An effective list scheduling algorithm for homogeneous multi-core processor

With increasing of the number of processors, the quantity of data and the communication traffic in multi-core parallel systems, data scheduling becomes an important factor to restrict the performance improvement. Based on the classic list scheduling-HEFT algorithm, an improved algorithm has been proposed in this paper to make better result of reordering the same priority level tasks. The presented algorithm improves the quality of scheduling by introducing the sum of communication time and executing time as a new parameter. The experiment results show that the proposed algorithm has good effect on lists derived from a variety of node priority levels.

[1]  Wayne H. Wolf,et al.  TGFF: task graphs for free , 1998, Proceedings of the Sixth International Workshop on Hardware/Software Codesign. (CODES/CASHE'98).

[2]  Leonel Sousa,et al.  List scheduling: extension for contention awareness and evaluation of node priorities for heterogeneous cluster architectures , 2004, Parallel Comput..

[3]  Salim Hariri,et al.  Task scheduling algorithms for heterogeneous processors , 1999, Proceedings. Eighth Heterogeneous Computing Workshop (HCW'99).

[4]  Mickaël Raulet,et al.  Advanced list scheduling heuristic for task scheduling with communication contention for parallel embedded systems , 2010, Science China Information Sciences.

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

[6]  Tao Yang,et al.  DSC: Scheduling Parallel Tasks on an Unbounded Number of Processors , 1994, IEEE Trans. Parallel Distributed Syst..