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
FlexPDA: A Flexible Programming Framework for Deep Learning Accelerators

文献类型：期刊论文

作者Liu, Lei3,4; Ma, Xiu3,4; Liu, Hua-Xiao3,4; Li, Guang-Li1,2; Liu, Lei2
刊名JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
出版日期2022-10-01
卷号37期号:5页码:1200-1220
ISSN号1000-9000
关键词deep learning accelerator programming framework domain-specific language
DOI10.1007/s11390-021-1406-9
英文摘要There are a wide variety of intelligence accelerators with promising performance and energy efficiency, deployed in a broad range of applications such as computer vision and speech recognition. However, programming productivity hinders the deployment of deep learning accelerators. The low-level library invoked in the high-level deep learning framework which supports the end-to-end execution with a given model, is designed to reduce the programming burden on the intelligence accelerators. Unfortunately, it is inflexible for developers to build a network model for every deep learning application, which probably brings unnecessary repetitive implementation. In this paper, a flexible and efficient programming framework for deep learning accelerators, FlexPDA, is proposed, which provides more optimization opportunities than the low-level library and realizes quick transplantation of applications to intelligence accelerators for fast upgrades. We evaluate FlexPDA by using 10 representative operators selected from deep learning algorithms and an end-to-end network. The experimental results validate the effectiveness of FlexPDA, which achieves an end-to-end performance improvement of 1.620x over the low-level library.
资助项目National Key Research and Development Program of China[2017YFB1003103] ; Natural Science Research Foundation of Jilin Province of China[20190201193JC] ; Fundamental Research Funds for the Central Universities
WOS研究方向Computer Science
语种英语
出版者SCIENCE PRESS
WOS记录号WOS:000870734200013
源URL[http://119.78.100.204/handle/2XEOYT63/19772]  
专题中国科学院计算技术研究所期刊论文
通讯作者Liu, Hua-Xiao
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100190, Peoples R China
3.Jilin Univ, Minist Educ, Key Lab Symbol Computat & Knowledge Engn, Changchun 130012, Peoples R China
4.Jilin Univ, Coll Comp Sci & Technol, Changchun 130012, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Lei,Ma, Xiu,Liu, Hua-Xiao,et al. FlexPDA: A Flexible Programming Framework for Deep Learning Accelerators[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2022,37(5):1200-1220.
APA Liu, Lei,Ma, Xiu,Liu, Hua-Xiao,Li, Guang-Li,&Liu, Lei.(2022).FlexPDA: A Flexible Programming Framework for Deep Learning Accelerators.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,37(5),1200-1220.
MLA Liu, Lei,et al."FlexPDA: A Flexible Programming Framework for Deep Learning Accelerators".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 37.5(2022):1200-1220.

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。