冯·诺依曼瓶颈下计算机体系结构的创新  

Innovation of computer architecture under the bottleneck of von Neuman

作　　者：吕启闻 陈泽乾 张曦月 周朋 张鲁峰 于春霖 陈钦 叶涛 李璇 Lv Qiwen;Chen Zeqian;Zhang Xiyue;Zhou Peng;Zhang Lufeng;Yu Chunin;Chen Qin;Ye Tao;Li Xuan(China Great Wall Research Institute,China Great Wall Technology Group Co.,Ltd,Shenzhen 518057,China;College of Computing,Central South University,Changsha 410083,China;Science and Technology Development Department,China Electronics Corporation,Shenzhen 518057,China;College of Engineering,Southern University of Science and Technology,Shenzhen 518055,China)

机构地区：[1]中国长城科技集团股份有限公司中国长城研究院,广东深圳518057 [2]中南大学计算机学院,湖南长沙410083 [3]中国电子信息产业集团有限公司科技发展部,广东深圳518057 [4]南方科技大学工学院,广东深圳518055

出　　处：《电子技术应用》2023年第11期28-34,共7页Application of Electronic Technique

摘　　要：在计算机体系结构的发展过程中,冯·诺依曼架构无疑是最为传统且主流的架构之一。为了追求更加高速的计算效率,人们在冯·诺依曼架构的基础上不断做出优化,直至达到其发展瓶颈。从传统冯·诺依曼架构出发,分析了该架构固有的局限性,并列举了针对这些局限性所作出的基本改良措施。然后具体介绍了存算一体、数据流计算等在冯·诺依曼架构上进行创新的多种技术手段。最后简述了突破原始电子计算机物理材料体系的其他非冯·诺依曼架构的发展历程,例如类脑计算机和量子计算机等,并展望了现代计算机体系结构的发展前景与方向。In the development of computer architecture,the von Neumann architecture is undoubtedly one of the most traditional and mainstream architectures.In order to pursue higher-speed computing efficiency,people continue to make optimizations on the basis of the von Neumann architecture until it reaches its development bottleneck.Starting from the traditional von Neumann ar‐chitecture,this paper analyzes the inherent limitations of the architecture,and lists the basic improvement measures for these limi‐tations.Then it specifically introduces a variety of technical means for innovation on the von Neumann architecture,such as the computing in memory,and data flow calculation.Finally,the development process of other non-von Neumann architectures that break through the original electronic computer physical material system,such as brain-inspired computer and quantum computer,is briefly described,and the development prospects and directions of modern computer architectures are prospected.

关 键 词：体系结构 冯·诺依曼瓶颈 数据流计算机 非冯·诺依曼架构 

分 类 号：TP303[自动化与计算机技术—计算机系统结构]