An Implementation of Differential Evolution for Independent Tasks Scheduling on GPU
Department of Computer Science, Faculty of Electrical Engineering and Computer Science, VSB – Technical University of Ostrava – 17. listopadu 15, 708 33 Ostrava – Poruba, Czech Republic
Hybrid Artificial Intelligent Systems, Lecture Notes in Computer Science, Volume 6678/2011, 372-379, 2011
@article{kromer2011implementation,
title={An Implementation of Differential Evolution for Independent Tasks Scheduling on GPU},
author={Kr{"o}mer, P. and Plato{v{s}}, J. and Sn{‘a}{v{s}}el, V. and Abraham, A.},
journal={Hybrid Artificial Intelligent Systems},
pages={372–379},
year={2011},
publisher={Springer}
}
Differential evolution is an efficient meta-heuristic optimization method with solid record of real world applications. In this paper, we present a simple and efficient implementation of the differential evolution using the massively parallel CUDA architecture. We demonstrate the speedup and improvements obtained by the parallelization of this intelligent algorithm on the problem of scheduling of independent tasks in heterogeneous environments.
November 1, 2011 by hgpu
