从计算机体系结构发展历程看数据流计算思想  

The impact of data flow computing thinking on the development of computer architecture

作　　者：窦勇[1] 王嘉伦 苏华友[1] 徐辰 宫晓利 阳王东 翁楚良 李战怀[5] 李肯立 于戈 周傲英 Yong DOU;Jialun WANG;Huayou SU;Chen XU;Xiaoli GONG;Wangdong YANG;Chuliang WENG;Zhanhuai LI;Kenli LI;Ge YU;Aoying ZHOU(College of Computer,National University of Defense and Technology,Changsha 410073,China;School of Data Science and Engineering,East China Normal University,Shanghai 200062,China;College of Cyber Science,Nankai University,Tianjian 300071,China;College of Computer Science and Electronic Engineering,Hunan University,Changsha 410082,China;School of Computer Science,Northwestern Polytechnical,Xi'an 710072,China;School of Computer Science and Engineering,Northeastern University,Shenyang 110169,China)

机构地区：[1]国防科技大学计算机学院,长沙410073 [2]华东师范大学数据科学与工程学院,上海200062 [3]南开大学网络空间安全学院,天津300071 [4]湖南大学信息科学与工程学院,长沙410082 [5]西北工业大学计算机学院,西安710072 [6]东北大学计算机科学与工程学院,沈阳110169

出　　处：《中国科学：信息科学》2020年第11期1697-1713,共17页Scientia Sinica(Informationis)

基　　金：国家重点研发计划(批准号:2018YFB1003400)资助项目。

摘　　要：在计算机体系结构发展历程中,冯·诺依曼(von Neumann)计算机结构一直是计算机系统的主流架构.谈及非冯计算机体系结构时,数据流计算机无疑是被提及最多的.本文从计算机体系结构发展历程的角度,分析数据流计算思想在计算机体系结构创新发展过程中发挥的重要作用.本文首先回顾数据流计算思想、分析早期数据流计算机的局限性;之后分析在现代中央处理器(central processing unit,CPU)技术中所借鉴的数据流计算思想,乱序执行和多线程技术;进一步介绍流计算思想、流处理器技术和图形处理器(graphics processing unit,GPU)中的数据流计算思想;然后针对大数据智能化时代计算机系统的发展变化分析数据流计算思想的运用.最后总结数据流计算思想运用规律,展望未来发展趋势.Throughout the entire history of computer architecture,the von Neumann model has been the most mainstream model for computer systems architecture.Data flow computer systems are undoubtedly the most well-studied type of non-von Neumann computer architecture.In this paper,from the perspective of the computer architecture development,we analyze the important role that data flow computing thinking has played in both innovation in computer architecture and in the development of computer architecture over time.We first review the thinking behind data flow computing and analyze the limitations it faced in its early stages.Then we analyze two important technologies used in modern CPUs-out-of-order execution and multi-threading technology-that were both developed using data flow computing thinking.We continue to view streaming computing,streaming processor architecture,and modern GPUs through the lens of data flow computing thinking.Further,we analyze how to apply data flow computing thinking to the development of computer systems in the era of big data intelligence.Finally,we summarize the rules of data flow computing thinking and forecast future development trends.

关 键 词：数据流 大数据 异构计算 GPU 智能计算 

分 类 号：TP303[自动化与计算机技术—计算机系统结构]