A new general method to compute virtual channels occupancy probabilities in wormhole networks

N. Alzeidi*, M. Ould-Khaoua, A. Khonsari

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

Virtual channels have been proposed to develop deadlock free routing algorithms and to overcome the performance degradation due to chains of blocked messages in wormhole switched networks. Hence, capturing the effect of virtual channels has always been an important issue in developing analytical performance models for these interconnection networks. Almost all previous models relayed on a method proposed by Dally to compute the probability of the number of busy virtual channels per physical channel. Dally's method is based on a Markov chain and after extensive investigation our results reveal that its accuracy degrades as traffic increases. In this study we propose and validate a new general method to compute this probability. The new general method is based on an M/G/1 queue and it exhibits a good degree of accuracy at different traffic conditions. We further showed that Dally's method can be deduced as a special case of the general method. Predictions from both, Dally's method and the new general method are validated against results obtained from an event-driven simulator that mimics the behaviour of wormhole-switch networks.

Original languageEnglish
Pages (from-to)1033-1042
Number of pages10
JournalJournal of Computer and System Sciences
Volume74
Issue number6
DOIs
Publication statusPublished - Sept 2008
Externally publishedYes

Keywords

  • M/G/1 queues
  • Multicomputers
  • Networks
  • Performance modelling
  • Simulation
  • Wormhole switching

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Networks and Communications
  • Computational Theory and Mathematics
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'A new general method to compute virtual channels occupancy probabilities in wormhole networks'. Together they form a unique fingerprint.

Cite this