ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Parallel Gaussian Elimination for Banded Matrix - A Computational Model

Mani, V and Dattaguru, B and Balakrishnan, N and Ramamurthy, TS (1990) Parallel Gaussian Elimination for Banded Matrix - A Computational Model. In: IEEE Region 10 Conference on Computer and Communication Systems, Hong Kong, pp. 170-174.

[img]
Preview
PDF
PARALLEL_GAUSSIAN_ELIMINATION.pdf

Download (2MB)

Abstract

Parallel Gaussian elimination technique for the solution of a system of equations Ax C where A is a banded matrix, is modeled as a acyclic directed graph. This graph is useful in the identification of parallel operations, the minimum absolute completion time for the solution process and the minimum number of processors required to solve it in minimum time. Hu's level scheduling strategy is used for scheduling operations to processors. The absolute minimum completion time sets a limit on the speed-up. The absolute minimum completion time is dependent on the order of A matrix and is independent of the bandwidth. The minimum number of processors required to complete the solution process is fixed by the bandwidth and is independent of the order of A matrix. A method of incorporating communication aspects in between processors in four kinds of interconnections is also presented.

Item Type: Conference Paper
Publisher: IEEE
Additional Information: ©1990 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Keywords: Parallel Gaussian elimination
Department/Centre: Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited: 21 Jul 2004
Last Modified: 19 Sep 2010 04:14
URI: http://eprints.iisc.ac.in/id/eprint/1077

Actions (login required)

View Item View Item