Novel Algorithms and Techniques In Telecommunications, Automation and Industrial Electronics pp 432-437 | Cite as
Design and analysis of optical interconnection networks for a dataflow parallel computer
This work shows the design, simulation, and analysis of two optical interconnection networks for a Dataflow parallel computer architecture. To verify the optical interconnection network performance on the Dataflow architecture, we have analyzed the load balancing among the processors during the parallel programs executions. The load balancing is a very important parameter because it is directly associated to the dataflow parallelism degree. This article proves that optical interconnection networks designed with simple optical devices can provide efficiently the dataflow requirements of a high performance communication system.
Keywords
Load Balance Optical Network Interconnection Network Queue Size Tuning TimePreview
Unable to display preview. Download preview PDF.
References
- [1]S. Neuendorffer, E. Lee: Hierarchical reconfiguration of dataflow models, Proceedings of the Second ACM and IEEE International Conference on Formal Methods and Models for Co-Design, June 2004, pp.179- 188Google Scholar
- [2]Jackob Carlstrom, T. Bodén: Synchronous Dataflow Architecture for Network Processors, IEEE Micro, vol. 24(5), (September/ October 2004), pp. 10-18,Google Scholar
- [3]Wesley M. Johnston, J. R. P. Hanna, R. J. Millar: Advances in Dataflow Programming languages. ACM Computing Surveys, vol. 36(1),: March 2004, pp 1-34Google Scholar
- [4]Dolev Dotan, Ron Y. Pinter: Hyperflow: an Integrated Visual Query and dataflow Language for End-User Information Analysis, Proceedings of the 2005 IEEE Symposium on Visual Languages and Human-Centric Computing , 2005Google Scholar
- [5]Jackob Carlstrom et al: A 40Gb/ s Network Processor with PISC Dataflow Architecture, IEEE International Solid-State Circuits Conference, 2004Google Scholar
- [6]Yijun Liu, Steve Furber: A Low Power Embedded Dataflow Coprocessor, Proceedings of the IEEE Computer Society Annual Symposium on VLSI , 2005Google Scholar
- [7]Toshitsugu Yuba, et al.: Dataflow Computer Development in Japan, ACM SIGARCH Computer Architecture News - Proceedings of the 4th international conference on Supercomputing, June 1990, pp. 140-147Google Scholar
- [8]P. P. Mitra; J. B. Stark: Nonlinear Limits to the Information Capacity of Optical Fibre Communications, Nature, vol. 411, June 2001, pp.1027-1030Google Scholar
- [9]J. R. Gurd, C. C. Kirkham; I. Watson: The Manchester prototype dataflow computer; Communications of the ACM, vol. 28(1), 1985, pp. 34-52CrossRefGoogle Scholar
- [10]M. A. Cavenaghi; G. Travieso: A.G. Neto, A simple mechanism to deal with sequential code in dataflow architectures, IEEE Proceedings - 5th International Conference on High Performance Computing, 1988, pp. 188-193Google Scholar
- [11]M. A. Cavenaghi, J. A. Martini, A. G. Neto: Proposal to solve workload problems in the simulator of the Wolf architecture. IEEE Proceedings of the Fourth International Conference/ Exhibition on High Performance Computing in the Asia-Pacific Region, may 2000, pp. 315 - 318Google Scholar
- [12]James Hicks; D . Chiou; Boon Seong Ang; Arving: Performance Studies of Id on the Monsoon Dataflow System . Journal of Parallel and Distributed Computing, vol. 18, 1993, pp. 273-300CrossRefGoogle Scholar
- [13]E. L. Johnson, K. M. Sivalingam, M. Mishra: Scheduling in Optical WDM Networks Using Hidden Markov Chain Based Trffic Predication, Photonic Network Communications, vol. 3(3), 2001, pp. 269-283CrossRefGoogle Scholar
- [14]B. Mukherjee: WDM-based local lightwave networks. I. Single-hop systems, IEEE Network, vol. 6(3). May 1992, pp.12- 27Google Scholar
- [15]B. Mukherjee: WDM-based local lightwave networks. II. Multihop systems, IEEE Network , vol. 6(4), July 1992, pp. 20- 32. Google Scholar