Skip to main content
SpringerLink
Log in

Evaluation of Communication Mechanisms in Invalidate-based Shared Memory Multiprocessors

  • Conference paper
  • First Online:
Parallel Computer Routing and Communication (PCRCW 1997)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1417))

Included in the following conference series:

Abstract

Producer-initiated mechanisms are added to invalidate- based systems to reduce communication latencies by transferring data as soon as it is produced. This paper compares the performance of three producer-initiated mechanisms: lock, deliver, and StreamLine. All three approaches out-perform invalidate with prefetch in most cases.

Cached-based locks offer 10–20% speedup over prefetch for two of the three benchmarks studies. StreamLine performs well in low-bandwidth environments, but does not improve with increased bandwidth. Deliver is generally competitive with prefetch, but does not offer a significant performance advantage overall.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 74.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Hazim Abdel-Shafi et al. An evaluation of fine-grain producer-initiated communication in cache-coherent multiprocessors. In 3rd Intl. Symp. on High-Perf. Comp. Architecture, pages 204–215, February 1997.

    Google Scholar 

  2. Nagi Aboulenein et al. Hardware support for synchronization in the Scalable Coherent Interface (SCI). In 8th Intl. Parallel Processing Symp., pages 141–150, April 1994.

    Google Scholar 

  3. Gregory T. Byrd and Bruce A. Delagi. StreamLine: cache-based message passing in scalable multiprocessors. In 1991 Intl. Conf. on Parallel Processing, volume I, pages 251–254, August 1991.

    Google Scholar 

  4. Bruce A. Delagi et al. Instrumented architectural simulation. In 1988 Intl. Conf. on Supercomputing, volume 1, pages 8–11, May 1988.

    Google Scholar 

  5. James R. Goodman et al. Efficient synchronization primitives for large-scale cache-coherent multiprocessors. In 3rd Intl. Conf. on Arch. Support for Prog. Languages and Operating Systems (ASPLOS-III), pages 64–75, April 1989.

    Google Scholar 

  6. Alain Kägi, Doug Burger, and James R. Goodman. Efficient synchronization: Let them eat QOLB. In 24th Intl. Symp. on Comp. Architecture, June 1997.

    Google Scholar 

  7. John Kubiatowicz and Anant Agarwal. Anatomy of a message in the Alewife multiprocessor. In 7th ACM Intl. Conf. on Supercomputing, July 1993.

    Google Scholar 

  8. Daniel Lenoski et al. The Stanford DASH multiprocessor. Computer, 25(3):63–79, March 1992.

    Google Scholar 

  9. Todd Mowry and Anoop Gupta. Tolerating latency through software-controlled prefetching in shared-memory multiprocessors. Journal of Parallel and Distr. Computing, 12(2):87–106, June 1991.

    Google Scholar 

  10. David K. Poulsen and Pen-Chung Yew. Integrating fine-grained message passing in cache coherent shared memory multiprocessors. Journal of Parallel and Distr. Computing, 33(2):172–188, March 1996.

    Google Scholar 

  11. Umakishore Ramachandran et al. Architectural mechanisms for explicit communication in shared memory multiprocessors. In Supercomputing’ 95, December 1995.

    Google Scholar 

  12. Umakishore Ramachandran and Joonwon Lee. Cache-based synchronization in shared memory multiprocessors. Journal of Parallel and Distr. Computing, 32(1):11–27, January 1996.

    Google Scholar 

  13. C. Scheurich and M. Dubois. Concurrent miss resolution in multiprocessor caches. In 1988 Intl. Conf. on Parallel Processing, volume 1, pages 118–125, August 1988.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Systems Laboratory, Stanford University, Stanford, CA

    Gregory T. Byrd & Michael J. Flynn

Authors
  1. Gregory T. Byrd
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Michael J. Flynn
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Georgia Institute of Technology, School of Electrical and Computer Science, Atlanta, Georgia, 30332-0250, USA

    Sudhakar Yalamanchili

  2. Facultad de Informàtica, Universidad Politécnica de Valencia, Camino de Vera s/n, E-46071, Valencia, Spain

    José Duato

Rights and permissions

Reprints and permissions

Copyright information

© 1998 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Byrd, G.T., Flynn, M.J. (1998). Evaluation of Communication Mechanisms in Invalidate-based Shared Memory Multiprocessors. In: Yalamanchili, S., Duato, J. (eds) Parallel Computer Routing and Communication. PCRCW 1997. Lecture Notes in Computer Science, vol 1417. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-69352-1_14

Download citation

  • DOI: https://doi.org/10.1007/3-540-69352-1_14

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-64571-9

  • Online ISBN: 978-3-540-69352-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation