Abstract
In creating interconnection networks, an efficient design is crucial because of its impact on the parallel computer performance. A routing scheme that minimises contention and avoids the formation of hot-spots should be included in the design. Static schemes are not able to adapt to traffic conditions. We have developed a new method to uniformly distribute traffic over the network, called Distributed Routing Balancing (DRB), that is based on limited and load-controlled path expansion in order to maintain a low message latency. The method uniformly balances the communication load between all links of the interconnection network and maintains a controlled latency, provided that total bandwidth requirements do not exceed the total link bandwidth available in the interconnection network. DRB defines how to create alternative paths to expand single paths (expanded path definition) and when to use them depending on traffic load (expanded path selection policies). We explain the DRB principles and show the performance evaluation of the method carried out by simulation.
This work has been supported by the Spanish Comisión Interministerial de Ciencia y Tecnologìa (CICYT) under contract number TIC 95/0868.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Beivide, R., et al.: Optimal Distance Networks of Low Degree for Parallel Computers. IEEE Trans. on Computers 40(10), 1109–1124 (1992)
Bokhari, S.: Multiphase Complete Exchange on Paragon, SP2 and CS2. IEEE Parallel and Distributed Technology 4(3), 45–49 (1996)
Chien, A.A., Kim, J.H.: Planar Adaptive Routing: Low-Cost Adaptive Networks for Multiprocessors. In: Proc. 19th Symp. on Computer Architecture, May 1992, pp. 268–277 (1992)
Dally, W.J., Seitz, C.L.: Deadlock-Free Message Routing in Multiprocessor Interconnection Networks. IEEE Trans. On Computers C-36(5), 547–553 (1987)
Dally, W.J.: Performance analysis of k-ary n-cube interconnection networks. IEEE Trans. On Comput. 39 (June 1990)
Duato, J.: A new theory of Dead-lock free adaptive routing in wormhole networks. IEEE Transactions on Parallel and Distributed Systems 4(12), 1320–1331 (1993)
Duato, J., Yalamanchili, S., Ni, L.: Interconnection Networks, an Engineering Approach. IEEE Computer Society Press, Los Alamitos (1997)
Garces, I., Franco, D., Luque, E.: Improving Parallel Computer Communication: Dynamic Routing Balancing. In: Proc. 6th Euromicro Workshop on Parallel and Distributed Processing (IEEE-Euromicro) PDP 1998, Madrid, Spain, January 21-23, pp. 111–119 (1998)
Kim, J., Liu, Z., Chien, A.: Comprensionless Routing: A Framework for Adaptive and Fault-Tolerant Routing. In: Proc. of the 21st Int. Symp. On Comp. Arch. April 1994, pp. 289–300 (1994)
Konstanyinidou, S., Snyder, L.: Chaos Router: Architecure and Performance. In: Proc. Of the 18th International Symposium on Computer Architecture, May 1991, pp. 212–221 (1991)
May, M.D., Thompson, P.W., Welch, P.H. (eds.): Networks, Routers and Transputers: Function, Performance and application. IOS Press, Amsterdam (1993)
Merlin, P.M., Schweitzer, P.J.: Deadlock Avoidance in Store-and-Forward Networks-I: Store-and-Forward Deadlock. IEEE Trans. On Comm. V. Com 28(3), 345–354 (1980)
Ni, L., Glass, C.: The Turn model for Adaptive Routing. In: Proc. of the 19th Intl. Symp. on Computer Architecture, pp. 278–287. IEEE Computer Society, Los Alamitos (1992)
Pfister, G.F., Norton, A.: Hot-Spot Contention and Combining in Multistage Interconnection Networks. IEEE Trans. On Computers 34(10) (October 1985)
Pifarre, G.D., et al.: Fully adaptive Minimal Deadlock Free Packet Routing in Hypercubes, Meshes and Other Networks: Algorithms and Simulations. IEEE Transactions on Parallel and Distributed Systems 5(3) (March 1994)
Snir, M., Hochschild, P., Frye, D.D., Gildea, K.J.: The communication software and parallel environment of the IBM SP2. IBM Systems Journal 34(2), 205–221
Valiant, L.G., Brebner, G.J.: Universal Schemes for Parallel Communication. ACM STOC, Milwaukee, 263–277 (1981)
Yantchev, J.T., Jesshope, C.R.: Adaptive, Low Latency, Deadlock Free Packet Routing for Networks of Processors. IEE Proceedings Pt.E 136(3) (May 1989)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Franco, D., Garcés, I., Luque, E. (1999). Dynamic Routing Balancing in Parallel Computer Interconnection Networks. In: Hernández, V., Palma, J.M.L.M., Dongarra, J.J. (eds) Vector and Parallel Processing – VECPAR’98. VECPAR 1998. Lecture Notes in Computer Science, vol 1573. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10703040_37
Download citation
DOI: https://doi.org/10.1007/10703040_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66228-0
Online ISBN: 978-3-540-48516-2
eBook Packages: Springer Book Archive