Re: [OMPI users] How openmpi-1.6.3 using nodes which not LSF dispatch?

Thanks Ralph and Jeff, I understand. On 2013年02月05日 03:34, Jeff Squyres (jsquyres) wrote: To be clear: this is a common misconception. Open MPI does not determine which network to use for MPI communication by the hostname(s) you use to launch your application. Specifically: the hostnames tha

Re: [OMPI users] How openmpi-1.6.3 using nodes which not LSF dispatch?

To be clear: this is a common misconception. Open MPI does not determine which network to use for MPI communication by the hostname(s) you use to launch your application. Specifically: the hostnames that you list in the hostfile, command line, or whatever your resource manager provides are *no

Re: [OMPI users] OpenMPI 1.6 with Intel 11 Compiler

Unless you really need VampirTrace, just add --disable-vt to your configure On Feb 4, 2013, at 7:11 AM, Clarinet wrote: > Dear OpenMPI users, > > > I am trying to compile OpenMPI 1.6 (1.6.3) with Intel 11.0.081 set of > compilers. The compilation fails with > > CXXLD otfprofile > otfprofi

[OMPI users] All_to_allv algorithm patch

I'll try running this by the mailing list again, before resigning myself to maintaining this privately I've looked in detail at the current two MPI_Alltoallv algorithms and wanted to raise a couple of ideas. Firstly, the new default "pairwise" algorithm. * There is no optimisation for spa

[OMPI users] Simple MPI hello world hangs over IB

I am trying to debug an issue which is really weird. I have simple MPI hello world application (attached) that hangs when I try to run on our cluster using 256 nodes with 16 cores on each node. The cluster uses QDR IB. I am able to run the test over ethernet by excluding openib from the btl. Howev

[OMPI users] OpenMPI 1.6 with Intel 11 Compiler

Dear OpenMPI users, I am trying to compile OpenMPI 1.6 (1.6.3) with Intel 11.0.081 set of compilers. The compilation fails with CXXLD otfprofile otfprofile-create_latex.o: In function `std::locale::_Impl::_M_remove_reference()': ./create_latex.cpp:(.gnu.linkonce.t._ZNSt6locale5_Impl19_M_r

Re: [OMPI users] Asynchronous parallel I/O concerning MPI_File_write_all_begin() and MPI_File_write_all_end()

Stefan, The MPI definition of progress is pretty loose. There is absolutely no guarantee regarding the asynchrony of any non-blocking or asynchronous operations, more specifically there is no guarantee of progress when the library is outside an MPI call. George. PS: For the file operation an i

[OMPI users] FW: error configuring OpenMPI 1.6.3 with gcc 4.7.2

For completeness to the list and archive in case it helps anyone else now or in the future The problem was due to me not adding the lib64 directory for my gcc build to LD_RUN_PATH, which is needed when gcc is linking other applications, as well as LD_LIBRARY_PATH which is used at run time.