Speedups between x70 and x120 for a generic local search (memetic) algorithm on a single GPGPU chip
LSIIT – UMR 7005, Pole API, Bd Sebastien Brant, 67400 Illkirch – France
Applications of Evolutionary Computation, Lecture Notes in Computer Science, 2010, Volume 6024/2010, 501-511
@article{kruger2010speedups,
title={Speedups between$times$ 70 and$times$ 120 for a Generic Local Search (Memetic) Algorithm on a Single GPGPU Chip},
author={Kr{\”u}ger, F. and Maitre, O. and Jim{‘e}nez, S. and Baumes, L. and Collet, P.},
journal={Applications of Evolutionary Computation},
pages={501–511},
year={2010},
publisher={Springer}
}
This paper presents the first implementation of a generic memetic algorithm on one of the two GPU (Graphic Processing Unit) chips of a GTX295 gaming card. Observed speedups range between x70 and x120, mainly depending on the population size. An automatic parallelization of a memetic algorithm is provided through an upgrade of the EASEA language, so that the EC community can benefit from the extraordinary power of these cards without needing to program them.
January 21, 2011 by hgpu
