Fault-free: A Fault-resilient Deep Neural Network Accelerator based on Realistic ReRAM Devices
Authors:
- 5 December 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1039-1044
Abstract
Energy-efficient Resistive RAM (ReRAM) based deep neural network (DNN) accelerator suffers from severe Stuck-At-Fault (SAF) problem that drastically degrades the inference accuracy. The SAF problem gets even worse in realistic ReRAM devices with low cell resolution. To address the issue, we propose a fault-resilient DNN accelerator based on realistic ReRAM devices. We first analyze the SAF problem in a realistic ReRAM device and propose a 3-stage offline fault-resilient compilation and lightweight online compensation. The proposed work enables the reliable execution of DNN with only 5% area and 0.8% energy overhead from the ideal ReRAM-based DNN accelerator.Keywords
Funding Information
- National Research Foundation
This publication has 18 references indexed in Scilit:
- Stuck-at Fault Tolerance in RRAM Computing SystemsIEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2017
- Fault-Tolerant Training with On-Line Fault Detection for RRAM-Based Neural Computing Systems2017
- Neural Collaborative Filtering2017
- Findings of the 2017 Conference on Machine Translation (WMT17)2017
- ISAACACM SIGARCH Computer Architecture News, 2016
- PRIMEACM SIGARCH Computer Architecture News, 2016
- The MovieLens DatasetsACM Transactions on Interactive Intelligent Systems, 2015
- DaDianNao: A Machine-Learning Supercomputer2014
- RRAM Defect Modeling and Failure Analysis Based on March Test and a Novel Squeeze-Search SchemeIEEE Transactions on Computers, 2014
- ImageNet: A large-scale hierarchical image database2009