This Article 
 Bibliographic References 
 Add to: 
Hypercube Algorithms on Mesh Connected Multicomputers
December 2002 (vol. 13 no. 12)
pp. 1247-1260

Abstract—A new methodology named CALMANT (CC-cube Algorithms on Meshes and Tori) for mapping a kind of algorithms that we call CC-cube algorithm onto multicomputers with hypercube, mesh, or torus interconnection topology is proposed. This methodology is suitable when the initial problem can be expressed as a set of processes that communicate through a hypercube topology (a CC-cube algorithm). There are many important algorithms that fit into the CC-cube type. CALMANT is based on three different techniques: a) the standard embedding to assign the processes of the algorithm to the nodes of the mesh multicomputer; b) the communication pipelining technique to increase the level of communication parallelism inherent in the CC-cube algorithms; and c) optimal message-scheduling algorithms proposed in this work in order to avoid conflicts and minimizing in this way the communication time. Although CALMANT is proposed for multicomputers with different interconnection network topologies, this paper only focuses on the particular case of meshes.

[1] S.H. Bokhari and H. Berryman, “Complete Exchange on a Circuit Switched Mesh,” Proc. IEEE Scalable High Performance Computing Conf., pp. 300-306, 1992.
[2] L.M. Díaz de Cerio, A. González, and M. Valero-García, “Communication Pipelining in Hypercubes,” Parallel Processing Letters, vol. 6, no. 4, pp. 507-523, 1996.
[3] L.M. Díaz de Cerio, M. Valero-García, and A. González, “A Method For Exploiting Communication/Computation Overlap in Hypercubes,” Parallel Computing, vol. 24, no. 2, pp. 221-245, 1998.
[4] A. González and M. Valero-García, “The Xor Embedding: An Embedding of Hypercubes onto Rings and Toruses,” Proc. Int'l Conf. Applications Specific Array Processors, pp. 15-28, 1993.
[5] A. González, M. Valero-García, and L.M. Díaz de Cerio, “Executing Algorithms with Hypercube Topology on Torus Multicomputers,” IEEE Trans. Parallel and Distributed Systems, vol. 6, no. 8, pp. 803-814, 1995.
[6] S.L. Johnsson and R.L. Krawitz, “Cooley-Tukey FFT on the Connection Machine,” Parallel Computing, no. 18, pp. 1201-1221, 1992.
[7] S.L. Johnsson and C.T. Ho, “Optimal All-to-All Personalized Communication with Minimum Span on Boolean Cubes,” Proc. Sixth IEEE Distributed Memory Computing Conf., pp. 299-304, 1991.
[8] T.H. Lai and A.P. Sprague, “Placement of the Processors of a Hypercube,” IEEE Trans. Computers, vol. 40, no 6, pp. 714-722, June 1991.
[9] M. Lam, “Software Pipelining: An Effective Schedulling Technique for VLIW Machines,” Proc. Conf. Programming Language Design and Implementation, pp. 318-328, 1988.
[10] S. Matic, “Emulation of Hypercube Architecture on Nearest-Neighbor Mesh-Connected Processing Elements,” IEEE Trans. Computers, vol. 39, no. 5, pp. 698-700, May 1990.
[11] D.S. Scott, “Efficient All-to-All Communication Patterns in Hypercube and Mesh Topologies,” Proc. Sixth IEEE Distributed Memory Computing Conf., pp. 398-403, 1991.
[12] N.S. Sundar, D.N. Jayasimha, D.K. Panda, and P. Sadayappan, “Complete Exchange in 2D Meshes,” Proc. IEEE Scalable High Performance Computing Conf., pp. 406-413, 1994.
[13] N.S. Sundar, D.N. Jayasimha, D.K. Panda, and P. Sadayappan, “Hybrid Algorithms for Complete Exchange in 2D Meshes,” Proc. ACM Int'l Conf. Supercomputing, pp. 181-188, 1996.
[14] S. Takkella and S. Seidel, “Complete Exchange and Broadcast Algorithms for Meshes,” Proc. IEEE Scalable High Performance Computing Conf., pp. 422-428, 1994.

Index Terms:
Mapping algorithms, hypercube algorithms, mesh interconnected multicomputers, standard embedding, communication pipelining, message-scheduling algorithms, complete exchange.
Luis Díaz de Cerio, Miguel Valero-García, Antonio González, "Hypercube Algorithms on Mesh Connected Multicomputers," IEEE Transactions on Parallel and Distributed Systems, vol. 13, no. 12, pp. 1247-1260, Dec. 2002, doi:10.1109/TPDS.2002.1158263
Usage of this product signifies your acceptance of the Terms of Use.