1
1
openmpi/ompi/mca
Andrew Friedley c68c6ac122 A number of fixes and the usual cleanup..
- Added some basic flow control to limit number of posted sends.
- Merged endpoint send/recv lock into single endpoint lock.
- Set the LMR triplet length in the send path, not at allocation time.
  This has to be done because upper layers might send less than the
  amount allocated.
- Alter the tie-breaker if statement protecting the second call
  to dat_ep_connect().  The logic was reversed compared to the tie-
  breaker for the first dat_ep_connect(), making it possible for
  3 or more processes to form a deadlock loop.
- Some asserts were added for debugging purposes.. leaving them
  in place for now.

This commit was SVN r10317.
2006-06-12 22:42:01 +00:00
..
allocator make ompi_free_list_item_t a class.. 2006-06-12 16:44:00 +00:00
bml Temporary solution for in-bound computation of the next BTL. 2006-05-22 23:28:40 +00:00
btl A number of fixes and the usual cleanup.. 2006-06-12 22:42:01 +00:00
coll Thanks to Gleb now we are able to call the schduler on Windows. Instead of using 2006-04-20 19:56:50 +00:00
common - update function name inside debug statement 2006-05-16 14:33:41 +00:00
io finished the ompi_free_list_t class nightmare.. 2006-06-12 22:09:03 +00:00
mpool make ompi_free_list_item_t a class.. 2006-06-12 16:44:00 +00:00
osc The return value is random. Let's return something that make sense. 2006-05-03 18:17:00 +00:00
pml finished the ompi_free_list_t class nightmare.. 2006-06-12 22:09:03 +00:00
rcache finished the ompi_free_list_t class nightmare.. 2006-06-12 22:09:03 +00:00
topo Next step in the project split, mainly source code re-arranging 2006-02-12 01:33:29 +00:00
win_makefile Update the copyright notices for IU and UTK. 2005-11-05 19:57:48 +00:00