Novel GPU-based LFM Signal Processing System

摘要：

To satisfy the requirements of high resolution and multi-function, the computation of radar real-time processing are increasing greater. Nowadays, DSP and FPGA are the main current processors to achieve realtime processing, but their computing capabilities seem poor comparing with GPU (Graphic Processing Unit) which contains hundreds of processing cores. In this paper, we implement a GPU-based (NVIDIA GTX470) radar processing system which can complete the LFM signal processing of pulse compression, coherent integration and target detecting. After our parallel optimization on the key algorithm implement and the memory accessing, this GPU-based system achieve the processing performance of about 20 TS201 (ADSP TigerSHARC 201).

关键词： GPU radar parallelism LFM

作者: Wang Jun Yao Wang Zhang Yuxi Yuan Yunneng

作者单位: School of Electronic and Information Engineering,Beihang University (BUAA) Beijing 100191,P.R.China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer and Network Technology(ICCNT 2011)(2011第三届IEEE计算机与网络技术国际会议)

会议地点: 太原

会议语种:英文

页码: 126-128

在线出版日期: 2011-02-26（万方平台首次上网日期，不代表论文的发表时间）