Simulation of Fast Threshold CFAR Processing Algorithm with CUDA

Author

Xue, Wenhu ; Jiang, Yanyang

Author_Institution

Dept. of Electron. Eng., Naval Univ. of Eng., Wuhan, China

fYear

2012

Firstpage

621

Lastpage

624

Abstract

Signal level simulation is necessary to improve the fidelity of radar signal processing simulation, however the computation loads are too high for a CPU based platform. Compute Unified Device Architecture (CUDA) provides a new way to implement signal level simulation on a cost effective device. In order to compare the performances of signal level simulation based on Graphic Processor Unit (GPU) and CPU, we design and implement a typical module of radar signal processing system named with fast threshold Constant False Alarm Rate (CFAR) processing algorithm. Simulation results show that the operation rate based on GPU with CUDA is superior to that based on CPU.

Keywords

graphics processing units; parallel architectures; radar computing; radar signal processing; CPU; CPU based platform; CUDA; GPU; central processing unit; computation loads; compute unified device architecture; constant false alarm rate; fast threshold CFAR processing algorithm; fidelity improvement; graphic processor unit; radar signal processing simulation; signal level simulation; Computational modeling; Graphics processing unit; Instruction sets; Kernel; Radar; Radar signal processing; Vectors; compute unified device architecture; constant false alarm rate; graphic processor unit; signal level simulation;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Distributed Control and Intelligent Environmental Monitoring (CDCIEM), 2012 International Conference on

Conference_Location

Hunan

Print_ISBN

978-1-4673-0458-0

Type

conf

DOI

10.1109/CDCIEM.2012.153

Filename

6178482