利用CUDA实现的基于GPU的SAR成像算法  

Imaging algorithm of synthetic aperture radar based on GPU via CUDA

作　　者：柳彬[1] 王开志[1] 刘兴钊[1] 郁文贤[1] 

机构地区：[1]上海交通大学电子工程系,上海200240

出　　处：《信息技术》2009年第11期62-65,共4页Information Technology

摘　　要：高速发展的图形处理器(Graphics Processing Unit,GPU)为高效合成孔径雷达(Synthetic Aperture Radar,SAR)成像算法提供了具有发展前景的新型运算平台。与CPU相比,利用GPU进行通用计算具有成本低、性能高的特点。提出利用CUDA实现的基于GPU的SAR成像算法,与传统的基于CPU的成像算法相比,有两位数以上的效率提升,为应对SAR信号处理领域新的挑战提供具有前景的研究方向。Recently, graphics processing unit （GPU） is developing at top speed, which is a novel and promising computation platform for highly efficient synthetic aperture radar （SAR） imaging algorithms. Compared to CPU, general purpose computations based on GPU show higher performance with lower cost. A SAR imaging algorithm based on GPU via CUDA is introduced in this paper. This imaging algorithm via CUDA is more than ten times as fast as traditional CPU-based SAR imaging algorithms. 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 成像算法 图形处理器 CUDA 

分 类 号：TN957[电子电信—信号与信息处理]