Reinforcement learning for automated performance tuning: Initial evaluation for sparse matrix format selection

Warren Armstrong*, Alistair P. Rendell

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    9 Citations (Scopus)

    Abstract

    The field of reinforcement learning has developed techniques for choosing beneficial actions within a dynamic environment. Such techniques learn from experience and do not require teaching. This paper explores how reinforcement learning techniques might be used to determine efficient storage formats for sparse matrices. Three different storage formats are considered: coordinate, compressed sparse row, and blocked compressed sparse row. Which format performs best depends heavily on the nature of the matrix and the computer system being used. To test the above a program has been written to generate a series of sparse matrices, where any given matrix performs optimally using one of the three different storage types. For each matrix several sparse matrix vector products are performed. The goal of the learning agent is to predict the optimal sparse matrix storage format for that matrix. The proposed agent uses five attributes of the sparse matrix: the number of rows, the number of columns, the number of non-zero elements, the standard deviation of non-zeroes per row and the mean number of neighbours. The agent is characterized by two parameters: an exploration rate and a parameter that determines how the state space is partitioned. The ability of the agent to successfully predict the optimal storage format is analyzed for a series of 1,000 automatically generated test matrices.

    Original languageEnglish
    Title of host publicationProceedings of the 2008 IEEE International Conference on Cluster Computing, CCGRID 2008
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages411-420
    Number of pages10
    ISBN (Print)9781424426409
    DOIs
    Publication statusPublished - 2008
    Event2008 IEEE International Conference on Cluster Computing, ICCC 2008 - Tsukuba, Japan
    Duration: 29 Sept 20081 Oct 2008

    Publication series

    NameProceedings - IEEE International Conference on Cluster Computing, ICCC
    VolumeProceedings of the 2008 IEEE International Conference on Clus...
    ISSN (Print)1552-5244

    Conference

    Conference2008 IEEE International Conference on Cluster Computing, ICCC 2008
    Country/TerritoryJapan
    CityTsukuba
    Period29/09/081/10/08

    Fingerprint

    Dive into the research topics of 'Reinforcement learning for automated performance tuning: Initial evaluation for sparse matrix format selection'. Together they form a unique fingerprint.

    Cite this