MRFI: An Open-Source Multiresolution Fault Injection Framework for Neural Network Processing

doi:10.1109/TVLSI.2024.3384404

	MRFI: An Open-Source Multiresolution Fault Injection Framework for Neural Network Processing
	Huang, Haitong 1,2; Liu, Cheng 1,2; Xue, Xinghua 1,2; Liu, Bo 3; Li, Huawei 1,2; Li, Xiaowei 1,2
	2024-04-10
发表期刊	IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS
ISSN	1063-8210
页码	11
摘要	To ensure resilient neural network processing on even unreliable hardware, comprehensive reliability analysis against various hardware faults is generally required before the neural network models are deployed, and efficient fault injection tools are highly demanded. However, many existing fault injection tools remain limited to basic fault injection and fail to provide fine-grained vulnerability analysis capability. In addition, many of the fault injection tools also need to change the neural network models and make the fault injection closely coupled with normal neural network processing, which complicates the use of these tools and slows down the fault simulation. The various fault injection implementations and error metrics make the comparison between different fault-tolerant studies difficult. To this end, we propose MRFI, a highly configurable multiresolution fault injection tool for deep neural networks. It enables users to modify an independent fault configuration file rather than neural network models for fault injection and vulnerability analysis. Particularly, it integrates extensive fault analysis functionalities from different perspectives and enables multiresolution investigation of the vulnerability of neural networks. In addition, it does not modify the major neural network computing framework of PyTorch. Hence, it allows parallel processing on GPUs naturally and exhibits fast fault simulation according to our experiments. Moreover, we also have the fault injection calibrated with fault simulation with architectural details and validate the accuracy of the proposed fault injection. Finally, MRFI is also open-sourced on GitHub (MRFI https://github.com/fffasttime/MRFI).
关键词	Biological neural networks Hardware Reliability Computational modeling Neural networks Fault tolerant systems Fault tolerance Fault evaluation fault injection fault simulation multiresolution neural network reliability
DOI	10.1109/TVLSI.2024.3384404
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic
WOS记录号	WOS:001201933900001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38727
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, Sch Comp Sci & Technol, Beijing 100190, Peoples R China 3.Beijing Inst Control Engn, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Huang, Haitong,Liu, Cheng,Xue, Xinghua,et al. MRFI: An Open-Source Multiresolution Fault Injection Framework for Neural Network Processing[J]. IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS,2024:11.
APA	Huang, Haitong,Liu, Cheng,Xue, Xinghua,Liu, Bo,Li, Huawei,&Li, Xiaowei.(2024).MRFI: An Open-Source Multiresolution Fault Injection Framework for Neural Network Processing.IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS,11.
MLA	Huang, Haitong,et al."MRFI: An Open-Source Multiresolution Fault Injection Framework for Neural Network Processing".IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS (2024):11.