Skip to main content
SpringerLink
Log in

Synthetic-perturbation tuning of MIMD programs

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Synthetic-perturbation tuning (SPT) is a novel technique for assaying and improving the performance of programs on MIMD systems. Conceptually, SPT brings the powerful, mathematical perspective of statistically designed experiments to the interdependent, sometimes refractory aspects of MIMD program tuning. Practically, synthetic perturbations provide a much needed quick-change mechanism for what otherwise would be ad hoc, hand-configured experiment setups. Overall, the technique identifies bottlenecks in programs directly as quantitative effects upon a measured response. SPT works on programs for both shared and distributed memory and it scales well with increasing system size.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Anderson, T.E., and Lazowska, E.D. 1990. Quartz: A tool for tuning parallel program performance. InProc.—SIGMETRICS 1990 Conf. (Boston, May), ACM, pp. 115–125.

  • Box, G.E.P., Hunter, W.G., and Hunter, J.S. 1978.Statistics for Experimenters. John Wiley & Sons, New York.

    Google Scholar 

  • Drouin, N. 1993. Building Hadamard matrices in steps of 4 to order 200. NISTIR 5121 (NTIS order no. PB93-189835), NTIS, Springfield, Va.

    Google Scholar 

  • Freiberger, W., ed. 1972.Statistical Computer Performance Evaluation—Proc. of a Conf. at Brown University (Providence, R.I., Nov. 22–23, 1971), Academic Press, New York.

    Google Scholar 

  • Graham, S.L., Kessler, P.B., and McKusick, M.K. 1982. Gprof: A Call Graph Execution Profiler. InConf. Proc.—ACM SIGPLAN Symp. on Compiler Construction (Boston, June), ACM, pp. 120–126.

    Google Scholar 

  • Gunter, B.H. 1993. How statistical design concepts can improve experimentation in the physical sciences.Computers in Physics, 7, 3(May/June):262–272.

    Google Scholar 

  • Hoare, C.A.R. 1962. Quicksort.Comp. J., 5, 1(Jan.):10–15.

    Google Scholar 

  • Jain, R. 1991.The Art of Computer Systems Performance Analysis. J. Wiley & Sons, New York.

    Google Scholar 

  • Kacker, R.N., Lagergren, E.S., and Filliben, J.J. 1991. Taguchi's orthogonal arrays are classical designs of experiments.J. Res. Natl. Inst. Stand. Technol., 96, 5(Sept.–Oct.): 577–591.

    Google Scholar 

  • Snelick, R. 1991. Performance evaluation of hypercube applications: Using a global clock and time dilation. NISTIR 4630 (NTIS order no. PB91-222588), NTIS, Springfield, Va.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Advanced Systems Division, National Institute of Standards and Technology, 20899, Gaithersburg, MD

    Gordon Lyon & Robert Snelick

  2. Statistical Engineering Division, National Institute of Standards and Technology, 20899, Gaithersburg, MD

    Raghu Kacker

Authors
  1. Gordon Lyon
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Robert Snelick
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Raghu Kacker
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Lyon, G., Snelick, R. & Kacker, R. Synthetic-perturbation tuning of MIMD programs. J Supercomput 8, 5–28 (1994). https://doi.org/10.1007/BF01666906

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01666906

Keywords

Search

Navigation