BSHIFT: A Low Cost Deep Neural Networks Accelerator

doi:10.1007/s10766-018-00624-9

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	BSHIFT: A Low Cost Deep Neural Networks Accelerator
	Yu, Yong 3,4,5; Zhi, Tian 5; Zhou, Xuda 2; Cheng, Shuyao 1; Chen, Yunji 4,5; Liu, Shaoli 3,5
刊名	INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING
	2019-06-01
卷号	47 期号:3 页码:360-372
关键词	Deep neural networks Low power Lossless Accelerator
ISSN号	0885-7458
DOI	10.1007/s10766-018-00624-9
英文摘要	Deep neural networks (DNNs) have become ubiquitous in artificial intelligence applications, including image processing, speech processing and natural language processing. However, the main characteristic of DNNs is that they are computationally and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources and power budgets. To address this limitation, we introduce a new quantization method with mixed data structure and bit-shifting broadcast accelerator structure BSHIFT. These works together reduce the storage requirement of neural networks models from 32 to 5bits without affecting their accuracy. We implement BSHIFT at TSMC 16nm technology node, and the efficiency achieves 64TOPS/s per watt in our experiments.
资助项目	National Key Research and Development Program of China[2017YFA0700902] ; National Key Research and Development Program of China[2017YFB1003101] ; NSF of China[61472396] ; NSF of China[61432016] ; NSF of China[61473275] ; NSF of China[61522211] ; NSF of China[61532016] ; NSF of China[61521092] ; NSF of China[61502446] ; NSF of China[61672491] ; NSF of China[61602441] ; NSF of China[61602446] ; NSF of China[61732002] ; NSF of China[61702478] ; 973 Program of China[2015CB358800] ; National Science and Technology Major Project[2018ZX01031102]
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER/PLENUM PUBLISHERS
WOS记录号	WOS:000471644400003
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/4193]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yu, Yong
作者单位	1.Tsinghua Univ, Beijing 100084, Peoples R China 2.Univ Sci & Technol China, Hefei 230026, Anhui, Peoples R China 3.Cambricon Tech Ltd, Beijing 100191, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 5.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Yu, Yong,Zhi, Tian,Zhou, Xuda,et al. BSHIFT: A Low Cost Deep Neural Networks Accelerator[J]. INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING,2019,47(3):360-372.
APA	Yu, Yong,Zhi, Tian,Zhou, Xuda,Cheng, Shuyao,Chen, Yunji,&Liu, Shaoli.(2019).BSHIFT: A Low Cost Deep Neural Networks Accelerator.INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING,47(3),360-372.
MLA	Yu, Yong,et al."BSHIFT: A Low Cost Deep Neural Networks Accelerator".INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING 47.3(2019):360-372.