Exploration of Cache Line Size for Sawtooth Compressed Row Storage based SpMV Multiplication

R. Chinthala, Amitava Datta, S.K. Nandy

    Research output: Chapter in Book/Conference paperConference paperpeer-review

    Abstract

    © 2015, Australian Computer Society, Inc. Sparse Matrix Vector Multiplication (SpMV) is an important kernel in Sparse Linear Algebra. Cache based systems performance is poor during SpMV multiplication due to poor data locality of sparse matrix storage formats. In this paper, we propose a Sawtooth Compressed Row Storage (SCRS) data structure to represent sparse matrix which requires less memory and improves temporal locality compared to Compressed Row Storage (CRS), Incremental CRS (ICRS), Zig-Zag ICRS (ZZICRS) (A. Yzelman et al. 2009). We also propose a SCRS based Sawtooth Sparse Matrix Vector (SpMV) multiplication algorithm to exploit the improved temporal locality. The simulation results indicate that our proposed SCRS based SpMV algorithm achieves fewer cache misses and shorter execution time than the state of the art storage format based SpMV algorithms.
    Original languageEnglish
    Title of host publicationConferences in Research and Practice in Information Technology Series
    EditorsBahman Javadi, Saurabh Kumar
    PublisherAustralian Computer Society
    Pages93-96
    Volume163
    ISBN (Print)9781921770456
    Publication statusPublished - 2015
    Event13th Australasian Symposium on Parallel and Distributed Computing - Sydney, Australia, Sydney, Australia
    Duration: 27 Jan 201530 Jan 2015
    Conference number: 13
    https://auspdc-scem.uts.edu.au/

    Conference

    Conference13th Australasian Symposium on Parallel and Distributed Computing
    Abbreviated titleAusPDC 2015
    Country/TerritoryAustralia
    CitySydney
    Period27/01/1530/01/15
    Internet address

    Fingerprint

    Dive into the research topics of 'Exploration of Cache Line Size for Sawtooth Compressed Row Storage based SpMV Multiplication'. Together they form a unique fingerprint.

    Cite this