Publication 1996 Issue No. 12 - December Abstract - Mesh-Connected Trees: A Bridge Between Grids and Meshes of Trees
Mesh-Connected Trees: A Bridge Between Grids and Meshes of Trees
December 1996 (vol. 7 no. 12)
pp. 1281-1291
 ASCII Text x Kemal Efe, Antonio Fernández, "Mesh-Connected Trees: A Bridge Between Grids and Meshes of Trees," IEEE Transactions on Parallel and Distributed Systems, vol. 7, no. 12, pp. 1281-1291, December, 1996.
 BibTex x @article{ 10.1109/71.553283,author = {Kemal Efe and Antonio Fernández},title = {Mesh-Connected Trees: A Bridge Between Grids and Meshes of Trees},journal ={IEEE Transactions on Parallel and Distributed Systems},volume = {7},number = {12},issn = {1045-9219},year = {1996},pages = {1281-1291},doi = {http://doi.ieeecomputersociety.org/10.1109/71.553283},publisher = {IEEE Computer Society},address = {Los Alamitos, CA, USA},}
 RefWorks Procite/RefMan/Endnote x TY - JOURJO - IEEE Transactions on Parallel and Distributed SystemsTI - Mesh-Connected Trees: A Bridge Between Grids and Meshes of TreesIS - 12SN - 1045-9219SP1281EP1291EPD - 1281-1291A1 - Kemal Efe, A1 - Antonio Fernández, PY - 1996KW - Parallel architecturesKW - interconnection networksKW - parallel algorithmsKW - product networksKW - graph embeddingKW - binary treeKW - gridsKW - hypercubesKW - mesh of trees.VL - 7JA - IEEE Transactions on Parallel and Distributed SystemsER -

Abstract—The grid and the mesh of trees (or MOT) are among the best-known parallel architectures in the literature. Both of them enjoy efficient VLSI layouts, simplicity of topology, and a large number of parallel algorithms that can efficiently execute on them. One drawback of these architectures is that algorithms that perform best on one of them do not perform very well on the other. Thus there is a gap between the algorithmic capabilities of these two architectures.

We propose a new class of parallel architectures, called the mesh-connected trees (or MCT) that can execute grid algorithms as efficiently as the grid, and MOT algorithms as efficiently as the MOT, up to a constant amount of slowdown. In particular, the MCT topology contains the MOT as a subgraph and emulates the grid via embedding with dilation 3 and congestion two. This significant amount of computational versatility offered by the MCT comes at no additional VLSI area cost over these earlier networks. Many topological, routing, and embedding properties analyzed here suggests that the MCT architecture is also a serious competitor for the hypercube. In fact, while the MCT is much simpler and cheaper than the hypercube, for all the algorithms we developed, the running time complexity on the MCT matches those of well known hypercube algorithms.

We also present an interesting variant of the MCT architecture that admits both the MOT and the torus as its subgraphs. While most of the discussion in this paper is focused on the MCT architecture itself, these analyses can be easily extended to the variant of the MCT presented here.

[1] M. Baumslag and F. Annexstein, "A Unified Framework for Off-Line Permutation Routing in Parallel Networks," Math. Systems Theory, vol. 24, no. 4, pp. 233-251, 1991.
[2] S.N. Bhatt, F.R.K. Chung, J.-W. Hong, F.T. Leighton, B. Obrenic, A.L. Rosenberg, and E.J. Schwabe, “Optimal Emulations by Butterfly-Like Networks,” J. ACM, vol. 43, pp. 293-330, 1996.
[3] S.N. Bhatt and I.C.F. Ipsen, "How to Embed Trees in Hypercubes," Technical Report RR-443, Department of Computer Science, Yale Univ., New Haven, Conn., 1985.
[4] K. Efe,“Embedding mesh of trees in the hypercube,” J. Parallel and Distributed Computing, vol. 11, no. 3, pp. 222-230, Mar. 1991.
[5] K. Efe and A. Fernández, "Products of Networks with Logarithmic Diameter and Fixed Degree," IEEE Trans. Parallel and Distributed Systems, vol. 6, pp. 963-975, Sept. 1995.
[6] K. Efe and A. Fernández, "Mesh-connected Trees: A Bridge Between Grids and Meshes of Trees," Technical Report 94-8-7, Center for Advanced Computer Studies, University of Southwestern Louisiana (also available from the first author).
[7] A. Fernández, "Homogeneous Product Networks for Processor Interconnection," PhD Thesis, Center for Advanced Computer Studies, Univ. of Southwestern Louisiana, Dec. 1994.
[8] A. Fernández, N.A. Eleser, and K. Efe, "Generalized Algorithm for Parallel Sorting on Product Networks," Proc. 1995 Int'l Conf. Parallel Processing, vol. III, pp. 155 - 159, Aug.14-18 1995.
[9] T. El-Ghazawi and A. Youssef, "A General Framework for Developing Adaptive Fault-Tolerant Routing Algorithms," IEEE Trans. Reliability, vol. 42, pp. 250-258, June 1993.
[10] I. Havel and P. Liebl, "Embedding the Polytomic Tree into the N-cube," $\mathord{\buildrel{\lower3pt\hbox{$\scriptscriptstyle\smile$}}\over C} aspios\ pro \ P\mathord{\buildrel{\lower3pt\hbox{$\scriptscriptstyle\smile$}}\over e} stov{\buildrel\, '\over a}n\ i\ Matematiky$, vol. 98, pp. 307-314, 1973.
[11] R. Heckmann, R. Klasing, B. Monien, and W. Unger, "Optimal Embeddings of Complete Binary trees into Lines and Grids," Proc. 17th Int'l Workshop, WG'91, Graph-Theoretic Concepts in Computer Science, G. Schmidt and R. Berghammer, eds., vol. 570of Lecture Notes in Computer Science, pp. 25-35.Fischbachau, Germany: Springer Verlag, June 1991.
[12] R.E. Ladner and M.J. Fischer, "Parallel Prefix Computation," J. ACM, vol. 27, no. 4, pp. 831-838, Oct. 1980.
[13] F.T. Leighton, Complexity Issues in VLSI.Cambridge, Mass.: MIT Press, 1983.
[14] F.T. Leighton,Introduction to Parallel Algorithms and Architectures: Arrays, Trees, Hypercubes.San Mateo, Calif.: Morgan Kaufmann, 1992.
[15] C.E. Leiserson, "Area-Efficient graph Layout (for VLSI)," Proc. 21st Annual Symp. Foundations of Computer Science, pp. 270-281, Oct. 1980.
[16] Fault-Tolerant Computing: Theory and Techniques, D.K. Pradhan ed., vol. 2, c. 7. Englewood Cliffs, N.J.: Prentice Hall, 1986.
[17] A.L. Rosenberg,“Product-shuffle networks: Toward reconciling shuffles and butterflies,” Discrete Applied Mathematics, vol. 37/38, pp. 465-488, July 1992.
[18] C.D. Thompson,“A complexity theory for VLSI,” PhD thesis, Carnegie-Mellon Univ., Aug. 1980.
[19] J.D. Ullman, Computational Aspects of VLSI.Rockville, Md.: Computer Science Press, 1984.
[20] A. Youssef, "Product Networks: A Unified Theory of Fixed Interconnection Networks," Technical Report GWU-IIST-90-38, Inst. Information Science and Technology, Dept. Electrical Engineering and Computer Science, School of Eng. and Applied Science, George Washington Univ., Washington, D.C. 20052, Dec. 1990.

Index Terms:
Parallel architectures, interconnection networks, parallel algorithms, product networks, graph embedding, binary tree, grids, hypercubes, mesh of trees.
Citation:
Kemal Efe, Antonio Fernández, "Mesh-Connected Trees: A Bridge Between Grids and Meshes of Trees," IEEE Transactions on Parallel and Distributed Systems, vol. 7, no. 12, pp. 1281-1291, Dec. 1996, doi:10.1109/71.553283