Dynamic workload peak detection for slack management

A. Milutinovic, Kees Goossens, Gerardus Johannes Maria Smit

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

    84 Downloads (Pure)

    Abstract

    In this paper an analytical study on dynamism and possibilities on slack exploitation by dynamic power management is presented. We introduce a specific workload decomposition method for work required for (streaming) application processing data tokens (e.g. video frames) with work behaviour patterns as a mix of periodic and aperiodic patterns. It offers efficient and computationally light method for speculation on considerable work variations and its exploitation in energy saving techniques. It is used by a dynamic power management policy which has low overhead and reduces both requirements for buffering space, and deadline misses (increase QoS). We evaluate our policy in experiments on MPEG4 decoding of several different input sequences and present results.
    Original languageUndefined
    Title of host publicationProceedings of International Symposium on System-on-Chip, 2009. SOC 2009.
    EditorsJan Kuper, J. Kuper
    Place of PublicationTampere
    PublisherIEEE Computer Society
    Pages42-47
    Number of pages6
    ISBN (Print)978-1-4244-4465-6
    DOIs
    Publication statusPublished - 5 Oct 2009

    Publication series

    Name
    PublisherIEEE Computer Society

    Keywords

    • METIS-264158
    • IR-68663
    • EWI-16533
    • CAES-EEA: Efficient Embedded Architectures
    • Low power
    • Embedded Systems
    • Power Management

    Cite this