Re: [OMPI devel] modex getting corrupted

2016-05-21 Thread Ralph Castain
Please provide the exact code used for both send/recv - you likely have an error in the syntax > On May 20, 2016, at 9:36 PM, dpchoudh . wrote: > > Hello all > > I have a naive question: > > My 'cluster' consists of two nodes, connected back to back with a proprietary >

[OMPI devel] [1.10.3rc2] testing summary

2016-05-21 Thread Paul Hargrove
Overnight my (relatively) slow ARM and MIPS testers completed. Most of those have been moved to real hardware (vs QEMU) and I've been able to increase coverage as a result. I will note that I was not able to test IA64 (yet?) because that system is down. I've emailed the owners of that system and

Re: [OMPI devel] [1.10.3rc2] OpenBSD build failure

2016-05-21 Thread Paul Hargrove
Gilles, As I said there is no urgency. If the respective RMs are OK w/o the MPICH/ROMIO folks feedback then it would be great to get this fixed in the 1.10.3 and 2.0.0 releases. However, it they think it is best to wait, that is fine too. I just wanted to be sure it wasn't a case of this fix

Re: [OMPI devel] [1.10.3rc2] Build failure with Studio 12.5-beta

2016-05-21 Thread Gilles Gouaillardet
Paul, the v2.x commit message says it was cherry-picked from master. I can pr this for v1.10 too Cheers, Gilles On Saturday, May 21, 2016, Paul Hargrove wrote: > The Solaris Studio 12.5 Fortran compiler is not being identified correctly > by libtool. > This is the same

[OMPI devel] [1.10.3rc2] Build failure with Studio 12.5-beta

2016-05-21 Thread Paul Hargrove
The Solaris Studio 12.5 Fortran compiler is not being identified correctly by libtool. This is the same problem described for 2.0.0rc2 in https://www.open-mpi.org/community/lists/devel/2016/05/18949.php That email includes a patch that Gilles turned into a PR:

Re: [OMPI devel] [1.10.3rc2] OpenBSD build failure

2016-05-21 Thread Gilles Gouaillardet
Paul, I was hoping I got some feedback from mpich folks before I commit it into master and PR to the release branches. I am fine to merge it and pr now if needed Cheers, Gilles On Saturday, May 21, 2016, Paul Hargrove wrote: > As before, this RC cannot build ROMIO on

[OMPI devel] [1.10.3rc2] OpenBSD build failure

2016-05-21 Thread Paul Hargrove
As before, this RC cannot build ROMIO on OpenBSD 5.7 and higher. Unlike previous times that I've reported this issue, Gilles now has a fix available. However, it it currently stuck in a PR for master: https://github.com/open-mpi/ompi/pull/1643 Not a high priority, but thought I mention it. -Paul

[OMPI devel] modex getting corrupted

2016-05-21 Thread dpchoudh .
Hello all I have a naive question: My 'cluster' consists of two nodes, connected back to back with a proprietary link as well as GbE (over a switch). I am calling OPAL_MODEX_SEND() and the modex consists of just this: struct modex {char name[20], unsigned mtu}; The mtu field is not currently

[OMPI devel] v1.10.3rc2 ready for final testing

2016-05-21 Thread Ralph Castain
Hi folks I have posted rc2 of 1.10.3 - this contains all the changes that have been provided, and should be the final release candidate. Barring anything you find, I expect to just make a final pass on the NEWS items and release by end of May. https://www.open-mpi.org/software/ompi/v1.10/