Ralph Castain f2c49c6c19 Fix the map-by object mapper to handle cpus-per-proc by accounting for the request when computing the number of procs to put on each object. This ensures that the binding routine doesn't automatically overload the cores. ...

cmr=v1.7.4:reviewer=jsquyres

This commit was SVN r29843.

2013-12-08 16:59:25 +00:00

..

base

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

lama

Move the MCA / MPI_T level of the LAMA component down to 5 (from 9).

2013-09-20 15:23:27 +00:00

mindist

mindist: cosmetic, use fallback to byslot if unable to read NUMA info, small fix.

2013-11-13 09:26:40 +00:00

ppr

Do some cleanup of the --without-hwloc build - no need to work on coprocessors since we can't detect them anyway, cleanup some unused variables in the ppr mapper

2013-10-23 01:45:21 +00:00

rank_file

If a rankfile is given and the number of procs not specified in the mpirun cmd line, then set the number of procs to the number of ranks in the rankfile

2013-09-02 15:04:40 +00:00

resilient

don't need the return value, but should check for error

2013-05-16 15:15:02 +00:00

round_robin

Fix the map-by object mapper to handle cpus-per-proc by accounting for the request when computing the number of procs to put on each object. This ensures that the binding routine doesn't automatically overload the cores.

2013-12-08 16:59:25 +00:00

seq

Update ORTE frameworks to use the MCA framework system.

2013-03-27 21:14:43 +00:00

staged

Mapping policies must be tested as equalities as they are values, not bitmasks

2013-05-15 13:45:00 +00:00

Makefile.am

Fix mistake that came in via the ompi-agen tree in r23764. The mistake wasn't part of the core autogen upgrade; it was an additional 'bonus' cleanup. Oops. The mistake will always create a set of directories under installdir, even if you do not --with-devel-headers. The set of directories will be empty, but still -- they should not be there at all. This commit fixes that -- the directories are not created at all if you do not --with-devel-headers

2010-09-24 22:53:28 +00:00

rmaps_types.h

This commit introduces a new "mindist" ORTE RMAPS mapper, as well as

2013-05-22 13:04:40 +00:00

rmaps.h

Sorry for mid-day commit, but I had promised on the call to do this upon my return.

2012-04-06 14:23:13 +00:00