This Article 
 Bibliographic References 
 Add to: 
The Crossed Cube Architecture for Parallel Computation
September 1992 (vol. 3 no. 5)
pp. 513-524
The construction of a crossed cube which has many of the properties of the hypercube, but has diameter only about half as large, is discussed. This network is self-routing, in the sense that there is a simple distributed routing algorithm which guarantees optimal paths between any pair of vertices. This fact, together with other properties such as regularity, symmetry, high connectivity, and a simple recursive structure, suggests that the crossed cube may be an attractive alternative to the ordinary hypercube for massively parallel architectures, SIMD algorithms, which utilize the architecture are developed, and it is shown that the CQ/sub n/ architecture can profitably emulate the ordinary hypercube. It is also shown that addition of simple switches can improve the capabilities of the system significantly. For instance, the dynamic reconfiguration capability allows hypercube algorithms to be executed on the proposed architecture. The use of these switches also improves the embedding properties of the system.

[1] L. N. Bhuyan and D. P. Agrawal, "Generalized hypercube and hyperbus structures for a computer network,"IEEE Trans. Comput., vol. C-33, no. 4, pp. 323-333, Apr. 1984.
[2] J.W. Dolter, P. Ramanathan, and K.G. Shin, "A Microprogrammable VLSI Routing Controller for HARTS,"Proc. Int'l Conf. Computer Design: VLSI in Computers, Computer Society Press, Order No. 1971, Oct. 1989, pp. 160-163.
[3] K. Efe, "Programming the twisted cube architectures," inProc. 9th Int. Conf. DCS, June 1989, pp. 254-262.
[4] K. Efe, "Multi-operand addition with conditional sum logic," inProc. 5th IEEE Symp. Comput. Arithmetic, May 1981, pp. 251-155.
[5] K. Efe, "The crossed-cube architecture for parallel computation," Tech. Rep. TR 90-8-7, Center for Advanced Computer Studies, Univ. Southwestern Louisiana.
[6] A. Esfahanian, L. Ni, and B. Sagan, "On enhancing hypercube multiprocessors," inProc. 1988 Int. Conf. Parallel Processing, 1988, pp. 86-89.
[7] K. Hwang and D. Kim, "Generalization of orthogonal multiprocessor for massively parallel computation," inProc. 2nd Frontiers MPC, Oct. 1988, pp. 391-398.
[8] F. Harary,Graph Theory. Reading, MA: Addison-Wesley, 1972.
[9] M. Imase and M. Itoh, "Design to minimize diameter on building block network,"IEEE Trans. Comput., C-30, no. 6, pp. 439-442, 1981.
[10] F. P. Preparata and J. Vuillemin, "The cube-connected cycle: A versatile network for parallel computation,"Commun. ACM, vol. 24, pp. 300-309, May 1981.
[11] A. S. Youssef and B. Narahari, "Banyan-hypercube networks,"IEEE Trans. Parallel Distributed Syst., vol. 1, no. 2, pp. 160-169, Apr. 1990.

Index Terms:
Index Termsself routing network; crossed cube architecture; parallel computation; distributed routingalgorithm; regularity; symmetry; high connectivity; recursive structure; massively parallel architectures; SIMD algorithms; CQ/sub n/ architecture; switches; dynamicreconfiguration; hypercube algorithms; embedding properties; multiprocessorinterconnection networks; parallel algorithms; parallel architectures
K. Efe, "The Crossed Cube Architecture for Parallel Computation," IEEE Transactions on Parallel and Distributed Systems, vol. 3, no. 5, pp. 513-524, Sept. 1992, doi:10.1109/71.159036
Usage of this product signifies your acceptance of the Terms of Use.