LINAC: A Spatially Linear Accelerator for Convolutional Neural Networks

doi:10.1109/LCA.2022.3167465

	LINAC: A Spatially Linear Accelerator for Convolutional Neural Networks
	Xiao, Hang 1,2; Xu, Haobo 1,2; Wang, Ying 1,2,3; Wang, Yujie 1,2; Han, Yinhe 1,2,3
	2022
发表期刊	IEEE COMPUTER ARCHITECTURE LETTERS
ISSN	1556-6056
卷号	21 期号:1 页码:29-32
摘要	We first propose a method to utilize the spatially linear correlation between activations and weights of CNN models and accelerate the inference process via linear regression. With the proposed linear regression-based acceleration method, stronger bit-sparsity is excavated to reduce ineffectual computations during the inference in CNN acceleration systems without introducing any errors to the algorithm. We also propose the corresponding hardware accelerator based on the linear convolution mechanism: LINAC, which implements the linear convolution that exploits bit-sparsity to boost performance and energy efficiency significantly. In our experiments, LINAC boosts the inference performance by 11x on average over the present value-agnostic accelerator and outperforms other state-of-the-art bit-sparse accelerators.
关键词	Linear particle accelerator Correlation Kernel Convolution Linear regression System-on-chip Quantization (signal) Neural network acceleration convolution linear regression bit-sparsity
DOI	10.1109/LCA.2022.3167465
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China (NSFC)[61834006] ; National Natural Science Foundation of China (NSFC)[62025404] ; National Natural Science Foundation of China (NSFC)[61876173] ; National Natural Science Foundation of China (NSFC)[62104229] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDC05030100] ; Zhejiang Lab[2021PC0AC01]
WOS研究方向	Computer Science
WOS类目	Computer Science, Hardware & Architecture
WOS记录号	WOS:000790807700003
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19633
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Ying; Han, Yinhe
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Zhejiang Lab, Hangzhou 311100, Zhejiang, Peoples R China
推荐引用方式 GB/T 7714	Xiao, Hang,Xu, Haobo,Wang, Ying,et al. LINAC: A Spatially Linear Accelerator for Convolutional Neural Networks[J]. IEEE COMPUTER ARCHITECTURE LETTERS,2022,21(1):29-32.
APA	Xiao, Hang,Xu, Haobo,Wang, Ying,Wang, Yujie,&Han, Yinhe.(2022).LINAC: A Spatially Linear Accelerator for Convolutional Neural Networks.IEEE COMPUTER ARCHITECTURE LETTERS,21(1),29-32.
MLA	Xiao, Hang,et al."LINAC: A Spatially Linear Accelerator for Convolutional Neural Networks".IEEE COMPUTER ARCHITECTURE LETTERS 21.1(2022):29-32.