This Article 
 Bibliographic References 
 Add to: 
A Theory of Wormhole Routing in Parallel Computers
June 1996 (vol. 45 no. 6)
pp. 704-713

Abstract—Virtually all theoretical work on message routing in parallel computers has dwelt on packet routing: messages are conveyed as packets, an entire packet can reside at a node of the network, and a packet is sent from the queue of one node to the queue of another node until its reaches its destination. A trend in multicomputer architecture, however, is to use wormhole routing. In wormhole routing a message is transmitted as a contiguous stream of bits, physically occupying a sequence of nodes/edges in the network. Thus, a message resembles a worm burrowing through the network. In this paper we give theoretical analyses of simple wormhole routing algorithms, showing them to be nearly optimal for butterfly and mesh connected networks. Our analysis requires initial random delays in injecting messages to the network. We report simulation results suggesting that the idea of random initial delays may have an impact beyond theoretical analysis.

[1] B. Aiello, F.T. Leighton, B. Maggs, and M. Newman, "Fast Algorithms for Bit-Serial Routing on a Hypercube," Second Ann. ACM Symp. Parallel Algorithms and Architectures, pp. 55-64. ACM Press, 1990.
[2] R. Aleliunas, "Randomized Parallel Communication," ACM-SIGOPS Symp. Principles of Distributed Systems, pp. 60-72, 1982.
[3] W.C. Athas, "Physically Compact, High Performance Multicomputers," Sixth MIT Conf. Advanced Research in VLSI, pp. 302-313. MIT Press, 1990.
[4] H. Chernoff, "A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the Sum of Observations," Annals of Math. Statistics, vol. 23, pp. 493-509, 1952.
[5] A.A. Chien, "Congestion Control in Routing Networks," MS Thesis, MIT, 1986.
[6] W.J. Dally, "Performance Analysis of k-ary n-Cube Interconnection Networks," IEEE Trans. Computers, vol. 39, no. 6, pp. 775-785, June 1992.
[7] W.J. Dally and H. Aoki, "Deadlock-Free Adaptive Routing in Multicomputer Networks Using Virtual Channels," IEEE Trans. Parallel and Distributed Systems, vol. 4, no. 4, pp. 466-475, Apr. 1993.
[8] W.J. Dally and C.L. Seitz, “Deadlock-Free Message Routing in Multiprocessor Interconnection Networks,” IEEE Trans. Computers, Vol. C-36, No. 5, May 1987, pp. 547-553.
[9] W.J. Dally,“Fine-grain message passing concurrent computers,” Proc. Third Conf. Hypercube Concurrent Computers, vol. 1, pp. 2-12, Jan. 1988.
[10] W.J. Dally, “Virtual-Channel Flow Control,” Proc. 17th Ann. Symp. Computer Architecture, CS Press, 1990, pp. 60-68.
[11] J. Duato,“On the design of deadlock-free adaptive routing algorithms for multicomputers: Theoretical aspects,” Proc. Second Europe Distributed Memory Computing Conf., Apr. 1991.
[12] U. Feige and P. Raghavan, "Exact Analysis of Hot Potato Routing. 33rd Ann. Symp. Foundations of Computer Science, pp. 553-562, Oct. 1992.
[13] J. Kim and C.R. Das,“Modeling wormhold routing in hypercubes,” Proc. Int’l Conf. Distributed Systems, pp. 386-393, 1991.
[14] F.T. Leighton,"Average Case Analysis of Greedy Routing Algorithms on Arrays," Proc. Second Ann. ACM Symp. Parallel Algorithms and Architectures, SPAA '90, Crete, July2-6, 1990.
[15] F.T. Leighton,Introduction to Parallel Algorithms and Architectures: Arrays, Trees, Hypercubes.San Mateo, Calif.: Morgan Kaufmann, 1992.
[16] F. Makedon and A. Simvonis, "On Bit-Serial Packet Routing for the Mesh and the Torus," Third Symp. Frontiers of Massively Parallel Computation, pp. 294-302. IEEE CS Press, 1990.
[17] I. Newman and A. Schuster, "Hot-Potato Worm Routing is Almost as Easy as Store-and-Forward Packet Routing," Proc. Second Israel Symp. Theory and Computing Systems, pp. 202-211, 1993.
[18] M. Noakes and W.J. Dally, “System Design of the J-Machine,” Proc. Advanced Research in VLSI, pp. 179-192, 1990.
[19] N. Pippenger, "Parallel Communication with Limited Buffers," 25th Ann. Symp. Foundations of Computer Science, pp. 127-136, 1984.
[20] W.H. Press, Numerical Recipes in C: The Art of Scientific Computing. Cambridge University Press, 1988.
[21] A. Ranade, "How to Emulate Shared Memory," Proc. 28th Ann. IEEE Symp. Foundations of Computer Science, pp. 185-194, 1987.
[22] D.S. Reeves, E.F. Gehringer, and A. Chandiramani, "Adaptive Routing and Deadlock Recovery: a Simulation Study," Fourth Conf. Hypercube Concurrent Computers and Applications, pp. 331-337. Golden Gate Enterprises, 1989.
[23] C.L. Seitz et al., "The Architecture and Programming of the Ametak Series 2010," Proc. Third Conf. Hypercube Concurrent Computers and Applications, pp. 33-37, Jan. 1988.
[24] R.J. Smith II, "Experimental System Kit Hardware," Fourth Conf. Hypercube Concurrent Computers and Applications, pp. 713-725. Golden Gate Enterprises, 1989.
[25] E. Upfal,“Efficient schemes for parallel communication,”J. ACM, pp. 507–517, 1984.
[26] Eli Upfal, "An O(log N) Deterministic Packet Routing Scheme," J. ACM, pp. 55-70, 1992.
[27] L.G. Valiant and G.J. Brebner,"Universal Schemes for Parallel Communication," Proc. 13th Ann. ACM Symp. Theory of Computing, pp. 263-277, May 1981.
[28] L.G. Valiant, "A Scheme for Fast Parallel Communication," SIAM J. Computing, vol. 11, no. 2, pp. 350-361, 1982.

Index Terms:
Communication networks, parallel processing, routing, flow control, probabilistic analysis, butterfly, mesh.
Sergio Felperin, Prabhakar Raghavan, Eli Upfal, "A Theory of Wormhole Routing in Parallel Computers," IEEE Transactions on Computers, vol. 45, no. 6, pp. 704-713, June 1996, doi:10.1109/12.506426
Usage of this product signifies your acceptance of the Terms of Use.