arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.12203cs.DCcs.LG
收藏

FT-CNN:卷积神经网络的一种基于递归的容错算法

FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks

University of California, Riverside(加州大学河滨分校);Argonne National Laboratory(阿贡国家实验室);Oak Ridge National Laboratory(橡树岭国家实验室)

Kai Zhao, Sheng Di, Sihuan Li, Xin Liang, Yujia Zhai, Jieyang Chen, Kaiming Ouyang, Franck Cappello, Zizhong Chen

摘要:

卷积神经网络(CNN)在解决许多领域的挑战性和关键性问题方面变得越来越重要。CNN推理应用已经部署在安全关键系统中,这些系统可能会遭受由高能粒子、高温或异常电压引起的软错误。至关重要的是确保CNN推理过程对软错误的稳定性。传统的容错方法不适用于CNN推理,因为纠错码无法保护计算组件,指令复制技术会产生很高的开销,并且现有的基于算法的容错(ABFT)技术无法保护所有卷积实现。在本文中,我们专注于如何尽可能有效地保护CNN推理过程免受软错误的影响,有以下三个贡献。(1)本文提出了几种基于校验和技术的ABFT系统方案,并对其故障保护能力和运行时间进行了深入的分析,与传统的基于矩阵-矩阵乘法的ABFT不同,我们的方案支持任何卷积实现。(2)我们设计了一个新的工作流程集成所有建议的方案,以获得高的检测/校正能力,有限的总运行时开销。(3)我们使用ImageNet和知名的CNN模型进行评估,包括AlexNet、VGG-19、ResNet-18和YOLOv 2。实验结果表明,我们的实现可以处理软错误非常有限的运行时开销(4%~8%在无错误和错误注入的情况下)。

英文摘要:

Convolutional neural networks (CNNs) are becoming more and more important for solving challenging and critical problems in many fields. CNN inference applications have been deployed in safety-critical systems, which may suffer from soft errors caused by high-energy particles, high temperature, or abnormal voltage. Of critical importance is ensuring the stability of the CNN inference process against soft errors. Traditional fault tolerance methods are not suitable for CNN inference because error-correcting code is unable to protect computational components, instruction duplication techniques incur high overhead, and existing algorithm-based fault tolerance (ABFT) techniques cannot protect all convolution implementations. In this paper, we focus on how to protect the CNN inference process against soft errors as efficiently as possible, with the following three contributions. (1) We propose several systematic ABFT schemes based on checksum techniques and analyze their fault protection ability and runtime thoroughly.Unlike traditional ABFT based on matrix-matrix multiplication, our schemes support any convolution implementations. (2) We design a novel workflow integrating all the proposed schemes to obtain a high detection/correction ability with limited total runtime overhead. (3) We perform our evaluation using ImageNet with well-known CNN models including AlexNet, VGG-19, ResNet-18, and YOLOv2. Experimental results demonstrate that our implementation can handle soft errors with very limited runtime overhead (4%~8% in both error-free and error-injected situations).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑