Communication delay analysis of fault-tolerant pipelined circuit switching in torus

F. Safaei, A. Khonsari, M. Fathy, M. Ould-Khaoua

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Large-scale parallel systems, Multiprocessors System-on-Chip (MP-SoCs), multicomputers, and cluster computers are often composed of hundreds or thousands of components (such as routers, channels and connectors) that collectively possess failure rates higher than what arise in the ordinary systems. One of the most important issues in the design of such systems is the development of the efficient fault-tolerant mechanisms that provide high throughput and low latency in communications to ensure that these systems will keep running in a degraded mode until the faulty components are repaired. Pipelined Circuit Switching (PCS) has been suggested as an efficient switching method for supporting inter-processor communications in networks due to its ability to preserve both communication performance and fault-tolerant demands in such systems. This paper presents a new mathematical model to investigate the effects of failures and capture the mean message latency in torus using PCS in the presence of faulty components. Simulation experiments confirm that the analytical model exhibits a good degree of accuracy under different working conditions.

Original languageEnglish
Pages (from-to)1131-1144
Number of pages14
JournalJournal of Computer and System Sciences
Volume73
Issue number8
DOIs
Publication statusPublished - Dec 2007

Fingerprint

Circuit Switching
Switching circuits
Communication Delay
Fault-tolerant
Torus
Communication
Latency
Interprocessor Communication
Routers
Multicomputers
Connector
Analytical models
Multiprocessor Systems
Failure Rate
Parallel Systems
Large-scale Systems
Router
Throughput
Analytical Model
Mathematical models

Keywords

  • Adaptive routing
  • Fault-tolerance
  • Large-scale parallel systems
  • Message latency
  • PCS
  • Performance evaluation
  • Queuing theory
  • Torus
  • Virtual channels

ASJC Scopus subject areas

  • Computational Theory and Mathematics

Cite this

Communication delay analysis of fault-tolerant pipelined circuit switching in torus. / Safaei, F.; Khonsari, A.; Fathy, M.; Ould-Khaoua, M.

In: Journal of Computer and System Sciences, Vol. 73, No. 8, 12.2007, p. 1131-1144.

Research output: Contribution to journalArticle

@article{f816819c1c4d44a29f586bc22dccf4a1,
title = "Communication delay analysis of fault-tolerant pipelined circuit switching in torus",
abstract = "Large-scale parallel systems, Multiprocessors System-on-Chip (MP-SoCs), multicomputers, and cluster computers are often composed of hundreds or thousands of components (such as routers, channels and connectors) that collectively possess failure rates higher than what arise in the ordinary systems. One of the most important issues in the design of such systems is the development of the efficient fault-tolerant mechanisms that provide high throughput and low latency in communications to ensure that these systems will keep running in a degraded mode until the faulty components are repaired. Pipelined Circuit Switching (PCS) has been suggested as an efficient switching method for supporting inter-processor communications in networks due to its ability to preserve both communication performance and fault-tolerant demands in such systems. This paper presents a new mathematical model to investigate the effects of failures and capture the mean message latency in torus using PCS in the presence of faulty components. Simulation experiments confirm that the analytical model exhibits a good degree of accuracy under different working conditions.",
keywords = "Adaptive routing, Fault-tolerance, Large-scale parallel systems, Message latency, PCS, Performance evaluation, Queuing theory, Torus, Virtual channels",
author = "F. Safaei and A. Khonsari and M. Fathy and M. Ould-Khaoua",
year = "2007",
month = "12",
doi = "10.1016/j.jcss.2007.02.003",
language = "English",
volume = "73",
pages = "1131--1144",
journal = "Journal of Computer and System Sciences",
issn = "0022-0000",
publisher = "Academic Press Inc.",
number = "8",

}

TY - JOUR

T1 - Communication delay analysis of fault-tolerant pipelined circuit switching in torus

AU - Safaei, F.

AU - Khonsari, A.

AU - Fathy, M.

AU - Ould-Khaoua, M.

PY - 2007/12

Y1 - 2007/12

N2 - Large-scale parallel systems, Multiprocessors System-on-Chip (MP-SoCs), multicomputers, and cluster computers are often composed of hundreds or thousands of components (such as routers, channels and connectors) that collectively possess failure rates higher than what arise in the ordinary systems. One of the most important issues in the design of such systems is the development of the efficient fault-tolerant mechanisms that provide high throughput and low latency in communications to ensure that these systems will keep running in a degraded mode until the faulty components are repaired. Pipelined Circuit Switching (PCS) has been suggested as an efficient switching method for supporting inter-processor communications in networks due to its ability to preserve both communication performance and fault-tolerant demands in such systems. This paper presents a new mathematical model to investigate the effects of failures and capture the mean message latency in torus using PCS in the presence of faulty components. Simulation experiments confirm that the analytical model exhibits a good degree of accuracy under different working conditions.

AB - Large-scale parallel systems, Multiprocessors System-on-Chip (MP-SoCs), multicomputers, and cluster computers are often composed of hundreds or thousands of components (such as routers, channels and connectors) that collectively possess failure rates higher than what arise in the ordinary systems. One of the most important issues in the design of such systems is the development of the efficient fault-tolerant mechanisms that provide high throughput and low latency in communications to ensure that these systems will keep running in a degraded mode until the faulty components are repaired. Pipelined Circuit Switching (PCS) has been suggested as an efficient switching method for supporting inter-processor communications in networks due to its ability to preserve both communication performance and fault-tolerant demands in such systems. This paper presents a new mathematical model to investigate the effects of failures and capture the mean message latency in torus using PCS in the presence of faulty components. Simulation experiments confirm that the analytical model exhibits a good degree of accuracy under different working conditions.

KW - Adaptive routing

KW - Fault-tolerance

KW - Large-scale parallel systems

KW - Message latency

KW - PCS

KW - Performance evaluation

KW - Queuing theory

KW - Torus

KW - Virtual channels

UR - http://www.scopus.com/inward/record.url?scp=34948862252&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34948862252&partnerID=8YFLogxK

U2 - 10.1016/j.jcss.2007.02.003

DO - 10.1016/j.jcss.2007.02.003

M3 - Article

AN - SCOPUS:34948862252

VL - 73

SP - 1131

EP - 1144

JO - Journal of Computer and System Sciences

JF - Journal of Computer and System Sciences

SN - 0022-0000

IS - 8

ER -