Re: [hwloc-users] Using hwloc to map GPU layout on system

On Feb 7, 2014, at 9:45 AM, Brice Goglin wrote: > Le 06/02/2014 21:31, Brock Palen a écrit : >> Actually that did turn out to help. The nvml# devices appear to be numbered >> in the way that CUDA_VISABLE_DEVICES sees them, while the cuda# devices are >> in the order

Re: [OMPI users] Can't build openmpi-1.6.5 with latest FCA 2.5 release.

Mike, We checked it over, here is what the guy who knows OFED much better than I do sent me: We are running version 1.3.8.MLNX_20120424-0.1 of libibmad and version 1.3.7.MLNX_20130110_ff06102-0.1 of libibumad. The 1.5.3-4.0.42 release notes indicate that these are the latest versions of the

Re: [OMPI users] Does sendrecv guarantee order?

Thank you Jeff for the clarification. Saliya On Fri, Feb 14, 2014 at 7:06 AM, Jeff Squyres (jsquyres) wrote: > On Feb 13, 2014, at 10:59 PM, Saliya Ekanayake wrote: > > > Anyway, to answer your question I was trying to do sendrecv in a chain > where

Re: [OMPI users] Configure issue with/without HWLOC when PGI used and CUDA support enabled

To avoid a few back-n-forths in email, you might want to send all the diagnostic info here: http://www.open-mpi.org/community/help/ On Feb 14, 2014, at 12:15 PM, Rolf vandeVaart wrote: > I assume your first issue is happening because you configured hwloc with cuda

Re: [OMPI users] one more finding in openmpi-1.7.5a1

On Feb 14, 2014, at 5:59 AM, Reuti wrote: > Am 14.02.2014 um 11:23 schrieb tmish...@jcity.maeda.co.jp: > >> You've found it in the dream, interesting! > > It happens sometimes to get insights while dreaming: > >

Re: [OMPI users] Configure issue with/without HWLOC when PGI used and CUDA support enabled

I assume your first issue is happening because you configured hwloc with cuda support which creates a dependency on libcudart.so. Not sure why that would mess up Open MPI. Can you send me how you configured hwloc? I am not sure I understand the second issue. Open MPI puts everything in lib

Re: [OMPI users] one more finding in openmpi-1.7.5a1

nothing that profound, I fear. Just the old man's brain continuing to itch over something while in that light sleep stage until the scratching gets enough that you realize the cause of the itch :-) On Feb 14, 2014, at 2:59 AM, Reuti wrote: > Am 14.02.2014 um

[OMPI users] Configure issue with/without HWLOC when PGI used and CUDA support enabled

Dear Open MPI developers, I just want to point to a weird behavior of the configure procedure I discovered. I am compiling Open MPI 1.7.4 with CUDA support (CUDA 6.0 RC) and PGI 14.1 If I explicitly compile against a self-compiled version of HWLOC (1.8.1) using this configure line

Re: [OMPI users] Questions on MPI I/O and ompi_info

On Feb 13, 2014, at 7:30 PM, Ralph Castain wrote: > Hmmm...well, a little digging says that we probably didn't do this as > thoroughly as we should have :-/ Actually, it works exactly as we designed it... but the reasons for doing so (and its effects) are a bit obscure.

Re: [OMPI users] Does sendrecv guarantee order?

On Feb 13, 2014, at 10:59 PM, Saliya Ekanayake wrote: > Anyway, to answer your question I was trying to do sendrecv in a chain where > "toSend" and "receiveFrom" ranks are not the same. I was using a single > buffer, which resulted in cases where the buffer content got

Re: [OMPI users] one more finding in openmpi-1.7.5a1

Am 14.02.2014 um 11:23 schrieb tmish...@jcity.maeda.co.jp: > You've found it in the dream, interesting! It happens sometimes to get insights while dreaming: https://skeptics.stackexchange.com/questions/5317/was-the-periodic-table-discovered-in-a-dream-by-dmitri-mendeleyev -- Reuti > Tetsuya

Re: [OMPI users] one more finding in openmpi-1.7.5a1

Thanks - hit me in the middle of the night over here that we had missed some options, but nice to find you had also seen it. Slightly modified patch will be applied and brought over to 1.7.5 On Feb 13, 2014, at 10:16 PM, tmish...@jcity.maeda.co.jp wrote: > > > > Please try attached patch -

Re: [OMPI users] one more finding in openmpi-1.7.5a1

Please try attached patch - from r30723. (See attached file: patch.rmaps_base_frame.from_r30723) Tetsuya Mishima > Thanks for prompt help. > Could you please resent the patch as attachment which can be applied with "patch" command, my mail client messes long lines. > > > On Fri, Feb 14, 2014

Re: [OMPI users] one more finding in openmpi-1.7.5a1

Thanks for prompt help. Could you please resent the patch as attachment which can be applied with "patch" command, my mail client messes long lines. On Fri, Feb 14, 2014 at 7:40 AM, wrote: > > > Thanks. I'm not familiar with mindist mapper. But obviously > checking

Re: [OMPI users] one more finding in openmpi-1.7.5a1

Thanks. I'm not familiar with mindist mapper. But obviously checking for ORTE_MAPPING_BYDIST is missing. In addition, ORTE_MAPPING_PPR is missing again by my mistake. Please try this patch. if OPAL_HAVE_HWLOC } else if (ORTE_MAPPING_BYCORE == ORTE_GET_MAPPING_POLICY (mapping)) {

Re: [OMPI users] one more finding in openmpi-1.7.5a1

Hi, after this patch we get this in jenkins: *07:03:15* [vegas12.mtr.labs.mlnx:01646] [[26922,0],0] ORTE_ERROR_LOG: Not implemented in file rmaps_mindist_module.c at line 391*07:03:15* [vegas12.mtr.labs.mlnx:01646] [[26922,0],0] ORTE_ERROR_LOG: Not implemented in file base/rmaps_base_map_job.c at