A parallel processing architecture for solving large-scale linear systems

Arun Nagari, Itamar Elhanany, Ben Thompson, Fangxing Li, Thomas King

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

    Abstract

    Solving linear systems with a large number of variables is at the core of many scientific problems. Parallel processing techniques for solving such systems have received much attention in recent years. A pivotal theme in the literature pertains to the application of LU decomposing which factorizes an N x N square matrix in to two triangular matrices so that the resulting linear system can be more easily solved in O(N 2) work. Inherently, the computational complexity of LU decomposition is O(N 3). Moreover, it is a process that is challenging to parallelize. A highly- parallel methodology for solving large-scale, dense, linear systems is proposed in this paper by means of a novel application of Cramer's Rule. A numerically stable scheme is described, yielding an overall computational complexity of O(N) with N 2 processing units.

    Original languageEnglish
    Title of host publicationProceedings of the 2008 International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA 2008
    Pages307-312
    Number of pages6
    StatePublished - 2008
    Event2008 International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA 2008 - Las Vegas, NV, United States
    Duration: Jul 14 2008Jul 17 2008

    Publication series

    NameProceedings of the 2008 International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA 2008

    Conference

    Conference2008 International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA 2008
    Country/TerritoryUnited States
    CityLas Vegas, NV
    Period07/14/0807/17/08

    Fingerprint

    Dive into the research topics of 'A parallel processing architecture for solving large-scale linear systems'. Together they form a unique fingerprint.

    Cite this