All,
We accidentally tagged mpich-3.0.4 incorrectly in the mpich git repo to
point to [85acf6c5], instead of the correct hash [0f1067da]. The
release tarball is still fine; just the git tag was incorrect.
We have fixed this in the git repo now. If you have pulled the 3.0.4
tag from the mpich git repo, please correct your cloned copy using:
% git tag -d v3.0.4
% git fetch origin tag v3.0.4
You might also be able to do:
% git pull --tags
(though we are not entirely sure that'll work).
Sorry about the mess-up. Once again, the release tarball is correct.
Just the tag was incorrect.
Regards,
The MPICH Team
--
Pavan Balaji
http://www.mcs.anl.gov/~balaji
The MPICH team is pleased to announce the availability of a new bug-fix
release (mpich-3.0.4). This release adds several performance features
for the Hydra process manager, support for communicator-specific tuning
of eager/rendezvous thresholds, and fixes several bugs present in 3.0.3.
http://www.mpich.org
A list of changes in this release is included at the end of this email.
Regards,
The MPICH Team
===============================================================================
Changes in 3.0.4
===============================================================================
# BUILD SYSTEM: Reordered the default compiler search to prefer Intel
and PG compilers over GNU compilers because of the performance
difference.
WARNING: If you do not explicitly specify the compiler you want
through CC and friends, this might break ABI for you relative to
the previous 3.0.x release.
# OVERALL: Added support to manage per-communicator eager-rendezvous
thresholds.
# PM/PMI: Performance improvements to the Hydra process manager on
large-scale systems by allowing for key/value caching.
# Several other minor bug fixes, memory leak fixes, and code cleanup.
A full list of changes is available at the following link:
http://git.mpich.org/mpich.git/shortlog/v3.0.3..v3.0.4
--
Pavan Balaji
http://www.mcs.anl.gov/~balaji
