-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi John,
On 28/03/14 21:04, Biddiscombe, John A. wrote:
> Just as a follow up to this thread. I spoke with someone from IBM
> and they tell me that 2 cores of 4 hardware threads each are hidden
> from the kernel (how do they do that?) and used for th
> -Original Message-
> From: hwloc-users [mailto:hwloc-users-boun...@open-mpi.org] On Behalf
> Of Chris Samuel
> Sent: 26 March 2014 13:42
> To: Hardware locality user list
> Subject: Re: [hwloc-users] BGQ question.
>
> On Wed, 26 Mar 2014 11:56:08 AM Biddiscombe, John A. wr
On Wed, 26 Mar 2014 06:49:30 AM Kenneth A. Lloyd wrote:
> Is there a difference between INK and CNK?
BG/Q IO nodes run RHEL6 with a patched distro kernel.
BGQ compute nodes run CNK which is a custom kernel written in C++ and licensed
under the Eclipse Public License (EPL). It does not implem
Subject: Re: [hwloc-users] BGQ question.
On Wed, 26 Mar 2014 11:56:08 AM Biddiscombe, John A. wrote:
> I can’t test this as the system is down for maintenance, but if memory
> serves me correctly, the GCC compiled lstopo also showed 60 cores
> instead of 64/68.
It can only report
On Wed, 26 Mar 2014 11:56:08 AM Biddiscombe, John A. wrote:
> I can’t test this as the system is down for maintenance, but if memory
> serves me correctly, the GCC compiled lstopo also showed 60 cores instead
> of 64/68.
It can only report what the kernel reports and it appears your kernel is not
>
>If you build this with GCC (the standard system one, not the
>cross-compiler for BGQ) does it still get it wrong?
I can’t test this as the system is down for maintenance, but if memory
serves me correctly, the GCC compiled lstopo also showed 60 cores instead
of 64/68.
I am not certain if this
Le 26/03/2014 01:00, Christopher Samuel a écrit :
> On 26/03/14 01:34, Biddiscombe, John A. wrote:
>
> > If I compile on the login node, but run lstopo on the ION, I get
> > this (wrong, below)
>
> If you build this with GCC (the standard system one, not the
> cross-compiler for BGQ) does it still
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 26/03/14 01:34, Biddiscombe, John A. wrote:
> If I compile on the login node, but run lstopo on the ION, I get
> this (wrong, below)
If you build this with GCC (the standard system one, not the
cross-compiler for BGQ) does it still get it wrong?
Just an update to confim I'm doing it all wrong
If I compile on the login node, but run lstopo on the ION, I get this (wrong,
below)
if I set export HWLOC_FORCE_BGQ=1 and run on the ION, I get the old message ...
Topology became empty, aborting!
Aborted (core dumped)
JB
*** Fou
Chris
> Out of interest, why on an I/O node?
I'm targeting the BGQ BGAS nodes with flash cards installed. We've done tests
with GPFS mounted on the flash and are trying to get comparable results with an
in-house driver.
JB
On Tue, 25 Mar 2014 08:22:51 AM Jeff Hammond wrote:
> I am inclined to think the issue us that ion Linux uses only 16 cores. When
> hwloc does n-- for CNK to skip the 17th (OS) core, it gets the wrong answer
> for Linux.
Not here, it exposes all 17 cores on our BG/Q IO nodes.
I wonder if it's s
I am inclined to think the issue us that ion Linux uses only 16 cores. When
hwloc does n-- for CNK to skip the 17th (OS) core, it gets the wrong answer for
Linux.
Just check for Linux support and use /proc/cpuinfo and don't adjust manually.
I'm not sure hwloc on BGQ ion ion needs and special
On Tue, 25 Mar 2014 06:51:49 AM Biddiscombe, John A. wrote:
> I’m compiling hwloc using clang (bgclang++11 from ANL) to run on IO nodes af
> a BGQ.
Out of interest, why on an I/O node?
> It seems to have compiled ok, and when I run lstopo, I get an output
> like this (below), which looks reasona
me special projects where we are trying
> to customise the IO.
>
> JB
>
> From: Brice Goglin [mailto:brice.gog...@inria.fr]
> Sent: 25 March 2014 08:43
> To: Hardware locality user list; Biddiscombe, John A.
> Subject: Re: [hwloc-users] BGQ question.
>
> Wait, I miss
Biddiscombe, John A., le Tue 25 Mar 2014 08:56:02 +, a écrit :
> Looking at /proc/cpuinfo on the io node itself, I see only 60 cores listed. I
> wonder if they’ve reserved one socket of 4 cores for IO purposes
That's possible, yes.
> and in fact hwloc is seeing the correct information.
At le
Goglin [mailto:brice.gog...@inria.fr]
Sent: 25 March 2014 09:28
To: Biddiscombe, John A.; Hardware locality user list
Subject: Re: [hwloc-users] BGQ question.
Can you run hwloc-gather-topology foo and send the resulting foo.tar.bz2 ?
If the tarball is too bug, feel free to send it to me in a private
ere we
> are trying to customise the IO.
>
>
>
> JB
>
>
>
> *From:*Brice Goglin [mailto:brice.gog...@inria.fr]
> *Sent:* 25 March 2014 08:43
> *To:* Hardware locality user list; Biddiscombe, John A.
> *Subject:* Re: [hwloc-users] BGQ question.
>
>
&
some special projects where we are trying to
customise the IO.
JB
From: Brice Goglin [mailto:brice.gog...@inria.fr]
Sent: 25 March 2014 08:43
To: Hardware locality user list; Biddiscombe, John A.
Subject: Re: [hwloc-users] BGQ question.
Wait, I missed the "io node" part of your first mai
x=/gpfs/bbp.cscs.ch/home/biddisco/apps/clang/hwloc-1.8.1
>
>should I rerun with something set?
>
>Thanks
>
>JB
>
>
>From: hwloc-users [mailto:hwloc-users-boun...@open-mpi.org] On Behalf
>Of Brice Goglin
>Sent: 25 March 2014 08:04
>To: Hardware locality user list
&g
with something set?
Thanks
JB
From: hwloc-users [mailto:hwloc-users-boun...@open-mpi.org] On Behalf Of Brice
Goglin
Sent: 25 March 2014 08:04
To: Hardware locality user list
Subject: Re: [hwloc-users] BGQ question.
Le 25/03/2014 07:51, Biddiscombe, John A. a écrit :
I'm compiling hwloc
Le 25/03/2014 07:51, Biddiscombe, John A. a écrit :
>
> I'm compiling hwloc using clang (bgclang++11 from ANL) to run on IO
> nodes af a BGQ. It seems to have compiled ok, and when I run lstopo, I
> get an output like this (below), which looks reasonable, but there are
> 15 sockets instead of 16. I
I'm compiling hwloc using clang (bgclang++11 from ANL) to run on IO nodes af a
BGQ. It seems to have compiled ok, and when I run lstopo, I get an output like
this (below), which looks reasonable, but there are 15 sockets instead of 16.
I'm a little worried because the first time I compiled, I ha
22 matches
Mail list logo