Re: [OMPI devel] [PATCH] Fix for xlc-13.1.0 ICE (hwloc)

2016-05-09 Thread Josh Hursey
(Just to followup for the list) I merged in the master PR, and created a PR for v2.0.0: https://github.com/open-mpi/ompi-release/pull/1149 Thanks Paul and Brice! On Sun, May 8, 2016 at 3:21 PM, Brice Goglin wrote: > Thanks, applied to hwloc. And PR for OMPI master at > https://github.com/ope

Re: [OMPI devel] Master broken for ILP32

2016-05-09 Thread Paul Hargrove
I would say the switch to __sync atomics by default is surprising to me. I am *not* campaigning to reverse the result of the RFC (of which I mist have missed the details and outcome). However, I have a couple observations: 1) The loss of aqc/rel distinctions is probably minor on x86/x86-64 but mig

Re: [OMPI devel] Master broken for ILP32

2016-05-09 Thread Hjelm, Nathan Thomas
We have chosen to use the __sync builtins by default on master. There was an rfc on it awhile ago. Is there a good reason to go back to the inline by default or is this just surprising? From: devel on behalf of Paul Hargrove Sent: Monday, May 09, 2016 11

Re: [OMPI devel] Master broken for ILP32

2016-05-09 Thread Paul Hargrove
Regarding "distro": This was happening, for instance, on OpenBSD and NetBSD (32-bit kernels on 64-bit h/w) when testing your PR1643. However, it sounds like Nathan knows how/where to fix this. HOWEVER, that is not the only issue here. Why is master is picking the BUILTIN (__sync) atomics (as shown

Re: [OMPI devel] Master broken for ILP32

2016-05-09 Thread Hjelm, Nathan Thomas
Nevermind. Looks like there are two different macros for 64-bit and one is wrong in this case. Fix incoming. From: devel on behalf of Gilles Gouaillardet Sent: Monday, May 09, 2016 2:22:24 AM To: Open MPI Developers Subject: Re: [OMPI devel] Master broken

Re: [OMPI devel] Master broken for ILP32

2016-05-09 Thread Hjelm, Nathan Thomas
This really isnt a problem with the atomics code. We have a macro to indicate whether 64-bit is really supported. Something in opal is using 64-bit atomics without checking if they are supported. With sync atomics we get a link error but with the others it is a compile error. I fixed a similar p

Re: [OMPI devel] Master broken for ILP32

2016-05-09 Thread Gilles Gouaillardet
Paul, on which distro are you running ? are you compiling on a 64 bit distro to generate a 32 bit library ? it seems we are currently only testing a atomic on a long (32 bits on a 32 bits arch) and then incorrectly assume it works also on 64 bits (!) Cheers, Gilles On 5/9/2016 3:59 P

[OMPI devel] Master broken for ILP32

2016-05-09 Thread Paul Hargrove
Perhaps this is already known. Several builds I've tried recently from the ompi (not ompi-release) repo are failing on 32-bit platforms with ../../../opal/.libs/libopen-pal.so: undefined reference to `__sync_add_and_fetch_8' This is impacting PRs that I am being asked to test (e.g. 1643). Note