A Verification Framework for Streamlining Empirical Auto-Tuning

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

Abstract

Empirical auto-Tuning is getting attention in the field of high-performance computing (HPC) because it effectively reduces programmers' burden to improve the execution performance of an application. In the tuning process, a programmer selects a high-performance kernel variant of the application by evaluating the performances of multiple kernel variants. Since HPC applications need quite a huge number of floating-point operations, not all kernel variants produce exactly the same computation result as the original code. Although it is possible to verify the correctness of each kernel variant by executing the whole application to the end, it takes a long time to verify the final computation results of all kernel variants especially in the cases of long-running applications. Therefore, this paper proposes a framework that reduces the time for verifying the computation result on tuning a large-scale application. The framework uses user-specified information of the final computation result of the application to verify the correctness of every kernel variant. The framework also automatically skips unnecessary verifications to reduce the overall verification time. As a result, the framework streamlines empirical auto-Tuning.

Original languageEnglish
Title of host publicationProceedings - 2015 3rd International Symposium on Computing and Networking, CANDAR 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages508-514
Number of pages7
ISBN (Electronic)9781467397971
DOIs
Publication statusPublished - 2016 Mar 2
Event3rd International Symposium on Computing and Networking, CANDAR 2015 - Sapporo, Hokkaido, Japan
Duration: 2015 Dec 82015 Dec 11

Publication series

NameProceedings - 2015 3rd International Symposium on Computing and Networking, CANDAR 2015

Other

Other3rd International Symposium on Computing and Networking, CANDAR 2015
CountryJapan
CitySapporo, Hokkaido
Period15/12/815/12/11

Keywords

  • Correctness
  • Empirical auto-Tuning
  • Verification

ASJC Scopus subject areas

  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'A Verification Framework for Streamlining Empirical Auto-Tuning'. Together they form a unique fingerprint.

  • Cite this

    Hirasawa, S., Takizawa, H., & Kobayashi, H. (2016). A Verification Framework for Streamlining Empirical Auto-Tuning. In Proceedings - 2015 3rd International Symposium on Computing and Networking, CANDAR 2015 (pp. 508-514). [7424767] (Proceedings - 2015 3rd International Symposium on Computing and Networking, CANDAR 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CANDAR.2015.115