Parallel and scalable custom computing for real-time fluid simulation on a cluster node with four tightly-coupled FPGAs

Kentaro Sano, Ryo Ito, Hayato Suzuki, Yoshiaki Kono

Research output: Contribution to conferencePaper

Abstract

Numerical simulation based on computational fluid dynamics (CFD) is now an indispensable technique especially in industry due to its acquisition capability of various data at a lower cost than experiments using a wind tunnel. The lattice Boltzmann method (LBM) is one of the CFD schemes, which is used to compute various problems including multiphase flow. LBM has good parallelism, but simultaneously requires many data to compute each lattice point, resulting in a low operational intensity. Consequently, the sustained performance of LBM is limited by memory bandwidth rather than arithmetic performance when computed by using general-purpose processors and GPUs. To make matters worse, insufficient bandwidth and high-latency of an interconnection network cause a relatively big overhead in parallel computing, especially in the case of strong-scaling.

Original languageEnglish
DOIs
Publication statusPublished - 2013 Jan 1
Event2013 23rd International Conference on Field Programmable Logic and Applications, FPL 2013 - Porto, Portugal
Duration: 2013 Sep 22013 Sep 4

Other

Other2013 23rd International Conference on Field Programmable Logic and Applications, FPL 2013
CountryPortugal
CityPorto
Period13/9/213/9/4

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Parallel and scalable custom computing for real-time fluid simulation on a cluster node with four tightly-coupled FPGAs'. Together they form a unique fingerprint.

  • Cite this

    Sano, K., Ito, R., Suzuki, H., & Kono, Y. (2013). Parallel and scalable custom computing for real-time fluid simulation on a cluster node with four tightly-coupled FPGAs. Paper presented at 2013 23rd International Conference on Field Programmable Logic and Applications, FPL 2013, Porto, Portugal. https://doi.org/10.1109/FPL.2013.6645625