George Bosilca d56656580a Profiling shows that we spend way to much time (it's relative of course but it's still more ... than I want to) on the constructor and destructor loops. Compress the constructors and destructors array to remove all the useless tests against NULL. Now we use the cache a little bit more efficient. Correct a threading problem in the obj_update function. In the threaded case we have to return the value returned by the ompi_atomic_add function otherwise there are ways leading to the release of an object twice. This commit was SVN r8966.		2006-02-10 21:04:26 +00:00
..
asm	* fix assembly issues for linux, which wants a notation to make the stack	2006-01-11 04:49:40 +00:00
class	Profiling shows that we spend way to much time (it's relative of course but it's still more	2006-02-10 21:04:26 +00:00
event	* Fix situation where we were unlocking a mutex we didn't own in an error	2006-02-04 23:26:58 +00:00
include	More protection around the atomic operations on Windows. Still ahve to find	2005-12-22 00:13:09 +00:00
mca	* add a #define for Galen as to whether or not any memory component was	2006-02-08 00:50:42 +00:00
memoryhooks	More memory hooks tweaks... Set a flag on callbacks if the allocation /	2005-12-16 01:12:45 +00:00
runtime	* Merge of wrapper compiler updates from the bwb-wrapper-fix branch (r8690 -	2006-01-16 01:48:03 +00:00
threads	Update the windows threads.	2006-02-06 04:17:13 +00:00
tools	* with ptmalloc2, prefer syscall over dlsym for calling the real munmap. This	2006-01-19 18:48:58 +00:00
util	* we really shouldn't be setting umask(0), since that's going to make files	2006-02-08 16:18:15 +00:00
win32	- Change the spacing preventing finding the struct from script.	2006-01-26 11:55:00 +00:00
Makefile.am	* Merge of wrapper compiler updates from the bwb-wrapper-fix branch (r8690 -	2006-01-16 01:48:03 +00:00
win_makefile	Move all win32 related files in opal, and modify all the Makefiles.am to	2005-12-08 06:17:15 +00:00