openmpi

comm

We stripped the process info packing routine to minimize message size when sending the launch message, but tools still require all the info. So modify the tool-hnp handshake to explicitly add the missing info

2013-12-19 20:42:20 +00:00

dash_host

Initialize variable so dash-host option gets correctly parsed

2014-01-08 15:17:16 +00:00

hostfile

Shift the verbose output a bit

2014-01-20 14:41:37 +00:00

context_fns.c

MCA/base: Add new MCA variable system

2013-03-27 21:09:41 +00:00

context_fns.h

... Delayed due to notifier commits earlier this day ...

2009-04-29 01:32:14 +00:00

error_strings.c

Some minor cleanups:

2014-01-23 21:35:20 +00:00

error_strings.h

Introduce staged execution. If you don't have adequate resources to run everything without oversubscribing, don't want to oversubscribe, and aren't using MPI, then staged execution lets you (a) run as many procs as there are available resources, and (b) start additional procs as others complete and free up resources. Adds a new mapper as well as a new state machine.

2012-08-28 21:20:17 +00:00

help-regex.txt

Fix regular expression analyzer for slurmd - use a slurm-specific version

2011-07-13 22:49:56 +00:00

hnp_contact.c

As per the RFC, bring in the ORTE async progress code and the rewrite of OOB:

2013-08-22 16:37:40 +00:00

hnp_contact.h

As requested by Aurelien at the July design meeting - long time coming, but finally got around to it.

2008-12-10 17:10:39 +00:00

Makefile.am

Fix longstanding issue with our multi-project support. Rather than using

2014-01-07 22:11:15 +00:00

name_fns.c

As per the RFC, bring in the ORTE async progress code and the rewrite of OOB:

2013-08-22 16:37:40 +00:00

name_fns.h

Roll in the rest of the modex change. Eliminate all non-modex API access of RTE info from the MPI layer - in some cases, the info was already present (either in the ompi_proc_t or in the orte_process_info struct) and no call was necessary. This removes all calls to orte_ess from the MPI layer. Calls to orte_grpcomm remain required.

2012-06-27 14:53:55 +00:00

nidmap.c

Per request from Nathan, add an offset value to the job struct so we can construct a "global rank" that spans multiple jobs during dynamic launch operations. Store a new ORTE_DB_GLOBAL_RANK value for each process in the database, and ensure that we share our own value during connect_accept so both sides can see it.

2013-11-14 17:01:43 +00:00

nidmap.h

Introduce staged execution. If you don't have adequate resources to run everything without oversubscribing, don't want to oversubscribe, and aren't using MPI, then staged execution lets you (a) run as many procs as there are available resources, and (b) start additional procs as others complete and free up resources. Adds a new mapper as well as a new state machine.

2012-08-28 21:20:17 +00:00

parse_options.c

Use ports as multicast channels instead of networks so we avoid stepping into reserved spaces.

2011-04-29 18:46:40 +00:00

parse_options.h

Use ports as multicast channels instead of networks so we avoid stepping into reserved spaces.

2011-04-29 18:46:40 +00:00

pre_condition_transports.c

MCA/base: Add new MCA variable system

2013-03-27 21:09:41 +00:00

pre_condition_transports.h

In the case of direct-launched processes running under slurm, psm requires that the pre_condition_transports MCA param be set. This is normally computed by mpirun and inserted into each proc's environ, but that doesn't work here.

2011-04-28 13:54:33 +00:00

proc_info.c

Use unique collective ids for the checkpoint/restart code

2014-02-04 14:03:05 +00:00

proc_info.h

Use unique collective ids for the checkpoint/restart code

2014-02-04 14:03:05 +00:00

regex.c

Cleanup some potential memory overruns

2014-01-19 16:31:26 +00:00

regex.h

Fix some major bit-rot on scalable launch. If static ports are provided, then daemons can connect back to the HNP via the routed connection tree instead of doing so directly. In order to do that at scale, the node list must be passed as a regular expression - otherwise, the orted command line gets too long.

2011-07-07 18:54:30 +00:00

session_dir.c

Grant Nathan his wish - add an --disable-getpwuid to the configure options and protect all users of that code so it disappears if disabled.

2014-01-24 19:18:37 +00:00

session_dir.h

- Revert r20739

2009-03-05 21:56:03 +00:00

show_help.c

Some minor cleanups:

2014-01-23 21:35:20 +00:00

show_help.h

Remove the old configure option for disabling full rte support - we now use the OMPI rte framework for such purposes

2013-02-28 01:35:55 +00:00