基于国产处理器的智能大数据一体机架构及应用研究

Research on architectures and applications of intelligent big data machines using China's processors

分析比较国内外智能芯片产品现状,概述智能芯片的相关软硬件技术栈,针对国内大数据与人工智能产业支撑体系尚不完善、尚未建立国产化信息处理安全保障体系的问题,提出基于国产芯片自主研发的智能大数据一体机研究与设计。解决基础设施的运维部署、海量数据存储以及时效性处理等问题,通过对比异构计算系统的分析研究,文中提出的基于国产CPU和NPU异构硬件加速的一体化计算平台具有信息安全、领域普适性强、运行效率高等特点。

This paper analyzes and compares artificial intelligence chips produced in China and other countries,and summarizes the relevant software and hardware technological stacks of them.Since the big data and artificial intelligence industry in China has not yet been perfectly supported,and the localized information processing security system has not yet been established,we propose an architecture that integrates th using domestic chips.This architecture solves problems such as infrastructure operation and maintenance,massive data storage,and time-sensitive processing.Compared with other heterogeneous computing systems,the integrated computing platform that uses Chinas CPU and NPU for heterogeneous hardware acceleration,has good information security,strong field universality,and high operating efficiency.