DianNao Family: Energy-Efficient Hardware Accelerators for Machine Learning

doi:10.1145/2996864

	DianNao Family: Energy-Efficient Hardware Accelerators for Machine Learning
	Chen, Yunji 1; Chen, Tianshi 1; Xu, Zhiwei 1; Sun, Ninghui 1; Temam, Olivier 2
	2016-11-01
发表期刊	COMMUNICATIONS OF THE ACM
ISSN	0001-0782
卷号	59 期号:11 页码:105-112
摘要	Machine Learning (ML) tasks are becoming pervasive in a broad range of applications, and in a broad range of systems (from embedded systems to data centers). As computer architectures evolve toward heterogeneous multi-cores composed of a mix of cores and hardware accelerators, designing hardware accelerators for ML techniques can simultaneously achieve high efficiency and broad application scope. While efficient computational primitives are important for a hardware accelerator, inefficient memory transfers can potentially void the throughput, energy, or cost advantages of accelerators, that is, an Amdahl's law effect, and thus, they should become a first-order concern, just like in processors, rather than an element factored in accelerator design on a second step. In this article, we introduce a series of hardware accelerators (i.e., the DianNao family) designed for ML (especially neural networks), with a special emphasis on the impact of memory on accelerator design, performance, and energy. We show that, on a number of representative neural network layers, it is possible to achieve a speedup of 450.65x over a GPU, and reduce the energy by 150.31x on average for a 64-chip DaDianNao system (a member of the DianNao family).
DOI	10.1145/2996864
收录类别	SCI
语种	英语
资助项目	NSF of China[61133004] ; NSF of China[61303158] ; NSF of China[61432016] ; NSF of China[61472396] ; NSF of China[61473275] ; NSF of China[61522211] ; NSF of China[61532016] ; NSF of China[61521092] ; 973 Program of China[2015CB358800] ; Strategic Priority Research Program of the CAS[XDA06010403] ; Strategic Priority Research Program of the CAS[XDB02040009] ; International Collaboration Key Program of the CAS[171111KYS-B20130002] ; 10,000 talent program, a Google Faculty Research Award ; Intel Collaborative Research Institute for Computational Intelligence (ICRI-CI)
WOS研究方向	Computer Science
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号	WOS:000387897700028
出版者	ASSOC COMPUTING MACHINERY
引用统计	被引频次：127[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/7912
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chen, Yunji
作者单位	1.Chinese Acad Sci, ICT, Beijing, Peoples R China 2.Inria Saclay, Palaiseau, France
推荐引用方式 GB/T 7714	Chen, Yunji,Chen, Tianshi,Xu, Zhiwei,et al. DianNao Family: Energy-Efficient Hardware Accelerators for Machine Learning[J]. COMMUNICATIONS OF THE ACM,2016,59(11):105-112.
APA	Chen, Yunji,Chen, Tianshi,Xu, Zhiwei,Sun, Ninghui,&Temam, Olivier.(2016).DianNao Family: Energy-Efficient Hardware Accelerators for Machine Learning.COMMUNICATIONS OF THE ACM,59(11),105-112.
MLA	Chen, Yunji,et al."DianNao Family: Energy-Efficient Hardware Accelerators for Machine Learning".COMMUNICATIONS OF THE ACM 59.11(2016):105-112.