Thanks to all who provided their opinion.

Based on the results, the Open MPI developer community will work on v3.0.0 
after the v2.1.x series.


On Nov 28, 2016, at 5:18 PM, Jeff Squyres (jsquyres) 
<<>> wrote:

If you have an opinion on the v2.2.x-vs-v3.x question, please submit your vote 
by COB this upcoming Friday, 2 Dec, 2016:


On Nov 22, 2016, at 4:32 PM, Pritchard Jr., Howard 
<<>> wrote:

Hello Folks,

This is a followup to the question posed at the SC’16 Open MPI BOF:  Would the 
prefer to have a v2.2.x limited feature but backwards compatible release 
in 2017, or would the community prefer a v3.x (not backwards compatible but 
more features) sometime in late 2017 to early 2018?

BOF attendees expressed an interest in having a list of features that might 
make it in to v2.2.x
and ones that the Open MPI developers think would be too hard to back port from
the development branch (master) to a v2.2.x release stream.

Here are the requested lists:

Features that we anticipate we could port to a v2.2.x release
• Improved collective performance (a new “tuned” module)
• Enable Linux CMA shared memory support by default
• PMIx 3.0 (If new functionality were to be used in this release of Open MPI)
Features that we anticipate would be too difficult to port to a v2.2.x release
• Revamped CUDA support
• MPI_ALLOC_MEM integration with memkind
• OpenMP affinity/placement integration
• THREAD_MULTIPLE improvements to MTLs (not so clear on the level of difficult 
for this one)
You can register your opinion on whether to go with a v2.2.x release next year
or to go from v2.1.x to v3.x in late 2017 or early 2018 at the link below:

Thanks very much,


Howard Pritchard
Los Alamos National Laboratory

announce mailing list

Jeff Squyres<>
For corporate legal information go to:

announce mailing list

Jeff Squyres<>
For corporate legal information go to:

announce mailing list

Reply via email to