Skip to main navigation Skip to search Skip to main content

The Performance of Multicast Banyan Networks

Research output: Contribution to journalArticlepeer-review

8 Scopus citations

Abstract

Multicast is the ability to transmit information from a single source node to multiple selected destination nodes in a network. Current trends in networking applications indicate that there will be an increasing demand in future networks for multicast communication. Efficient multicast communication is critical to the network performance. Banyan networks have been proposed for use in ATM high-speed communications networks and have been used for the interconnection of processors in scalable parallel computers. This paper addresses the performance issues of supporting multicast communication in banyan networks. Previous work on the performance of banyan networks has been primarily for the networks which can support only one-to-one communication (i.e., unicast banyan networks). We present here an analytical model for the performance of banyan networks which support multicast communication (i.e., multicast banyan networks). Our model yields a set of equations that can be solved for the throughput of the network. We show that the throughput of a multicast banyan network is generally higher than that of a unicast banyan network. In particular, we obtain that the throughput of a multicast banyan network is Θ(N), where N is the size of the network, compared with Θ(NlogN) for a unicast banyan network. In addition to throughput, we also derive formulas for another important performance metric, packet loss probability, for multicast banyan networks in this paper.

Original languageEnglish
Pages (from-to)909-923
Number of pages15
JournalJournal of Parallel and Distributed Computing
Volume60
Issue number8
DOIs
StatePublished - Aug 2000

Keywords

  • Banyan networks
  • Multicast communication
  • Multistage interconnection networks (MINs)
  • Performance analysis
  • Throughput

Fingerprint

Dive into the research topics of 'The Performance of Multicast Banyan Networks'. Together they form a unique fingerprint.

Cite this