Objet : Developers list for StarPU
Archives de la liste
- From: Nathalie Furmento <nathalie.furmento@labri.fr>
- To: starpu-devel@lists.gforge.inria.fr, amani.alonazi@kaust.edu.sa, Hatem Ltaief <Hatem.Ltaief@kaust.edu.sa>
- Subject: Re: [Starpu-devel] Not stable performance model
- Date: Mon, 29 Apr 2019 15:49:33 +0200
- Authentication-results: mail3-smtp-sop.national.inria.fr; spf=None smtp.pra=nathalie.furmento@labri.fr; spf=Pass smtp.mailfrom=nathalie.furmento@labri.fr; spf=None smtp.helo=postmaster@v-zimmta02.u-bordeaux.fr
- List-archive: <http://lists.gforge.inria.fr/pipermail/starpu-devel/>
- List-id: "Developers list. For discussion of new features, code changes, etc." <starpu-devel.lists.gforge.inria.fr>
(sending email again to add missing
recipients)
On 29/04/2019 15:42, Lionel
Eyraud-Dubois wrote:
Dear Amani,
You can use the STARPU_HOSTNAME
environment variable to make starpu use a custom name, instead
of the default hostname.
See here :
http://starpu.gforge.inria.fr/doc/html/ExecutionConfigurationThroughEnvironmentVariables.html
Regards,
Lionel ED.
Le 29/04/2019 à 15:39, Amani Alonazi
a écrit :
Dear Starpu-dev,
Is it possible to set StarPU calibration to be
unified across multiple nodes? In other words to remove
the hostname from the end of the sampling files? The
reason is that I'm using starpu on a supercomputer with
"homogeneous" node performance. Correct me if I'm wrong,
the calibration on one node can be useful for other
node.
I'm getting several messages with
"[starpu][_starpu_load_history_based_model]
codelets/45//scpy.e03n15 does not exist or is not
readable"
Many thanks,
Amani
_______________________________________________ Starpu-devel mailing list Starpu-devel@lists.gforge.inria.fr https://lists.gforge.inria.fr/mailman/listinfo/starpu-devel
_______________________________________________ Starpu-devel mailing list Starpu-devel@lists.gforge.inria.fr https://lists.gforge.inria.fr/mailman/listinfo/starpu-devel -- Dr Nathalie Furmento Ingénieure de recherche CNRS http://www.labri.fr/~furmento/ LaBRI - Université Bordeaux |
- [Starpu-devel] Not stable performance model, Amani Alonazi, 29/04/2019
- Re: [Starpu-devel] Not stable performance model, Lionel Eyraud-Dubois, 29/04/2019
- Re: [Starpu-devel] Not stable performance model, Nathalie Furmento, 29/04/2019
- Re: [Starpu-devel] Not stable performance model, Samuel Thibault, 29/04/2019
- Re: [Starpu-devel] Not stable performance model, Lionel Eyraud-Dubois, 29/04/2019
Archives gérées par MHonArc 2.6.19+.