High performance BLAS formulation of the multipole-to-local operator in 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.date.accessioned | 2024-04-15T09:57:07Z | |
| dc.date.available | 2024-04-15T09:57:07Z | |
| dc.date.issued | 2008 | |
| dc.identifier.issn | 0021-9991 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/198890 | |
| dc.description.abstractEn | The multipole-to-local (M2L) operator is the most time-consuming part of the far field computation in the Fast Multipole Method for Laplace equation. Its natural expression, though commonly used, does not respect a sharp error bound: we here first prove the correctness of a second expression. We then propose a matrix formulation implemented with BLAS (Basic Linear Algebra Subprograms) routines in order to speed up its computation for these two expressions. We also introduce special data storages in memory to gain greater computational efficiency. This BLAS scheme is finally compared, for uniform distributions, to other M2L improvements such as block FFT, rotations and plane wave expansions. When considering runtime, extra memory storage, numerical stability and common precisions for Laplace equation, the BLAS version appears as the best one. | |
| dc.language.iso | en | |
| dc.publisher | Elsevier | |
| dc.subject.en | Fast Multipole Methods | |
| dc.subject.en | Laplace equation | |
| dc.subject.en | BLAS routines | |
| dc.subject.en | error bound | |
| dc.subject.en | Fast Fourier Transform | |
| dc.subject.en | rotations | |
| dc.subject.en | plane waves | |
| dc.subject.en | uniform distribution | |
| dc.title.en | High performance BLAS formulation of the multipole-to-local operator in the Fast Multipole Method | |
| dc.type | Article de revue | |
| dc.identifier.doi | 10.1016/j.jcp.2007.09.027 | |
| dc.subject.hal | Informatique [cs]/Analyse numérique [cs.NA] | |
| dc.subject.hal | Informatique [cs]/Algorithme et structure de données [cs.DS] | |
| bordeaux.journal | Journal of Computational Physics | |
| bordeaux.page | 1836-1862 | |
| bordeaux.volume | 227 | |
| bordeaux.hal.laboratories | Laboratoire Bordelais de Recherche en Informatique (LaBRI) - UMR 5800 | * |
| bordeaux.issue | 3 | |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | inria-00000957 | |
| hal.version | 1 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//inria-00000957v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Journal%20of%20Computational%20Physics&rft.date=2008&rft.volume=227&rft.issue=3&rft.spage=1836-1862&rft.epage=1836-1862&rft.eissn=0021-9991&rft.issn=0021-9991&rft.au=COULAUD,%20Olivier&FORTIN,%20Pierre&ROMAN,%20Jean&rft.genre=article |
Fichier(s) constituant ce document
| Fichiers | Taille | Format | Vue |
|---|---|---|---|
|
Il n'y a pas de fichiers associés à ce document. |
|||