Lattice Boltzmann Simulations at Petascale on Multi-GPU Systems with Asynchronous Data Transfer and Strictly Enforced Memory Read Alignment

Fredrik Robertsén, Jan Westerholm, Keijo Mattila

Research output: Chapter in Book/Conference proceedingConference contributionScientificpeer-review

6 Citations (Scopus)

Abstract

The lattice Boltzmann method is a well-established numerical approach for complex fluid flow simulations. Recently general-purpose graphics processing units have become accessible as high-performance computing resources at large-scale. We report on implementing a lattice Boltzmann solver for multi-GPU systems that achieves 0.69 PFLOPS performance on 16384 GPUs. In addition to optimizing the data layout on the GPUs and eliminating the halo sites, we make use of the possibility to overlap data transfer between the host CPU and the device GPU with computing on the GPU. We simulate flow in porous media and measure both strong and weak scaling performance with the emphasis being on a large scale simulation using realistic input data.
Original languageUndefined/Unknown
Title of host publicationParallel, Distributed and Network-Based Processing (PDP), 2015 23rd Euromicro International Conference on
EditorsDaneshtalab Masoud, Aldinucci Marco, Leppänen Ville, Lilius Johan, Brorsson Mats
PublisherIEEE
Pages604–609
ISBN (Print)978-1-4799-8492-3
DOIs
Publication statusPublished - 2015
MoE publication typeA4 Article in a conference publication
EventEuromicro International Conference on Parallel, Distributed and Network-Based Processing - 23rd Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP 2015)
Duration: 4 Mar 20156 Mar 2015

Conference

ConferenceEuromicro International Conference on Parallel, Distributed and Network-Based Processing
Period04/03/1506/03/15

Keywords

  • GPU
  • Lattice Boltzmann methods

Cite this