Solving 3D incompressible Navier-Stokes equations on hybrid CPU/GPU systems

Yushan Wang, Marc Baboulin, Karl Rupp, Olivier Le Maitre, Yann Fraigneau

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

Abstract

This paper describes a hybrid multicore/GPU solver for the incompressible Navier-Stokes equations with constant coefficients, discretized by the finite difference method. By applying the prediction-projection method, the Navier-Stokes equations are transformed into a combination of Helmholtz-like and Poisson equations for which we describe efficient solvers. As an extension of our previous paper [1], this paper proposes a new implementation that takes advantage of GPU accelerators. We present numerical experiments on a current hybrid machine.

Original languageEnglish (US)
Title of host publicationProceedings of the 2014 Spring Simulation Multiconference, SpringSim 2014 - High Performance Computing Symposium, HPC 2014
PublisherThe Society for Modeling and Simulation International
Pages87-94
Number of pages8
Edition5
ISBN (Print)9781632662163
StatePublished - Jan 1 2014
Event22nd High Performance Computing Symposium, HPC 2014, Part of the 2014 Summer Simulation Multiconference, SummerSim 2014 - Tampa, FL, United States
Duration: Apr 13 2014Apr 16 2014

Publication series

NameSimulation Series
Number5
Volume46
ISSN (Print)0735-9276

Other

Other22nd High Performance Computing Symposium, HPC 2014, Part of the 2014 Summer Simulation Multiconference, SummerSim 2014
CountryUnited States
CityTampa, FL
Period04/13/1404/16/14

Keywords

  • Graphics Processing Unit (GPU)
  • Navier-Stokes equations
  • Parallel computing
  • Prediction-projection method

ASJC Scopus subject areas

  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Solving 3D incompressible Navier-Stokes equations on hybrid CPU/GPU systems'. Together they form a unique fingerprint.

Cite this