This Article 
 Bibliographic References 
 Add to: 
Reconfiguration with Time Division Multiplexed MIN's for Multiprocessor Communications
April 1994 (vol. 5 no. 4)
pp. 337-352

Time division multiplexed multistage interconnection networks (TDM-MIN's) are proposed for multiprocessor communications. Connections required by an application are partitioned into a number of subsets, called mappings, such that connections in each mapping can be established in an MIN without conflict. Switch settings for establishing connections in each mapping are determined and stored in shift registers. By repeatedly changing switch settings, connections in each mapping are established for a time slot in a round-robin fashion. Thus, all connections required by an application may be established in an MIN in a time division multiplexed way. TDM-MIN's can emulate a completely connected network using N time slots. It can also emulate regular networks such as rings, meshes, cube-connected-cycles (CCC), binary trees, and n-dimensional hypercubes using 2, 4, 3, 4, and n time slots, respectively. The problem of partitioning an arbitrary set of requests into a minimal number of mappings is NP-hard. Simple heuristic algorithms are presented and their performances are shown to be close to optimal. The flexibility of TDM-MIN's allows for the support of run-time requests through dynamic reconfigurations. The techniques are especially suitable for hybrid electro-optical systems with optical interconnects.

[1] M. Abidi and D. Agrawal, "On conflict-free permutations in multistage interconnection networks,"J. Digital Syst., vol. V, no. 2, pp. 115-134, 1980.
[2] K. E. Batcher, "The flip network in STARAN,"1976 Int. Conf. Parallel Processing, pp. 65-71.
[3] K. E. Batcher, "The multi-dimensional access in STARAN,"IEEE Trans. Comput., Special Issue on Parallel Processing, vol. C-27, no. 2, pp. 174-177, Feb. 1977.
[4] P. Bernhard and D. Rosenkrantz, "The complexity of routing through an omega network,"Proc 25th Ann. Allerton Conf. Commun., Control and Computing, pp. 1027-1036, Sept. 1987. (Also appeared inIEEE Trans. Parallel Distrib. Syst., vol. 2, pp. 503-507, 1991.
[5] P. Bernhard, "Bounds on the performance of message routing heuristics,"Proc. 3rd Symp. Parallel Distrib. Processing, pp. 856-863, Dec. 1991.
[6] J. Deogun and Z. Fang, "A heuristic algorithm for conflict resolution problem in multistage interconnection networks,"Proc. 1987 Int. Conf. Parallel Processing, 1987, pp. 475-478.
[7] P. Dowd, "Random access protocols for high speed interprocessor communication based on a passive star topology,"J. Lightwave Technol., vol. LT-5, no. 12, pp. 1782-1793, Dec. 1987.
[8] T. Y. Feng, "Data manipulating functions in parallel processors and their implementations,"IEEE Trans. Comput., vol. C-23, no. 3, pp. 309-318, Mar. 1974.
[9] A. Ganz and Z. Koren, "WDM passive star protocols and performance analysis,"Proc. IEEE INFOCOM'91., 1991, pp. 9A.2.1-9A.2.10.
[10] L. R. Goke and G. J. Lipovski, "Banyan networks for partitioning multiprocessor systems," inProc. 1st Annu. Symp. Comput. Architecture, Dec. 1973, pp. 21-28.
[11] Z. Guo, R. Melhem, R. Hall, D. Chiarulli, and S. Levitan, "Array processors with pipelined optical busses,"J. Parallel Distributed Comput., vol. 12, no. 3, pp. 269-282, 1991.
[12] C. Kruskal and M. Snir, "The performance of multistage interconnection networks for multiprocessors,"IEEE Trans. Comput., vol. C-32, no. 12, pp. 1091-1098, Dec. 1983.
[13] D.H. Lawrie, "Access and alignment of data in an array processor,"IEEE Trans. Comput., vol. C-24, pp. 1145-1155, Dec. 1975.
[14] J. Lenfant, "Parallel permutations of data: A Benes network control algorithm for frequently used permutations,"IEEE Trans. Comput., vol. C-27, no. 7, pp. 637-647, July 1978.
[15] G. Lev, N. Pippenger, and L.G. Valiant, "A fast parallel algorithm for routing in permutation networks,"IEEE Trans. Comput., vol. C-30, no. 2, pp. 93-100, 1981.
[16] W. Lin and C.-L. Wu, "Configuring computation tree topologies on a distributed computing system,"Proc. Int. Conf. Parallel Processing, 1983, pp. 114-116.
[17] R. Melhem, D. Chiarulli, and S. Levitan, "Space multiplexing of waveguides in optically interconnected multiprocessor systems,"Comput. J., vol. 32, no. 4, pp. 362-369, 1989.
[18] D. Nassimi and S. Sahni, "Parallel algorithms to set up the Benes permutation network,"IEEE Trans. Comput., vol. C-31, no. 2, pp. 148-154, Feb. 1982.
[19] D. Opferman and N. Taou-Wu, "On a class of rearrangeable switching networks,"Bell Syst. Tech. J., vol. 50, pp. 1579-1600, May 1971.
[20] M. C. Pease, "The indirect binaryn-cube microprocessor array,"IEEE Trans. Comput., vol. C-26, no. 5, pp. 458-473, May 1987.
[21] U. V. Premkumar and J. C. Browne, "Resource allocation in rectangular SW-banyans," inProc. 9th Annu. Symp. Comput. Architecture, Apr. 1982, pp. 326-333.
[22] C. Qiao, "A high speed interconnection paradigm for multiprocessors and its applications to optical interconnection networks," Ph.D. dissertation (in preparation), Department of Comput. Sci., Univ. of Pittsburgh.
[23] C. Qiao and R. Melhem, "Time-division optical communications in multiprocessor arrays,"IEEE Trans. Comput., vol. 42, pp. 577-590, May 1993.
[24] C. Qiao, R. Melhem, D. Chiarulli, and S. Levitan, "Dynamic reconfiguration of optically interconnected networks with time division multiplexing,"J. Parallel Distrib. Computing, to appear.
[25] C. S. Raghavendra and A. Varma, "Fault-tolerant multiprocessors with redundant path interconnection network,"IEEE Trans. Comput., vol. C-35, no. 4, pp. 307-316, Apr. 1986.
[26] H. Ramanujam, "Decomposition of permutation networks,"IEEE Trans. Comput., vol. 22, no. 7, pp. 639-643, July 1973.
[27] D. Sarrazin, H. Jordan, and V. Heuring, "Digital fiber optic delay line memory,"Digital Optical Computing II, SPIE, vol. 1215, pp. 366-375, Jan. 1990.
[28] J. Sauer, "A multi-Gb/s optical interconnect,"SPIE Proc., Digital Computing II, vol. 1215, pp. 198-207, 1990.
[29] A. Shimer and S. Ruhman, "Toward a generalization of two- and three-pass multistage blocking interconnection networks,"Proc. Int. Conf. Parallel Processing, 1980, pp. 337-346.
[30] H. J. Siegel and S. D. Smith, "Study of multistage SIMD interconnection networks," inProc. 5th Annu. Symp. Comput. Architecture, Apr. 1978, pp. 223-229.
[31] A. Somani and S. Choi, "On embedding permutations in hypercubes,"Proc. 1991 Distrib. Memory Computing Conf.1991, pp. 622-629.
[32] H. S. Stone, "Parallel processing with the perfect shuffle,"IEEE Trans. Comput., vol. C-20, no. 2, pp. 153-161, Feb. 1971.
[33] S. Thanawastien and V. Nelson, "Interference analysis of shuffle/exchange networks,"IEEE Trans. Comput., vol. C-30, no. 8, pp. 545-556, Aug. 1981.
[34] R. A. Thompson, "Photonic time-multiplexed permutation switching using the dilated slipped banyan network,"Proc. OSA Topical Meeting on Photon. Switching 1989, 1991, pp. 64-66.
[35] N. Tzeng and S. Wei, "Enhanced hypercubes,"IEEE Trans. Comput., vol. 40, pp. 284-294, Mar. 1991.
[36] C.-L Wu and T. Y. Feng, "On a class of multistage interconnection networks,"IEEE Trans. Comput., vol. C-29, no. 8, pp. 694-702, Aug. 1980.
[37] C.-L Wu and T. Y. Feng, "The universality of the shuffle-exchange network,"IEEE Trans. Comput., vol. C-30, no. 5, pp. 324-332, May 1981.
[38] A. Youssef, "Off-line permutation scheduling on circuit-switched fixed routing networks,"Proc. 4th Symp. Frontiers of Massively Parallel Computation, 1992, pp. 389-396.

Index Terms:
Index Termsmultiprocessor interconnection networks; time division multiplexing; time division multiplexed; MIN's; multiprocessor communications; multistage interconnection networks; mappings; shift registers; round-robin; TDM-MIN's; N time slots; rings; meshes; cube-connected-cycles; binary trees; n-dimensional hypercubes; partitioning; NP-hard; optical interconnects; embedding; Markov analysis; reconfiguration; partition of connection requests
C. Qiao, R. Melhem, "Reconfiguration with Time Division Multiplexed MIN's for Multiprocessor Communications," IEEE Transactions on Parallel and Distributed Systems, vol. 5, no. 4, pp. 337-352, April 1994, doi:10.1109/71.273043
Usage of this product signifies your acceptance of the Terms of Use.