Analytical models of combining Banyan networks

Authors:
Arif Merchant
Affiliations:
IBM T. J. Watson Research Center, P.O. Box 704, Yorktown Heights, NY
Venue:
SIGMETRICS '92/PERFORMANCE '92 Proceedings of the 1992 ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems
Year:
1992

Citing 4
Cited 1

A Performance Bound of Multistage Combining Networks

IEEE Transactions on Computers
A Markov chain approximation for the analysis of banyan networks

SIGMETRICS '91 Proceedings of the 1991 ACM SIGMETRICS conference on Measurement and modeling of computer systems
Analysis and design of rate-based congestion control of high speed networks, I: stochastic fluid models, access regulation

Queueing Systems: Theory and Applications
Analytical models for the performance analysis of banyan networks

Analytical models for the performance analysis of banyan networks

Performance Analysis of Combining Multistage Interconnection Networks

ICPP '94 Proceedings of the 1994 International Conference on Parallel Processing - Volume 01

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present in this paper an analytical model of a multistage combining Banyan network with output buffered switches, in hot-sport traffic. In a combining network, packets bound for the same destination are combined into one if they meet at a switch; this alleviates the problem of tree-saturation caused by hot-spot traffic. We model the flow processes in the network as Markov chains and recursively approximate the departure processes of each stage of the network in terms of the departure processes of the preceding stage. This model is used to predict the throughput of the combining network, and comparison with simulation results shows the prediction to be accurate.A modified combining scheme based on low priorites for hot packets is proposed and analyzed. It is shown that this scheme yields substantial improvements in throughput over the standard combining scheme.