Design and Tool Flow of a Reconfigurable Asynchronous Neural Network Accelerator

作     者：Jilin Zhang Hui Wu Weijia Chen Shaojun Wei Hong Chen Jilin Zhang;Hui Wu;Weijia Chen;Shaojun Wei;Hong Chen

作者机构：the Institute of MicroelectronicsTsinghua National Laboratory for Information Science and Technologyand Beijing Engineering Center of Technology and research on Wireless Medical and Health SystemTsinghua UniversityBeijing 100084China 

基　　金：supported by National Science and Technology Major Project from Minister of Science and Technology,China(No.2018AAA0103100) the National Natural Science Foundation of China(No.61674090) partly supported by Beijing National Research Center for Information Science and Technology(No.042003266) Beijing Engineering Research Center(No.BG0149) 

出 版 物：《Tsinghua Science and Technology》 (清华大学学报（自然科学版（英文版）)

年 卷 期：2021年第26卷第5期

页      码：565-573页

摘      要：Convolutional Neural Networks(CNNs)are widely used in computer vision,natural language processing,and so on,which generally require low power and high efficiency in real ***,energy efficiency has become a critical indicator of CNN *** that asynchronous circuits have the advantages of low power consumption,high speed,and no clock distribution problems,we design and implement an energy-efficient asynchronous CNN accelerator with a 65 nm Complementary Metal Oxide Semiconductor(CMOS)*** the absence of a commercial design tool flow for asynchronous circuits,we develop a novel design flow to implement Click-based asynchronous bundled data circuits efficiently to mask layout with conventional Electronic Design Automation(EDA)*** also introduce an adaptive delay matching method and perform accurate static timing analysis for the circuits to ensure correct *** accelerator for handwriting recognition network(LeNet-5 model)is *** test results show that the asynchronous accelerator has 30%less power in computing array than the synchronous one and that the energy efficiency of the asynchronous accelerator achieves 1.538 TOPS/W,which is 12%higher than that of the synchronous chip.

主 题 词：Convolutional Neural Network(CNN)accelerator asynchronous circuit energy efficiency adaptive delay matching asynchronous design flow 

学科分类：12[管理学] 1201[管理学-管理科学与工程类] 081104[081104] 08[工学] 0835[0835] 0811[工学-水利类] 0812[工学-测绘类] 

核心收录：

D　O　I：10.26599/TST.2020.9010048

馆 藏 号：203102824...