On Sep 1, 2009, at 4:57 AM, Ashika Umanga Umagiliya wrote:
It worked fine.But I have small issue.Following code demonstrates
how I use mpi::intercommunicator.But in the spawned child processes,
the intercommunicator size is same as number of spawned
processes.But it should be 1 ,right?
Because,I execute the manager process (manager.cpp) as "mpirun -np 1
manager" .So there should be only one process.
I'm not familiar with the details of Boost.MPI, but when you call
MPI_COMM_SPAWN, the resulting intercommunicator will have a remote
group size of the number of processes that were spawned and the local
group size of the number of processes that invoked MPI_COMM_SPAWN.
Hence, in your case (mpirun -np 1 manager), the local group size will
be 1 and the remote group size will be 5.
manager.cpp (manager process which spawns child processes) - rank 0
------------------------------------------------------------
int main(int argc,char *argv[]) {
mpi::environment evn(argc,argv);
mpi::communicator world;
MPI_Comm everyone;
//spawn 5 child processes.
MPI_Comm_spawn("./worker", MPI_ARGV_NULL, 5,
MPI_INFO_NULL, 0, MPI_COMM_SELF, &everyone,
MPI_ERRCODES_IGNORE);
intercommunicator intcomm(everyone,comm_duplicate);
if(rank==0){
GPSPosition *obj=new GPSPosition(100,200,300);
shared_ptr<Position> pos(new Position);
pos->setVals();
obj->addP(pos);
intcomm.send(0,100,obj);
}
return 0;
}
--
Jeff Squyres
jsquy...@cisco.com
