Scheduling Parallel Programs Based on Architecture–Supported Regions
Modern multicore processor technology can fairly easily deliver special accelerator processors dedicated to fast optimised execution of critical computational functions. Multi CMP (Chip Multi-Processor) systems can be composed as a set of dedicated and general purpose computational modules interconnected by a global data exchange network. The paper proposes special program scheduling algorithms for such systems. Dedicated CMP modules assumed in the paper are based on a new data communication model called communication on the fly. It enables strong reduction of inter–process and inter–core communication overheads for intensively shared data.
KeywordsSchedule Algorithm Program Graph Support Region List Schedule Architectural Node
Unable to display preview. Download preview PDF.
- 1.Nurmi, J., Tenhunen, H., Isoaho, J., Jantsch, A. (eds.): Interconnect–Centric Design for Advanced SOC and NOC. Springer (2004)Google Scholar
- 2.Kundu, S., Peh, L.S.: On–Chip Interconnects for Multicores. IEEE Micro, 3–5 (September-October 2007)Google Scholar
- 3.Owens, J.D., et al.: Research Challenges for On–Chip Interconnection Networks. IEEE Micro, 96–108 (September-October 2007)Google Scholar
- 5.Tudruj, M., Maśko, Ł.: Dynamic SMP Clusters with Communication on the Fly in NoC Technology for Very Fine Grain Computations. In: 3rd Int. Symp. on Parallel and Distributed Computing, ISPDC 2004, Cork, pp. 97–104 (July 2004)Google Scholar
- 6.Tudruj, M., Maśko, Ł.: Towards Massively Parallel Computations Based on Dynamic SMP Clusters wih Communication on the Fly. In: Proceedings of the 4th International Symposium on Parallel and Distributed Computing, ISPDC 2005, Lille, France, July 4-6, pp. 155–162. IEEE CS Press (2005)Google Scholar
- 7.Tudruj, M., Maśko, Ł.: Data Transfers on the Fly for Hierarchical Systems of Chip Multi–Processors. In: Wyrzykowski, R., et al. (eds.) PPAM 2011, Part I. LNCS, vol. 7203, pp. 50–59. Springer, Heidelberg (2012)Google Scholar
- 9.Maśko, Ł., Tudruj, M.: Task Scheduling for SoC–Based Dynamic SMP Clusters with Communication on the Fly. In: 7th Int. Symp. on Parallel and Distributed Computing, ISPDC 2008, pp. 99–106 (2008)Google Scholar
- 10.Hwang, J.-J., Chow, Y.-C., Anger, F.D., Lee, C.-Y.: Scheduling precedence graphs in systems with interprocessor communication times. SIAM Journal on Computing 18(2) (1989)Google Scholar