The possibility of fast large-scale numerical simulation implemented with graphics processing units

Chi-Jer Yu*, Chii Tung Liu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The main purpose of this paper is to demonstrate how we make use of the powerful graphics processor, NVIDIA GTX280, in numerical simulation with the support of double precision floating number. Apply the finite volume method in simulating the Euler equation, two well-known examples for travelling shock waves were examined in high resolution. We had achieved at best 878 times faster than a Core 2 Duo E8500 system as one core used. Beside that, the potential of multi-GPU parallelism in large-scale model is also been exhibited.

Original languageEnglish
Title of host publicationProceedings - International Symposium on Parallel and Distributed Processing with Applications, ISPA 2010
Pages550-556
Number of pages7
DOIs
StatePublished - 1 Dec 2010
EventInternational Symposium on Parallel and Distributed Processing with Applications, ISPA 2010 - Taipei, Taiwan
Duration: 6 Sep 20109 Sep 2010

Publication series

NameProceedings - International Symposium on Parallel and Distributed Processing with Applications, ISPA 2010

Conference

ConferenceInternational Symposium on Parallel and Distributed Processing with Applications, ISPA 2010
CountryTaiwan
CityTaipei
Period6/09/109/09/10

Keywords

  • CUDA
  • Euler equation
  • Finite volume
  • GPU
  • Parallel computing
  • Shock wave

Fingerprint Dive into the research topics of 'The possibility of fast large-scale numerical simulation implemented with graphics processing units'. Together they form a unique fingerprint.

  • Cite this

    Yu, C-J., & Liu, C. T. (2010). The possibility of fast large-scale numerical simulation implemented with graphics processing units. In Proceedings - International Symposium on Parallel and Distributed Processing with Applications, ISPA 2010 (pp. 550-556). [5634379] (Proceedings - International Symposium on Parallel and Distributed Processing with Applications, ISPA 2010). https://doi.org/10.1109/ISPA.2010.37