[mpich-announce] Announcing the availability of mpich-3.1
balaji at mcs.anl.gov
Thu Feb 20 13:43:02 CST 2014
The MPICH team is pleased to announce the availability of a new stable
This is a new major release that adds several capabilities including full
binary (ABI) compatibility with Intel MPI 5.0, an integrated MPICH-PAMID
code base for IBM BG/Q (contributed by IBM), several improvements to Intel
Xeon Phi (contributed by Intel and NEC), a major revamp of the MPI_T tools
interface, large improvements to one-sided communication in shared memory
environments, a number of improvements to mpiexec process binding
capabilities, various improvements to the support of large counts (more
than 2GB data), and a large number of bug fixes.
All production environments are encouraged to upgrade to this release.
More information about the release can be found on the MPICH website:
A list of changes in this release is included at the end of this email.
The MPICH Team
Changes in 3.1
# Implement runtime compatibility with MPICH-derived implementations as
the ABI Compatibility Initiative (see www.mpich.org/abi for more
# Integrated MPICH-PAMI code base for Blue Gene/Q and other IBM
# Several improvements to the SCIF netmod. (code contribution from
# Major revamp of the MPI_T interface added in MPI-3.
# Added environment variables to control a lot more capabilities for
collectives. See the README.envvar file for more information.
# Allow non-blocking collectives and fault tolerance at the same
time. The option MPIR_PARAM_ENABLE_COLL_FT_RET has been deprecated as
it is no longer necessary.
# Improvements to MPI_WIN_ALLOCATE to internally allocate shared
memory between processes on the same node.
# Performance improvements for MPI RMA operations on shared memory
for MPI_WIN_ALLOCATE and MPI_WIN_ALLOCATE_SHARED.
# Enable shared library builds by default.
# Upgraded hwloc to 1.8.
# Several improvements to the Hydra-SLURM integration.
# Several improvements to the Hydra process binding code. See the
Hydra wiki page for more information:
# MPICH now supports operations on very large datatypes (those that
more than 32 bits of data). This work also allows MPICH to fully
MPI-3's introduction of MPI_Count.
# Several other minor bug fixes, memory leak fixes, and code cleanup.
A full list of changes is available at the following link:
A full list of bugs that have been fixed is available at the
More information about the announce