| .. |
|
attribute
|
more c99 updates
|
2015-06-25 10:14:13 -06:00 |
|
class
|
Purge whitespace from the repo
|
2015-06-23 20:59:57 -07:00 |
|
communicator
|
Refactor the request completion (#1422)
|
2016-05-24 18:20:51 -05:00 |
|
contrib
|
Purge whitespace from the repo
|
2015-06-23 20:59:57 -07:00 |
|
datatype
|
Fix MPI datatype args.
|
2016-05-24 23:36:54 -04:00 |
|
debuggers
|
Merge pull request #1640 from jsquyres/pr/mpir-cleanup
|
2016-05-05 21:23:30 -04:00 |
|
dpm
|
ompi/dpm: retrieves OPAL_PMIX_ARCH in heterogeneous mode
|
2016-02-22 11:01:06 +09:00 |
|
errhandler
|
Per request from Jeff, aggregate all help messages during MPI_Init thru MPI_Finalize as long as the RTE is available
|
2016-04-15 13:37:22 -07:00 |
|
etc
|
Purge whitespace from the repo
|
2015-06-23 20:59:57 -07:00 |
|
file
|
io: do not cast way the const modifier when this is not necessary
|
2015-09-09 09:18:58 +09:00 |
|
group
|
ompi/group: fix sparse group proc reference counting
|
2016-04-27 15:55:13 -06:00 |
|
include
|
fortran: add missing constants for MPI_WIN_CREATE_FLAVOR and MPI_WIN_MODEL
|
2016-03-14 10:19:21 +09:00 |
|
info
|
ompi: fixup hostname max length usage
|
2016-04-25 07:08:23 +02:00 |
|
mca
|
Removal of ompi_request_lock from pml/ucx.
|
2016-05-26 12:36:58 -04:00 |
|
message
|
Purge whitespace from the repo
|
2015-06-23 20:59:57 -07:00 |
|
mpi
|
Refactor the request completion (#1422)
|
2016-05-24 18:20:51 -05:00 |
|
mpiext
|
configury: remove the --enable-mpi-profiling option
|
2015-10-13 08:52:35 +09:00 |
|
op
|
op: allow user operations in ompi_3buff_op_reduce
|
2015-10-02 10:35:21 -06:00 |
|
patterns
|
Purge whitespace from the repo
|
2015-06-23 20:59:57 -07:00 |
|
peruse
|
more c99 updates
|
2015-06-25 10:14:13 -06:00 |
|
proc
|
ompi_proc_complete_init_single: make the subroutine public
|
2016-02-22 11:01:06 +09:00 |
|
request
|
request: fix compilation error
|
2016-05-25 09:52:23 -06:00 |
|
runtime
|
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 |
|
tools
|
Merge pull request #1552 from kmroz/wip-hostname-len-cleanup-1
|
2016-05-02 09:44:18 -04:00 |
|
win
|
win: add support for accumulate_ordering info key
|
2016-05-24 11:13:30 -06:00 |
|
Makefile.am
|
use-mpi extensions do not have a .la lib, so the fortran module should not depend on them.
|
2016-05-03 11:54:35 -04:00 |
