LACC:a hardware and software co-design accelerator for deep neural networks  

作　　者：Yu Yong Zhi Tian Zhou Shengyuan 于涌;Zhi Tian;Zhou Shengyuan(State Key Laboratory of Computer Architecture,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,P.R.China;School of Computer Science and Technology,University of Chinese Academy of Sciences,Beijing 100049,P.R.China;Cambricon Technologies Ltd,Beijing 100190,P.R.China)

机构地区：[1]State Key Laboratory of Computer Architecture,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,P.R.China [2]School of Computer Science and Technology,University of Chinese Academy of Sciences,Beijing 100049,P.R.China [3]Cambricon Technologies Ltd,Beijing 100190,P.R.China

出　　处：《High Technology Letters》2021年第1期62-67,共6页高技术通讯（英文版）

基　　金：Supported by the National Key Research and Development Program of China(No.2018AAA0103300,2017YFA0700900,2017YFA0700902,2017YFA0700901,2019AAA0103802,2020AAA0103802)。

摘　　要：With the increasing of data size and model size,deep neural networks(DNNs)show outstanding performance in many artificial intelligence(AI)applications.But the big model size makes it a challenge for high-performance and low-power running DNN on processors,such as central processing unit(CPU),graphics processing unit(GPU),and tensor processing unit(TPU).This paper proposes a LOGNN data representation of 8 bits and a hardware and software co-design deep neural network accelerator LACC to meet the challenge.LOGNN data representation replaces multiply operations to add and shift operations in running DNN.LACC accelerator achieves higher efficiency than the state-of-the-art DNN accelerators by domain specific arithmetic computing units.Finally,LACC speeds up the performance per watt by 1.5 times,compared to the state-of-the-art DNN accelerators on average.

关 键 词：deep neural network(DNN) domain specific accelerator domain specific data type 

分 类 号：TP332[自动化与计算机技术—计算机系统结构] TP183[自动化与计算机技术—计算机科学与技术]