Abstract
The performance of parallel computer heavily depends on the topology of the interconnection network. Two-dimensional mesh is a well-known topology for processor arrays. However, its large diameter increases execution time when the parallel algorithm requires communication between arbitrary pair of nodes. Wraparound connections between end nodes reduces its diameter, however, increases the complexity in the design of parallel algorithms. In this paper, we have proposed an intermediate approach, where additional links are used to reduce the diameter without increasing the design complexity. These additional optical links provides high-speed communication between nodes that are separated by half the number of nodes in each dimension. Also, we present efficient parallel algorithms for some elementary problems on the proposed system.
References
Alverson, R., et al.: The Tera Computer System. In: International Conference on Supercomputing, Assoc. of Comput. Machinery (1990) 1–6
Scott, S., Thorson, G.: Optimized routing in the Cray T3D. In: First International workshop on Parallel Computer Routing and Communication, LNCS, Vol. 853 (1994) 281–294
Gara, N.A., et al.: Overview of the Blue Gene/L system architecture, IBM J. Res. & Dev., Vol. 49, No. 213 (2005) 195–212
Das, D., Sinha, B.P.: A new network topologies with multiple meshes. IEEE Transaction on Computers, Vol. 44, No. 5 (1999) 536–551
Chen, W.M., Chen, G.H., Hsu, D.F.: Combinatorial properties of mesh of trees,. In: International Symposium on Parallel, Architectures, Algorithms and Networks (2000) 134–139
Jana, P.K.: Multi-mesh of trees with its parallel algorithms. Journal of System Architecture, Vol. 50 (2004) 193–206
Marsden, G.C., Marchand, P.J., Harvey, P., Esener, S.C.: Optical Transpose Interconnection System Architecture, Optical Letters, Vol. 18, No. 3 (1993) 1083–1085
Wang, C.F., Sahani, S.: Basic Operation on OTIS-Mesh Optoelectronics Computer. IEEE Transaction on Parallel and Distributed Systems, Vol. 19, No. 12 (1998) 1226–1233
Sinha, B.P., Banyopadhyay, S.: OMULT: An Optical Interconnection System for Parallel Computing. LNCS, Vol. 3149 (2004) 302–312
Ladner, R.E., Fischer, M.J.: Parallel Prefix Computation, Journal of the Association of Computing Machinery, Vol. 27, No. 4 (1980) 831–838
Egecioglu, O., Srinivasan, A.: Optimal Parallel Prefix on Mesh Architecture, Parallel Algorithms Appl., Vol. 1 (1993) 191–209
Jha, S.K.: An Improved parallel Prefix Computation on 2-D Mesh Network, Procedia Technology, Vol. 10 (2013) 919–926
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Amritanjali (2018). A New Two-Dimensional Mesh Topology with Optical Interlinks. In: Sa, P., Sahoo, M., Murugappan, M., Wu, Y., Majhi, B. (eds) Progress in Intelligent Computing Techniques: Theory, Practice, and Applications. Advances in Intelligent Systems and Computing, vol 719. Springer, Singapore. https://doi.org/10.1007/978-981-10-3376-6_47
Download citation
DOI: https://doi.org/10.1007/978-981-10-3376-6_47
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3375-9
Online ISBN: 978-981-10-3376-6
eBook Packages: EngineeringEngineering (R0)