From sparse matrix to optimal GPU CUDA sparse matrix vector product implementation

Ahmed H. El Zein, Alistair P. Rendell

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

    9 Citations (Scopus)

    Abstract

    The CUDA model for GPUs presents the programmer with a plethora of different programming options. These includes different memory types, different memory access methods, and different data types. Identifying which options to use and when is a non-trivial exercise. This paper explores the effect of these different options on the performance of a routine that evaluates sparse matrix vector products. A process for analysing performance and selecting the subset of implementations that perform best is proposed. The potential for mapping sparse matrix attributes to optimal CUDA sparse matrix vector product implementation is discussed.

    Original languageEnglish
    Title of host publicationCCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing
    Pages808-813
    Number of pages6
    DOIs
    Publication statusPublished - 2010
    Event10th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2010 - Melbourne, VIC, Australia
    Duration: 17 May 201020 May 2010

    Publication series

    NameCCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing

    Conference

    Conference10th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2010
    Country/TerritoryAustralia
    CityMelbourne, VIC
    Period17/05/1020/05/10

    Fingerprint

    Dive into the research topics of 'From sparse matrix to optimal GPU CUDA sparse matrix vector product implementation'. Together they form a unique fingerprint.

    Cite this