skip to main content
10.1145/1787275.1787310acmconferencesArticle/Chapter ViewAbstractPublication PagescfConference Proceedingsconference-collections
poster

Automatic tuning of MPI runtime parameter settings by using machine learning

Published: 17 May 2010 Publication History

Abstract

MPI implementations provide several hundred runtime parameters that can be tuned for performance improvement. The ideal parameter setting does not only depend on the target multiprocessor architecture but also on the application, its problem and communicator size.
This paper presents ATune, an automatic performance tuning tool that uses machine learning techniques to determine the program-specific optimal settings for a subset of the Open MPI's runtime parameters. ATune learns the behaviour of a target system by means of a training phase where several MPI benchmarks and MPI applications are run on a target architecture for varying problem and communicator sizes. For new input programs, only one run is required in order for ATune to deliver a prediction of the optimal runtime parameters values.
Experiments based on the NAS Parallel Benchmarks performed on a cluster of SMP machines are shown that demonstrate the effectiveness of ATune. For these experiments, ATune derives MPI runtime parameter settings that are on average within 4% of the maximum performance achievable on the target system resulting in a performance gain of up to 18% with respect to the default parameter setting.

References

[1]
Leo 2 supercomputer: www.uibk.ac.at/zid/systeme/hpc-systeme/leo2/
[2]
E. Alpaydin. Introduction to Machine Learning (Adaptive Computation and Machine Learning). The MIT Press, 2004.
[3]
R. F. V. der Wijngaart. Nas Parallel Benchmarks Version 2.4. Technical Report NAS-02-007, Computer Science Corporation NASA Advanced Supercomputing (NAS) Division, October 2002.
[4]
Open MPI Modular Component Architecture, 2000. http://www.open-mpi.org/faq/?category=tuning
[5]
DPS University of Innsbruck The INSIEME system: http://www.dps.uibk.ac.at/insieme
[6]
S. Pellegrini, J. Wang, T. Fahringer, and H. Moritsch. Optimizing mpi runtime parameter settings by using machine learning. In Proceedings of the 16th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface, pages 196--206, Berlin, Heidelberg, 2009. Springer-Verlag.
[7]
MVAPICH Team. MVAPICH 1.0 User and Tuning Guide, 2008.

Cited By

View all
  • (2018)Employing MPI_T in MPI Advisor to optimize application performanceInternational Journal of High Performance Computing Applications10.1177/109434201668400532:6(882-896)Online publication date: 1-Nov-2018
  • (2013)MDMPProceedings of the 2013 15th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing10.1109/SYNASC.2013.71(496-502)Online publication date: 23-Sep-2013
  • (2012)Tuning MPI Runtime Parameter Setting for High Performance ComputingProceedings of the 2012 IEEE International Conference on Cluster Computing Workshops10.1109/ClusterW.2012.15(213-221)Online publication date: 24-Sep-2012
  • Show More Cited By

Index Terms

  1. Automatic tuning of MPI runtime parameter settings by using machine learning

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    CF '10: Proceedings of the 7th ACM international conference on Computing frontiers
    May 2010
    370 pages
    ISBN:9781450300445
    DOI:10.1145/1787275
    Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 17 May 2010

    Check for updates

    Author Tags

    1. machine learning
    2. mpi runtime parameters
    3. tuning

    Qualifiers

    • Poster

    Conference

    CF'10
    Sponsor:
    CF'10: Computing Frontiers Conference
    May 17 - 19, 2010
    Bertinoro, Italy

    Acceptance Rates

    CF '10 Paper Acceptance Rate 30 of 113 submissions, 27%;
    Overall Acceptance Rate 273 of 785 submissions, 35%

    Upcoming Conference

    CF '25

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)17
    • Downloads (Last 6 weeks)2
    Reflects downloads up to 17 Jan 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2018)Employing MPI_T in MPI Advisor to optimize application performanceInternational Journal of High Performance Computing Applications10.1177/109434201668400532:6(882-896)Online publication date: 1-Nov-2018
    • (2013)MDMPProceedings of the 2013 15th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing10.1109/SYNASC.2013.71(496-502)Online publication date: 23-Sep-2013
    • (2012)Tuning MPI Runtime Parameter Setting for High Performance ComputingProceedings of the 2012 IEEE International Conference on Cluster Computing Workshops10.1109/ClusterW.2012.15(213-221)Online publication date: 24-Sep-2012
    • (2012)On the Effects of CPU Caches on MPI Point-to-Point CommunicationsProceedings of the 2012 IEEE International Conference on Cluster Computing10.1109/CLUSTER.2012.22(495-503)Online publication date: 24-Sep-2012

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media