> On Mar 24, 2016, at 4:51 PM, Gilles Gouaillardet <gil...@rist.or.jp> wrote: > > Jeff, > > from mpi 3.1 page 217 > >> Finally, in multithreaded implementations, one can have more than one, >> concurrently >> executing, collective communication call at a process. In these situations, >> it is the user's responsibility >> to ensure that the same communicator is not used concurrently by two di erent >> collective communication calls at the same process. > > is this what you were thinking of ? >
Yes. Thanks. > in the program that was posted, each thread uses its own communicator, so it > complies with the above lines. > I didn't see the attachment. Sorry. Reading email at the beach appears to be a bad idea on multiple levels :-) You are right that duping the comm for the second file makes this a correct program. Jeff > Cheers, > > Gilles > > >> On 3/25/2016 4:25 AM, Jeff Hammond wrote: >> >> >>> On Thursday, March 24, 2016, Sebastian Rettenberger <rette...@in.tum.de> >>> wrote: >>> Hi, >>> >>> I tried to run the attached program with OpenMPI. It works well with MPICH >>> and Intel MPI but I get a deadlock when using OpenMPI. >>> I am using OpenMPI 1.10.0 with support for MPI_THREAD_MULTIPLE. >>> >>> It seems like ROMIO uses global locks in OpenMPI which is a problem if >>> multiple threads want to do collective I/O. >> >> This isn't valid MPI, if I understand you correctly. I'm not near a copy of >> the standard to be more specific, but you should look at restrictions on >> collective calls like barrier wrt threads in the same proc. >> >> Jeff >> >>> Any idea how one can get around this issue? >>> >>> Best regards, >>> Sebastian >>> >>> -- >>> Sebastian Rettenberger, M.Sc. >>> Technische Universität München >>> Department of Informatics >>> Chair of Scientific Computing >>> Boltzmannstrasse 3, 85748 Garching, Germany >>> http://www5.in.tum.de/ >> >> >> -- >> Jeff Hammond >> jeff.scie...@gmail.com >> http://jeffhammond.github.io/ >> >> >> _______________________________________________ >> users mailing list >> us...@open-mpi.org >> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users >> Link to this post: >> http://www.open-mpi.org/community/lists/users/2016/03/28822.php > > _______________________________________________ > users mailing list > us...@open-mpi.org > Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users > Link to this post: > http://www.open-mpi.org/community/lists/users/2016/03/28823.php
