A stochastic approach to estimating earliest start times of nodes for scheduling DAGs on heterogeneous distributed computing systems
Previously, DAG scheduling schemes used the mean (average) of computation or communication time in dealing with temporal heterogeneity. However, it is not optimal to consider only the means of computation and communication times in DAG scheduling on a temporally (and spatially) heterogeneous distributed computing system. In this paper, it is proposed that the second order moments of computation and communication times, such as the standard deviations, be taken into account in addition to their means, in scheduling “stochastic” DAGs. An effective scheduling approach which accurately estimates the earliest start time of each node and derives a schedule leading to a shorter average parallel execution time has been developed. Through an extensive computer simulation, it has been shown that a significant improvement (reduction) in the average parallel execution times of stochastic DAGs can be achieved by the proposed approach.
KeywordsAverage parallel execution time Competing situation Scheduling Spatial heterogeneity Stochastic DAG Temporal heterogeneity
Unable to display preview. Download preview PDF.
- 1.Grajcar, M.: Genetic list scheduling algorithm for scheduling and allocation on a loosely coupled heterogeneous multiprocessor system. In: Proceedings of the 36th Design Automation Conference, pp. 280–285 (1999) Google Scholar
- 4.Park, G.-L., Shirazi, B., Marquis, J., Choo, H.: Decisive path scheduling: a new list scheduling method. In: Proceedings of the 1997 International Conference on Parallel Processing, Aug. 1997, pp. 472–480 Google Scholar
- 5.Chan, W.-Y., Li, C.-K.: Heterogeneous dominant sequence cluster (HDSC): a low complexity heterogeneous scheduling algorithm. In: IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, vol. 2, Aug. 1997, pp. 956–959 Google Scholar
- 6.Liu, Z.: Scheduling of random task graphs on parallel processors. In: Proceedings of the Third International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS ’95), Jan. 1995, pp. 143–147 Google Scholar
- 9.Kwok, Y.-K.: Parallel program execution on a heterogeneous PC cluster using task duplication. In: Proceedings of the 9th Heterogeneous Computing Workshop, 2000(HCW 2000), May 2000, pp. 364–374 Google Scholar
- 10.Liu, Z., Fang, B., Zhang, Y., Tang, J.: Scheduling algorithms for a fork DAG in a NOWs. In: Proceedings of the Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, vol. 2, May 2000, pp. 959–960 Google Scholar
- 13.Almeida, V.A.F., Vasconcelos, I.M.M., Árabe, J.N.C., Menascé, D.A.: Using random task graphs to investigate the potential benefits of heterogeneity in parallel systems. In: Proceedings of the 1992 ACM/IEEE Conference on Supercomputing, Nov. 1992, pp. 683–691 Google Scholar
- 15.Huang, J., Lee, S.-Y.: Effects of spatial and temporal heterogeneity on performance of a target task in heterogeneous computing environments. In: 15th ISCA International Conference on Parallel and Distributed Systems, Sept. 2002, pp. 301–306 Google Scholar
- 16.Yang, L., Schopf, J.M., Foster, I.: Conservative scheduling: using predicted variance to improve scheduling decisions in dynamic environments. In: SuperComputing’03, November 2003, pp. 31–45 Google Scholar
- 17.Schopf, J., Berman, F.: Stochastic scheduling. CS Dept. Technical Report CS-99-03, University of California, San Diego Google Scholar
- 19.Dogan, A., Ozguner, F.: Stochastic scheduling of a meta-task in heterogeneous distributed computing. In: International Conference on Parallel Processing Workshops, pp. 369–374 (2001) Google Scholar
- 23.Boeres, C., Chochia, G., Thanisch, P.: On the scope of applicability of the ETF algorithm. In: Workshop on Parallel Algorithms for Irregularly Structured Problems, pp. 159–164 (1995) Google Scholar