Rich Graham afcd1016fd move temp buffer allocation out of the iteration loop - i.e. always use the ...

same temp loop.  The algorithm is rather synchronous already...

This commit was SVN r17831.

2008-03-16 03:20:46 +00:00

..

.ompi_ignore

skeleton for new shared memory collective component.

2008-01-25 19:35:26 +00:00

.ompi_unignore

skeleton for new shared memory collective component.

2008-01-25 19:35:26 +00:00

coll_sm2_allreduce.c

move temp buffer allocation out of the iteration loop - i.e. always use the

2008-03-16 03:20:46 +00:00

coll_sm2_barrier.c

fix some barrier addressing errors.

2008-03-15 22:46:19 +00:00

coll_sm2_component.c

increase max data segments size.

2008-03-02 19:11:09 +00:00

coll_sm2_module.c

fix some barrier addressing errors.

2008-03-15 22:46:19 +00:00

coll_sm2_service.c

move some test code to another machine.

2008-03-07 19:18:02 +00:00

coll_sm2.h

check point

2008-03-15 13:31:21 +00:00

configure.params

skeleton for new shared memory collective component.

2008-01-25 19:35:26 +00:00

help-coll-sm.txt

skeleton for new shared memory collective component.

2008-01-25 19:35:26 +00:00

Makefile.am

generate reduction tree.

2008-02-24 03:25:40 +00:00