Fault-Tolerant Neural Network Accelerators With Selective TMR

被引:10
作者
Bertoa, Timoteo Garcia [1 ,2 ]
Gambardella, Giulio [1 ]
Fraser, Nicholas J. [1 ]
Blott, Michaela [1 ]
McAllister, John [2 ]
机构
[1] Xilinx Res Labs, Dublin, Ireland
[2] Queens Univ Belfast, Belfast BT7 1NN, North Ireland
关键词
Hardware; Artificial neural networks; Fault tolerant systems; Reliability; Training; Redundancy; Fats; neural networks; safety; redundancy; automotive; FPGA; binary neural networks; FINN; RELIABILITY; IMPACT;
D O I
10.1109/MDAT.2022.3174181
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Editor's notes: This article presents a tool that analyzes sensitive computations in the neural network and triplicates them to increase the functional safety of the neural network accelerator. - Fei Su, Intel Corporation © 2013 IEEE.
引用
收藏
页码:67 / 74
页数:8
相关论文
共 13 条
[1]  
Brosser F, 2014, PROCEEDINGS OF THE 2014 INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY (FPT), P296, DOI 10.1109/FPT.2014.7082803
[2]  
GAMBARDELLA G, 2019, P IEEE INT S DEF FAU, P1, DOI DOI 10.1109/DFT.2019.8875314
[3]  
Hubara I, 2016, ADV NEUR IN, V29
[4]  
Khoshavi N., 2020, P 57 ACM IEEE DES AU, P1
[5]  
Krizhevsky A., 2009, CIFAR-100 Dataset, P5
[6]   How Reduced Data Precision and Degree of Parallelism Impact the Reliability of Convolutional Neural Networks on FPGAs [J].
Libano, F. ;
Rech, P. ;
Neuman, B. ;
Leavitt, J. ;
Wirthlin, M. ;
Brunhaver, J. .
IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2021, 68 (05) :865-872
[7]   Selective Hardening for Neural Networks in FPGAs [J].
Libano, F. ;
Wilson, B. ;
Anderson, J. ;
Wirthlin, M. J. ;
Cazzaniga, C. ;
Frost, C. ;
Rech, P. .
IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2019, 66 (01) :216-222
[8]  
Spyrou T, 2021, PROCEEDINGS OF THE 2021 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE 2021), P743, DOI 10.23919/DATE51398.2021.9474081
[9]   FINN: A Framework for Fast, Scalable Binarized Neural Network Inference [J].
Umuroglu, Yaman ;
Fraser, Nicholas J. ;
Gambardella, Giulio ;
Blott, Michaela ;
Leong, Philip ;
Jahre, Magnus ;
Vissers, Kees .
FPGA'17: PROCEEDINGS OF THE 2017 ACM/SIGDA INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE GATE ARRAYS, 2017, :65-74
[10]   Impact of Single-Event Upsets on Convolutional Neural Networks in Xilinx Zynq FPGAs [J].
Wang, H. -B. ;
Wang, Y. -S. ;
Xiao, J. -H. ;
Wang, S. -L. ;
Liang, T. -J. .
IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2021, 68 (04) :394-401