Mostrar el registro sencillo del ítem

Analysis of Dynamic Scheduling Strategies for Matrix Multiplication on Heterogeneous Platforms

hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierReformulations based algorithms for Combinatorial Optimization [Realopt]
dc.contributor.authorBEAUMONT, Olivier
hal.structure.identifierLaboratoire de l'Informatique du Parallélisme [LIP]
hal.structure.identifierOptimisation des ressources : modèles, algorithmes et ordonnancement [ROMA]
dc.contributor.authorMARCHAL, Loris
dc.date.accessioned2024-04-04T03:19:55Z
dc.date.available2024-04-04T03:19:55Z
dc.date.issued2014
dc.date.conference2014-06-23
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/194548
dc.description.abstractEnThe tremendous increase in the size and heterogeneity of supercomputers makes it very difficult to predict the perfor-mance of a scheduling algorithm. Therefore, dynamic solu-tions, where scheduling decisions are made at runtime have overpassed static allocation strategies. The simplicity and efficiency of dynamic schedulers such as Hadoop are a key of the success of the MapReduce framework. Dynamic sched-ulers such as StarPU, PaRSEC or StarSs are also developed for more constrained computations, e.g. task graphs coming from linear algebra. To make their decisions, these runtime systems make use of some static information, such as the distance of tasks to the critical path or the affinity between tasks and computing resources (CPU, GPU,. . .) and of dy-namic information, such as where input data are actually located. In this paper, we concentrate on two elementary linear algebra kernels, namely the outer product and the matrix multiplication. For each problem, we propose sev-eral dynamic strategies that can be used at runtime and we provide an analytic study of their theoretical performance. We prove that the theoretical analysis provides very good estimate of the amount of communications induced by a dy-namic strategy and can be used in order to efficiently deter-mine thresholds used in dynamic scheduler, thus enabling to choose among them for a given problem and architecture.
dc.description.sponsorshipSolveurs pour architectures hétérogènes utilisant des supports d'exécution - ANR-13-MONU-0007
dc.description.sponsorshipRésilience des applications scientifiques sur machines exascales - ANR-10-BLAN-0301
dc.language.isoen
dc.subject.enDynamic scheduling
dc.subject.endata-aware algorithms
dc.subject.enrandomized al-gorithms
dc.subject.enperformance evaluation
dc.subject.enmatrix multiplication
dc.title.enAnalysis of Dynamic Scheduling Strategies for Matrix Multiplication on Heterogeneous Platforms
dc.typeCommunication dans un congrès
dc.identifier.doi10.1145/2600212.2600223
dc.subject.halInformatique [cs]/Calcul parallèle, distribué et partagé [cs.DC]
dc.identifier.arxiv1404.3913
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleACM Symposium on High-Performance Parallel and Distributed Computing
bordeaux.countryCA
bordeaux.conference.cityVancouver
bordeaux.peerReviewedoui
hal.identifierhal-01090254
hal.version1
hal.invitednon
hal.proceedingsoui
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-01090254v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2014&rft.au=BEAUMONT,%20Olivier&MARCHAL,%20Loris&rft.genre=unknown


Archivos en el ítem

ArchivosTamañoFormatoVer

No hay archivos asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem