Many-threaded implementation of differential evolution for the CUDA platform
VSB – Technical University of Ostrava, Ostrava, Czech Rep
Proceedings of the 13th annual conference on Genetic and evolutionary computation, GECCO ’11, 2011
@inproceedings{kromer2011many,
title={Many-threaded implementation of differential evolution for the CUDA platform},
author={Kr{\"o}mer, P. and Sn{aa}{v{s}}el, V. and Plato{v{s}}, J. and Abraham, A.},
booktitle={Proceedings of the 13th annual conference on Genetic and evolutionary computation},
pages={1595–1602},
year={2011},
organization={ACM}
}
Differential evolution is an efficient populational meta — heuristic optimization algorithm successful in solving difficult real world problems. Due to the simplicity of its operations and data structures, it is suitable for a parallel implementation on multicore systems and on the GPU. In this paper, we design a simple yet highly parallel implementation of the differential evolution using the CUDA architecture. We demonstrate the speedup obtained by the proposed parallelization of the differential evolution on an NP hard combinatorial optimization problem and on a benchmark function of many variables.
September 29, 2011 by hgpu
