GPU-Accelerated FDTD simulation of human tissue using C++ AMP

Author

Lingze Zhang ; Yongxing Du ; Daocheng Wu

Author_Institution

Sch. of Life Sci. & Technol., Xi´an Jiaotong Univ., Xi´an, China

fYear

2015

fDate

22-26 March 2015

Firstpage

1

Lastpage

2

Abstract

We present results of 3D time-domain simulations of human tissue performed on high-performance graphics processing unit (GPU) hardware using a new simulation code, C++ Accelerated Massive Parallelism (AMP). A GPU implementation of the finite-difference time-domain (FDTD) method is shown to give an at least 30x reduction in execution time compared to an equivalent central processor unit (CPU) code.

Keywords

C++ language; biological tissues; biology computing; finite difference time-domain analysis; graphics processing units; 3D time-domain simulations; C++ AMP; C++ accelerated massive parallelism; CPU code; FDTD method; GPU hardware; GPU implementation; GPU-accelerated FDTD simulation; equivalent central processor unit code; finite-difference time-domain method; high-performance graphics processing unit; human tissue; simulation code; Acceleration; Arrays; Computational modeling; Finite difference methods; Graphics processing units; Hardware; Time-domain analysis; C++ AMP; FDTD; GPU accelerating;

fLanguage

English

Publisher

ieee

Conference_Titel

Applied Computational Electromagnetics (ACES), 2015 31st International Review of Progress in

Conference_Location

Williamsburg, VA

Type

conf

Filename

7109641