Dynamic Thread Pinning for Phase-Based OpenMP Programs
| hal.structure.identifier | Parallélisme, Réseaux, Systèmes, Modélisation [PRISM] | |
| dc.contributor.author | MAZOUZ, Abdelhafid | |
| hal.structure.identifier | Models and methods of analysis and optimization for systems with real-time and embedding constraints [AOSTE] | |
| dc.contributor.author | TOUATI, Sid | |
| hal.structure.identifier | Laboratoire Bordelais de Recherche en Informatique [LaBRI] | |
| hal.structure.identifier | Efficient runtime systems for parallel architectures [RUNTIME] | |
| dc.contributor.author | BARTHOU, Denis | |
| dc.contributor.editor | Wolf | |
| dc.contributor.editor | Felix and Mohr | |
| dc.contributor.editor | Bernd and an Mey | |
| dc.contributor.editor | Dieter | |
| dc.date.accessioned | 2024-04-15T09:43:18Z | |
| dc.date.available | 2024-04-15T09:43:18Z | |
| dc.date.created | 2013-02-08 | |
| dc.date.issued | 2013-08-26 | |
| dc.date.conference | 2013-08-26 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/197753 | |
| dc.description.abstractEn | Thread affinity has appeared as an important technique to improve the overall program performance and for better performance stability. However, if we consider a program with multiple phases, it is unlikely that a single thread affinity produces the best program performance for all these phases. If we consider the case of OpenMP, applications may have multiple parallel regions, each with a distinct inter-thread data sharing pattern. In this paper, we propose an approach that allows to change thread affinity dynamically (thread migrations) between parallel regions at runtime to account for these distinct inter-thread data sharing patterns. We demonstrate that as far as cache sharing is concerned for SPEC OMP01, not all the tested OpenMP applications exhibit a distinct phase behavior. However, we show that while fixing thread affinity for the whole execution may improve performance by up to 30%, allowing dynamic thread pinning may improve performance by up to 40%. Furthermore, we provide an analysis about the required conditions to improve the effectiveness of the approach | |
| dc.language.iso | en | |
| dc.publisher | Springer | |
| dc.source.title | Euro-Par 2013 Parallel processing | |
| dc.subject.en | OpenMP | |
| dc.subject.en | thread level parallelism | |
| dc.subject.en | thread affinity | |
| dc.subject.en | multicores. | |
| dc.subject.en | multicores | |
| dc.title.en | Dynamic Thread Pinning for Phase-Based OpenMP Programs | |
| dc.type | Communication dans un congrès | |
| dc.identifier.doi | 10.1007/978-3-642-40047-6_8 | |
| dc.subject.hal | Informatique [cs]/Calcul parallèle, distribué et partagé [cs.DC] | |
| bordeaux.page | 53-64 | |
| bordeaux.volume | 8097 | |
| bordeaux.hal.laboratories | Laboratoire Bordelais de Recherche en Informatique (LaBRI) - UMR 5800 | * |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.conference.title | The Euro-Par 2013 conference | |
| bordeaux.country | DE | |
| bordeaux.title.proceeding | Euro-Par 2013 Parallel processing | |
| bordeaux.conference.city | Aachen | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-00847482 | |
| hal.version | 1 | |
| hal.invited | non | |
| hal.proceedings | oui | |
| hal.conference.end | 2013-08-30 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-00847482v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.btitle=Euro-Par%202013%20Parallel%20processing&rft.date=2013-08-26&rft.volume=8097&rft.spage=53-64&rft.epage=53-64&rft.au=MAZOUZ,%20Abdelhafid&TOUATI,%20Sid&BARTHOU,%20Denis&rft.genre=unknown |
Fichier(s) constituant ce document
| Fichiers | Taille | Format | Vue |
|---|---|---|---|
|
Il n'y a pas de fichiers associés à ce document. |
|||