Bridging the Gap between Performance and Bounds of Cholesky Factorization on Heterogeneous Platforms
hal.structure.identifier | High-End Parallel Algorithms for Challenging Numerical Simulations [HiePACS] | |
dc.contributor.author | AGULLO, Emmanuel | |
hal.structure.identifier | Laboratoire Bordelais de Recherche en Informatique [LaBRI] | |
hal.structure.identifier | Reformulations based algorithms for Combinatorial Optimization [Realopt] | |
dc.contributor.author | BEAUMONT, Olivier | |
hal.structure.identifier | Laboratoire Bordelais de Recherche en Informatique [LaBRI] | |
hal.structure.identifier | Reformulations based algorithms for Combinatorial Optimization [Realopt] | |
dc.contributor.author | EYRAUD-DUBOIS, Lionel | |
hal.structure.identifier | Optimisation des ressources : modèles, algorithmes et ordonnancement [ROMA] | |
dc.contributor.author | HERRMANN, Julien | |
hal.structure.identifier | High-End Parallel Algorithms for Challenging Numerical Simulations [HiePACS] | |
hal.structure.identifier | Reformulations based algorithms for Combinatorial Optimization [Realopt] | |
hal.structure.identifier | Efficient runtime systems for parallel architectures [RUNTIME] | |
hal.structure.identifier | STatic Optimizations, Runtime Methods [STORM] | |
dc.contributor.author | KUMAR, Suraj | |
hal.structure.identifier | Optimisation des ressources : modèles, algorithmes et ordonnancement [ROMA] | |
hal.structure.identifier | Laboratoire de l'Informatique du Parallélisme [LIP] | |
dc.contributor.author | MARCHAL, Loris | |
hal.structure.identifier | STatic Optimizations, Runtime Methods [STORM] | |
hal.structure.identifier | Laboratoire Bordelais de Recherche en Informatique [LaBRI] | |
hal.structure.identifier | Efficient runtime systems for parallel architectures [RUNTIME] | |
dc.contributor.author | THIBAULT, Samuel | |
dc.date.accessioned | 2024-04-15T09:57:24Z | |
dc.date.available | 2024-04-15T09:57:24Z | |
dc.date.created | 2015-02-25 | |
dc.date.issued | 2015-05-25 | |
dc.date.conference | 2015-05-25 | |
dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/198910 | |
dc.description.abstractEn | We consider the problem of allocating and scheduling dense linear application on fully heterogeneous platforms made of CPUs and GPUs. More specifically, we focus on the Cholesky factorization since it exhibits the main features of such problems. Indeed, the relative performance of CPU and GPU highly depends on the sub-routine: GPUs are for instance much more efficient to process regular kernels such as matrix-matrix multiplications rather than more irregular kernels such as matrix factorization. In this context, one solution consists in relying on dynamic scheduling and resource allocation mechanisms such as the ones provided by PaRSEC or StarPU. In this paper we analyze the performance of dynamic schedulers based on both actual executions and simulations, and we investigate how adding static rules based on an offline analysis of the problem to their decision process can indeed improve their performance, up to reaching some improved theoretical performance bounds which we introduce. | |
dc.description.sponsorship | Simulation de systèmes de prochaine génération - ANR-11-INFR-0013 | |
dc.description.sponsorship | Solveurs pour architectures hétérogènes utilisant des supports d'exécution - ANR-13-MONU-0007 | |
dc.language.iso | en | |
dc.subject.en | starpu-simgrid | |
dc.subject.en | Dense Linear Algebra | |
dc.subject.en | Cholesky Factorization | |
dc.subject.en | Resource Allocation | |
dc.subject.en | Scheduling | |
dc.subject.en | Dynamic Schedulers | |
dc.subject.en | Heterogeneous Resources | |
dc.subject.en | Simulation | |
dc.title.en | Bridging the Gap between Performance and Bounds of Cholesky Factorization on Heterogeneous Platforms | |
dc.type | Communication dans un congrès | |
dc.identifier.doi | 10.1109/IPDPSW.2015.35 | |
dc.subject.hal | Informatique [cs]/Calcul parallèle, distribué et partagé [cs.DC] | |
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 | Heterogeneity in Computing Workshop 2015 | |
bordeaux.country | IN | |
bordeaux.conference.city | Hyderabad | |
bordeaux.peerReviewed | oui | |
hal.identifier | hal-01120507 | |
hal.version | 1 | |
hal.invited | non | |
hal.proceedings | oui | |
hal.conference.end | 2015-05-29 | |
hal.popular | non | |
hal.audience | Internationale | |
hal.origin.link | https://hal.archives-ouvertes.fr//hal-01120507v1 | |
bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2015-05-25&rft.au=AGULLO,%20Emmanuel&BEAUMONT,%20Olivier&EYRAUD-DUBOIS,%20Lionel&HERRMANN,%20Julien&KUMAR,%20Suraj&rft.genre=unknown |
Fichier(s) constituant ce document
Fichiers | Taille | Format | Vue |
---|---|---|---|
Il n'y a pas de fichiers associés à ce document. |