Title :
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
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;
Conference_Titel :
Computer Distributed Control and Intelligent Environmental Monitoring (CDCIEM), 2012 International Conference on
Conference_Location :
Hunan
Print_ISBN :
978-1-4673-0458-0
DOI :
10.1109/CDCIEM.2012.153
