Lesson 12

Date: 4/16/2014
High Performance Computing (part I)
Linux for Engineering and IT applications


Parallel regions and loops

Exercise
  • Simple "Hello World" program. Every thread executes all code enclosed in the parallel section. OpenMP library routines are used to obtain thread identifiers and total number of threads.
    C / C++ - Parallel Region Example 
    #include <omp.h>
#include <stdio.h>

main ()  {

int nthreads, tid;

/* Fork a team of threads with each thread having a private tid variable */
#pragma omp parallel private(tid)
  {

  /* Obtain and print thread id */
  tid = omp_get_thread_num();
  printf("Hello World from thread = %d\n", tid);

  /* Only master thread does this */
  if (tid == 0) 
    {
    nthreads = omp_get_num_threads();
    printf("Number of threads = %d\n", nthreads);
    }

  }  /* All threads join master thread and terminate */

}
    Copy the content of the code above into file hello.c, then compile and run it as follows: 
    gcc -fopenmp -o hello.x hello.c
export OMP_NUM_THREADS=4
./hello.x

    C / C++ - for Directive Example 
    #include <stdio.h>
#include <omp.h>

#define CHUNKSIZE 100
#define N     1000

main ()  
{

int i, chunk, tid;
float a[N], b[N], c[N];

/* Some initializations */
for (i=0; i < N; i++)
  a[i] = b[i] = i * 1.0;
chunk = CHUNKSIZE;

#pragma omp parallel shared(a,b,c,chunk) private(i)
  {

  #pragma omp for schedule(dynamic,chunk) nowait
  for (i=0; i < N; i++)
   {
     c[i] = a[i] + b[i];

      /* Obtain and print thread id and array index number */
     tid = omp_get_thread_num();
     printf("thread = %d, i = %d\n", tid, i);
   }

  }  /* end of parallel section */

}
    Copy the content of the code above into file for.c, then compile and run it as follows: 
    gcc -fopenmp -o for.x for.c
export OMP_NUM_THREADS=4
./for.x
    Run ./for.x several times and observe how the array elements are distributed across the threads.



    • Take me to the Course Website