中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
SynergyFlow: An Elastic Accelerator Architecture Supporting Batch Processing of Large-Scale Deep Neural Networks

文献类型：期刊论文

作者Jiang, Shuhao1,2; Wu, Jingya1,2; Li, Xiaowei1,2; Li, Jiajun1,2; Yan, Guihai1,2; Lu, Wenyan1,2; Gong, Shijun1,2
刊名ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS
出版日期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
DOI10.1145/3275243
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
WOS记录号WOS:000455951700008
出版者ASSOC COMPUTING MACHINERY
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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。