Graham Fagg 25375759c3 arrgh. reduce could for very small message sizes and proc counts call a linear function ... this was implemented using a chain (tree followed with pipeline) by setting the chain fanout to a factor of size etc but the chain datastructure was fixed in length and if exceeded the topo create returned a null which isn't helpfull in cid next function of comdup... Anyway two fixes, first we do have a real linear function so changed the decision function and second altered the topo chain create to force chain fanouts of less than 1 to 1 and fanouts bigger than max to max. next check in will change chain to dynamically allocd array (reallocable) but we shouldn't ever use a chain fanout for a linear tree anyway. (lession must rerun all tests for all data sizes when changing decision functions) This commit was SVN r8662.		2006-01-08 02:41:09 +00:00
..
allocator	Protect the headers	2005-12-11 05:49:29 +00:00
bml	changes required by dr	2005-12-21 15:11:40 +00:00
btl	merge in changes from release branch	2006-01-04 16:34:45 +00:00
coll	arrgh. reduce could for very small message sizes and proc counts call a linear function	2006-01-08 02:41:09 +00:00
common	Ensure that seg is always initialized, even in the return_error case.	2006-01-04 23:01:50 +00:00
io	Add full path for the header files.	2005-12-28 19:28:32 +00:00
mpool	improve error reporting when registrations fail	2005-12-22 16:05:28 +00:00
pml	We need the copyright ...	2005-12-31 15:51:57 +00:00
ptl	Use the common SM component to unmap the shared memory file.	2005-12-31 15:07:48 +00:00
rcache	The Windows protection is called __WINDOWS__ (and it's a mix between WIN32 and _WIN32).	2005-12-10 22:10:39 +00:00
topo	fixes suggested by Ralf for supporting both Libtool 1 and 2 in Open MPI...	2005-12-19 03:10:23 +00:00
win_makefile	Update the copyright notices for IU and UTK.	2005-11-05 19:57:48 +00:00