1
1
openmpi/ompi/mca/mpool
Brian Barrett 5cadbbbf41 Fix for bug #140. If we're leaving things pinned, certain assumptions about
where to look for registrations that were used in the alloc/free code don't
work (because the memory returned from malloc() -- whowever gets around to
calling it) might actually be registered already.  So just call malloc
and free directly and avoid the whole issue when leave pinned is on.  After
all, you have to pay the registration cost sometime, and if leave pinned
is on, you only have to pay it once.  It makes things much simpler to
have that once be at first use rather than during ALLOC_MEM, and as far
as I can read, we're still standards conformant this way.

This commit was SVN r10406.
2006-06-17 18:34:41 +00:00
..
base Fix for bug #140. If we're leaving things pinned, certain assumptions about 2006-06-17 18:34:41 +00:00
gm use memalign instead of malloc + manually alignment in the mvapi mpool 2006-06-07 23:21:23 +00:00
mvapi Complete the move of the mpool registration from opal_list_item_t to the 2006-06-14 17:43:50 +00:00
openib make ompi_free_list_item_t a class.. 2006-06-12 16:44:00 +00:00
sm Next step in the project split, mainly source code re-arranging 2006-02-12 01:33:29 +00:00
udapl Mostly cleanups - preprocessor fixes and removal of OPAL_OUTPUTs. 2006-06-09 00:18:29 +00:00
Makefile.am Fix a bunch of install locations for header files 2005-12-08 00:54:44 +00:00
mpool.h Complete the move of the mpool registration from opal_list_item_t to the 2006-06-14 17:43:50 +00:00