This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Clustering Approach for Identifying and Quantifying Irregularities in Interconnection Networks
December 2003 (vol. 14 no. 12)
pp. 1222-1239

Abstract—Support for arbitrary topologies has become more popular for system-area networks but very little has been done in trying to characterize their behavior and performance. Traditional parameters like diameter and bisection width are not sufficient for characterizing the irregularies that abound in such networks and fail to give much insight into throughput performance. A clustering approach for partitioning a network into clusters of richly-connected regions is proposed as a means of defining two performance-correlated characterization metrics: intercluster bandwidth index and intercluster link-cost index. The two characterization metrics are shown to have a strong correlation to saturation throughput when link and load distribution of a network is imbalanced. Simulation results also show that the clustering algorithm can be applied to a variety of network configurations and traffic scenarios, particularly irregular ones. With the proposed characterization metrics that correlate more strongly with performance, it is possible to classify networks into categories having similar peformance.

[1] M.D. Schroeder et al., Autonet: A High-Speed, Self-Configuring Local Area Network Using Point to Point Links Technical Report SRC research report 59, DEC, Apr. 1990.
[2] R.E. Felderman, A.E. Kulawik, C.L. Seitz, J. Seizovic, N.J. Boden, D. Cohen, and W. Su., Myrinet A Gigabit Per Second Local Area Network IEEE Micro, pp. 29-36, Feb. 1995.
[3] R. Horst, “ServerNet Deadlock Avoidance and Fractahedral Topologies,” Proc. Int'l Parallel Processing Symp., pp. 274–280, Apr. 1996.
[4] M. Galles, Scalable Pipelined Interconnect for Distributed Endpoint Routing: The SGI Spider Chip Proc. Hot Interconnects IV Symp., pp. 141-146, Aug. 1996.
[5] InfiniBand Architecture Standard Version 1.0 www.infiniband ta.com, Oct. 2000.
[6] K. Malavalli et al., Fibre Channel Switch Fabric-2 (FC-SW-2) NCITS 321-200x T11/Project 1305-D/Rev 4.3 Specification, pp. 57-74, Mar. 2000.
[7] A. Sivasubramaniam, F. Silla, J. Duato, and C.R. Das, Virtual Channel Multiplexing in Networks of Workstations with Irregular Topology Proc. Fifth Interconnection Conf. High Performance Computing, pp. 147-154, Dec. 1998.
[8] J. Duato, S. Yalamanchili, and L. Ni, Interconnection Networks: An Engineering Approach. IEEE Computer Society Press, 1997.
[9] B.W. Kernighan and S. Lin, An Efficient Heuristic Procedure for Partitioning Graphs The Bell System Technical J., vol. 49, pp. 291-307, 1970.
[10] J. Duato, "A New Theory of Deadlock-Free Adaptive Routing in Wormhole Networks," IEEE Trans. Parallel and Distributed Systems, vol. 4, no. 12, pp. 1,320-1,331, Dec. 1993.
[11] L. Schwiebert and R. Bell, The Impact of Output Selection Function Choice on the Performance of Adaptive Wormhole Routing Proc. Int'l Conf. Parallel and Distributed Computing Systems, pp. 539-544, Oct. 1997.
[12] T.M. Pinkston, “Flexible and Efficient Routing Based on Progressive Deadlock Recovery,” IEEE Trans. Computers, vol. 48, no. 7, pp. 649-669, July 1999.
[13] W.H. Ho and T.M. Pinkston, A Clustering Approach in Characterizing Interconnection Networks Proc. Fifth Int'l Conf. High Performance Computing, pp. 277-284, Dec. 1998.
[14] T.M. Pinkston and S. Warnakulasuriya, On Deadlocks in Interconnection Networks Proc. 24th Int'l Symp. Computer Architecture, pp. 38-49, June 1997.
[15] F. Silla and J. Duato, Improving the Efficiency of Adaptive Routing in Networks with Irregular Topology Proc. Int'l Conf. High Performance Computing, Dec. 1997.
[16] J.M. Martínez, P. López, J. Duato, and T.M. Pinkston, “Software-Based Deadlock Recovery Technique for True Fully Adaptive Routing in Wormhole Networks,” Proc. Int'l Conf. Parallel Processing, pp. 182-189, Aug. 1997.
[17] S. Woo, M. Ohara, E. Torrie, J.P. Singh, and A. Gupta, “The SPLASH-2 Programs: Characterization and Methodological Considerations,” Proc. Int'l Symp. Computer Architecture, pp. 24-36, June 1995.
[18] J.M. Orduna, F. Silla, and J. Duato, A New Task Mapping Technique for Communication-Aware Scheduling Strategies 2001 Int'l Conf. Parallel Processing, pp. 349-354, Sept. 2000.
[19] J.M. Orduna, V. Arnau, A. Ruiz, R. Valero, and J. Duato, On the Design of Communication-Aware Task Scheduling Strategies for Heterogeneous Systems Proc. 2000 Int'l Conf. Parallel Processing, pp. 391-398, Aug. 2000.
[20] S. Warnakulasuriya and T.M. Pinkston, Characterization of Deadlocks in Irregular Networks J. Parallel and Distributed Computing, vol. 62, no. 1, pp. 61-84, Jan. 2002.
[21] W.E. Donath and A.J. Hoffman, Lower Bounds for the Partitioning of Graphs IBM J. Research and Development, vol. 17, pp. 420-425, 1973.
[22] G. Karypis and V. Kumar, Multilevel K-Way Partitioning Scheme for Irregular Graphs J. Parallel and Distributed Computing, vol. 48, no. 1, pp. 96-129, 1998.
[23] V. Arnau, J.M. Orduna, A. Ruiz, and J. Duato, On the Characterization of Interconnection Networks with Irregular Topology: A New Model of Communication Cost Proc. XI IASTED Int'l Conf. Parallel and Distributed Computing and Systems, Nov. 1999.

Index Terms:
Clustering, network partitioning, network characterization, performance-correlated metrics, irregular topologies.
Citation:
Wai Hong Ho, Timothy Mark Pinkston, "A Clustering Approach for Identifying and Quantifying Irregularities in Interconnection Networks," IEEE Transactions on Parallel and Distributed Systems, vol. 14, no. 12, pp. 1222-1239, Dec. 2003, doi:10.1109/TPDS.2003.1255635
Usage of this product signifies your acceptance of the Terms of Use.