Evolutionary computing on consumer graphics hardware

Kai Ling FOK, Tien Tsin WONG, Man Leung WONG

Research output: Journal PublicationsJournal Article (refereed)peer-review

85 Citations (Scopus)


Evolutionary algorithms (EA) are proven effective and robust in searching large varied spaces in a wide range of applications such as feature selection, electrical-circuit synthesis, and data mining. A growing demand from the multimedia and games industries has enabled graphics hardware companies to develop high-performance parallel graphics accelerators that resulted in the development of graphics processing unit (GPU). GPU handles rendering requests using a 3D graphics application programming interface (API). GPU lets processors communicate with any other processor directly, which enables to implement more flexible, fine grained EAs. A parallel EA can be implemented on consumer graphics cards found in many PCs. Evolutionary programming and genetic algorithms have been successfully applied to several numerical and optimization problems. EP requires mutation and is less computationally intensive than Genetic algorithm.
Original languageEnglish
Pages (from-to)69-78
Number of pages10
JournalIEEE Intelligent Systems
Issue number2
Publication statusPublished - 1 Jan 2007


Dive into the research topics of 'Evolutionary computing on consumer graphics hardware'. Together they form a unique fingerprint.

Cite this