Compiling your parallel code

The -par-schedule<keyword>=n option specifies a scheduling algorithm for DO loop iterations. <keyword> specifies the scheduling algorithm and can be any of

      PROGRAM WORKSHARE1

      INTEGER NTHREADS, TID, OMP_GET_NUM_THREADS,
     +  OMP_GET_THREAD_NUM, N, CHUNKSIZE, CHUNK, I
      PARAMETER (N=100)
      PARAMETER (CHUNKSIZE=10) 
      REAL A(N), B(N), C(N)

!     Some initializations
      DO I = 1, N
        A(I) = I * 1.0
        B(I) = A(I)
      ENDDO
      CHUNK = CHUNKSIZE

!$OMP PARALLEL SHARED(A,B,C,NTHREADS,CHUNK) PRIVATE(I,TID)

      TID = OMP_GET_THREAD_NUM()
      IF (TID .EQ. 0) THEN
        NTHREADS = OMP_GET_NUM_THREADS()
        PRINT *, 'Number of threads =', NTHREADS
      END IF
      PRINT *, 'Thread',TID,' starting...'

!$OMP DO SCHEDULE(DYNAMIC,CHUNK)
      DO I = 1, N
        C(I) = A(I) + B(I)
        WRITE(*,100) TID,I,C(I)
 100    FORMAT(' Thread',I2,': C(',I3,')=',F8.2)
      ENDDO
!$OMP END DO NOWAIT

      PRINT *, 'Thread',TID,' done.'

!$OMP END PARALLEL

      END

/******************************************************************************
* FILE: mpi_array.c
* DESCRIPTION: 
*   MPI Example - Array Assignment - C Version
*   This program demonstrates a simple data decomposition. The master task
*   first initializes an array and then distributes an equal portion that
*   array to the other tasks. After the other tasks receive their portion
*   of the array, they perform an addition operation to each array element.
*   They also maintain a sum for their portion of the array. The master task 
*   does likewise with its portion of the array. As each of the non-master
*   tasks finish, they send their updated portion of the array to the master.
*   An MPI collective communication call is used to collect the sums 
*   maintained by each task.  Finally, the master task displays selected 
*   parts of the final array and the global sum of all array elements. 
*   NOTE: the number of MPI tasks must be evenly disible by 4.
* AUTHOR: Blaise Barney
* LAST REVISED: 04/13/05
****************************************************************************/
#include "mpi.h"
#include 
#include 
#define  ARRAYSIZE	16000000
#define  MASTER		0

float  data[ARRAYSIZE];

int main (int argc, char *argv[])
{
int   numtasks, taskid, rc, dest, offset, i, j, tag1,
      tag2, source, chunksize; 
float mysum, sum;
float update(int myoffset, int chunk, int myid);
MPI_Status status;

/***** Initializations *****/
MPI_Init(&argc, &argv);
MPI_Comm_size(MPI_COMM_WORLD, &numtasks);
if (numtasks % 4 != 0) {
   printf("Quitting. Number of MPI tasks must be divisible by 4.\n");
   MPI_Abort(MPI_COMM_WORLD, rc);
   exit(0);
   }
MPI_Comm_rank(MPI_COMM_WORLD,&taskid);
printf ("MPI task %d has started...\n", taskid);
chunksize = (ARRAYSIZE / numtasks);
tag2 = 1;
tag1 = 2;

/***** Master task only ******/
if (taskid == MASTER){

  /* Initialize the array */
  sum = 0;
  for(i=0; i<5; j++) 
      printf("  %e",data[offset+j]);
    printf("\n");
    offset = offset + chunksize;
    }
  printf("*** Final sum= %e ***\n",sum);

  }  /* end of master section */



/***** Non-master tasks only *****/

if (taskid > MASTER) {

  /* Receive my portion of array from the master task */
  source = MASTER;
  MPI_Recv(&offset, 1, MPI_INT, source, tag1, MPI_COMM_WORLD, &status);
  MPI_Recv(&data[offset], chunksize, MPI_FLOAT, source, tag2, 
    MPI_COMM_WORLD, &status);

  mysum = update(offset, chunksize, taskid);

  /* Send my results back to the master task */
  dest = MASTER;
  MPI_Send(&offset, 1, MPI_INT, dest, tag1, MPI_COMM_WORLD);
  MPI_Send(&data[offset], chunksize, MPI_FLOAT, MASTER, tag2, MPI_COMM_WORLD);

  MPI_Reduce(&mysum, &sum, 1, MPI_FLOAT, MPI_SUM, MASTER, MPI_COMM_WORLD);

  } /* end of non-master */


MPI_Finalize();

}   /* end of main */


float update(int myoffset, int chunk, int myid) {
  int i; 
  float mysum;
  /* Perform addition to each of my array elements and keep my sum */
  mysum = 0;
  for(i=myoffset; i < myoffset + chunk; i++) {
    data[i] = data[i] + i * 1.0;
    mysum = mysum + data[i];
    }
  printf("Task %d mysum = %e\n",myid,mysum);
  return(mysum);
  }

/******************************************************************************
* FILE: arrayloops.c
* DESCRIPTION:
*   Example code demonstrating decomposition of array processing by
*   distributing loop iterations.  A global sum is maintained by a mutex
*   variable.  
* AUTHOR: Blaise Barney
* LAST REVISED: 04/05/05
******************************************************************************/
#include 

#include 
#include 

#define NTHREADS      4
#define ARRAYSIZE   1000000
#define ITERATIONS   ARRAYSIZE / NTHREADS

double  sum=0.0, a[ARRAYSIZE];
pthread_mutex_t sum_mutex;


void *do_work(void *tid) 
{
  int i, start, *mytid, end;
  double mysum=0.0;

  /* Initialize my part of the global array and keep local sum */
  mytid = (int *) tid;
  start = (*mytid * ITERATIONS);
  end = start + ITERATIONS;
  printf ("Thread %d doing iterations %d to %d\n",*mytid,start,end-1); 
  for (i=start; i < end ; i++) {
    a[i] = i * 1.0;
    mysum = mysum + a[i];
    }

  /* Lock the mutex and update the global sum, then exit */
  pthread_mutex_lock (&sum_mutex);
  sum = sum + mysum;
  pthread_mutex_unlock (&sum_mutex);
  pthread_exit(NULL);
}


int main(int argc, char *argv[])
{
  int i, start, tids[NTHREADS];
  pthread_t threads[NTHREADS];
  pthread_attr_t attr;

  /* Pthreads setup: initialize mutex and explicitly create threads in a
     joinable state (for portability).  Pass each thread its loop offset */
  pthread_mutex_init(&sum_mutex, NULL);
  pthread_attr_init(&attr);
  pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_JOINABLE);
  for (i=0; i