Calculation by artificial compressibility method and virtual flux method on GPU

In this study, artificial compressibility method and virtual flux method were implemented on GPUs. Because GPUs are recognized as massively parallel computers, DP-LUR was employed as time integration method. In spite of slow convergence characteristics of DP-LUR, calculation by the coupling of DP-LUR and GPU is about 15 times faster in time than that of LU-SGS and single CPU. Virtual flux method, which enables to calculate flow around curved surface on the Cartesian grid is also implemented to artificial compressibility method on GPU program, which was implemented in this study. GPU code of virtual flux method is about 8 times faster than CPU code.