ATL / WTL / STL

#include "mpi.h"

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

#define  ARRAYSIZE	2000

#define  MASTER		0



int  data[ARRAYSIZE];




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

int   numtasks, taskid, rc, dest, offset, i, j, tag1, tag2, source, chunksize, namelen; 

int mysum;

long sum;

int update(int myoffset, int chunk, int myid);
char myname[MPI_MAX_PROCESSOR_NAME];

MPI_Status status;
double start = 0.0, stop = 0.0, time = 0.0;
double totaltime;
FILE *fp;
char line[128];
char element;
int n;
int k=0;




/***** Initializations *****/

MPI_Init(&argc, &argv);

MPI_Comm_size(MPI_COMM_WORLD, &numtasks);

MPI_Comm_rank(MPI_COMM_WORLD,&taskid); 
MPI_Get_processor_name(myname, &namelen);

printf ("MPI task %d has started on host %s...\n", taskid, myname);

chunksize = (ARRAYSIZE / numtasks);

tag2 = 1;

tag1 = 2;

//Read the data from file and store into array


// printf("Initialized array sum = %d\n",sum);


//data = malloc(ARRAYSIZE * sizeof(int));

/***** Master task only ******/

if (taskid == MASTER){

  fp=fopen("integers.txt", "r");
  if(fp != NULL){
   sum = 0;
   while(fgets(line, sizeof line, fp)!= NULL){
    fscanf(fp,"%d",&data[k]);
    sum = sum + data[k]; // calculate sum to verify later on
    k++;
   }
  }


printf("Initialized array sum %d", sum);

  /* Send each task its portion of the array - master keeps 1st part */

  offset = chunksize;

  for (dest=1; dest<numtasks; dest++) {

    MPI_Send(&offset, 1, MPI_INT, dest, tag1, MPI_COMM_WORLD);

    MPI_Send(&data[offset], chunksize, MPI_INT, dest, tag2, MPI_COMM_WORLD);

    printf("Sent %d elements to task %d offset= %d\n",chunksize,dest,offset);

    offset = offset + chunksize;

   }



  /* Master does its part of the work */

  offset = 0;
  mysum = run_kernel(&data[offset], chunksize);
  printf("Kernel returns sum %d", mysum);

  //mysum = update(offset, chunksize, taskid);



  /* Wait to receive results from each task */

  for (i=1; i<numtasks; i++) {

    source = i;

    MPI_Recv(&offset, 1, MPI_INT, source, tag1, MPI_COMM_WORLD, &status);

    MPI_Recv(&data[offset], chunksize, MPI_INT, source, tag2,MPI_COMM_WORLD, &status);

   }



  /* Get final sum and print sample results */  

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



  printf("\n*** Final sum= %d ***\n",sum);



 }  /* end of master section */





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



if (taskid > MASTER) {



  /* Receive my portion of array from the master task */
  start= MPI_Wtime();

  source = MASTER;

  MPI_Recv(&offset, 1, MPI_INT, source, tag1, MPI_COMM_WORLD, &status);

  MPI_Recv(&data[offset], chunksize, MPI_INT, source, tag2,MPI_COMM_WORLD, &status);

  mysum = run_kernel(&data[offset], chunksize);
  printf("\nKernel returns sum %d ", mysum);

// mysum = update(offset, chunksize, taskid);
  stop = MPI_Wtime();
  time = stop -start;
  printf("time taken by process %d to recieve elements and caluclate own sum is = %lf seconds \n", taskid, time);
  
 // totaltime = totaltime + time;



  /* 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_INT, MASTER, tag2, MPI_COMM_WORLD);



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



  } /* end of non-master */



 MPI_Finalize();



}   



int update(int myoffset, int chunk, int myid) {

  int i,j; 

  int mysum = 0;

  for(i=myoffset; i < myoffset + chunk; i++) {

    mysum = mysum + data[i];

    }

  printf("Task %d has sum = %d\n",myid,mysum);

  return(mysum);

}

#include <stdio.h>



__global__ void add(int *devarray, int *devsum)
{
        int index = blockIdx.x * blockDim.x + threadIdx.x;
        devsum = devsum + devarray[index];
}

extern "C"
int * run_kernel(int array[],int nelements)
{
        int  *devarray, *sum, *devsum;
       
        printf("\nrun_kernel called..............");       
        
        cudaMalloc((void**) &devarray, sizeof(int)*nelements);
        cudaMalloc((void**) &devsum, sizeof(int));
        cudaMemcpy(devarray, array, sizeof(int)*nelements, cudaMemcpyHostToDevice);
        add<<<2, 3>>>(devarray, devsum);
       	
	cudaMemcpy(sum, devsum, sizeof(int), cudaMemcpyDeviceToHost);

        printf(" \nthe sum is %d", sum);
        cudaFree(devarray);
	return sum;
        
}

 #include <stdio.h>
#include <stdlib.h>
#include <cuda.h>
#include <cuda_runtime.h>
#include <sys/time.h>
#include <mpi.h>

#define NREPEAT 10
#define NBYTES 10.e6

int main (int argc, char *argv[])
{
int rank, size, n, len, numbytes;
void *a_h, *a_d;
struct timeval time[2];
double bandwidth;
char name[MPI_MAX_PROCESSOR_NAME];
MPI_Status status;

MPI_Init (&argc, &argv);
MPI_Comm_rank (MPI_COMM_WORLD, &rank);
MPI_Comm_size (MPI_COMM_WORLD, &size);

MPI_Get_processor_name(name, &len);
printf("Process %d is on %s\n", rank, name);

printf("Using regular memory \n");
a_h = malloc(NBYTES);

cudaMalloc( (void **) &a_d, NBYTES);

/* Test host -> device bandwidth. */
MPI_Barrier(MPI_COMM_WORLD);

gettimeofday(&time[0], NULL);
for (n=0; n<NREPEAT; n )
{
cudaMemcpy(a_d, a_h, NBYTES, cudaMemcpyHostToDevice);
}
gettimeofday(&time[1], NULL);

bandwidth = time[1].tv_sec - time[0].tv_sec;
bandwidth = 1.e-6*(time[1].tv_usec - time[0].tv_usec);
bandwidth = NBYTES*NREPEAT/1.e6/bandwidth;

printf("Host->device bandwidth for process %d: %f MB/sec\n",rank,bandwidth);

/* Test MPI send/recv bandwidth. */
MPI_Barrier(MPI_COMM_WORLD);

gettimeofday(&time[0], NULL);
for (n=0; n<NREPEAT; n )
{
if (rank == 0)
MPI_Send(a_h, NBYTES/sizeof(int), MPI_INT, 1, 0, MPI_COMM_WORLD);
else
MPI_Recv(a_h, NBYTES/sizeof(int), MPI_INT, 0, 0, MPI_COMM_WORLD, &status);
}
gettimeofday(&time[1], NULL);

bandwidth = time[1].tv_sec - time[0].tv_sec;
bandwidth = 1.e-6*(time[1].tv_usec - time[0].tv_usec);
bandwidth = NBYTES*NREPEAT/1.e6/bandwidth;

if (rank == 0)
printf("MPI send/recv bandwidth: %f MB/sec\n", bandwidth);

cudaFree(a_d);
free(a_h);

MPI_Finalize();
return 0;
}