Heterogeneous Computing and Grid Scheduling with Hierarchically Parallel Evolutionary Algorithms
School of Computer Science and Technology, Shandong University, Jinan 250101, China
Journal of Computational Information Systems 10: 8, 3291-3298, 2014
@article{wang2014heterogeneous,
title={Heterogeneous Computing and Grid Scheduling with Hierarchically Parallel Evolutionary Algorithms},
author={Wang, Jinglian and Gong, Bin and Liu, Hong and Li, Shaohui and Yi, Juan},
year={2014}
}
This work presents the novel parallel evolutionary algorithm (EA) for task scheduling in distributed heterogeneous computing and grid environments, NP-hard problems with capital relevance in distributed computing. Parallelization of the biologically inspired heuristics is hierarchically designed and integrates with the two traditional parallel models (master-slave models and island models). The method has been specifically implemented on the newly developed supercomputer platform of hybrid multi-core CPU+GPU using C-CUDA for solving large-sized realistic instances. Experiments are performed on both well-known problem instances and large instances that model medium-sized grid environments. The comparative study shows that the proposed parallel approach is able to achieve high solving efficacy, outperforming previous results reported in the related literature, and also showing a good scalability behavior when facing high dimension problem instances.
April 29, 2014 by hgpu
