DNNTune: Automatic Benchmarking DNN Models for Mobile-cloud Computing

doi:10.1145/3368305

	DNNTune: Automatic Benchmarking DNN Models for Mobile-cloud Computing
	Xia, Chunwei 1,2; Zhao, Jiacheng 1,2; Cui, Huimin 1,2; Feng, Xiaobing 1,2; Xue, Jingling 3
	2019-12-01
发表期刊	ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION
ISSN	1544-3566
卷号	16 期号:4 页码:26
摘要	Deep Neural Networks (DNNs) are now increasingly adopted in a variety of Artificial Intelligence (AI) applications. Meantime, more and more DNNs are moving from cloud to the mobile devices, as emerging AI chips are integrated into mobiles. Therefore, the DNN models can be deployed in the cloud, on the mobile devices, or even mobile-cloud coordinate processing, making it a big challenge to select an optimal deployment strategy under specific objectives. This article proposes a DNN tuning framework, i.e., DNNTune, that can provide layer-wise behavior analysis across a number of platforms. Using DNNTune, this article further selects 13 representative DNN models, including CNN, LSTM, and MLP, and three mobile devices ranging from low-end to high-end, and two AI accelerator chips to characterize the DNN models on these devices to further assist users finding opportunities for mobile-cloud coordinate computing. Our experimental results demonstrate that DNNTune can find a coordinated deployment achieving up to 1.66x speedup and 15% energy saving comparing with mobile-only and cloud-only deployment.
关键词	DNN mobile-cloud computing heterogeneous computing
DOI	10.1145/3368305
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2016YFB1000402] ; National Natural Science Foundation of China[61802368] ; National Natural Science Foundation of China[61521092] ; National Natural Science Foundation of China[61432016] ; National Natural Science Foundation of China[61432018] ; National Natural Science Foundation of China[61332009] ; National Natural Science Foundation of China[61702485] ; National Natural Science Foundation of China[61872043] ; CCF-Tencent Open Research Fund ; Australian Research Council[RG171010]
WOS研究方向	Computer Science
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods
WOS记录号	WOS:000504657400016
出版者	ASSOC COMPUTING MACHINERY
引用统计	被引频次：20[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/2XEOYT63/14981
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhao, Jiacheng
作者单位	1.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, 6 Kexueyuan South Rd Zhongguancun, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, 19 A Yuquan Rd, Beijing 100049, Peoples R China 3.Univ New South Wales, Sch Comp Sci & Engn, Gate 14 Barker St, Sydney, NSW 2052, Australia
推荐引用方式 GB/T 7714	Xia, Chunwei,Zhao, Jiacheng,Cui, Huimin,et al. DNNTune: Automatic Benchmarking DNN Models for Mobile-cloud Computing[J]. ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION,2019,16(4):26.
APA	Xia, Chunwei,Zhao, Jiacheng,Cui, Huimin,Feng, Xiaobing,&Xue, Jingling.(2019).DNNTune: Automatic Benchmarking DNN Models for Mobile-cloud Computing.ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION,16(4),26.
MLA	Xia, Chunwei,et al."DNNTune: Automatic Benchmarking DNN Models for Mobile-cloud Computing".ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION 16.4(2019):26.