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
HyCA: A Hybrid Computing Architecture for Fault-Tolerant Deep Learning

文献类型：期刊论文

作者Liu, Cheng3; Chu, Cheng2,3; Xu, Dawen2,3; Wang, Ying3; Wang, Qianlong2,3; Li, Huawei3; Li, Xiaowei3; Cheng, Kwang-Ting1
刊名IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
出版日期2022-10-01
卷号41期号:10页码:3400-3413
ISSN号0278-0070
关键词Circuit faults Computational modeling Deep learning Hardware Redundancy Neural networks Computer architecture Deep learning accelerator (DLA) fault detection fault tolerance hybrid computing architecture (HyCA)
DOI10.1109/TCAD.2021.3124763
英文摘要Hardware faults on the regular 2-D computing array of a typical deep learning accelerator (DLA) can lead to dramatic prediction accuracy loss. Prior redundancy design approaches typically have each homogeneous redundant processing element (PE) to mitigate faulty PEs for a limited region of the 2-D computing array rather than the entire computing array to avoid the excessive hardware overhead. However, they fail to recover the computing array when the number of faulty PEs in any region exceeds the number of redundant PEs in the same region. The mismatch problem deteriorates when the fault injection rate rises and the faults are unevenly distributed. To address the problem, we propose a hybrid computing architecture (HyCA) for fault-tolerant DLAs. It has a set of dot-production processing units (DPPUs) to recompute all the operations that are mapped to the faulty PEs despite the faulty PE locations. According to our experiments, HyCA shows significantly higher reliability, scalability, and performance with less chip area penalty when compared to the conventional redundancy approaches. Moreover, by taking advantage of the flexible recomputing, HyCA can also be utilized to scan the entire 2-D computing array and detect the faulty PEs effectively at runtime.
资助项目National Key Research and Development Program of China[2020YFB1600201] ; National Natural Science Foundation of China[62174162] ; National Natural Science Foundation of China[61902375] ; National Natural Science Foundation of China[61834006]
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000856129900022
源URL[http://119.78.100.204/handle/2XEOYT63/19414]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Xu, Dawen
作者单位1.Hong Kong Univ Sci & Technol, Dept Comp Sci & Engn, Hong Kong, Peoples R China
2.Hefei Univ Technol, Sch Microelect, Hefei 230009, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, SKLCA, Beijing 100080, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Cheng,Chu, Cheng,Xu, Dawen,et al. HyCA: A Hybrid Computing Architecture for Fault-Tolerant Deep Learning[J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,2022,41(10):3400-3413.
APA Liu, Cheng.,Chu, Cheng.,Xu, Dawen.,Wang, Ying.,Wang, Qianlong.,...&Cheng, Kwang-Ting.(2022).HyCA: A Hybrid Computing Architecture for Fault-Tolerant Deep Learning.IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,41(10),3400-3413.
MLA Liu, Cheng,et al."HyCA: A Hybrid Computing Architecture for Fault-Tolerant Deep Learning".IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 41.10(2022):3400-3413.

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。