Skip to main content
SpringerLink
Log in

Benchmarking the cache memory effect

  • Conference paper
  • First Online:
Applied Parallel Computing Computations in Physics, Chemistry and Engineering Science (PARA 1995)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1041))

Included in the following conference series:

  • 193 Accesses

Abstract

A new performance model of the memory hierarchy is first introduced, which describes all possible scenarios for the calculation process, including the important case when the cache memory is bypassed. A detailed study of each scenario is then given along with the derivation of corresponding formulae. In these formulae the cache load time associated with the penalty which must be paid to transfer data between the main memory and the cache is also taken into account. A two-parameter linear model for performance characterisation of cache memory effect is introduced. The double-performance parameter, n2 is defined to describe the performance degradation for problem sizes that do not fit into the cache memory. This parameter determines the problem size required to preserve twice the asymptotic performance. Excellent agreement is shown between the estimated performance figures and several benchmark measurements on iPSC/860.

The results presented here were previously published in an extended version of this article which appeared in Supercomputer 63, vol XI (5), 1995. They are re-produced with kind permission of ASFRA BV, The Netherlands.

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. Anderson, E., Z. Bai, C. Bischof, J. Demmel, J. Dongarra, J. DuCroz, A. Greenbaum, S. Hammarling, A. McKenney and D. Sorensen, LAPACK: A Portable Linear Algebra Library for High-Performance Computers, Proceedings Supercomputing'90, IEEE Computer Society Press, 1–10, 1990.

    Google Scholar 

  2. Hockney, R.W. and C.R. Jesshope, Parallel Computers 2: Architecture, Programming and Algorithms, IOP Publishing/Adam Hilger, Bristol and Philadelphia, 1988.

    Google Scholar 

  3. Berrendorf, R. and J. Helin, Evaluating the Basic Performance of the Intel iPSC/860 Parallel Computer, Concurrency: Practice and Experience, 4 (3), 223–240, 1992.

    Google Scholar 

  4. Bailey, D.H., RISC Microprocessors and Scientific Computing, Proceedings Supercomputing'93, IEEE Computer Society Press, 645–654, 1993.

    Google Scholar 

  5. Schönauer, W. and H. Häfner, Explaining the Gap between Theoretical Peak Performance and Real Performance for Supercomputer Architectures, Scientific Programming, 3 (2), 157–168, 1994.

    Google Scholar 

  6. Getov, V.S. and R.W. Hockney, Comparative Performance Analysis of Uniformly Distributed Applications, Proceedings of Euromicro Workshop on Parallel and Distributed Processing, IEEE Computer Society Press, 259–262, January 1993.

    Google Scholar 

  7. Miles, D., Beyond Vector Processing: Parallel Processing on the CRAY APP, Proceedings COMPCON Spring'93, IEEE Computer Society Press, 321–328, February, 1993.

    Google Scholar 

  8. Getov, V.S., 1-Dimensional Parallel FFT Benchmark on SUPRENUM, in: Etiemble, D. and J.-C. Syre (Eds.), PARLE'92, Parallel Architectures and Languages Europe, Lecture Notes in Computer Science, 605, Springer Verlag, 163–174, 1992.

    Google Scholar 

  9. Hey, T., R. Hockney, V. Getov, I. Wolton, J. Merlin and J. Allwright, The GENESIS Distributed Memory Benchmarks. Part 2: COMMS1, TRANS1, FFT1 and QCD2 Benchmarks on the SUPRENUM and iPSC/860 Computers, Concurrency: Practice and Experience, 1995 (to appear).

    Google Scholar 

  10. Hey, A.J.G.; The GENESIS Distributed Memory Benchmarks, Parallel Computing, 17(10–11), 1275–1283, 1991.

    Google Scholar 

  11. PARKBENCH Committee (assembled by R. Hockney and M. Berry, with contributions from D. Bailey, M. Berry, J. Dongarra, V. Getov, T. Haupt, T. Hey, R. Hockney and D. Walker), PARKBENCH Report-1: Public International Benchmarks for Parallel Computers, Scientific Programming, 3 (2), 101–146, 1994.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science and Information Systems Engineering, University of Westminster, 115 New Cavendish St., W1M 8JS, London, UK

    Vladimir Getov

Authors
  1. Vladimir Getov
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Jack Dongarra Kaj Madsen Jerzy Waśniewski

Rights and permissions

Reprints and permissions

Copyright information

© 1996 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Getov, V. (1996). Benchmarking the cache memory effect. In: Dongarra, J., Madsen, K., Waśniewski, J. (eds) Applied Parallel Computing Computations in Physics, Chemistry and Engineering Science. PARA 1995. Lecture Notes in Computer Science, vol 1041. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60902-4_27

Download citation

  • DOI: https://doi.org/10.1007/3-540-60902-4_27

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-60902-5

  • Online ISBN: 978-3-540-49670-0

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation