Chris --
Can you verify the attached patch? If so, I'll commit it to the SVN trunk and
the pending OMPI v1.5 patch.
On Nov 2, 2011, at 10:05 AM, Brice Goglin wrote:
> If we can't find any other way, filtering (during export) would be an
> easy solution.
>
> For the v1.2 branch, the attached
If we can't find any other way, filtering (during export) would be an
easy solution.
For the v1.2 branch, the attached patch seems to help. It just prevents
the creation of internal matrices with invalid relative depth. No
internal matrix, means no XML export, which means you don't break your
impo
Should we just filter out the "distance" attribute in the XML on the v1.2ompi
branch? We're not using it (yet) in OMPI.
On Nov 2, 2011, at 9:32 AM, Brice Goglin wrote:
> Hello,
>
> The v1.2 branch has known problems with distance matrices when the topology
> is asymmetric (especially when Lin
Hello,
The v1.2 branch has known problems with distance matrices when the
topology is asymmetric (especially when Linux cpuset make some NUMA
nodes CPU-less). This is what causes wrong relative_depth here. It can
even be negative is some cases which is obviously wrong.
This should be fixed in v1.
Doh! I forgot to add hwloc-devel before hitting send.
Brice / Samuel - see below.
Sent from my phone. No type good.
On Nov 2, 2011, at 8:40 AM, "Jeff Squyres (jsquyres)"
wrote:
> Chris -
>
> I totally missed this email; sorry! I'm cc-ing hwloc-devel to see if
> brice/Samuel can fix.
>
