Open MPI logo

Hardware Locality Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |  

This web mail archive is frozen.

This page is part of a frozen web archive of this mailing list.

You can still navigate around this archive, but know that no new mails have been added to it since July of 2016.

Click here to be taken to the new web archives of this list; it includes all the mails that are in this frozen archive plus all new mails that have been sent to the list since it was migrated to the new archives.

Subject: Re: [hwloc-devel] hwloc 1.1 rc2 make check fails on SLES10SP1 on PPC64
From: Samuel Thibault (samuel.thibault_at_[hidden])
Date: 2010-11-21 02:34:27

Christopher Samuel, le Sun 21 Nov 2010 08:23:34 +0100, a écrit :
> > So, it looks like running lstopo on the tarball doesn't work fine. It
> > doesn't see any caches (which may be related to /proc/device-tree/ too).
> OK, so the weird thing is that 1.1rc2 on this x86-64 laptop
> seems to show the right thing, but 1.1rc2 on the PPC64 box
> doesn't..

So the issues lies in the execution itself...

> > If so, first check that /tmp/sles10sp1-ppc64/proc/device-tree/
> > seems to contain what's also in /proc/device-tree/
> Way different, the captured version just has
> proc/device-tree/cpus and none of the rest.

That is expected: gather-topology only keeps what it needs.

> > Then reconfigure with --enable-debug and send the whole
> > stdout/stderr of "HWLOC_FSROOT=/tmp/sles10sp1-ppc64 lstopo"
> OK, here's both a good run and a bad run for you to compare.

We'll have a look, thanks.