//
//コンパイル： gcc *.c -O3(コンパイルの最適化) -fopenmp 
//-----------------------------------------------------------

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

#define N 2048
#define P 8

double A[N][N],B[N][N],C[N][N];

int main(int argc,char *argv[]){
  int i,j,k;
  
  /*Comment out next line if not omp*/
  omp_set_num_threads(P);

  #pragma omp parallel for private(j)
  for(i=0;i<N;i++){
    for(j=0;j<N;j++){
      if(i==j){
	A[i][j] = (double)i+1;
	B[i][j] = 1.0;
      }else{
	A[i][j] = 0.0;
	B[i][j] = 0.0;
      }
    }
  }

  /*forks off the threads and starts*/
  /*the work-sharing constrect*/
  #pragma omp parallel for private(j,k)
  for(i=0;i<N;i++){
    for(j=0;j<N;j++){
      for(k=0;k<N;k++){
	C[i][j] += A[i][k] * B[k][j];
      }
    }
  }
}