Open MPI logo

Hardware Locality Users' Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Hardware Locality Users mailing list

Subject: Re: [hwloc-users] Magny Cours L3 cache issue
From: Wheeler, Kyle Bruce (kbwheel_at_[hidden])
Date: 2011-08-16 10:49:23

On Aug 15, 2011, at 4:14 PM, Samuel Thibault wrote:

> Wheeler, Kyle Bruce, le Tue 16 Aug 2011 00:11:41 +0200, a écrit :
>> I'm having the problem that my Magny Cours system is being identified (via hwloc-ls) as sharing an L3 cache between the NUMAnodes on a single socket. I know that this is not actually true, and I don't know how to begin debugging hwloc to see why it thinks that about the L3 cache. Thoughts?
> I guess you have updated to the latest Linux kernel version?

Unfortunately, this is not on a machine I have root access to. But, for what it's worth, here's the uname -a output:
Linux mzlogin01e #1 SMP 2010-02-22 16:49:47 +0100 x86_64 x86_64 x86_64 GNU/Linux

> If the problem persists, please attach the output of lstopo after having
> given the --enable-debug option to ./configure and rebuilt completely,
> to get debugging output. Also attach the /proc + /sys tarball generated
> by the installed script

I'm attaching the lstopo output, but hwloc-gather-topology doesn't seem to work on my compute nodes... not sure why. It doesn't report any failures, but it doesn't create the tarball either (just spits out more lstopo output).

Kyle B. Wheeler
Dept. 1423: Scalable System Software
Sandia National Laboratories