The For Directive

Within a parallel region we often want to implement a for loop. If we use for alone, the entire loop will be replicated by each thread, when we want it distributed among the team. But using parallel for will not usually work or do what we want. OpenMP provides a directive specifically for this situation, the fo directive. It should be used within a parallel region.

Like the omp parallel for, this construct requires that the for/do loop be in canonical form, as defined by the OpenMP standard. For the most part, this means the loop variable must be an integer, the upper bound must be a simple arithmetic expression involving the loop variable, and the increment must be an addition and/or multiplication of the loop variable. (See the standard section cited above for detailed specifics.)

Syntax:

C/C++

#pragma omp parallel
{
    code
    #pragma omp for
    for (int i=0; i<N; i++) {
        code
    }
}

Example

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

int main(int argc, char *argv[]){

    #pragma omp parallel
    {
        int tid=omp_get_thread_num();
        printf("Hello from thread %d\n",tid);
    }
    
    return 0;
}

Fortran

!$omp parallel
    code
    !$omp do
        code
    !$omp end do
!$omp end parallel

Reminder to Fortran programmers: Fortran parallel regions often require a private clause because most Fortran programs do not use block statements and variables are not declared within the parallel region.

Example

program omp_par
use omp_lib

   integer :: tid

   !$omp parallel private(tid)
   tid=omp_get_thread_num()
   write(*,'(a,i4)') "Hello from thread ",tid
   !$omp end parallel

end program

Python (for omp4py)

with omp("parallel"):
    code
    with omp("for"):
        code

Like Fortran, Python can also require a private clause. In this example, the omp for directive can only include a for loop, nothing more, so we initialize its loop variable outside it and thus must add the private clause.

Example

from omp4py import *

@omp
def hello():
    with omp("parallel"):
        tid=omp_get_thread_num()
        print(f"Hello from thread {tid}")
    
hello()