Afficher la notice abrégée

Adaptive Task Size Control on High Level Programming for GPU/CPU Work Sharing

hal.structure.identifierGraduate School of Systems and Information Engineering [Tsukuba]
dc.contributor.authorODAJIMA, Tetsuya
hal.structure.identifierGraduate School of Systems and Information Engineering [Tsukuba]
hal.structure.identifierCenter for Computational Sciences [Tsukuba] [CCS]
dc.contributor.authorBOKU, Taisuke
hal.structure.identifierCenter for Computational Sciences [Tsukuba] [CCS]
hal.structure.identifierGraduate School of Systems and Information Engineering [Tsukuba]
dc.contributor.authorSATO, Mitsuhisa
hal.structure.identifierCenter for Computational Sciences [Tsukuba] [CCS]
dc.contributor.authorHANAWA, Toshihiro
hal.structure.identifierGraduate School of Systems and Information Engineering [Tsukuba]
hal.structure.identifierCenter for Computational Sciences [Tsukuba] [CCS]
dc.contributor.authorKODAMA, Yuetsu
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierEfficient runtime systems for parallel architectures [RUNTIME]
dc.contributor.authorNAMYST, Raymond
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierEfficient runtime systems for parallel architectures [RUNTIME]
dc.contributor.authorTHIBAULT, Samuel
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierEfficient runtime systems for parallel architectures [RUNTIME]
dc.contributor.authorAUMAGE, Olivier
dc.date.accessioned2024-04-15T09:42:10Z
dc.date.available2024-04-15T09:42:10Z
dc.date.issued2013-12-19
dc.date.conference2013-12-18
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/197661
dc.description.abstractEnOn the work sharing among GPUs and CPU cores on GPU equipped clusters, it is a critical issue to keep load balance among these heterogeneous computing resources. We have been developing a runtime system for this problem on PGAS language named XcalableMP- dev/StarPU [1]. Through the development, we found the necessity of adaptive load balancing for GPU/CPU work sharing to achieve the best performance for various application codes. In this paper, we enhance our language system XcalableMP-dev/StarPU to add a new feature which can control the task size to be assigned to these heterogeneous resources dynamically during application execution. As a result of performance evaluation on several benchmarks, we confirmed the proposed feature correctly works and the performance with heterogeneous work sharing provides up to about 40% higher performance than GPU-only utilization even for relatively small size of problems.
dc.language.isoen
dc.title.enAdaptive Task Size Control on High Level Programming for GPU/CPU Work Sharing
dc.typeCommunication dans un congrès
dc.identifier.doi10.1007/978-3-319-03889-6_7
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.titleThe 2013 International Symposium on Advances of Distributed and Parallel Computing (ADPC 2013)
bordeaux.countryIT
bordeaux.conference.cityVietri sul Mare
bordeaux.peerReviewedoui
hal.identifierhal-00920915
hal.version1
hal.invitednon
hal.proceedingsoui
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-00920915v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2013-12-19&rft.au=ODAJIMA,%20Tetsuya&BOKU,%20Taisuke&SATO,%20Mitsuhisa&HANAWA,%20Toshihiro&KODAMA,%20Yuetsu&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