
   {  int pn1,pn2,i,mysum=0;
      int me = omp_get_thread_num();
      nth = omp_get_num_threads(); 
      // in checking all (i,j) pairs, partition the work according to i;
      // to get good load balance, this thread me will handle all i that equal
      // me mod nth
      for (i = me; i < n; i += nth) {
         mysum += procpairs(i);
      }
      #pragma omp atomic
      tot += mysum;
      #pragma omp barrier
   }
   int divisor = n * (n-1) / 2;
   return ((float) tot)/divisor;
}

int main(int argc, char **argv)
{   int n2 = n/2,i,j;
    n = atoi(argv[1]);  // number of matrix rows/cols
    int msize = n * n * sizeof(int);  
    m = (int *) malloc(msize);  
    // as a test, fill matrix with random 1s and 0s
    for (i = 0; i < n; i++) {
       m[n*i+i] = 0;
       for (j = 0; j < n; j++) {
          if (j != i) m[i*n+j] = rand() % 2;
       }
    }
    if (n < 10) {
       for (i = 0; i < n; i++) {
          for (j = 0; j < n; j++) printf("%d  ",m[n*i+j]);
          printf("\n");
       }
    }
    tot = 0;
    float meanml = dowork();
    printf("mean = %f\n",meanml);
}