ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Matrix algorithms on data-flow computers

Matej Žniderič (2017) Matrix algorithms on data-flow computers. MSc thesis.

Download (1755Kb)


    While the processor frequency has failed to significantly increase in the last decade, the needs of science for computing power continue to increase. Data-flow computer architecture presents a good alternative to traditional control-flow computer. In this work a set of algorithms for matrix-vector multiplication and matrix-matrix multiplication was developed. It was compared with control-flow implementations. With matrix-vector multiplication there was no speedup. Algorithm for multiplying matrix with a set of vectors achieved almost 4-fold speedup. Matrix-matrix multiplication algorithm achieved more than 100-fold speedup. Further matrix exponentiation and all-pairs shortest path search algorithm were implemented. First algorithm achieved 100-times speedup, while the second one was about the same speed as control-flow Floyd-Warshall algorithm.

    Item Type: Thesis (MSc thesis)
    Keywords: dataflow architecture, matrix multiplication, matrix algorithms, graph algorithms, Maxeler Technologies
    Number of Pages: 86
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    doc. dr. Jurij Mihelič305UNSPECIFIED
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537345731)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 3754
    Date Deposited: 18 Jan 2017 15:03
    Last Modified: 03 Feb 2017 11:30
    URI: http://eprints.fri.uni-lj.si/id/eprint/3754

    Actions (login required)

    View Item