Skip to search boxSkip to navigationSkip to main content

Evaluation of autoparallelization toolkits for commodity GPUs

  • David Williams
    ,
  • Valeriu Codreanu
    ,
  • Po Yang
    ,
  • Baoquan Liu
    ,
  • Feng Dong
    ,
  • Burhan Yasar
Research Output: Chapter in Book/Report/Conference proceeding Chapter Peer-review

Abstract

In this paper we evaluate the performance of the OpenACC and Mint toolkits against C and CUDA implementations of the standard PolyBench test suite. Our analysis reveals that performance is similar in many cases, but that a certain set of code constructs impede the ability of Mint to generate optimal code. We then present some small improvements which we integrate into our own GPSME toolkit (which is derived from Mint) and show that our toolkit now out-performs OpenACC in the majority of tests.

Publication Information

Output type

Research Output: Chapter in Book/Report/Conference proceeding Chapter Peer-review

Original language

English

Pages from-to (Number of pages)

Pages 447-457

Publication milestones

  • Published - 31/12/2014

Publication status

Published - 31/12/2014

Publisher

Springer, Japan, India, Australia, Germany, United States, United Arab Emirates, Austria, Switzerland, Italy, China, United Kingdom, Netherlands, Brazil, France, Singapore

ISBN (Print)

9783642552236

External Publication IDs

  • handle.net: 10547/624621
  • Scopus: 84901278042

Host publication title

Parallel Processing and Applied Mathematics: 10th International Conference, PPAM 2013, Warsaw, Poland, September 8-11, 2013, Revised Selected Papers, Part I

Access to documents

Publication metrics

Metrics