Skip to main content
SpringerLink
Log in

A new approach to array redistribution: Strip mining redistribution

  • Conference paper
  • First Online:
PARLE'94 Parallel Architectures and Languages Europe (PARLE 1994)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 817))

Abstract

Languages such as High Performance Fortran are used to implement parallel algorithms by distributing large data structures across a multicomputer system. To reduce the communication time for the redistribution of arrays, we proposes a new scheme, strip mining redistribution.

By using this scheme, the communication overhead is almost completely overlapped with the preceding or following computation. We have implemented a library for two-dimensional arrays using strip mining redistribution, and have achieved a speedup of 1.7 for a 2048×2048 ADI program.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Seema Hiranandani, Ken Kennedy, and Chau-Wen Tseng. Compiling Fortran D for distributed-memory machines. Communications ACM, 35(8):66–80, August 1992.

    Article  Google Scholar 

  2. High Performance Fortran Forum. High Performance Fortran Specification Version 1.0. Technical report, Rice University, Houston Texas, December 1992.

    Google Scholar 

  3. K. Kaneko et al. Processing element design for a parallel computer. IEEE MICRO, 10(2):26–38, 1990.

    Article  Google Scholar 

  4. Michaell Noakes, Deborah Wallach, and William Dally. The J-Machine multicomputer: An architectural evaluation. In Intl. Symp. on Computer Architecture, pages 224–235, 1993.

    Google Scholar 

  5. William Press. Numerical Recipes in C, pages 665–666. Cambridge, 1988.

    Google Scholar 

  6. Michael Wolfe. Optimizaing Supercompilers for Supercomputers, pages 97–123. The MIT Press, 1989.

    Google Scholar 

  7. Akiyoshi Wakatani and Michael Wolfe. The effectiveness of message strip mining. In Seventh Int'l Conf. on Parallel and Distributed Computing Systems (submitted), 1994.

    Google Scholar 

  8. Akiyoshi Wakatani and Michael Wolfe. Optimization of the redistribution of arrays for distributed memory multicomputers. In Parallel Computing (submitted), 1994.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Matsushita Electric Industrial, Japan

    Akiyoshi Wakatani

  2. Oregon Graduate Institute of Science & Technology, USA

    Michael Wolfe

Authors
  1. Akiyoshi Wakatani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Michael Wolfe
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Costas Halatsis Dimitrios Maritsas George Philokyprou Sergios Theodoridis

Rights and permissions

Reprints and permissions

Copyright information

© 1994 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Wakatani, A., Wolfe, M. (1994). A new approach to array redistribution: Strip mining redistribution. In: Halatsis, C., Maritsas, D., Philokyprou, G., Theodoridis, S. (eds) PARLE'94 Parallel Architectures and Languages Europe. PARLE 1994. Lecture Notes in Computer Science, vol 817. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58184-7_112

Download citation

  • DOI: https://doi.org/10.1007/3-540-58184-7_112

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-58184-0

  • Online ISBN: 978-3-540-48477-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation