cuSten
CUDA Finite Difference Library
view repo
In this paper we present cuSten, a new library of functions to handle the implementation of 2D finite-difference/stencil programs in CUDA. cuSten wraps data handling, kernel calls and streaming into four easy to use functions that speed up development of numerical codes on GPU platforms. The paper also presents an example of this library applied to solve the Cahn-Hilliard equation utilizing an ADI method with periodic boundary conditions.
READ FULL TEXTCUDA Finite Difference Library