Efficient Parallel Implementation of Evolutionary Algorithms on GPGPU Cards

Abstract : A parallel solution to the implementation of evolutionary algorithms is proposed, where the most costly part of the whole evolutionary algorithm computations (the population evaluation), is deported to a GPGPU card. Experiments are presented for two benchmark examples on two models of GPGPU cards: first a "toy" problem is used to illustrate some noticable behaviour characteristics before a real problem is tested out. Results show a speed-up of up to 100 times compared to an execution on a standard micro-processor. To our knowledge, this solution is the first showing such an efficiency with GPGPU cards. Finally, the EASEA language and its compiler are also extended to allow users to easily specify and generate efficient parallel implementations of evolutionay algorithms using GPGPU cards.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00504356
Contributor : Philippe Clauss <>
Submitted on : Tuesday, July 20, 2010 - 12:16:55 PM
Last modification on : Friday, April 13, 2018 - 7:54:13 PM

Links full text

Identifiers

Collections

Citation

Ogier Maître, Nicolas Lachiche, Philippe Clauss, Laurent Baumes, Avelino Corma, et al.. Efficient Parallel Implementation of Evolutionary Algorithms on GPGPU Cards. 15th International Euro-Par Conference on Parallel Processing 2009, Aug 2009, Delft, Netherlands. pp.974 - 985, ⟨10.1007/978-3-642-03869-3_89⟩. ⟨inria-00504356⟩

Share

Metrics

Record views

347