MV-Net: Toward Real-Time Deep Learning on Mobile GPGPU Systems

doi:10.1145/3358696

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

	MV-Net: Toward Real-Time Deep Learning on Mobile GPGPU Systems
	Tang, Yibin 2,3; Wang, Ying 2,3; Li, Huawei 1,2,3; Li, Xiaowei 2,3,4
刊名	ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS
	2019-12-01
卷号	15 期号:4 页码:25
关键词	Edge computing online scheduling deep learning energy efficiency approximate computing
ISSN号	1550-4832
DOI	10.1145/3358696
英文摘要	Recently the development of deep learning has been propelling the sheer growth of vision and speech applications on lightweight embedded and mobile systems. However, the limitation of computation resource and power delivery capability in embedded platforms is recognized as a significant bottleneck that prevents the systems from providing real-time deep learning ability, since the inference of deep convolutional neural networks (CNNs) and recurrent neural networks (RNNs) involves large quantities of weights and operations. Particularly, how to provide quality-of-services (QoS)-guaranteed neural network inference ability in the multitask execution environment of multicore SoCs is even more complicated due to the existence of resource contention. In this article, we present a novel deep neural network architecture, MV-Net, which provides performance elasticity and contention-aware self-scheduling ability for QoS enhancement in mobile computing systems. When the constraints of QoS, output accuracy, and resource contention status of the system change, MV-Net can dynamically reconfigure the corresponding neural network propagation paths and thus achieves an effective tradeoff between neural network computational complexity and prediction accuracy via approximate computing. The experimental results show that (1) MV-Net significantly improves the performance flexibility of current CNN models and makes it possible to provide always-guaranteed QoS in a multitask environment, and (2) it satisfies the quality-of-results (QoR) requirement, outperforming the baseline implementation significantly, and improves the system energy efficiency at the same time.
资助项目	National Natural Science Foundation of China[61874124] ; National Natural Science Foundation of China[61876173] ; National Natural Science Foundation of China[61432017] ; National Natural Science Foundation of China[61532017] ; National Natural Science Foundation of China[YESS2016qnrc001]
WOS研究方向	Computer Science ; Engineering ; Science & Technology - Other Topics
语种	英语
出版者	ASSOC COMPUTING MACHINERY
WOS记录号	WOS:000535716700005
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/15288]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Tang, Yibin; Li, Huawei
作者单位	1.Peng Cheng Lab, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.6 Ke Xue Yuan South Rd, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Tang, Yibin,Wang, Ying,Li, Huawei,et al. MV-Net: Toward Real-Time Deep Learning on Mobile GPGPU Systems[J]. ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS,2019,15(4):25.
APA	Tang, Yibin,Wang, Ying,Li, Huawei,&Li, Xiaowei.(2019).MV-Net: Toward Real-Time Deep Learning on Mobile GPGPU Systems.ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS,15(4),25.
MLA	Tang, Yibin,et al."MV-Net: Toward Real-Time Deep Learning on Mobile GPGPU Systems".ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS 15.4(2019):25.