[Users] [Commits] New changesets in Carpet Mercurial

Erik Schnetter schnetter at cct.lsu.edu
Mon Mar 19 12:05:58 CDT 2012


Luca

In general, the system should provide good settings, and you would not
use this parameter.

In some cases, the system may have a problem, and then this parameter
can provide a work-around. For example, we recently identified a
change of behaviour on Kraken at TACC, and were able to use this
parameter to work around a problem. (In the mean time, we found the
correct solution for Kraken.)

-erik

On Fri, Mar 16, 2012 at 8:37 PM, Luca Baiotti <baiotti at ile.osaka-u.ac.jp> wrote:
> Hello Erik,
>
> is set_cpu_affinity (already) recommended for production runs? What
> could one expect from it?
>
> Best,
>
> Luca
>
>
>
> On 17/3/12 12:16 AM, Carpet mercurial repositories wrote:
>> changeset:   3492:0a4e0bb3448a
>> parent:      3490:c81ef26b02ec
>> user:        Erik Schnetter<schnetter at gmail.com>
>> date:        Fri Mar 16 11:09:48 2012 -0400
>> summary:     Carpet: Add parameter set_cpuaffinity
>>
>> changeset:   3493:26551c89c940
>> parent:      3492:0a4e0bb3448a
>> parent:      3491:e8512ecd6c79
>> user:        Erik Schnetter<schnetter at gmail.com>
>> date:        Fri Mar 16 11:15:28 2012 -0400
>> summary:     Merge
>>
>> changeset:   3494:b85d9ecd647a
>> tag:         tip
>> user:        Erik Schnetter<schnetter at gmail.com>
>> date:        Fri Mar 16 11:16:19 2012 -0400
>> summary:     Carpet: Add example parameter files for CPU affinity handling
>>
>> _______________________________________________
>> Commits mailing list
>> Commits at einsteintoolkit.org
>> http://lists.einsteintoolkit.org/mailman/listinfo/commits
>>
>
> --
> Thanks for saving energy!
> _______________________________________________
> Users mailing list
> Users at einsteintoolkit.org
> http://lists.einsteintoolkit.org/mailman/listinfo/users



--
Erik Schnetter <schnetter at cct.lsu.edu>
http://www.perimeterinstitute.ca/personal/eschnetter/


More information about the Users mailing list