Ralph Castain 01ba861f2a When direct launching applications, we must allow the MPI layer to progress during RTE-level barriers. Neither SLURM nor Cray provide non-blocking fence functions, so push those calls into a separate event thread (use the OPAL async thread for this purpose so we don't create another one) and let the MPI thread sping in wait_for_completion. This also restores the "lazy" completion during MPI_Finalize to minimize cpu utilization. ... Update external as well Revise the change: we still need the MPI_Barrier in MPI_Finalize when we use a blocking fence, but do use the "lazy" wait for completion. Replace the direct logic in MPI_Init with a cleaner macro		2016-05-14 16:37:00 -07:00
..
bcol	bcol: fix coverity issues	2016-03-18 10:59:46 -06:00
bml	forgot to update copyright in commits 627a89b 4899c89	2016-05-13 11:34:59 -04:00
coll	coll/base: return MPI_ERR_UNSUPPORTED_OPERATION when coll_base_*_two_procs algo is used on a communicator that has no two tasks	2016-05-09 14:18:40 +09:00
common	Purge whitespace from the repo	2015-06-23 20:59:57 -07:00
crcp	opal: rework mpool and rcache frameworks	2016-03-14 10:50:41 -06:00
fbtl	use the actual preadv and pwritev functions if available. That's what the fbtl interfaces have been designed for.	2016-01-07 08:29:17 -06:00
fcoll	fcoll/static: fix coverity issues	2016-04-19 14:48:13 -06:00
fs	remove some unused variables that can cause compilation problems on netbsd	2016-05-03 10:25:15 -05:00
io	io/ompio: fix file size after file_preallocate	2016-05-06 08:20:59 -05:00
mtl	Update in PSM and PSM2 MTLs to detect entries created by drivers for	2016-05-09 12:08:44 -07:00
op	Remove stale component - I'm not going to get to it	2016-05-07 04:13:34 -07:00
osc	osc_rdma_peer: properly include ompi_config.h	2016-05-03 07:39:55 -07:00
pml	forgot to update copyright in commits 627a89b 4899c89	2016-05-13 11:34:59 -04:00
rte	When direct launching applications, we must allow the MPI layer to progress during RTE-level barriers. Neither SLURM nor Cray provide non-blocking fence functions, so push those calls into a separate event thread (use the OPAL async thread for this purpose so we don't create another one) and let the MPI thread sping in wait_for_completion. This also restores the "lazy" completion during MPI_Finalize to minimize cpu utilization.	2016-05-14 16:37:00 -07:00
sbgp	configury: test portability	2015-12-28 13:58:45 +09:00
sharedfp	will rivist the addproc component later in spring, right now it is constantly in the way of doing my tests.	2016-01-20 15:05:51 -06:00
topo	Merge pull request #1397 from hjelmn/enable_thread_multiple	2016-04-23 08:40:22 -06:00
vprotocol	opal: rework mpool and rcache frameworks	2016-03-14 10:50:41 -06:00
Makefile.am	Purge whitespace from the repo	2015-06-23 20:59:57 -07:00
mca.h	Purge whitespace from the repo	2015-06-23 20:59:57 -07:00