/* L-8 MCS 572 Fri 27 Jan 2012 : fan_out_integers
 * This program fans out an array of 800 integers over 8 processors,
 * so it must be executed with "mpirun -np 8".
 * To synchronize the printing, MPI_Barrier is used. */

#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <mpi.h>

#define size 80    /* size of the problem */
#define tag 100    /* tag of send/recv */
#define v 1        /* verbose flag */

int parity_offset ( int n, int s );
/* returns the offset of node with label n
 * for data of size s based on parity of n */

int main ( int argc, char *argv[] )
{
   int myid,p,s,i,j,d,b;
   int A[size];

   MPI_Status status;
   MPI_Init(&argc,&argv);
   MPI_Comm_size(MPI_COMM_WORLD,&p);
   MPI_Comm_rank(MPI_COMM_WORLD,&myid);

   if(myid == 0) /* manager initializes */
      for(i=0; i<size; i++) A[i] = i;

   s = size;
   for(i=0,d=1; i<3; i++,d*=2) /* A is fanned out */
   {
      s = s/2;
      if(v>0) MPI_Barrier(MPI_COMM_WORLD);
      if(myid == 0) if(v > 0) printf("stage %d, d = %d :\n",i,d);
      if(v>0) MPI_Barrier(MPI_COMM_WORLD);
      for(j=0; j<d; j++)
      {
         b = parity_offset(myid,size);
         if(myid == j)
         {
            if(v>0) printf("%d sends %d integers to %d at %d, start %d\n",
                           j,s,j+d,b+s,A[b+s]);
            MPI_Send(&A[b+s],s,MPI_INT,j+d,tag,MPI_COMM_WORLD);
         }
         else if(myid == j+d)
         {
            MPI_Recv(&A[b],s,MPI_INT,j,tag,MPI_COMM_WORLD,&status);
            if(v>0) printf("%d received %d integers from %d at %d, start %d\n",
                           j+d,s,j,b,A[b]);
         }
      }
   }
   if(v > 0) MPI_Barrier(MPI_COMM_WORLD);
   if(v > 0) if(myid == 0) printf("data at all nodes :\n");
   if(v > 0) MPI_Barrier(MPI_COMM_WORLD);
   printf("%d has %d integers starting at %d with %d, %d, %d\n",
          myid,size/p,b,A[b],A[b+1],A[b+2]);
   MPI_Finalize();
   return 0;
}

int parity_offset ( int n, int s )
{
   int offset = 0;
   s = s/2;
   while(n > 0)
   {
      int d = n % 2;
      if(d > 0) offset += s;
      n = n/2;
      s = s/2;
   }
   return offset;
}