OpenCL-Based FPGA Accelerator for 3D FDTD with Periodic and Absorbing Boundary Conditions

Hasitha Muthumala Waidyasooriya,Yasuo Ohtera,Tsukasa Endo,Masanori Hariyama

doi:10.1155/2017/6817674

Hasitha Muthumala Waidyasooriya, Yasuo Ohtera + Show 2 more

Open Access

https://doi.org/10.1155/2017/6817674

Copy DOI

Abstract

Finite difference time domain (FDTD) method is a very poplar way of numerically solving partial differential equations. FDTD has a low operational intensity so that the performances in CPUs and GPUs are often restricted by the memory bandwidth. Recently, deeply pipelined FPGA accelerators have shown a lot of success by exploiting streaming data flows in FDTD computation. In spite of this success, many FPGA accelerators are not suitable for real-world applications that contain complex boundary conditions. Boundary conditions break the regularity of the data flow, so that the performances are significantly reduced. This paper proposes an FPGA accelerator that computes commonly used absorbing and periodic boundary conditions in many 3D FDTD applications. Accelerator is designed using a “C-like” programming language called OpenCL (open computing language). As a result, the proposed accelerator can be customized easily by changing the software code. According to the experimental results, we achieved over 3.3 times and 1.5 times higher processing speed compared to the CPUs and GPUs, respectively. Moreover, the proposed accelerator is more than 14 times faster compared to the recently proposed FPGA accelerators that are capable of handling complex boundary conditions.

Highlights

Finite difference time domain (FDTD) method is a very important and widely used one in many areas such as electromagnetic field analysis [1], optoelectronics [2], and antennas [3]
The proposed accelerator is more than 14 times faster compared to the recently proposed FPGA accelerators that are capable of handling complex boundary conditions
We have proposed an FPGA accelerator for 3D FDTD that efficiently supports absorbing and periodic boundary conditions

Summary

Introduction

Finite difference time domain (FDTD) method is a very important and widely used one in many areas such as electromagnetic field analysis [1], optoelectronics [2], and antennas [3]. FDTD computation is an iterative method where a grid is updated in each iteration according to a fixed computation pattern. It is one of the most researched subjects and there are many proposals for new algorithms and accelerators. FPGA accelerators [4,5,6,7,8,9,10] are getting popular recently since they use deeply pipelined architectures by exploiting streaming data flows in FDTD computation. Streaming data flow computing is ideal for applications with low operational intensity [11] such as FDTD. In spite of the success, many FPGA accelerators are purely academic and cannot be used efficiently for real-world applications. The main reason for this is the lack of support for boundary conditions or the inefficiency of computing them

Methods

Results

Conclusion