Question

In the following C code I am using OpenMP in a nested loop. Since race condition occurs, I want to perform atomic operations at the end:

double mysumallatomic() {

  double S2 = 0.;
  #pragma omp parallel for shared(S2)
  for(int a=0; a<128; a++){
    for(int b=0; b<128;b++){
      double myterm = (double)a*b;
      #pragma omp atomic
      S2 += myterm;
    }
  }
  return S2;
}

The thing is that #pragma omp atomic has no effect on the program behaviour, even if I remove it, nothing happens. Even if I change it to #pragma oh_my_god, I get no error!

I wonder what is going wrong here, whether I can tell the compiler to be more strict when checking omp pragmas or why I do not get an error when I make the last change

PS: For compilation I use:

gcc-4.2 -fopenmp main.c functions.c -o main_elec_gcc.exe

PS2: New code that gives me the same problem and based on gillespie idea:

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

#define NRACK 64
#define NSTARS 1024

double mysumallatomic_serial(float rocks[NRACK][3], float moon[NSTARS][3],
                             float qr[NRACK],float ql[NSTARS]) {
  int j,i;
  float temp_div=0.,temp_sqrt=0.;
  float difx,dify,difz;
  float mod2x, mod2y, mod2z;
  double S2 = 0.;

  for(j=0; j<NRACK; j++){
    for(i=0; i<NSTARS;i++){     
      difx=rocks[j][0]-moon[i][0];
      dify=rocks[j][1]-moon[i][1];
      difz=rocks[j][2]-moon[i][2];
      mod2x=difx*difx;
      mod2y=dify*dify;
      mod2z=difz*difz;
      temp_sqrt=sqrt(mod2x+mod2y+mod2z);
      temp_div=1/temp_sqrt;
      S2 += ql[i]*temp_div*qr[j];       
    }
  }
  return S2;
}

double mysumallatomic(float rocks[NRACK][3], float moon[NSTARS][3], 
                      float qr[NRACK],float ql[NSTARS]) {
  float temp_div=0.,temp_sqrt=0.;
  float difx,dify,difz;
  float mod2x, mod2y, mod2z;
  double S2 = 0.;

  #pragma omp parallel for shared(S2)
  for(int j=0; j<NRACK; j++){
    for(int i=0; i<NSTARS;i++){
      difx=rocks[j][0]-moon[i][0];
      dify=rocks[j][1]-moon[i][1];
      difz=rocks[j][2]-moon[i][2];
      mod2x=difx*difx;
      mod2y=dify*dify;
      mod2z=difz*difz;
      temp_sqrt=sqrt(mod2x+mod2y+mod2z);
      temp_div=1/temp_sqrt;
      float myterm=ql[i]*temp_div*qr[j];    
      #pragma omp atomic
      S2 += myterm;
    }
  }
  return S2;
}
int main(int argc, char *argv[]) {
  float rocks[NRACK][3], moon[NSTARS][3];
  float qr[NRACK], ql[NSTARS];
  int i,j;

  for(j=0;j<NRACK;j++){
    rocks[j][0]=j;
    rocks[j][1]=j+1;
    rocks[j][2]=j+2;
    qr[j] = j*1e-4+1e-3;
    //qr[j] = 1;
  }

  for(i=0;i<NSTARS;i++){
    moon[i][0]=12000+i;
    moon[i][1]=12000+i+1;
    moon[i][2]=12000+i+2;
    ql[i] = i*1e-3 +1e-2 ;
    //ql[i] = 1 ;
  }
  printf(" serial: %f\n", mysumallatomic_serial(rocks,moon,qr,ql));
  printf(" openmp: %f\n", mysumallatomic(rocks,moon,qr,ql));
  return(0);
}

Answer 1

1. Using the flag -Wall highlights pragma errors. For example, when I misspell atomic I get the following warning.

   main.c:15: warning: ignoring #pragma omp atomic1

2. I’m sure you know, but just in case, your example should be handled with a reduction

3. When you use omp parallel, the default is for all variables to be shared. This is not what you want in your case. For example, each thread will have a different value difx. Instead, your loop should be:

   #pragma omp parallel for default(none),\
   private(difx, dify, difz, mod2x, mod2y, mod2z, temp_sqrt, temp_div, i, j),\
   shared(rocks, moon, ql, qr), reduction(+:S2)
   for(j=0; j<NRACK; j++){
     for(i=0; i<NSTARS;i++){
       difx=rocks[j][0]-moon[i][0];
       dify=rocks[j][1]-moon[i][1];
       difz=rocks[j][2]-moon[i][2];
       mod2x=difx*difx;
       mod2y=dify*dify;
       mod2z=difz*difz;
       temp_sqrt=sqrt(mod2x+mod2y+mod2z);
       temp_div=1/temp_sqrt;
       S2 += ql[i]*temp_div*qr[j];  
     }
   }