基于CPU+GPU混合架构的改进型距离徙动算法设计与实现  

Design and implementation of the modified range migration algorithm based on CPU+GPU hybrid architecture

作　　者：笪敏 孟祥新 李霆 柳桃荣 Da Min;Meng Xiangxin;Li Ting;Liu Taorong(Brainware Terahertz Information Technology Co.,Ltd,Hefei 230000,China)

机构地区：[1]博微太赫兹信息科技有限公司,合肥230000

出　　处：《电子测量技术》2020年第3期153-157,共5页Electronic Measurement Technology

摘　　要：改进型距离徙动算法是距离徙动算法的一种改进算法,相比于距离徙动算法,该算法可对任意距离切面成像,且无需插值,成像精度更高。改进型距离徙动算法的计算量大,单CPU难以满足实时成像需求,而CPU+GPU混合架构可解决此问题。两种算法的成像结果表明,改进型距离徙动算法的聚焦效果和图像对比度均优于距离徙动算法;NVIDIA GTX 1080Ti和Intel(R)Xeon(R)E5-2650 v4的实测结果表明,CPU+GPU混合架构与单CPU的加速比高达69.88。因此,基于CPU+GPU混合架构的改进型距离徙动算法实现是可行的。The modified range migration algorithm is an improved algorithm of range migration algorithm. Compared with range migration algorithm, this algorithm can image arbitrary range section without interpolation and has higher imaging accuracy. The computational complexity of the modified range migration algorithm is large, and it is difficult for a single CPU to meet the real-time imaging requirements. CPU + GPU hybrid architecture can solve this problem. The imaging results of two algorithms show that focus performance and image contrast of the improved range migration algorithm are better than that of the range migration algorithm. The experimental results of NVIDIA GTX 1080 Ti and Intel(R) Xeon(R) E5-2650 V4 show that the acceleration ratio of CPU+GPU hybrid architecture to single CPU is 69.88.Therefore, implementation of the modified range migration algorithm based on CPU + GPU hybrid architecture is feasible.

关 键 词：改进型 距离徙动算法 图形处理器(GPU) 混合架构 

分 类 号：TN95[电子电信—信号与信息处理]