openmpi

Fix an issue with extremely large data identified by tjb900.

Due to the conversion from ssize_t to int we were losing bytes, and
ended up writing outside the receiver buffer. Similarly on the send,
due to the conversion to a lesser type, we could missinterpret the
end of the fragment.

2017-01-18 10:33:12 -05:00

base

mca/base: plug a memory leak

2017-01-06 13:46:36 +09:00

openib

Only instantiate the HWLOC topology in an MPI process if it actually will be used.

2016-12-29 10:33:29 -08:00

portals4

btl/portals4: Take into account the limitation of portals4 (max_msg_size)

2016-07-19 15:19:29 +02:00

scif

btl/scif: reduce default exclusivity

2016-05-25 14:25:07 -06:00

self

btl/self: fix fragment segment length in mca_btl_self_prepare_src()

2016-11-24 10:44:56 +09:00

btl/sm: correctly handle nodes with zero NUMA hwloc object

2017-01-12 11:45:29 +09:00

smcuda

Only instantiate the HWLOC topology in an MPI process if it actually will be used.

2016-12-29 10:33:29 -08:00

tcp

Fix an issue with extremely large data identified by tjb900.

2017-01-18 10:33:12 -05:00

template

Purge whitespace from the repo

2015-06-23 20:59:57 -07:00

ugni

btl/ugni:vader swat some compiler warnings

2016-11-21 14:58:34 -06:00

usnic

usnic: add completion stats

2017-01-10 12:06:54 -08:00

vader

btl/vader: plug a memory leak

2016-12-22 16:04:36 +09:00

btl.h

btl: adjust values of new atomic flags

2016-06-02 19:21:34 -06:00

Makefile.am

Purge whitespace from the repo

2015-06-23 20:59:57 -07:00