A Hybrid Heuristic-Genetic Algorithm for Task Scheduling in Heterogeneous Multi-core System
Task scheduling on heterogeneous multi-core systems is NP-complete problem. This paper proposes a novel hybrid static scheduling algorithm named Hybrid Successor Concerned Heuristic-Genetic Scheduling (HSCGS) algorithm. The algorithm is a combination of heuristic and genetic scheduling algorithm. In the first phase we propose a heuristic algorithm named Successor Concerned List Heuristic Scheduling (SCLS) to generate a high quality scheduling result. SCLS algorithm takes the impact of current task’s scheduling to its successor into account. The second phase implements an Improved Genetic Algorithm (IGA) for scheduling, to optimize the scheduling results of SCLS iteratively. The comparison experiments are based on both random generated applications and some real world applications. The performance of HSCGS is compared with some famous task scheduling algorithms, such as HEFT and DLS. The results show that HSCGS is the best of them, and the advantages go up with the increase of the heterogeneous factor of inter-core link bandwidth.
KeywordsHeterogeneous multi-core Task scheduling Heuristic algorithm Genetic algorithm Hybrid Scheduing Directed acyclic graph
Unable to display preview. Download preview PDF.
- 1.Kumar, R., Tullsen, D., Jouppi, N., Ranganathan, P.: Heterogeneous Chip Multiprocessors. IEEE Computer, 32–38 (November 2005)Google Scholar
- 6.Eswari, R., Nickolas, S.: Path-based Heuristic Task Scheduling Algorithm for Heterogeneous Distributed Computing Systems. In: 2010 International Conference on Advances in Recent Technologies in Communication and Computing (2010)Google Scholar
- 12.Ilavarasan, E., Thambidurai, P., Mahilmannan, R.: Performance effective task scheduling algorithm for heterogeneous computing system. In: Proc. 4th International Symposium on Parallel and Distributed Computing, France, pp. 28–38 (2005)Google Scholar
- 13.Iverson, M., Ozguner, F., Follen, G.: Parallelizing existing applications in a distributed heterogeneous environment. In: Proc. 4th Heterogeneous Computing Workshop, Santa Barbara, CA, pp. 93–100 (1995)Google Scholar
- 14.Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.-A.: STARPU: a unified platform for task scheduling on heterogeneous multicore architectures. University of Bordeaux – LaBRI – INRIA Bordeaux Sud-OuesGoogle Scholar
- 15.Moghaddam, M.E., Bonyadi, M.R.: An Immune-based Genetic Algorithm with Reduced Search Space Coding for Multiprocessor Task Scheduling Problem. Int. J. Parallel Prog., doi:10.1007/s10766-011-0179-0Google Scholar
- 17.Chung, Y.C., Ranka, S.: Application and performance analysis of a compile-time optimization approach for list scheduling algorithms on distributed-memory multiprocessors. In: Proc. Supercomputing 1992, Minneapolis, MN, pp. 512–521 (1992)Google Scholar