Ralph Castain 55923eacd3 Stealing some pieces of Josh Hursey's PR #1583 and modifying a bit, allow the opal/pmix external component to handle both PMIx 1.1.4 and PMIx 2.0 versions. Automatically detect the version of the target external library and adjust the only two APIs that changed (PMIx_Init and PMIx_Finalize) ...

Rename temp vars in .m4 to avoid conflict with Travis

2016-05-27 08:06:31 -07:00

..

base

Fix registration of error handlers thru the pmix120 component. A thread-shift operation was hanging on the sync_event_base, which made it dependent on someone calling opal_progress. Unfortunately, a process in "sleep" or spinning outside the MPI library won't do that, and so we never complete errhandler registration.

2016-03-02 15:01:01 -08:00

cray

Merge pull request #1668 from rhc54/topic/slurm

2016-05-16 12:23:19 -07:00

external

Stealing some pieces of Josh Hursey's PR #1583 and modifying a bit, allow the opal/pmix external component to handle both PMIx 1.1.4 and PMIx 2.0 versions. Automatically detect the version of the target external library and adjust the only two APIs that changed (PMIx_Init and PMIx_Finalize)

2016-05-27 08:06:31 -07:00

isolated

Fix a number of issues, some of which have lingered for a long time:

2016-03-01 06:53:00 -08:00

pmix114

pmix: update .gitignore

2016-05-23 11:58:07 +09:00

s1

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

s2

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

Makefile.am

Integrate PMIx 1.0 with OMPI.

2015-08-29 16:04:10 -07:00

pmix_server.h

Add pmix120 component, update the error handling functions in the PMIx API.

2015-12-28 23:15:44 +09:00

pmix_types.h

Per user request, add some missing data and definitions:

2016-05-09 08:39:01 -07:00

pmix.h

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