A multi-GPU implementation of a D2Q37 lattice Boltzmann code

L. Biferale, F. Mantovani, M. Pivanti, F. Pozzati, M. Sbragaglia, Andrea Scagliarini, S.F. Schifano, F. Toschi, R. Tripiccione

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

18 Citations (Scopus)
1 Downloads (Pure)

Abstract

We describe a parallel implementation of a compressible Lattice Boltzmann code on a multi-GPU cluster based on Nvidia Fermi processors. We analyze how to optimize the algorithm for GP-GPU architectures, describe the implementation choices that we have adopted and compare our performance results with an implementation optimized for latest generation multi-core CPUs. Our program runs at ˜¿30% of the double-precision peak performance of one GPU and shows almost linear scaling when run on the multi-GPU cluster. Keywords: Computational fluid-dynamics – Lattice Boltzmann methods – GP-GPUs computing
Original languageEnglish
Title of host publicationParallel Processing and Applied Mathematics : 9th International Conference, PPAM 2011, Torun, Poland, September 11-14, 2011. Revised Selected Papers, Part I
EditorsR. Wyrzykowski, J. Dongarra, K. Karczewski, J. Wasniewski
Place of PublicationBerlin
PublisherSpringer
Pages640-650
ISBN (Print)978-3-642-31463-6
DOIs
Publication statusPublished - 2012
Event9th International Conference on Parallel Processing and Applied Mathematics, PPAM 2011 - Torun, Poland
Duration: 11 Sept 201114 Sept 2011
Conference number: 9

Publication series

NameLecture Notes in Computer Science
Volume7203
ISSN (Print)0302-9743

Conference

Conference9th International Conference on Parallel Processing and Applied Mathematics, PPAM 2011
Abbreviated titlePPAM 2011
Country/TerritoryPoland
CityTorun
Period11/09/1114/09/11

Fingerprint

Dive into the research topics of 'A multi-GPU implementation of a D2Q37 lattice Boltzmann code'. Together they form a unique fingerprint.

Cite this