Design features of block algorithms of FDTD-method implemented on a GPU using MATLAB

Abstract

The paper is devoted to the investigation of the implementation features of a block algorithm for the FDTD-method on GPU. The block algorithm in general and in the context of the FDTD-method in particular is discussed. The main attention is paid to specifics of determining the shape and volume of blocks, which stem from the use of MATLAB and its Parallel Computing Toolbox. The practical efficiency of the proposed techniques is shown. Possible applications and prospects are discussed.

Keywords

• FDTD-method
• block algorithms
• computational speed-up