[OMPI users] MPI_Alltoall with Vector Datatype

2014-05-07 Thread Spenser Gilliland
nk*4/wsize*4], 1, mpi_all_t, A[rank*4/wsize*4], 1, mpi_all_t, MPI_COMM_WORLD); for(int i = 0; i < 4; i++) { for (j = 0; j < 4; j++) { printf("%6.2g") } printf("\n"); } -- Spenser Gilliland Computer Engineer Doctoral Candidate

Re: [OMPI users] MPI_Alltoall with Vector Datatype

2014-05-07 Thread Spenser Gilliland
s for your insight. Thanks, Spenser -- Spenser Gilliland Computer Engineer Doctoral Candidate

Re: [OMPI users] MPI_Alltoall with Vector Datatype

2014-05-07 Thread Spenser Gilliland
ion using MPI derived datatypes with * MPI collective communications. * * Author: Spenser Gilliland */ #include #include #include #define N (8) float matrix[N][N]; void print_matrix(int wrank, int wrows) { int i , j; MPI_Barrier(MPI_COMM_WORLD); if(wrank == 0) printf(&qu

Re: [OMPI users] MPI_Alltoall with Vector Datatype

2014-05-08 Thread Spenser Gilliland
the local transpose it is altering the data that the other processors sent it? Thanks, Spenser -- Spenser Gilliland Computer Engineer Doctoral Candidate

Re: [OMPI users] MPI_Alltoall with Vector Datatype

2014-05-08 Thread Spenser Gilliland
d that process rank 1 with PID 9314 on node jarvis.cs.iit.edu exited on signal 11 (Segmentation fault). ------ -- Spenser Gilliland Computer Engineer Doctoral Candidate

Re: [OMPI users] MPI_Alltoall with Vector Datatype

2014-05-08 Thread Spenser Gilliland
o that out of bound > reads and writes will be obvious. > > Cheers, > > Matthieu > > 2014-05-08 21:16 GMT+02:00 Spenser Gilliland : >> George & Mattheiu, >> >>> The Alltoall should only return when all data is sent and received on >>> the curren

Re: [OMPI users] MPI_Alltoall with Vector Datatype

2014-05-08 Thread Spenser Gilliland
h means that the size is correct (using 4 byte floats with 2 processor on an 8x8 array this would be the 30th element). There's a similar drawing to what you made attached that's more focused on the specific instance in this code. Hopefully, this clears up the algorithm a b

Re: [OMPI users] MPI_Alltoall with Vector Datatype

2014-05-08 Thread Spenser Gilliland
e specific? I really want to get this working. Thanks, Spenser -- Spenser Gilliland Computer Engineer Doctoral Candidate

Re: [OMPI users] MPI_Alltoall with Vector Datatype

2014-05-08 Thread Spenser Gilliland
5:43 PM, Spenser Gilliland wrote: > George, > >> The alltoall exchanges data from all nodes to all nodes, including the >> local participant. So every participant will write the same amount of >> data. > > Yes, I believe that is what my code is doing. However, I

[OMPI users] Intercommunicators Collective Communciation

2014-05-09 Thread Spenser Gilliland
Hi, I'm having some trouble understanding Intercommunicators with Collective Communication. Is there a collective routine to express a transfer from all left process to all right processes? or vice versa? Thanks, Spenser -- Spenser Gilliland Computer Engineer Doctoral Candidate

Re: [OMPI users] Intercommunicators Collective Communciation

2014-05-09 Thread Spenser Gilliland
efine rank. Thanks, Spenser On May 9, 2014 7:22 PM, "Jeff Squyres (jsquyres)" wrote: > On May 9, 2014, at 7:56 PM, Spenser Gilliland > wrote: > > > I'm having some trouble understanding Intercommunicators with > > Collective Communication. Is there a collecti