1
1
Ralph Castain 06dbfa3098 Make the cpus-per-proc equivalent a little more intuitive:
* allow users to specify just a modifier for map-by instead of requiring that they also specify a policy. Thus, we now accept --map-by :pe=3 as indicating that we should use the default mapping policy, but bind 3 cpus/proc.

* if users specify a pe's/proc but no policy, default to --map-by NUMA to ensure we have access to multiple cpus for the request. This won't guarantee we have access to enough to meet the request, but gives us a chance. In addition, we know that binding a proc to multiple cpus will work best if those cpus are all in the same NUMA, so this provides some degree of optimized behavior.

Per a request from Jeff, define "oversubscribe" for binding as a synonym for the "overload" modifier.

cmr=v1.8.2:reviewer=rhc

This commit was SVN r31967.
2014-06-08 20:26:59 +00:00
..
2014-01-07 15:58:40 +00:00

12 Sep 2011

Notes for hwloc component maintainers:

1. There can only be *1* hwloc version component at a time.
   Specifically: if there are multiple hwlocXYZ components (i.e.,
   different versions of hwloc), then they must all be .ompi_ignore'd
   except for 1.  This is because we currently m4_include all of the
   underlying hwloc's .m4 files -- if there are multiple hwlocXYZ
   components, I don't know if m4 will barf at the multiple,
   conflicting AC_DEFUNs, or whether it'll just do something
   completely undefined.

1a. As a consequence, if you're adding a new hwloc version component,
   you'll need to .ompi_ignore all others while you're testing the new
   one. 

2. If someone wants to fix #1 someday, we might be able to do what we
   do for libevent: OPAL_CONFIG_SUBDIR (instead of slurping in hwloc's
   .m4 files).