source: CIVL/examples/pthread/mpithreads_threads.cvl@ 37bfb99

/*****************************************************************************
* SOURCE: This is a translation of a Pthread program from the Lawrence Livermore
* Computing Center POSIX Threads Programming Exercise at:
* https://computing.llnl.gov/tutorials/pthreads/exercise.html
* FILE: mpithreads_threads.cvl
* DESCRIPTION:
*   This simple program illustrates the use of Pthreads in a program obtained
*   by modifying a serial code that performs a dot product. It is the second
*   of four codes used to show the progression from a serial program to a
*   hybrid MPI/Pthreads program.  The other relevant codes are:
*      - mpithreads_serial.c   - The serial version
*      - mpithreads_mpi.c - A distributed memory programming model with MPI
*      - mpithreads_both.c - A hybrid model that utilizes both MPI and
*          Pthreads to execute on systems that are comprised of clusters
*          of SMP's.
*   The main data is made available to all threads through a globally 
*   accessible structure. Each thread works on a different part of the 
*   data.  The main thread waits for all the threads to complete their 
*   computations, and then it prints the resulting sum.
* Command line execution:
* civl verify -inputMAXTHRDS=8 -inputVECLEN=100 mpithreads_thread.cvl
******************************************************************************/
#include "pthread.cvh"
#include <civlc.h>
#include <stdio.h>
#include <stdlib.h>

/*   
The following structure contains the necessary information to allow the 
function "dotprod" to access its input data and place its output into 
the structure.  This structure is unchanged from the sequential version.
*/

typedef struct 
 {
   double      *a;
   double      *b;
   double     sum; 
   int     veclen; 
 } DOTDATA;

/* Define globally accessible variables and a mutex */

$input int MAXTHRDS;
$input int VECLEN;
DOTDATA dotstr; 
pthread_t callThd[MAXTHRDS];
pthread_mutex_t mutexsum;

/*
The function dotprod is activated when the thread is created.  As before, 
all input to this routine is obtained from a structure of type DOTDATA and 
all output from this function is written into this structure. The benefit 
of this approach is apparent for the multi-threaded program: when a thread 
is created we pass a single argument to the activated function - typically 
this argument is a thread number. All the other information required by the 
function is accessed from the globally accessible structure. 
*/

void *dotprod(void *arg)
{

   /* Define and use local variables for convenience */

   int i, start, end, len ;
   long offset;
   double mysum, *x, *y;
   offset = (long)*arg;
     
   len = dotstr.veclen;
   start = offset*len;
   end   = start + len;
   x = dotstr.a;
   y = dotstr.b;

   /*
   Perform the dot product and assign result to the appropriate variable in 
   the structure. 
   */

   mysum = 0;
   for (i=start; i<end ; i++) 
    {
      mysum += (x[i] * y[i]);
    }

   /*
   Lock a mutex prior to updating the value in the shared structure, and 
   unlock it upon updating.
   */
   pthread_mutex_lock (&mutexsum);
   printf("Thread %d adding partial sum of %f to global sum of %f\n",
          arg, mysum, dotstr.sum); // Removed l from %ld
   dotstr.sum += mysum;
   pthread_mutex_unlock (&mutexsum);

   pthread_exit(NULL, false, NULL, 0);
}

/* 
The main program creates threads which do all the work and then print out 
result upon completion. Before creating the threads, the input data is 
created. Since all threads update a shared structure, we need a mutex for 
mutual exclusion. The main thread needs to wait for all threads to complete, 
it waits for each one of the threads. We specify a thread attribute value 
that allow the main thread to join with the threads it creates. Note also 
that we free up handles  when they are no longer needed.
*/

int main (void)
{
long t[MAXTHRDS];
long i;
double *a, *b;
void *status;
pthread_attr_t attr;

/* Assign storage and initialize values */
a = (double*) malloc (MAXTHRDS*VECLEN*sizeof(double));
b = (double*) malloc (MAXTHRDS*VECLEN*sizeof(double));
  
for (i=0; i<VECLEN*MAXTHRDS; i++) {
  a[i]=1;
  b[i]=a[i];
  }

dotstr.veclen = VECLEN; 
dotstr.a = a; 
dotstr.b = b; 
dotstr.sum=0;

pthread_mutex_init(&mutexsum, NULL);
         
/* Create threads to perform the dotproduct  */
pthread_attr_init(&attr);
pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_JOINABLE);

for(i=0;i<MAXTHRDS;i++) {
  /* Each thread works on a different set of data.
  The offset is specified by 'i'. The size of
  the data for each thread is indicated by VECLEN.
  */
  t[i] = i;
  pthread_create( &callThd[i], &attr, dotprod, (void *)&t[i]); 
  }

pthread_attr_destroy(&attr);

/* Wait on the other threads */
for(i=0;i<MAXTHRDS;i++) {
  pthread_join( callThd[i], &status);
  }

/* After joining, print out the results and cleanup */
printf ("Done. Threaded version: sum =  %f \n", dotstr.sum);
free (a);
free (b);
pthread_mutex_destroy(&mutexsum);
pthread_exit(NULL, true, NULL, 0);
return 0;
}