Rolf vandeVaart 13e8975f83 In the case where we detect a value of 0 in the recvcount ...

array, fall back to the simpler algorithms.  This is not
the optimal solution, but it works.  

This commit was SVN r19702.

2008-10-07 19:44:51 +00:00

..

allocator

Fixes trac:1392, #1400

2008-07-28 22:40:57 +00:00

bml

Scalability patch, or slim-fast effect #1. All BML structures just

2008-09-30 21:02:37 +00:00

btl

The endpoint is actually a list_item_t -- not a base object. But only

2008-10-06 17:38:25 +00:00

coll

In the case where we detect a value of 0 in the recvcount

2008-10-07 19:44:51 +00:00

common

Per http://www.open-mpi.org/community/lists/devel/2008/09/4648.php,

2008-09-11 19:02:33 +00:00

crcp

Make sure to check the bounds of the communicator array before referencing it. Fixes some of the FT related Intel bugs seen in Odin testing last night.

2008-10-07 19:15:12 +00:00

dpm

Take into account Ralph's comments. There is no duplicate functionnality with the rml base. Also fix a stupid typo bug.

2008-10-01 02:31:14 +00:00

io

Patch originally from George to improve ROMIO's performance when

2008-09-06 09:50:12 +00:00

mpool

Change the default value of mpi_leave_pinned to -1, meaning that we'll

2008-09-16 22:06:14 +00:00

mtl

Fix a bunch of compiler warnings. Refs trac:1458

2008-09-26 16:15:05 +00:00

osc

Scalability patch, or slim-fast effect #1. All BML structures just

2008-09-30 21:02:37 +00:00

pml

Fixed a stupid type mismatch. Thanks Jeff for noticing.

2008-10-02 00:22:41 +00:00

pubsub

Per July technical meeting:

2008-08-04 16:43:12 +00:00

rcache

Fixes trac:1392, #1400

2008-07-28 22:40:57 +00:00

topo

Remove redundant code

2008-09-05 04:29:21 +00:00