Towards scalable collective communication for multicomputer interconnection networks

A. Y. Al-Dubai, M. Ould-Khaoua, K. El-Zayyat, I. Ababneh, S. Al-Dobai

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

A considerable number of broadcast algorithms have been proposed for the mesh over the past decade. Nonetheless, most of these algorithms do not exhibit good scalability properties as the network size increases. As a consequence, most existing broadcast algorithms cannot efficiently support real-world parallel applications that require large-scale system sizes due to their high computational demands. Motivated by these observations, this paper proposes the Nearest Side First Algorithm (or NSF for short) as a new adaptive broadcast algorithm for the mesh. One of the key results is that the performance of the NSF algorithm scales up well with the increase of processing elements, a feature not demonstrated by any previous broadcast algorithms, which enables the proposed algorithm to utilise massive parallel architectures with maximum effectiveness.

Original languageEnglish
Pages (from-to)293-310
Number of pages18
JournalInformation Sciences
Volume163
Issue number4
DOIs
Publication statusPublished - Jun 18 2004

Fingerprint

Collective Communication
Multicomputers
Interconnection Networks
Communication
Broadcast
Mesh
Parallel architectures
Adaptive algorithms
Scale-up
Interconnection
Parallel Architectures
Parallel Applications
Large-scale Systems
Real-world Applications
Scalability
Large scale systems
Processing

Keywords

  • Broadcast latency
  • Collective communication
  • Interconnection networks
  • Mesh
  • Simulation
  • Wormhole routing

ASJC Scopus subject areas

  • Statistics and Probability
  • Electrical and Electronic Engineering
  • Statistics, Probability and Uncertainty
  • Information Systems and Management
  • Information Systems
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Towards scalable collective communication for multicomputer interconnection networks. / Al-Dubai, A. Y.; Ould-Khaoua, M.; El-Zayyat, K.; Ababneh, I.; Al-Dobai, S.

In: Information Sciences, Vol. 163, No. 4, 18.06.2004, p. 293-310.

Research output: Contribution to journalArticle

Al-Dubai, A. Y. ; Ould-Khaoua, M. ; El-Zayyat, K. ; Ababneh, I. ; Al-Dobai, S. / Towards scalable collective communication for multicomputer interconnection networks. In: Information Sciences. 2004 ; Vol. 163, No. 4. pp. 293-310.
@article{797189e6f1f042ed853d7c4d6e1cc394,
title = "Towards scalable collective communication for multicomputer interconnection networks",
abstract = "A considerable number of broadcast algorithms have been proposed for the mesh over the past decade. Nonetheless, most of these algorithms do not exhibit good scalability properties as the network size increases. As a consequence, most existing broadcast algorithms cannot efficiently support real-world parallel applications that require large-scale system sizes due to their high computational demands. Motivated by these observations, this paper proposes the Nearest Side First Algorithm (or NSF for short) as a new adaptive broadcast algorithm for the mesh. One of the key results is that the performance of the NSF algorithm scales up well with the increase of processing elements, a feature not demonstrated by any previous broadcast algorithms, which enables the proposed algorithm to utilise massive parallel architectures with maximum effectiveness.",
keywords = "Broadcast latency, Collective communication, Interconnection networks, Mesh, Simulation, Wormhole routing",
author = "Al-Dubai, {A. Y.} and M. Ould-Khaoua and K. El-Zayyat and I. Ababneh and S. Al-Dobai",
year = "2004",
month = "6",
day = "18",
doi = "10.1016/j.ins.2003.06.014",
language = "English",
volume = "163",
pages = "293--310",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",
number = "4",

}

TY - JOUR

T1 - Towards scalable collective communication for multicomputer interconnection networks

AU - Al-Dubai, A. Y.

AU - Ould-Khaoua, M.

AU - El-Zayyat, K.

AU - Ababneh, I.

AU - Al-Dobai, S.

PY - 2004/6/18

Y1 - 2004/6/18

N2 - A considerable number of broadcast algorithms have been proposed for the mesh over the past decade. Nonetheless, most of these algorithms do not exhibit good scalability properties as the network size increases. As a consequence, most existing broadcast algorithms cannot efficiently support real-world parallel applications that require large-scale system sizes due to their high computational demands. Motivated by these observations, this paper proposes the Nearest Side First Algorithm (or NSF for short) as a new adaptive broadcast algorithm for the mesh. One of the key results is that the performance of the NSF algorithm scales up well with the increase of processing elements, a feature not demonstrated by any previous broadcast algorithms, which enables the proposed algorithm to utilise massive parallel architectures with maximum effectiveness.

AB - A considerable number of broadcast algorithms have been proposed for the mesh over the past decade. Nonetheless, most of these algorithms do not exhibit good scalability properties as the network size increases. As a consequence, most existing broadcast algorithms cannot efficiently support real-world parallel applications that require large-scale system sizes due to their high computational demands. Motivated by these observations, this paper proposes the Nearest Side First Algorithm (or NSF for short) as a new adaptive broadcast algorithm for the mesh. One of the key results is that the performance of the NSF algorithm scales up well with the increase of processing elements, a feature not demonstrated by any previous broadcast algorithms, which enables the proposed algorithm to utilise massive parallel architectures with maximum effectiveness.

KW - Broadcast latency

KW - Collective communication

KW - Interconnection networks

KW - Mesh

KW - Simulation

KW - Wormhole routing

UR - http://www.scopus.com/inward/record.url?scp=2642517979&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2642517979&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2003.06.014

DO - 10.1016/j.ins.2003.06.014

M3 - Article

AN - SCOPUS:2642517979

VL - 163

SP - 293

EP - 310

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

IS - 4

ER -