"Kirk, Benjamin (JSC-EG311)" <benjamin.k...@nasa.gov> writes:
> Jed, does the PETSc team have any experience with the NBC algorithm > deadlocking with OpenMPI-1.7? > > I know they don't officially advertise MPI_Ibarrier(), but it is there... I've had problems with other things in the past, but I don't recall this specific thing breaking. That said, while I have an Open MPI configuration that gets tested sometimes, Open MPI is not the primary MPI implementation on any machines that I frequently use. > See https://github.com/benkirk/mpi_playground.git - I've implemented the > nonblocking consensus & it seems to work reliably with mpich-3 and mpt-2, but > openmpi-1.7 randomly fails. Just curious if this is a known issue, although > some quick searches do not reveal anything. > > -Ben > > > > > ------------------------------------------------------------------------------ > October Webinars: Code for Performance > Free Intel webinars can help you accelerate application performance. > Explore tips for MPI, OpenMP, advanced profiling, and more. Get the most from > the latest Intel processors and coprocessors. See abstracts and register > > http://pubads.g.doubleclick.net/gampad/clk?id=60133471&iu=/4140/ostg.clktrk > _______________________________________________ > Libmesh-devel mailing list > Libmesh-devel@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/libmesh-devel
pgpLbQrsBNK1d.pgp
Description: PGP signature
------------------------------------------------------------------------------ October Webinars: Code for Performance Free Intel webinars can help you accelerate application performance. Explore tips for MPI, OpenMP, advanced profiling, and more. Get the most from the latest Intel processors and coprocessors. See abstracts and register > http://pubads.g.doubleclick.net/gampad/clk?id=60133471&iu=/4140/ostg.clktrk
_______________________________________________ Libmesh-devel mailing list Libmesh-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/libmesh-devel
