Hybrid MPI-Thread Parallelization of the Fast Multipole Method
| hal.structure.identifier | Algorithms and high performance computing for grand challenge applications [SCALAPPLIX] | |
| dc.contributor.author | COULAUD, Olivier | |
| hal.structure.identifier | Algorithms and high performance computing for grand challenge applications [SCALAPPLIX] | |
| dc.contributor.author | FORTIN, Pierre | |
| hal.structure.identifier | Algorithms and high performance computing for grand challenge applications [SCALAPPLIX] | |
| hal.structure.identifier | Laboratoire Bordelais de Recherche en Informatique [LaBRI] | |
| dc.contributor.author | ROMAN, Jean | |
| dc.contributor.editor | IEEE Computer Society | |
| dc.date.accessioned | 2024-04-15T09:56:34Z | |
| dc.date.available | 2024-04-15T09:56:34Z | |
| dc.date.issued | 2007-07-05 | |
| dc.date.conference | 2007-07-05 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/198848 | |
| dc.description.abstractEn | We present in this paper multi-thread and multi-process parallelizations of the Fast Multipole Method (FMM) for Laplace equation, for uniform and non uniform distributions. These parallelizations apply to the original FMM formulation and to our new matrix formulation with BLAS (Basic Linear Algebra Subprograms) routines. Differences between the multi-thread and the multi-process versions are detailed, and a hybrid MPI-thread approach enables to gain parallel efficiency and memory scalability over the pure MPI one on clusters of SMP nodes. On 128 processors, we obtain 85% (respectively 75%) parallel efficiency for uniform (respectively non uniform) distributions with up to 100 million particles. | |
| dc.language.iso | en | |
| dc.subject.en | Fast Multipole Methods | |
| dc.subject.en | parallel algorithmics | |
| dc.subject.en | MPI | |
| dc.subject.en | POSIX threads | |
| dc.subject.en | hybrid MPI-thread programming | |
| dc.subject.en | BLAS routines | |
| dc.title.en | Hybrid MPI-Thread Parallelization of the Fast Multipole Method | |
| dc.type | Communication dans un congrès | |
| dc.subject.hal | Informatique [cs]/Algorithme et structure de données [cs.DS] | |
| dc.subject.hal | Informatique [cs]/Calcul parallèle, distribué et partagé [cs.DC] | |
| dc.subject.hal | Informatique [cs]/Modélisation et simulation | |
| bordeaux.page | 391-398 | |
| 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 | ISPDC 2007, 6th International Symposium on Parallel and Distributed Computing | |
| bordeaux.country | AU | |
| bordeaux.conference.city | Hagenberg, Austria | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | inria-00131001 | |
| hal.version | 1 | |
| hal.invited | non | |
| hal.proceedings | oui | |
| hal.popular | non | |
| hal.audience | Non spécifiée | |
| hal.origin.link | https://hal.archives-ouvertes.fr//inria-00131001v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2007-07-05&rft.spage=391-398&rft.epage=391-398&rft.au=COULAUD,%20Olivier&FORTIN,%20Pierre&ROMAN,%20Jean&rft.genre=unknown |
Fichier(s) constituant ce document
| Fichiers | Taille | Format | Vue |
|---|---|---|---|
|
Il n'y a pas de fichiers associés à ce document. |
|||