// use MPI_Bsend to send several messages in buffered mode
// note that the total sum of memory(buffer) must be allocated first,
// otherwise it will produce error

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

#define M 3		// the number of times of sending messages

int main( int argc, char** argv )
{  
	int n, i;
	int rank;
	int size;
	int *buf;
	int *abuf;
	int blen;
	int ablen;
	MPI_Status status;

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

	if( size != 2 ) {
		if( rank == 0 ) {
			printf("Error: 2 processes required\n");
			fflush(stdout);
		}
		MPI_Abort(MPI_COMM_WORLD, MPI_ERR_OTHER );
	}

	if( rank == 0 ){
		blen = M * (sizeof(int) + MPI_BSEND_OVERHEAD);
		buf = (int*) malloc(blen);
		MPI_Buffer_attach(buf, blen);
		printf("attached %d bytes\n", blen);
		fflush(stdout);
		for(i = 0; i < M; i ++) {
			printf("starting send %d ...\n", i);
			fflush(stdout);
			n = i;
			MPI_Bsend(&n, 1, MPI_INT, 1, i, MPI_COMM_WORLD );
			printf("complete send %d\n", i);
			fflush(stdout);
			sleep(1);
		}

		MPI_Buffer_detach(&abuf, &ablen);
		printf("detached %d bytes\n", ablen);
		free(abuf);
	} else {
		for(i = M - 1; i >= 0; i --) {
			printf("starting recv %d ...\n", i);
			fflush(stdout);      
			MPI_Recv(&n, M, MPI_INT, 0, i, MPI_COMM_WORLD, &status );
			printf("complete recv: %d. received %d\n", i, n);
			fflush(stdout);
		}
	}

	MPI_Finalize();
	return 0;
}