DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shin, Hyein | ko |
dc.contributor.author | Kang, Myeonggu | ko |
dc.contributor.author | Kim, Lee-Sup | ko |
dc.date.accessioned | 2021-12-09T06:49:07Z | - |
dc.date.available | 2021-12-09T06:49:07Z | - |
dc.date.created | 2021-11-25 | - |
dc.date.issued | 2021-12 | - |
dc.identifier.citation | 58th ACM/IEEE Design Automation Conference, DAC 2021 | - |
dc.identifier.issn | 0738-100X | - |
dc.identifier.uri | http://hdl.handle.net/10203/290302 | - |
dc.description.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. | - |
dc.language | English | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Fault-free: A Fault-resilient Deep Neural Network Accelerator based on Realistic ReRAM Devices | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 58th ACM/IEEE Design Automation Conference, DAC 2021 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | San francisco, Virtual | - |
dc.identifier.doi | 10.1109/DAC18074.2021.9586286 | - |
dc.contributor.localauthor | Kim, Lee-Sup | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.