Review: High performance copy network design for multicast ATM switching

Authors:
Xinyi Liu;H. T. Mouftah
Affiliations:
Department of Electrical and Computer Engineering, Queen's University, Kingston, Ontario, Canada K7K 1E4;Department of Electrical and Computer Engineering, Queen's University, Kingston, Ontario, Canada K7K 1E4
Venue:
Computer Communications
Year:
1997

Citing 6
Cited 0

Asynchronous transfer mode: solution for broadband ISDN

Asynchronous transfer mode: solution for broadband ISDN
Design of a nonblocking shared-memory copy network for ATM

IEEE INFOCOM '92 Proceedings of the eleventh annual joint conference of the IEEE computer and communications societies on One world through communications (Vol. 2)
A copy network with shared buffers for large-scale multicast ATM switching

IEEE/ACM Transactions on Networking (TON)
A survey of modern high-performance switching techniques

IEEE Journal on Selected Areas in Communications
The Knockout Switch: A Simple, Modular Architecture for High-Performance Packet Switching

IEEE Journal on Selected Areas in Communications
Nonblocking copy networks for multicast packet switching

IEEE Journal on Selected Areas in Communications

Quantified Score

Hi-index	0.24

Visualization

Abstract

Multicast switches have found many applications in communication networks. A common design of multicast Asynchronous Transfer Mode (ATM) switches is a tandem of a copy network and a point-to-point routing network. The occurrence of overflow is an inherent problem in copy networks when the total number of copy requests exceeds the network size. Also, cells could be blocked due to the head-of-line fanout blocking, so that the cells with larger fanout than the remaining size of the idle output ports will be blocked. It limits the network throughput. This paper briefly review the multicast switch architectures, and discusses three efficient methods developed to avoid this kind of problem in copy network design for multicast ATM switching. They are buffering, input cell splitting and output size expansion. These methods and their effectiveness are described, and the corresponding copy network performance improvement obtained is demonstrated.