Skip to main content

Shared Memory vs. Message Passing: The COMOPS Benchmark Experiment

Abstract

This paper presents the comparison of the COMOPS benchmark performance in MPI and shared memory on four different shared memory platforms: the DEC AlphaServer 8400/300, the SGI Power Challenge, the SGI Origin2000, and the HP-Convex Exemplar SPP1600. The paper also qualitatively analyzes the obtained performance data based on an understanding of the corresponding architecture and the MPI implementations. Some conclusions are made for the inter-processor communication performance on these four shared memory platforms.

This is a preview of subscription content, access via your institution.

References

  1. CONVEX Computer Corporation.1994.Exemplar Architecture 2nd Edition, Doc. No. 081-023430-001. Richardson, TX: CONVEX Press. Nov. 1994

    Google Scholar 

  2. Digital Equipment Corp.1995.AlphaSer ¨ er 8000 Series Configuring Guide. DEC WWW home page http:rr www.digital.com r info r alphaserver r alphsrv8400 r 8000.htmlaspec.

  3. D. M. Fenwick, D. J. Foley, W. B. Gist, S. R. VanDoren, and D. Wissell.“The AlphaServer 8000 series: High-end server platform development.”Digital Technical Journal. Digital Equipment Corp. Vol. 7No. 1, 43-65, 1995.

    Google Scholar 

  4. W. Gropp, N. Doss, and A. Skjellum.A High-Performance, Portable Implementation of the MPI Message Passing Interface StandardOn-line Technical Report Available at http:rr www.mcs.anl. gov r mpi r mpicharticle r paper.html.Argonne, IL: Mathematics and Computer Science Division, Argonne National Laboratory,1996.

    Google Scholar 

  5. J. Reed. Personal Correspondence About SPP1600. Nov. 1996.

  6. E. Salo. Personal Correspondence About SGI MPI. Nov. 1996.

  7. Silicon Graphics Inc. Power Challenge Technical Report. SGI WWW home page http:rr www.sgi.com r Products r hardware r servers, 1995.

  8. L. T. Liu, D. E. Culler, and C. Yoshikawa. “Benchmarking message passing performance using MPI.” IEEE Computer Society, 1996International Conference on Parallel Processing.

  9. R. W. Numrich, P. L. Springer, and J. C. Peterson. “Measurement of communication rates on the Cray T3D interprocessor network.” HPCN Europe'94, Munich, Apr. 18-20, 1994.

  10. Y. Luo. “MPI performance study on the SGI Origin 2000.” IEEE Computer Society, PACRIM'97, Aug. 20-22, 1997.

  11. T. J. LeBlanc and E. P. Markatos. “Shared memory vs message passing in shared-memory multiprocessors.” Technical Report, Computer Science Department, University of Rochester, Rochester, NY, Ari. 1992.

    Google Scholar 

  12. T. J. LeBlanc. “Shared memory versus message passing in a tightly-coupled multiprocessor: A case study,” in Proceedings of the 1986 International Conference on Parallel Processing, pp. 463-466, Aug. 1986.

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Luo, Y. Shared Memory vs. Message Passing: The COMOPS Benchmark Experiment. The Journal of Supercomputing 13, 283–301 (1999). https://doi.org/10.1023/A:1008009103962

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1008009103962

  • shared memory
  • message passing
  • MPI
  • distributed computing
  • performance evaluation