ApproxDup: Developing an Approximate Instruction Duplication Mechanism for Efficient SDC Detection in GPGPUs

doi:10.1109/TCAD.2023.3330821

	ApproxDup: Developing an Approximate Instruction Duplication Mechanism for Efficient SDC Detection in GPGPUs
	Wei, Xiaohui 1; Jiang, Nan 1; Yue, Hengshan 1; Wang, Xiaonan 1; Zhao, Jianpeng 1; Li, Guangli 2; Qiu, Meikang 3
	2024-04-01
发表期刊	IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
ISSN	0278-0070
卷号	43 期号:4 页码:1051-1064
摘要	Nowadays, selective instruction duplication (SelDup) is the typical approach to detect silent data corruption (SDC) in GPGPU. However, owing to the up-to-billions fault sites of parallel GPGPU kernel functions, it usually introduces tremendous overhead to perform fault injections (FIs) for obtaining the duplication-candidate instruction set (although can be conducted in parallel). Moreover, current SelDup typically considers all SDCs severe and tends to duplicate more instructions. The nontrivial duplication overhead seriously restricts the deployment of current SelDup on resource-constrained systems (e.g., embedded GPGPUs). To address the above challenges, this article proposes an approximate instruction duplication (ApproxDup) mechanism for efficient SDC detection in GPGPUs. First, to replace the expensive FI-based duplication-candidate instructions identified method, we drive out a machine learning (ML)-based model (SDC-predictor) for instructionwise SDC proneness and severity estimation. Our key insight is that instruction type/functionality and instruction dependency set can efficaciously characterize the instructionwise SDC proneness in GPGPUs. In contrast, the instruction's original data magnitude, fault propagation range, and error detected features can distinguish its SDC severity. Second, incorporating the concept of approximate computing, we propose ApproxDup that preferentially duplicates severe-SDC-prone instructions while relaxing the detection of minor/detectable SDCs for traditional SelDup overhead reduction. Experimental results exhibit that ApproxDup can cover 92.51% of severe SDCs while merely increasing 38% of dynamic instructions, which achieves a better tradeoff between reliability and performance compared with the state-of-the-art SelDup. Furthermore, we discuss the effectiveness of the proposed method on different ML models/applications/GPGPU architectures.
关键词	Instruction sets Reliability Resilience Circuit faults Registers Kernel Graphics processing units Approximate computing GPGPUs instruction duplication silent data corruptions (SDCs) soft error
DOI	10.1109/TCAD.2023.3330821
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China (NSFC)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Interdisciplinary Applications ; Engineering, Electrical & Electronic
WOS记录号	WOS:001188376700021
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：3[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/2XEOYT63/38801
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yue, Hengshan
作者单位	1.Jilin Univ, Coll Comp Sci & Technol, Changchun 130012, Jilin, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Augusta Univ, Sch Comp & Cyber Sci, Augusta, GA 30912 USA
推荐引用方式 GB/T 7714	Wei, Xiaohui,Jiang, Nan,Yue, Hengshan,et al. ApproxDup: Developing an Approximate Instruction Duplication Mechanism for Efficient SDC Detection in GPGPUs[J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,2024,43(4):1051-1064.
APA	Wei, Xiaohui.,Jiang, Nan.,Yue, Hengshan.,Wang, Xiaonan.,Zhao, Jianpeng.,...&Qiu, Meikang.(2024).ApproxDup: Developing an Approximate Instruction Duplication Mechanism for Efficient SDC Detection in GPGPUs.IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,43(4),1051-1064.
MLA	Wei, Xiaohui,et al."ApproxDup: Developing an Approximate Instruction Duplication Mechanism for Efficient SDC Detection in GPGPUs".IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 43.4(2024):1051-1064.