Title: Performance modelling of adaptive routing communication networks in multi-cluster systems under bit-reversal traffic
Authors: Hojjat Sharifi; Mohammad K. Akbari; Bahman Javadi
Addresses: Department of Computer Engineering, Vali-e-Asr University of Rafsanjan, P.O. Box 518, Rafsanjan, Iran ' Computer Engineering and Information Technology Department, Amirkabir University of Technology, P.O. Box 15914, Tehran, Iran ' School of Computing, Engineering and Mathematics, University of Western Sydney, Locked Bag 1797, Penrith NSW 2751, Sydney, Australia
Abstract: Several analytical models of interconnection networks of multi-cluster systems under uniform traffic pattern have been proposed in the literature. However, there has been hardly any work reported yet that deals with other important non-uniform traffic patterns found in many parallel applications. In this paper we propose a new analytical model of adaptive routing in fat-tree-based interconnection networks in the presence of traffic pattern generated by bit-reversal permutation, which is an important communication operation in parallel applications such as FFT computations. The model is validated through comprehensive simulation, through which the proposed model exhibited a good degree of accuracy for various system organisations and under different working conditions.
Keywords: analytical modelling; adaptive routing; multi-cluster systems; latency; heterogeneity; bit-reversal traffic patterns; performance modelling; communication networks; simulation.
International Journal of Communication Networks and Distributed Systems, 2014 Vol.12 No.4, pp.442 - 465
Received: 13 Mar 2013
Accepted: 02 Apr 2013
Published online: 02 Jun 2014 *