ABSTRACT
One of the most promising approaches to building high speed networks and distributed multiprocessors is the use of optical interconnections. The basic component of such a system is a switch (interconnection network) that has a capacity of interconnecting a large number of inputs to outputs. In this paper we present an analysis of an N1 x N2 asynchronous crossbar switch model for all-optical circuit-switching networks that incorporates multi-rate arrival traffic with varied arrival distributions. We compare the model behavior using traffic loads derived from the Binomial, Pascal, and Poisson statistical distributions. We give efficient algorithms to compute the performance measures. We analyze the effect of load changes from particular traffic distribution streams on system performance and give a simple “economic” interpretation.
- 1.K. Batcher. Sorting Networks and their Applications. In AFIPS Proc. of SJCC, pages 307-314, vol. 32, t968.Google Scholar
- 2.V. Bene~. Mathematical Theory of Connecting Networks and Telephone Traffic. Academic Press, New York, 1965.Google Scholar
- 3.D. Bhandarkar. Analysis of Memory Interference in Multiprocessors. IEEE Trans. Computers, 24(9):897-908, September 1975.Google ScholarDigital Library
- 4.D. Bhandarkar. Some Performance Issues in Multiprocessor System Design. iEEE Trans. Computers, 26(5):506-511, May 1977.Google ScholarDigital Library
- 5.L. Bhuyan and C. Lee. An interference Analysis of Interconnection Networks. in Proc. Int. Conf. on Parallel Processing, pages 2-9, August 23-26th 1983.Google Scholar
- 6.G. Broomell and J. Heath. An integrated Circuit Crossbar Switching System. In Proc. d-th h,t. Conf. on Distributed Computing Systems, pages 278-287, May 1984.Google Scholar
- 7.D. Burman, j. Lehoczky, and Y.Lim. Insensitivity of Blocking Probabilities in a Circuit-Switched Network. J. Appl. Prob., 21:850-859, 1984.Google ScholarCross Ref
- 8.i. Cidon and I. Gopal. PARIS: An Approach to Integrated High Speed Networks. Intern. J. Digital and Analog Cabled Systems, 1:77-85, 1988.Google ScholarCross Ref
- 9.A. Conway and N. Georganas. A New Method for Computing the Normalization Constant of Multiple-Chain Queueing Networks. INFOR., 24(3):184-198, 1986.Google Scholar
- 10.A. Conway and N. Georganas. Queueing Networks- Exact Computatzonal Algorithms: A Unzfied Theory Based on Decomposition and Aggregation. MIT Press, Cambridge, MA, 1989. Google ScholarDigital Library
- 11.L. Delbrouck. A Unified Approximate Evaluation of Congestion Functions for Smooth and Peaky Traffic. IEEE. Trans. Commun., 29(2):85-91, February 1981.Google ScholarCross Ref
- 12.D. Diaz and J. Jump. Analysis and Simulation of Buffered Delta Networks. IEEE Trans. Computers, 30(4):273-282, April 1981.Google Scholar
- 13.Z. Dziong and J. Roberts. Congestion Probabilities in a Circuit-Switched integrated Services Network. Performance Evaluation, 7(4):267-284, November 1987. Google ScholarDigital Library
- 14.R. Goke and G. Lipovski. Banyan networks for Partitioning on Multiprocessor Systems. In Proc. First Conf. on Computer Architecture, pages 21- 28, 1973. Google ScholarDigital Library
- 15.A. Hartmann and S. Redfield. Design Sketches for Optical Crossbar Switches Intended for Large-Scale Parallel Processing Applications. Optical Engineering, 28(4):315-327, April 1989.Google ScholarCross Ref
- 16.H. Heffes. Moment Formulae for a Class of Mixed Multi-Job-Type Queueing Networks. Bell Syst. Tech. J., 61(5):709-745, June 1982.Google ScholarCross Ref
- 17.H. Hinton. Free-Space Systems and Devices. In Proc. IEEE Int. Conf. on Communzcations., volume 3, pages 1146-1151, Atlanta, CA, April 16-19 1990.Google ScholarCross Ref
- 18.A. Huang and S. Knauer. Starlite: A Wideband Digital Switch. In Proc. IEEE INFOCOM, pages 121-125, 1984.Google Scholar
- 19.F. Kelly. Reversibihty and Stochastic Networks. J. Wiley and Sons, New York, 1979.Google Scholar
- 20.F. Kelly. Routing in Circuit-Switched Networks: Optimization, Shadow Prices and Decentralization. Adv. Appl. Prob., 20:112-144, March 1988.Google ScholarCross Ref
- 21.C. Kruskal and M. Snir. The Performance of Multistage Interconnection Networks for Multiprocessots. IEEE Trans. Computers, 32(12):1091-1098, December 1983.Google ScholarDigital Library
- 22.T. Lang and H. Stone. A Shuffle-Exchange Network with Simplified Control. IEEE Trans. Computers, 25:55-66, January 1976.Google ScholarDigital Library
- 23.M. Marsan, G. Balbo, G. Conte, and F. Gregoretti. Modeling Bus Contention and Memory Interference in a Multiprocessor System. IEEE Trans. Computers, 32(1):60-72, January 1983.Google ScholarDigital Library
- 24.R. Mina. Modification of the Input Process used in Classical Traffic Theory. In Proc. 6th Int. Teletraffic Cong., Munich, West Germany, 1970.Google Scholar
- 25.Y. Oie, T. Suda, M. Murata, and H. Miyahara. Survey of the Performance of Non-Blocking Switches with FiFO Buffers. In Proc. IEEE Int. Conf. on Communications, pages 316.1.1-316.1.5, April 1990.Google Scholar
- 26.J. Patel. Performance of Processor-Memory Interconnections for Multiprocessors. IEEE Trans. Computers, 30(10):771-780, October 1981.Google ScholarDigital Library
- 27.E. Pinsky and A. Conway. Mean Value Analysis of Multi-Facility Models with State-Dependent Arrivals. 1991. Submitted for publication.Google Scholar
- 28.E. Pinsky and P. Stirpe. Modeling and Analysis of Hot Spots in an Asynchronous N x N Crossbar Switch. In Int. Conf. on Parallel Processing, pages 1-546-549, Chicago, Ill., August 1991.Google Scholar
- 29.P. Stirpe and E. Pinksy. Performance Analysis of an Asynchronous Multirate Crossbar. In Int. Symposium on Communications, pages 558-561, Tatwan, Republic of China, 1991.Google Scholar
- 30.P. Stirpe and E. Pinsky. The Performance Analysis of an Asynchronous Non-blocking Network Switch. In S~ngapore Int. Uonf. on Networks, pages 7-12, Raffles City Convention Centre, Singapore, September 1991.Google Scholar
- 31.H. Stone. Parallel Processing with the Perfect Shuffle. IEEE Trans. Computers, 20(2):153-161, February 1971.Google ScholarDigital Library
- 32.S. Thanawastien and V. Nelson. Interference Analysis of Shuffle/Exchange Networks. iEEE Trans. Computers, 30(8):545-556, August 1981.Google ScholarDigital Library
- 33.R. Wilkinson. Theories of Toll Tra~c Engineering in the U.S.A. Bell $yst. Tech. J., 35(2):421-514, 1956.Google ScholarCross Ref
- 34.Y. Yeh, M. Hluchyj, and A. Acampora. The Knockout Switch: A Simple Modular Architecture for High-Performance Packet Switching. IEEE j. SEC, SAC-5:1274-1283, 1987.Google Scholar
Index Terms
- Performance analysis of an asynchronous multi-rate crossbar with bursty traffic
Recommendations
Performance analysis of an asynchronous multi-rate crossbar with bursty traffic
One of the most promising approaches to building high speed networks and distributed multiprocessors is the use of optical interconnections. The basic component of such a system is a switch (interconnection network) that has a capacity of ...
Analytical Performance Modeling of NoCs under Priority Arbitration and Bursty Traffic
Networks-on-Chip (NoCs) used in commercial many-core processors typically incorporate priority arbitration. Moreover, they experience bursty traffic due to application workloads. However, most state-of-the-art NoC analytical performance analysis ...
The Performance of Crossbar-Based Binary Hypercubes
Wormhole routing is an attractive routing technique offering low latency communication without the need to buffer an entire packet in a single node. A new queueing-theoretic model for obtaining throughput and latency of binary hypercubes supporting ...
Comments