Soft Error Reliability Analysis of Vision Transformers

doi:10.1109/TVLSI.2023.3317138

	Soft Error Reliability Analysis of Vision Transformers
	Xue, Xinghua 1,2; Liu, Cheng 1,2; Wang, Ying 1,2; Yang, Bing 3; Luo, Tao 4; Zhang, Lei 1,2; Li, Huawei 1,2; Li, Xiaowei 1,2
	2023-10-05
发表期刊	IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS
ISSN	1063-8210
页码	11
摘要	Vision transformers (ViTs) that leverage self-attention mechanism have shown superior performance on many classical vision tasks compared to convolutional neural networks (CNNs) and gain increasing popularity recently. Existing ViTs' works mainly optimize performance and accuracy, but ViTs' reliability issues induced by soft errors in large-scale VLSI designs have generally been overlooked. In this work, we mainly study the reliability of ViTs and investigate the vulnerability from different architecture granularities ranging from models, layers, modules, and patches for the first time. The investigation reveals that ViTs with the self-attention mechanism are generally more resilient on linear computing including general matrix-matrix multiplication (GEMM) and full connection (FC) and show a relatively even vulnerability distribution across the patches. ViTs involve more fragile non-linear computing such as softmax and GELU compared to typical CNNs. With the above observations, we propose a lightweight block-wise algorithm-based fault-tolerance (LB-ABFT) approach to protect the linear computing implemented with distinct sizes of GEMM and apply a range-based protection scheme to mitigate soft errors in non-linear computing. According to our experiments, the proposed fault-tolerant approaches enhance ViTs' accuracy significantly with minor computing overhead in the presence of various soft errors.
关键词	ABFT fault-tolerance soft errors vision transformers (ViTs) vulnerability analysis
DOI	10.1109/TVLSI.2023.3317138
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62174162] ; Space Trusted Computing and Electronic Information Technology Laboratory of BICE[ETL-2022-07]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic
WOS记录号	WOS:001086432800001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[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/2XEOYT63/21092
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Cheng
作者单位	1.Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Dept Comp Sci, Beijing 100190, Peoples R China 3.Harbin Univ Sci & Technol, Dept Comp Sci & Technol, Harbin 150006, Peoples R China 4.ASTAR, Inst High Performance Comp, Singapore 138632, Singapore
推荐引用方式 GB/T 7714	Xue, Xinghua,Liu, Cheng,Wang, Ying,et al. Soft Error Reliability Analysis of Vision Transformers[J]. IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS,2023:11.
APA	Xue, Xinghua.,Liu, Cheng.,Wang, Ying.,Yang, Bing.,Luo, Tao.,...&Li, Xiaowei.(2023).Soft Error Reliability Analysis of Vision Transformers.IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS,11.
MLA	Xue, Xinghua,et al."Soft Error Reliability Analysis of Vision Transformers".IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS (2023):11.