论文信息 - Task Scheduling with Conflicting Objectives

Task Scheduling with Conflicting Objectives

The task scheduling problem for parallel and distributed systems was extensively studied in the literature. The outcome is a large set of heuristics, each of which generate an output schedule of the given application graph by preserving the task dependency constraints with the objective of minimizing the schedule length. We extend the general task scheduling model with multiple objectives of minimizing the schedule length (for task utilization) and minimizing the number of processors used (for resource utilization). These two objectives are both conflicting and complementary, which are combined into a single objective of cost minimization in our study. In this paper, the task scheduling problem for heterogeneous systems with the unified objective is formulated by a genetic search framework.

Haluk Topcuoglu | Can Sevilmis | H. Topcuoglu | Can Sevilmis

[1] Howard Jay Siegel,et al. A dynamic matching and scheduling algorithm for heterogeneous computing systems , 1998, Proceedings Seventh Heterogeneous Computing Workshop (HCW'98).

[2] D. E. Goldberg,et al. Genetic Algorithms in Search , 1989 .

[3] David E. Goldberg,et al. Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[4] Salim Hariri,et al. Performance-Effective and Low-Complexity Task Scheduling for Heterogeneous Computing , 2002, IEEE Trans. Parallel Distributed Syst..

[5] Edward A. Lee,et al. A Compile-Time Scheduling Heuristic for Interconnection-Constrained Heterogeneous Processor Architectures , 1993, IEEE Trans. Parallel Distributed Syst..

[6] Anthony A. Maciejewski,et al. Task Matching and Scheduling in Heterogenous Computing Environments Using a Genetic-Algorithm-Based Approach , 1997, J. Parallel Distributed Comput..

[7] Hesham El-Rewini,et al. Scheduling Parallel Program Tasks onto Arbitrary Target Machines , 1990, J. Parallel Distributed Comput..

[8] David Y. Y. Yun,et al. Simultaneous compression of makespan and number of processors using CRP , 1996, Proceedings of International Conference on Parallel Processing.