The description for MPI_GATHERV says (from http://www.mpi-forum.org/docs/mpi22-report/node95.htm#Node95):
The specification of counts, types, and displacements should not cause any location on the root to be written more than once. Such a call is erroneous. The ``in place'' option for intracommunicators is specified by passing MPI_IN_PLACE as the value of sendbuf at the root. In such a case, sendcount and sendtype are ignored, and the contribution of the root to the gathered vector is assumed to be already in the correct place in the receive buffer So if I understand your situation properly, you should be using MPI_IN_PLACE -- meaning that in general, you're probably getting lucky even if it works with Open MPI. On Sep 16, 2010, at 6:01 PM, Tom Rosmond wrote: > I am working with a Fortran 90 code with many MPI calls like this: > > call mpi_gatherv(x,nsize(rank+1), > mpi_real,x,nsize,nstep,mpi_real,root,mpi_comm_world,mstat) > > 'x' is allocated on root to be large enough to hold the results of the > gather, other arrays and parameters are defined correctly, and the code > runs as it should. However, I am concerned that having the same send > and receive buffer on root is a violation of the MPI standard. Am I > correct? I am aware of the MPI_IN_PLACE feature that can be used in > this situation, by defining it as the send buffer at root. > > The fact that the code as written seems to work on most system we run on > (some with OpenMPI, some with proprietary MPI's) indicates that in spite > of the standard, implementations allow it. Is this correct, or are we > just lucky. > > T. Rosmond > > > > _______________________________________________ > users mailing list > us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/users -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
