应用于射电天文的高效实时管道数据流传输与处理技术  

Efficient Real-time Data Transmission and ProcessingTechnologies Applied to Radio Astronomy

作　　者：张萌[1,2] 张海龙 王杰[1,2,4] 李健 冶鑫晨[1,4] 王万琼 李嘉[1] 王博群 张亚州[1,2] Zhang Meng;Zhang Hailong;Wang Jie;Li Jian;Ye Xinchen;Wang Wanqiong;Li Jia;Wang Boqun;Zhang Yazhou(Xinjiang Astronomical Observatory,Chinese Academy of Sciences,Urumqi 830011,China;University of Chinese Academy of Sciences,Beijing 100049,China;Key Laboratory of Radio Astronomy,Chinese Academy of Sciences,Nanjing 210008,China;National Astronomical Data Center,Beijing 100101,China)

机构地区：[1]中国科学院新疆天文台,新疆乌鲁木齐830011 [2]中国科学院大学,北京100049 [3]中国科学院射电天文重点实验室,江苏南京210008 [4]国家天文科学数据中心,北京100101

出　　处：《天文研究与技术》2021年第4期489-503,共15页Astronomical Research & Technology

基　　金：国家自然科学基金(12173077,11873082,11803080,12003062);中国科学院青年创新促进会;国家重点研发计划(2018YFA0404704);国家天文科学数据中心;中国科学院天文台站设备更新及重大仪器设备运行专项经费支持.

摘　　要：针对超宽带及多波束接收系统海量天文信号实时高效传输与处理问题,对基于现场可编程门阵列(Field Programmable Gate Array,FPGA)+图形处理器(Graphics Processing Unit,GPU)的主流终端设备软件系统进行了测试分析。超宽带接收设备要求终端系统软件能够在更宽带宽、更高时间分辨率和频率分辨率的条件下,实现数据流实时传输与处理。结合大口径射电观测设备未来发展的方向,提出了利用高速并行环形缓冲区实现数据流缓存,基于图形处理器集群实现数据流实时处理,基于BeeGFS实现分布式并行数据存储,模块化构建射电天文信号传输管道软件的设计思路。Aiming at problems of massive signals real-time transmission and processing in ultra-wideband and multi-beam receiving systems,we tested and analyzed the related software of the mainstream backend system based on FPGA+GPU.The ultra-wide band receiving equipment required the backend system software to be capable of wider bandwidth and higher time resolution and higher frequency resolution conditions,as well as the realization of real-time data stream transmission and processing.Combined with the future development direction of large aperture radio observation equipment,it was proposed to use high-speed parallel ring buffers to achieve data stream caching,GPU clusters to achieve data stream real-time processing,and distributed parallel data storage based on BeeGFS,modular construction of data stream transmission pipelines software design ideas.

关 键 词：数据传输与处理 射电天文 实时 FPGA+GPU 

分 类 号：P161.4[天文地球—天文学]