Parallelization of iterative and direct schemes for Keller-box method on distributed memory platform

Author

Alias, Norma ; Hamzah, Norhafiza ; Amin, Norsarahaida S. ; Darwis, Roziha ; Satam, Noriza ; Ghaffar, Zarith Safiza Abdul

Author_Institution

Ibnu Sina Inst., Univ. Teknol. Malaysia, Skudai, Malaysia

Volume

2

fYear

2010

fDate

16-18 April 2010

Abstract

In this paper, we present iterative schemes, specifically the conjugate gradient, and Gauss Seidel red-black (GSRB) and direct schemes namely LU factorization and Gauss elimination for Keller-box scheme. The aim of this paper is to offer reasonable assessments and contrasts on behalf of the numerical experiments of these two schemes ported to run through Parallel Virtual Machine (PVM) on distributed memory platform. The computational complexity also presented for the comparison purpose, and the graphs of parallel evaluation in terms of speedup, efficiency, effectiveness and temporal performance are presented as well.

Keywords

computational complexity; distributed memory systems; iterative methods; parallel machines; virtual machines; Gauss Seidel red-black scheme; Gauss elimination; Keller-box method; LU factorization; computational complexity; conjugate gradient schemes; distributed memory platform; iterative parallelization scheme; parallel evaluation graph; parallel virtual machine; Boundary conditions; Computational complexity; Gaussian distribution; Iterative methods; Linear systems; Mathematics; Navier-Stokes equations; Robustness; Sparse matrices; Virtual machining; direct; iterative; keller-box; parallel;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Engineering and Technology (ICCET), 2010 2nd International Conference on

Conference_Location

Chengdu

Print_ISBN

978-1-4244-6347-3

Type

conf

DOI

10.1109/ICCET.2010.5485561

Filename

5485561