A user-defined code transformation approach to overlapping mpi communication with computation

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

Abstract

The Xevolver framework has been developed to enable application programmers to define their own code translation rules outside of their codes so that they can express platform-specific optimizations separately from algorithm-level application codes. Due to the diversity of HPC node architectures, the Xevolver framework has so far mainly been used to separate node-level code optimizations from application codes. However, user-defined code transformation rules are also potentially useful for optimizing MPI applications without messing up their codes. Therefore, this paper shows a case study of using the Xevolver framework to optimize MPI applications through customizable code transformations without loss of high performance portability, and discusses the benefits of the framework.

Original languageEnglish
Title of host publicationProceedings - 2016 4th International Symposium on Computing and Networking, CANDAR 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages508-514
Number of pages7
ISBN (Electronic)9781509026555
DOIs
Publication statusPublished - 2017 Jan 13
Event4th International Symposium on Computing and Networking, CANDAR 2016 - Hiroshima, Japan
Duration: 2016 Nov 222016 Nov 25

Publication series

NameProceedings - 2016 4th International Symposium on Computing and Networking, CANDAR 2016

Other

Other4th International Symposium on Computing and Networking, CANDAR 2016
CountryJapan
CityHiroshima
Period16/11/2216/11/25

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Signal Processing
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'A user-defined code transformation approach to overlapping mpi communication with computation'. Together they form a unique fingerprint.

  • Cite this

    Hayashi, Y., Takizawa, H., & Kobayashi, H. (2017). A user-defined code transformation approach to overlapping mpi communication with computation. In Proceedings - 2016 4th International Symposium on Computing and Networking, CANDAR 2016 (pp. 508-514). [7818664] (Proceedings - 2016 4th International Symposium on Computing and Networking, CANDAR 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CANDAR.2016.35