On Jan 22, 2016, at 5:47 PM, Brice Goglin <brice.gog...@inria.fr> wrote: > > hwloc doesn't have any cuda specific configure variables. We just use > standard variables like LIBS and CPPFLAGS. I guess OMPI could propagate > --with-cuda directories to hwloc by setting LIBS and CPPFLAGS before running > hwloc m4 functions, but I don't think OMPI actually cares about hwloc > reporting CUDA device locality
I guess that's a question for NVIDIA -- do you guys use (or want to use) CUDA device locality in the Open MPI hwloc information? If so, it might be appropriate to do what Brice suggests -- in opal/mca/hwloc*/configure.m4, (temporarily) explode --with-cuda into CPPFLAGS and LDFLAGS. > anyway, and OMPI might stop embedding hwloc in the near future anyway. Mmm... I'm not convinced of that. :-) Regardless of what we decide w.r.t. embedding hwloc, I think it would be worth exploding --with-cuda in the hwloc configure.m4, if NVIDIA wants CUDA devices in the Open MPI hwloc info (my $0.02: NVIDIA: I think you should want this information :-) ). -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
