Abstract
Computation methods of parallel problem solving using graphic processing units (GPUs) have attracted much research interests in recent years. Genetic algorithms (GAs) can be implemented to GPUs in terms of the parallel processing of individuals in a population. This paper describes yet another implementation method of GAs to the CUDA environment where CUDA is a general-purpose computation environment for GPUs provided by NVIDIA. The major characteristic point of this study is that a steady-state GA is implemented on GPU utilizing on-chip memory in order to solve difficult optimization problems. The proposed implementation is evaluated through four test functions, then we found that the proposed implementation method yields 5.2-14.8 times faster results than those of a CPU implementation.
