Parallel solution of systems on the k-ary n-cube networks

Abdel Elah Al-Ayyoub, Khaled Day

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In this paper a parallel algorithm for solving systems of linear equation on the k-ary n-cube is presented and evaluated for the first time. The proposed algorithm is of O(N3/kn) computation complexity and uses O(Nn) commun ication time to factorize a matrix of order N on the k-airy n-cube. This is better than the best known results for the hypercube, O(N log kn), and the mesh, O(N√kn), each with approximately kn nodes. The proposed parallel algorithm takes advantage of the extra connectivity in the k-ary n-cube in order to reduce the communication time involved in tasks such as pivoting, row/column interchanges, and pivot row and multipliers column broadcasts.

Original languageEnglish
Pages (from-to)85-99
Number of pages15
JournalInternational Journal of High Speed Computing
Volume9
Issue number2
Publication statusPublished - Jun 1997

Fingerprint

K-ary N-cubes
Parallel algorithms
Parallel Algorithms
Factorise
N-cube
Pivoting
Pivot
Interchanges
System of Linear Equations
Linear equations
Hypercube
Broadcast
Multiplier
Connectivity
Mesh
Communication
Vertex of a graph

Keywords

  • Interconnection topologies
  • k-ary n-cube
  • Linear systems
  • Parallel computing

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Parallel solution of systems on the k-ary n-cube networks. / Al-Ayyoub, Abdel Elah; Day, Khaled.

In: International Journal of High Speed Computing, Vol. 9, No. 2, 06.1997, p. 85-99.

Research output: Contribution to journalArticle

@article{97fcf7185b884f7bb535c21b93e2b2fb,
title = "Parallel solution of systems on the k-ary n-cube networks",
abstract = "In this paper a parallel algorithm for solving systems of linear equation on the k-ary n-cube is presented and evaluated for the first time. The proposed algorithm is of O(N3/kn) computation complexity and uses O(Nn) commun ication time to factorize a matrix of order N on the k-airy n-cube. This is better than the best known results for the hypercube, O(N log kn), and the mesh, O(N√kn), each with approximately kn nodes. The proposed parallel algorithm takes advantage of the extra connectivity in the k-ary n-cube in order to reduce the communication time involved in tasks such as pivoting, row/column interchanges, and pivot row and multipliers column broadcasts.",
keywords = "Interconnection topologies, k-ary n-cube, Linear systems, Parallel computing",
author = "Al-Ayyoub, {Abdel Elah} and Khaled Day",
year = "1997",
month = "6",
language = "English",
volume = "9",
pages = "85--99",
journal = "International Journal of High Speed Computing",
issn = "0129-0533",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "2",

}

TY - JOUR

T1 - Parallel solution of systems on the k-ary n-cube networks

AU - Al-Ayyoub, Abdel Elah

AU - Day, Khaled

PY - 1997/6

Y1 - 1997/6

N2 - In this paper a parallel algorithm for solving systems of linear equation on the k-ary n-cube is presented and evaluated for the first time. The proposed algorithm is of O(N3/kn) computation complexity and uses O(Nn) commun ication time to factorize a matrix of order N on the k-airy n-cube. This is better than the best known results for the hypercube, O(N log kn), and the mesh, O(N√kn), each with approximately kn nodes. The proposed parallel algorithm takes advantage of the extra connectivity in the k-ary n-cube in order to reduce the communication time involved in tasks such as pivoting, row/column interchanges, and pivot row and multipliers column broadcasts.

AB - In this paper a parallel algorithm for solving systems of linear equation on the k-ary n-cube is presented and evaluated for the first time. The proposed algorithm is of O(N3/kn) computation complexity and uses O(Nn) commun ication time to factorize a matrix of order N on the k-airy n-cube. This is better than the best known results for the hypercube, O(N log kn), and the mesh, O(N√kn), each with approximately kn nodes. The proposed parallel algorithm takes advantage of the extra connectivity in the k-ary n-cube in order to reduce the communication time involved in tasks such as pivoting, row/column interchanges, and pivot row and multipliers column broadcasts.

KW - Interconnection topologies

KW - k-ary n-cube

KW - Linear systems

KW - Parallel computing

UR - http://www.scopus.com/inward/record.url?scp=0006192445&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0006192445&partnerID=8YFLogxK

M3 - Article

VL - 9

SP - 85

EP - 99

JO - International Journal of High Speed Computing

JF - International Journal of High Speed Computing

SN - 0129-0533

IS - 2

ER -