2012 | OriginalPaper | Buchkapitel
PARADE: A Massively Parallel Differential Evolution Template for EASEA
verfasst von : Jarosław Arabas, Ogier Maitre, Pierre Collet
Erschienen in: Swarm and Evolutionary Computation
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper presents an efficient PARAllelization of Differential Evolution on GPU hardware written as an EASEA (EAsy Specification of Evolutionary Algorithms) template for easy reproducibility and re-use. We provide results of experiments to illustrate the relationship between population size and efficiency of the parallel version based on GPU related to the sequential version on the CPU. We also discuss how the population size influences the number of generations to obtain a certain level of result quality.