SynergyFlow: An Elastic Accelerator Architecture Supporting Batch Processing of Large-Scale Deep Neural Networks

doi:10.1145/3275243

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

	SynergyFlow: An Elastic Accelerator Architecture Supporting Batch Processing of Large-Scale Deep Neural Networks
	Jiang, Shuhao 1,2; Wu, Jingya 1,2; Li, Xiaowei 1,2; Li, Jiajun 1,2; Yan, Guihai 1,2; Lu, Wenyan 1,2; Gong, Shijun 1,2
刊名	ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS
	2019
卷号	24 期号:1 页码:27
关键词	Deep neural networks convolutional neural networks accelerator architecture resource utilization complementary effect
ISSN号	1084-4309
DOI	10.1145/3275243
英文摘要	Neural networks (NNs) have achieved great success in a broad range of applications. As NN-based methods are often both computation and memory intensive, accelerator solutions have been proved to be highly promising in terms of both performance and energy efficiency. Although prior solutions can deliver high computational throughput for convolutional layers, they could incur severe performance degradation when accommodating the entire network model, because there exist very diverse computing and memory bandwidth requirements between convolutional layers and fully connected layers and, furthermore, among different NN models. To overcome this problem, we proposed an elastic accelerator architecture, called SynergyFlow, which intrinsically supports layer-level and model-level parallelism for large-scale deep neural networks. SynergyFlow boosts the resource utilization by exploiting the complementary effect of resource demanding in different layers and different NN models. SynergyFlow can dynamically reconfigure itself according to the workload characteristics, maintaining a high performance and high resource utilization among various models. As a case study, we implement SynergyFlow on a P395-AB FPGA board. Under 100MHz working frequency, our implementation improves the performance by 33.8% on average (up to 67.2% on AlexNet) compared to comparable provisioned previous architectures.
资助项目	National Natural Science Foundation of China[61572470] ; National Natural Science Foundation of China[61872336] ; National Natural Science Foundation of China[61532017] ; National Natural Science Foundation of China[61432017] ; National Natural Science Foundation of China[61521092] ; National Natural Science Foundation of China[61376043] ; Youth Innovation Promotion Association, CAS[Y404441000]
WOS研究方向	Computer Science
语种	英语
出版者	ASSOC COMPUTING MACHINERY
WOS记录号	WOS:000455951700008
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/3470]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Xiaowei; Yan, Guihai
作者单位	1.Univ Chinese Acad Sci, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, 6 Kexueyuan South Rd, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Jiang, Shuhao,Wu, Jingya,Li, Xiaowei,et al. SynergyFlow: An Elastic Accelerator Architecture Supporting Batch Processing of Large-Scale Deep Neural Networks[J]. ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS,2019,24(1):27.
APA	Jiang, Shuhao.,Wu, Jingya.,Li, Xiaowei.,Li, Jiajun.,Yan, Guihai.,...&Gong, Shijun.(2019).SynergyFlow: An Elastic Accelerator Architecture Supporting Batch Processing of Large-Scale Deep Neural Networks.ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS,24(1),27.
MLA	Jiang, Shuhao,et al."SynergyFlow: An Elastic Accelerator Architecture Supporting Batch Processing of Large-Scale Deep Neural Networks".ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS 24.1(2019):27.