Hi Daniel, Thanks very much for trying 2.0.1 out and reporting this. Looks like this may be a case of not checking “edge” cases in the use of this collective.
Would you please open an issue? There is currently an issue 2324 related to neighbor collectives, but it isn’t directly related to the problem you found. Thanks, Howard -- Howard Pritchard HPC-DES Los Alamos National Laboratory From: devel <devel-boun...@lists.open-mpi.org<mailto:devel-boun...@lists.open-mpi.org>> on behalf of "Ibanez, Daniel Alejandro" <daib...@sandia.gov<mailto:daib...@sandia.gov>> Reply-To: Open MPI Developers <devel@lists.open-mpi.org<mailto:devel@lists.open-mpi.org>> Date: Saturday, November 12, 2016 at 7:40 AM To: "devel@lists.open-mpi.org<mailto:devel@lists.open-mpi.org>" <devel@lists.open-mpi.org<mailto:devel@lists.open-mpi.org>> Cc: "Roberts, Nathan V" <nvro...@sandia.gov<mailto:nvro...@sandia.gov>>, "Thomas E. Voth" <tev...@software.sandia.gov<mailto:tev...@software.sandia.gov>> Subject: [OMPI devel] regression: MPI_Neighbor_alltoall with empty graph Hello, I'd like to report a bug with OpenMPI version 2.0.1. Attached to this email is a C program that runs with only one MPI rank, uses MPI_Dist_graph_create to create a graph topology with no communication edges, and then uses MPI_Neighbor_alltoall with that graph topology. This results in an error similar to the following: [Dans-MacBook-Air:52159] *** An error occurred in kk1G [Dans-MacBook-Air:52159] *** reported by process [2935488513,0] [Dans-MacBook-Air:52159] *** on communicator MPI COMMUNICATOR 3 CREATE FROM 0 [Dans-MacBook-Air:52159] *** MPI_ERR_INTERN: internal error [Dans-MacBook-Air:52159] *** MPI_ERRORS_ARE_FATAL (processes in this communicator will now abort, [Dans-MacBook-Air:52159] *** and potentially your MPI job) This symptom is exhibited by OpenMPI at git tag v2.0.1 and git hash a49422f (latest commit to master). Note that MPICH 3.3a1 runs this program without error. I have a report that OpenMPI v1.10.4 also runs this program without error, hence I'm labeling it a regression. I am confirming this now and will try git bisect to find the point of regression.
_______________________________________________ devel mailing list devel@lists.open-mpi.org https://rfd.newmexicoconsortium.org/mailman/listinfo/devel
