The Open MPI Team, representing a consortium of research, academic, and
industry partners, is pleased to announce the release of Open MPI version
2.1.6.
Open MPI v2.1.6 is expected to be the last release in the v2.1.x series.
Although we assume that many users have already upgraded to the newer series
(3.0.x, v3.1.x, or v4.0.x), this release is intended to fix a few remaining
bugs in the v2.1.x series before closing off the series for good (e.g., for
those who have locked their configuration on to the Open MPI v2.1.x series).
Open MPI v2.1.6 is only recommended for those who are still running Open MPI
v2.0.x or v2.1.x, and can be downloaded from the Open MPI web site:
https://www.open-mpi.org/software/ompi/v2.1/
Open MPI v2.1.6 only fixed a small number of issues:
- Update the openib BTL to handle a newer flavor of the
ibv_exp_query() API. Thanks to Angel Beltre (and others) for
reporting the issue.
- Fix a segv when specifying a username in a hostfile. Thanks to
StackOverflow user @derangedhk417 for reporting the issue.
- Work around Oracle compiler v5.15 bug (which resulted in a failure
to compile Open MPI source code).
- Disable CUDA async receive support in the openib BTL by default
because it is broken for sizes larger than the GPUDirect RDMA
limit. User can set the MCA variable btl_openib_cuda_async_recv to
true to re-enable CUDA async receive support.
- Various atomic and shared memory consistency bug fixes, especially
affecting the vader (shared memory) BTL and PMIx.
- Add openib BTL support for BCM57XXX and BCM58XXX Broadcom HCAs.
- Fix segv in oob/ud component. Thanks to Balázs Hajgató for
reporting the issue.
--
Jeff Squyres
jsquy...@cisco.com
_______________________________________________
announce mailing list
announce@lists.open-mpi.org
https://lists.open-mpi.org/mailman/listinfo/announce
