On static timing analysis of GPU kernels

Vesa Hirvisalo*

*Corresponding author for this work

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

    3 Citations (Scopus)

    Abstract

    We study static timing analysis of programs running on GPU accelerators. Such programs follow a data parallel programming model that allows massive parallelism on manycore processors. Data parallel programming and GPUs as accelerators have received wide use during the recent years. The timing analysis of programs running on single core machines is well known and applied also in practice. However for multicore and manycore machines, timing analysis presents a significant but yet not properly solved problem. In this paper, we present static timing analysis of GPU kernels based on a method that we call abstract CTA simulation. Cooperative Thread Arrays (CTA) are the basic execution structure that GPU devices use in their operation that proceeds in thread groups called warps. Abstract CTA simulation is based on static analysis of thread divergence in warps and their abstract scheduling.

    Original languageEnglish
    Title of host publication14th International Workshop on Worst-Case Execution Time Analysis, WCET 2014
    PublisherSchloss Dagstuhl - Leibniz-Zentrum für Informatik
    Pages43-52
    Number of pages10
    Volume39
    ISBN (Print)9783939897699
    DOIs
    Publication statusPublished - 2014
    MoE publication typeA4 Conference publication
    EventInternational Workshop on Worst-Case Execution Time Analysis - Madrid, Spain
    Duration: 18 Jul 201418 Jul 2014
    Conference number: 14

    Publication series

    NameOpenAccess Series in Informatics
    PublisherSchloss Dagstuhl--Leibniz-Zentrum fuer Informatik
    Volume39
    ISSN (Electronic)2190-6807

    Workshop

    WorkshopInternational Workshop on Worst-Case Execution Time Analysis
    Abbreviated titleWCET
    Country/TerritorySpain
    CityMadrid
    Period18/07/201418/07/2014

    Keywords

    • Parallelism
    • WCET

    Fingerprint

    Dive into the research topics of 'On static timing analysis of GPU kernels'. Together they form a unique fingerprint.

    Cite this