ABSTRACT
Over the past few years, owing to technological breakthroughs in building cheap, reliable and powerful microprocessors and relatively cheap LSI memories, interconnection networks have become the major hardware cost in design and implementation of the multiprocessor systems. This situation occurs from the fact that many more functions may be expected from the interconnection network (switch) than the establishment of simple bus connections. Even if only the communication links were considered, the complexity of some networks make their implementation prohibitive. An example of such a network is a crossbar whose complexity is 0(n**2) where n represents a number of resources which may be connected to another set of n resources. This switch provides a separate connection between each pair of resources (Figure 1). It has been empirically shown that implementation of a crossbar switch for a large n is very difficult and with a state-of-the-art technology practically infeasible for n>50.
- Batcher, K. E., "The flip network in STARAN," Proc. of the 1976 International Conference on Parallel Processing, August 1976, pp. 65--71.Google Scholar
- Feng, T., "Data manipulating functions in parallel processors and their implementations," IEEE Trans. on Comput., Vol. C-23, March 1974, pp. 309--318. Google ScholarDigital Library
- Goke, L. R., "Connecting networks for partitioning polymorphic systems," Ph.D. Dissertation, Dept. E.E., U. of Florida, 1976.Google Scholar
- Goke, L. R. and Lipovski, G. J., "Banyan networks for partitioning multiprocessor systems," Proc. First Annual Symposiums on Computer Architecture, Dec. 1973, pp. 21--28. Google ScholarDigital Library
- Lawrie, D., "Access and alignment of data in an array processor," IEEETC, Vol. C-24, No. 12, Dec. 1975. Google ScholarDigital Library
- Lawrie, D., "Memory-processor connection networks," University of Illinois, Report UTUCDCS-R-73-557, Feb. 1973.Google Scholar
- Premkumar, U. V., Malek, M., and Lipovski, G. J., "A theoretical basis for switching structures," submitted to the 7th International Symposium on Computer Architecture, 1980.Google Scholar
- Siegel, H. J., Mueller, P. T., Jr., and Smalley, H. E., Jr., "Control of a partitionable multimicroprocessor system," Proc. 1978 ICPP, 1978, pp. 9--17.Google Scholar
- Siegel, H. J., "Analysis techniques for SIMD machine interconnection networks and the effects of processor address masks," IEEE Trans. on Comput., Vol. C-26, Feb. 1977, pp. 153--161.Google Scholar
- Siegel, H. J., McMillen, R. J., and Mueller, P. T., Jr., "A survey of interconnection methods for reconfigurable parallel processing systems," Proc. of NCC, 1979, pp. 529--542.Google Scholar
- Stone, H., "Parallel processing with the perfect shuffle," IEEETC, Vol. C-20, No. 2, Feb. 1971, pp. 153--161. Google ScholarDigital Library
- Thompson, C. D., "Generalized connection networks for parallel processor intercommunication," IEEE Trans. on Comput., Vol. C-27, Dec. 1978. Google ScholarDigital Library
- Wu, C. and Feng, T., "Routing techniques for a class of multistage interconnection networks," Proc. of the 1978 International Conference on Parallel Processing, August 1979, pp. 197--205.Google Scholar
- Pease, M. C., "The indirect binary n-cube microprocessor array," IEEE Trans. on Comput., Vol. C-26, May 1977, pp. 458--473. Google ScholarDigital Library
- Lipovski, G. J. and Tripathi, A., "A reconfigurable varistructure array processor," Proc. 1977 ICPP, 1967, pp. 165--174.Google Scholar
- Radoy, C. H. and Lipovski, G. J., "Switched multiple instruction, multiple data stream processing," Proc. of Second Annual Symposium on Computer Architecture, 1974, pp. 183--187. Google ScholarDigital Library
- Lipovski, G. J., "An organization for optical linkages between integrated circuits," Proc. of NCC, 1977, pp. 227--236. Google ScholarDigital Library
- Premkumar, U. V., Kapur, R., and Lipovski, G. J., "Interprocessor communication in TRAC," Proc. of the first International Conference on Distributed Computing Systems. 1979, pp. 51--62.Google Scholar
- Seinowski, M. C. et al., "An overview of the Texas Reconfigurable Array Processor," submitted to Proc. of NCC, 1980. Google ScholarDigital Library
- Dujari, G. and Horne, P., "Node circuit for banyan switch of the Texas Reconfigurable Array Computer," Technical Report TRAC-9, University of Texas at Austin, January 1979.Google Scholar
Recommendations
The cyclic banyan network: a fault tolerant multistage interconnection network with the fully-adaptive self-routing
SPDP '95: Proceedings of the 7th IEEE Symposium on Parallel and Distributeed ProcessingIn this paper, we introduce a fault tolerant fully-adaptive self-routing scheme for a class of augmented banyan network. It can provide more multiple paths than the related previous networks between an input/output pair of a network by adding extra ...
The Banyan-Hypercube Networks
The authors introduce a family of networks that are a synthesis of banyans and hypercubes and are called the banyan-hypercubes (BH). They combine the advantageous features of banyans and hypercubes and thus have better communication capabilities.The ...
Design Exploration of Optical Interconnection Networks for Chip Multiprocessors
HOTI '08: Proceedings of the 2008 16th IEEE Symposium on High Performance InterconnectsThe Network-on-Chip (NoC) paradigm has emerged as a promising solution for providing connectivity among the increasing number of cores that get integrated into both systems-on chip(SoC) and chip multiprocessors (CMP). In future high performance CMPs, ...
Comments