Afficher la notice abrégée

hal.structure.identifierLaboratoire d'Informatique Parallélisme Réseaux Algorithmes Distribués [LI-PaRAD]
dc.contributor.authorHENRY, Sylvain
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierEfficient runtime systems for parallel architectures [RUNTIME]
dc.contributor.authorDENIS, Alexandre
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierEfficient runtime systems for parallel architectures [RUNTIME]
dc.contributor.authorBARTHOU, Denis
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierEfficient runtime systems for parallel architectures [RUNTIME]
dc.contributor.authorCOUNILH, Marie-Christine
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierEfficient runtime systems for parallel architectures [RUNTIME]
dc.contributor.authorNAMYST, Raymond
dc.contributor.editorFernando Silva
dc.contributor.editorInes Dutra
dc.contributor.editorVitor Santos Costa
dc.date.accessioned2024-04-15T09:58:15Z
dc.date.available2024-04-15T09:58:15Z
dc.date.issued2014-08-25
dc.date.conference2014-08-25
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/198985
dc.description.abstractEnTo fully tap into the potential of today heterogeneous machines, offloading parts of an application on accelerators is no longer sufficient. The real challenge is to build systems where the application would permanently spread across the entire machine, that is, where parallel tasks would be dynamically scheduled over the full set of available processing units. In this paper we present SOCL, an OpenCL implementation that improves and simplifies the programming experience on heterogeneous architectures. SOCL enables applications to dynamically dispatch computation kernels over processing devices so as to maximize their utilization. OpenCL applications can incrementally make use of light extensions to automatically schedule kernels in a controlled manner on multi-device architectures. We demonstrate the relevance of our approach by experimenting with several OpenCL applications on a range of heterogeneous architectures. We show that performance portability is enhanced by using SOCL extensions.
dc.language.isoen
dc.publisherSpringer
dc.subject.enOpenCL
dc.subject.enStarPU
dc.typeCommunication dans un congrès
dc.subject.halInformatique [cs]/Calcul parallèle, distribué et partagé [cs.DC]
bordeaux.hal.laboratoriesLaboratoire Bordelais de Recherche en Informatique (LaBRI) - UMR 5800*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleEuro-Par 2014
bordeaux.countryPT
bordeaux.conference.cityPorto
bordeaux.peerReviewedoui
hal.identifierhal-01005765
hal.version1
hal.invitednon
hal.proceedingsoui
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-01005765v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2014-08-25&rft.au=HENRY,%20Sylvain&DENIS,%20Alexandre&BARTHOU,%20Denis&COUNILH,%20Marie-Christine&NAMYST,%20Raymond&rft.genre=unknown


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée