This Article 
 Bibliographic References 
 Add to: 
Dynamic Broadcasting in Parallel Computing
February 1995 (vol. 6 no. 2)
pp. 120-131

Abstract—We consider the problem where broadcast requests are dynamically generated at random time instants at each node of a multiprocessor network. In particular, in our model packets arrive at each node of a network according to a Poisson process, and each packet has to be broadcast to all the other nodes. We propose an on-line, distributed routing scheme to execute the broadcasts in this dynamic environment. Our scheme consists of repeated execution of a partial multinode broadcast task, which is a static communication task where any $M \leq N$ arbitrary nodes of an $N$-processor network broadcast a packet to all the other nodes. The dynamic broadcasting scheme that we propose can be used in any topology, regular or not, for which partial multinode broadcast algorithms with certain properties can be found. We derive such an algorithm and we analyze the corresponding dynamic broadcasting scheme for the hypercube network. We show that its stability region tends to the maximum possible as the number of nodes of the hypercube tends to infinity. Furthermore, for any fixed load in the stability region, the average delay is of the order of the diameter of the hypercube. Our analysis does not use any approximating assumptions.

Index Terms—Dynamic broadcasting, queuing systems, average delay, stability region, hypercubes.

[1] D. Bertzekas and R. Gallager, Data Networks, second ed. Prentice-Hall, 1992.
[2] ——, unpublished research.
[3] D. Bertsekas, C. Ozveren, G. Stamoulis, P. Tseng, and J. Tsitsiklis, "Optimal Communication Algorithms for Hypercubes," J. Parallel and Distributed Computing, vol. 11, pp. 263-275, 1991.
[4] D.P. Bertsekas and J.N. Tsitsiklis, Parallel and Distributed Computation.Englewood Cliffs, N.J.: Prentice Hall International, 1989.
[5] G. E. Blelloch,“Scans as primitive parallel operations,”Proc. Int. Conf. Parallel Processing, pp. 355–362, Aug. 1986.
[6] C. T. Ho,“Full bandwidth communications on folded hypercubes,”IBM Almaden Research Center, Res. Rep. RJ 7434 (69605), Apr. 1990.
[7] S. L. Johnsson and C.-T. Ho,“Optimum broadcasting and personalized communication in hypercubes,”IEEE Trans. Comput.,vol. 38, pp. 1249–1268, Sept. 1989.
[8] P. Kermaniand and L. Kleinrock,“Virtual cut-through: A new computer communicating switching technique,”Comput. Networks, vol. 3, pp. 267–286, 1979.
[9] F.T. Leighton,Introduction to Parallel Algorithms and Architectures: Arrays, Trees, Hypercubes.San Mateo, Calif.: Morgan Kaufmann, 1992.
[10] Y. Lan, A.-H. Esfahanian, and L.M. Ni, "Multicast in Hypercube Multiprocessors," J. Parallel and Distributed Computing, vol. 8, pp. 30-41, Jan. 1990.
[11] G. D. Stamoulis,“Routing and performance evaluation in interconnection networks,”Ph.D. thesis, Rep. LIDS-TH-2035, Massachusetts Inst. of Tech., May 1991.
[12] G. D. Stamoulis and J. N. Tsitsiklis,“Efficient fouting schemes for multiple broadcasts in hypercubes,”IEEE Trans. Parallel Distrib. Syst., vol. 4, pp. 725–739, 1993.
[13] E. A. Varvarigos and D. P. Bertsekas,“Partial multinode broadcast and partial exchange in$d$-dimensional wraparound meshes,”to appear inJ. Parallel Distrib. Comput.
[14] ——,“Multinode broadcast in hypercubes and rings with randomly distributed length of packets,”IEEE Trans. Parallel Distrib. Syst., vol. 4, pp. 144–154, 1993.

Emmanouel A. Varvarigos, Dimitri P. Bertsekas, "Dynamic Broadcasting in Parallel Computing," IEEE Transactions on Parallel and Distributed Systems, vol. 6, no. 2, pp. 120-131, Feb. 1995, doi:10.1109/71.342123
Usage of this product signifies your acceptance of the Terms of Use.