FinFET/GAAFET纳电子学与人工智能芯片的新进展(续)  

New Progress in FinFET/GAAFET Nanoelectronics and Artificial Intelligence Chips(Continued)

作　　者：赵正平[1] Zhao Zhengping(China Electronics Technology Group Corporation,Beijing 100846,China)

机构地区：[1]中国电子科技集团公司,北京100846

出　　处：《微纳电子技术》2022年第4期293-305,共13页Micronanoelectronic Technology

摘　　要：集成电路在后摩尔时代的发展呈现出多模式创新的特点。综述了后摩尔时代中两大创新发展热点,即鳍式场效应晶体管/环绕栅场效应晶体管(FinFET/GAAFET)纳电子学和基于深度学习新算法的人工智能(AI)芯片,并介绍了其发展历程和近两年的最新进展。在FinFET/GAAFET纳电子学领域,综述并分析了当今Si基CMOS集成电路的发展现状,包含Intel的IDM模式、三星和台积电的代工模式3种技术路线,及其覆盖了22、14、10、7和5 nm集成电路纳电子学的5代技术各自的创新特点,以及未来3和2 nm技术节点GAAFET的各种创新结构的前瞻性技术研究。摩尔定律的继续发展将以Si基FinFET和GAAFET的技术发展为主。在AI芯片领域,综述并分析了数字AI芯片和模拟AI芯片的发展现状,包含神经网络云端和边缘计算应用的处理器(图像处理器(GPU)、张量处理器(TPU)和中央处理器(CPU))、加速器和神经网络处理器(NPU)等的计算架构的创新,各种神经网络算法和计算架构结合的创新,以及基于存储中计算新模式的静态随机存取存储器(SRAM)和电阻式随机存取存储器(RARAM)的创新。人工智能芯片的创新发展可弥补后摩尔时代集成电路随晶体管密度上升而计算能力增长缓慢的不足。The development of integrated circuits in the post-Moore era presents the characteristics of multimodal innovation.Two great innovation and development hots in the age of post-Moore are reviewed:fin field-effect transistor/gate all around field-effect transistor(FinFET/GAAFET)nanoelectronics and artificial intelligence(AI)chips based on the new algorithm of deep learning,and their development and the latest progress over the last two years are introduced.In the field of FinFET/GAAFET nanoelectronics,the current development status of Si-based CMOS integrated circuits(ICs)is reviewed and analyzed,including three technical routes about the IDM model of Intel,the foundry patterns of Samsung and TSMC,and their own innovative features covered the five-generation IC nanoelectronics technology on 22,14,10,7 and 5 nm,and the forward-looking technology research about various innovative structures of GAAFET in 3 and 2 nm technology nodes in the future.The continued development of Moore’s law will be dominated by the technological development of Si-based FinFET and GAAFET.In the field of AI chips,the current development of the digital AI chips and the analog AI chips are reviewed and analyzed,including the innovation on computing architectures of processors such as graphic processing unit(GPU),tensorflow processing unit(TPU)and central processing unit(CPU)in neural network cloud and edge computing applications,accelerators and NPU,the innovation of all kinds of neural network algorithms combined with computing architectures,and the innovation of static random-access memory(SRAM)and resistive random-access memory(RARAM)based on the new model of computing in the memory.The innovative development of AI chips can make up for the shortcomings of computing power slow growth of integrated circuits in the post-Moore era as transistor density increases.

关 键 词：鳍式场效应晶体管(FinFET) 环绕栅场效应晶体管(GAAFET) 互补场效应晶体管(CFET) 人工智能(AI)芯片 图像处理器(GPU) 张量处理器(TPU) 神经网络处理器(NPU) 存储中计算 静态随机存取存储器(SRAM) 电阻式随机存取存储器(RARAM) 

分 类 号：TN386[电子电信—物理电子学] TN431.2