Afficher la notice abrégée

A runtime approach to dynamic resource allocation for sparse direct solvers

hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierEfficient runtime systems for parallel architectures [RUNTIME]
dc.contributor.authorHUGO, A.-E
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierHigh-End Parallel Algorithms for Challenging Numerical Simulations [HiePACS]
dc.contributor.authorGUERMOUCHE, A
hal.structure.identifierEfficient runtime systems for parallel architectures [RUNTIME]
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorWACRENIER, P.-A
hal.structure.identifierEfficient runtime systems for parallel architectures [RUNTIME]
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorNAMYST, R
dc.date.accessioned2024-04-15T09:57:32Z
dc.date.available2024-04-15T09:57:32Z
dc.date.issued2014-09-09
dc.date.conference2014-09-09
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/198920
dc.description.abstractEn—To face the advent of multicore processors and the ever increasing complexity of hardware architectures, pro-gramming models based on DAG-of-tasks parallelism regained popularity in the high performance, scientific computing com-munity. In this context, enabling HPC applications to perform efficiently when dealing with graphs of parallel tasks that could potentially run simultaneously is a great challenge. Even if a uniform runtime system is used underneath, scheduling multiple parallel tasks over the same set of hardware resources introduces many issues, such as undesirable cache flushes or memory bus contention. In this paper, we show how runtime system-based scheduling contexts can be used to dynamically enforce locality of parallel tasks on multicore machines. We extend an existing generic sparse direct solver to use our mechanism and introduce a new decomposition method based on proportional mapping that is used to build the scheduling contexts. We propose a runtime-level dynamic context management policy to cope with the very irregular behavior of the application. A detailed performance analysis shows significant performance improvements of the solver over various multicore hardware.
dc.language.isoen
dc.source.titleInternational Conference on Parallel Processing (ICPP 2014)
dc.title.enA runtime approach to dynamic resource allocation for sparse direct solvers
dc.typeCommunication dans un congrès
dc.identifier.doi10.1109/ICPP.2014.57
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.title43rd International Conference on Parallel Processing
bordeaux.countryUS
bordeaux.title.proceedingInternational Conference on Parallel Processing (ICPP 2014)
bordeaux.conference.cityMinneapolis
bordeaux.peerReviewedoui
hal.identifierhal-01101054
hal.version1
hal.invitednon
hal.proceedingsoui
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-01101054v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.btitle=International%20Conference%20on%20Parallel%20Processing%20(ICPP%202014)&rft.date=2014-09-09&rft.au=HUGO,%20A.-E&GUERMOUCHE,%20A&WACRENIER,%20P.-A&NAMYST,%20R&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