WSEAS Transactions on Systems and Control
Print ISSN: 1991-8763, E-ISSN: 2224-2856
Volume 15, 2020
Analyzing the Impact of Soft Errors in Deep Neural Networks on GPUsfrom Instruction Level
Authors: , , , , ,
Abstract: Deep Neural Networks (DNNs) used in safetycritical systems cannot compromise their performance due to reliability issues. In particular, soft errors are the worst. Selective softwarebased protection solutions are among the best techniques to improve the reliability of DNNs efficiently. However, their most significant challenge is precisely hardening portions of the DNN model to avoid performance degradation. In this work, we propose a comprehensive methodology to analyze the reliability of object detection and classification algorithms run on GPUs from the lowest (instruction) evaluation level. The ultimate goal is to avoid the performance penalty of full instruction duplication by confidently identifying the vulnerable instructions. For this purpose, we propose a technique, Instruction Vulnerability Factor (IVF). By applying our methodology on ResNet and YOLO models, we demonstrate that both models’ most vulnerable instructions can be precisely determined. Moreover, we show that YOLO is more sensitive to the changes caused by soft errors than ResNet. Also, ResNet depends on the input image in its reliability, while YOLO tends to be independent.
Search Articles
Keywords: "Reliability, neural networks, GPUs, soft errors, instructionlevel vulnerability, selective hardening"
Pages: 699-708
DOI: 10.37394/23203.2020.15.70