Comparison of CPML implementations for the GPU-accelerated FDTD solver

Abstract

Three distinctively different implementations of convolutional perfectly matched layer for the FDTD method on CUDA enabled graphics processing units are presented. All implementations store ad- ditional variables only inside the convolutional perfectly matched lay- ers, and the computational speeds scale according to the thickness of these layers. The merits of the different approaches are discussed, and a comparison of computational performance is made using complex real-life benchmarks.