基于NVIDIA GPU 的机载SAR 实时成像处理算法CUDA 设计与实现

合成孔径雷达(SAR)成像处理的运算量较大，在基于中央处理器(Central Processing Unit, CPU)的工作站或服务器上一般需要耗费较长的时间，无法满足实时性要求。借助于通用并行计算架构(CUDA)编程架构，该文提出一种基于图形处理器(GPU)的SAR 成像处理算法实现方案。该方案解决了GPU 显存不足以容纳一景SAR 数据时数据处理环节与内存/显存间数据传输环节的并行化问题，并能够支持多GPU 设备的并行处理，充分利用了GPU设备的计算资源。在NVIDIA K20C 和INTEL E5645 上的测试表明，与传统基于GPU 的SAR 成像处理算法相比，该方案能够达到数十倍的速度提升，显著降低了处理设备的功耗，提高了处理设备的便携性，能够达到每秒约36兆采样点的实时处理速度。 

Airborne SAR Real-time Imaging Algorithm Design and Implementation with CUDA on NVIDIA GPU

Synthetic Aperture Radar (SAR) image processing requires huge computation amount. Traditionally, this task runs on the workstation or server based on Central Processing Unit (CPU) and is rather time-consuming, hence real-time processing of SAR data is impossible. Based on Compute Unified Device Architecture (CUDA) technology, a new plan of SAR imaging algorithm operated on NVIDIA Graphic Processing Unit (GPU) is proposed. The new proposal makes it possible that the data processing procedure and CPU/GPU data exchanging execute concurrently, especially when SAR data size exceeds total GPU global memory size. Multi-GPU is suitably supported by the new proposal and all of computational resources are fully exploited. It is shown by experiment on NVIDIA K20C and INTEL E5645 that the proposed solution accelerates SAR data processing by tens of times. Consequently, the GPU based SAR processing system with the proposed solution embedded is much more power saving and portable, which makes it qualified to be a real-time SAR data processing system. Experiment shows that SAR data of 36 Mega points can be processed in real-time per second by K20C with the new solution equipped.