一种基于GPU的高效合成孔径雷达信号处理器  

A highly efficient GPU-based signal processor of Synthetic Aperture Radar

作　　者：俞惊雷[1] 柳彬[1] 王开志[1] 刘兴钊[1] 郁文贤[1] 

机构地区：[1]上海交通大学电子系,上海200240

出　　处：《信息与电子工程》2010年第4期415-419,共5页information and electronic engineering

摘　　要：随着合成孔径雷达(SAR)应用的不断扩展,其所需要处理的数据量也在不断增加,传统的SAR信号处理器的处理速度成为其应用扩展的瓶颈。为了应对这些挑战,需要高效的SAR信号处理器来加快计算速度。文章利用图形处理器(GPU)这一新颖高效的的计算平台进行SAR信号处理,利用GPU通用并行计算,使用CUDA实现SAR成像算法,充分发挥其计算能力。实验结果表明,其处理速度是基于CPU的传统SAR信号处理器的10倍以上。它为解决在未来SAR信号处理中可能出现的问题提供了一种可靠的方法。With its extending applications,Synthetic Aperture Radar（SAR） is required to process more and more data.The processing speed of traditional SAR processor turns out to be a bottleneck of the extension of SAR applications.Highly efficient SAR signal processors need to be explored towards these challenges.Recently,Graphics Processing Unit（GPU） is developing at top speed,which is a novel and promising computation platform for efficient SAR processors.A GPU-based SAR signal processor is introduced in this paper.The implementation of this processor takes full advantage of GPU′s computation capability,using general purpose computations to implement the SAR imaging based on CUDA programming model.As the result shows,this processor is more than ten times as fast as traditional CPU-based SAR processor.It provides a promising way to solve the problems of SAR signal processing in the future.

关 键 词：合成孔径雷达 信号处理器 图形处理器 通用计算 CUDA编程模型 

分 类 号：TN958[电子电信—信号与信息处理]