There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.conferencePlace | US | - |
dc.citation.conferencePlace | Storrs, CT, USA | - |
dc.citation.endPage | 276 | - |
dc.citation.startPage | 269 | - |
dc.citation.title | IEEE International Conference on Computer Design | - |
dc.contributor.author | Lee, Sugil | - |
dc.contributor.author | Fouda, Mohammed | - |
dc.contributor.author | Lee, Jongeun | - |
dc.contributor.author | Eltawil, Ahmed | - |
dc.contributor.author | Kurdahi, Fadi | - |
dc.date.accessioned | 2024-01-31T21:10:25Z | - |
dc.date.available | 2024-01-31T21:10:25Z | - |
dc.date.created | 2022-01-06 | - |
dc.date.issued | 2021-10-24 | - |
dc.description.abstract | To overcome the programming variability (PV) of ReRAM crossbar arrays (RCAs), the most common method is program-verify, which, however, has high energy and latency overhead. In this paper we propose a very fast and low-cost method to mitigate the effect of PV and other variability for RCA-based DNN (Deep Neural Network) accelerators. Leveraging the statistical properties of DNN output, our method called Online Batch-Norm Correction (OBNC) can compensate for the effect of programming and other variability on RCA output without using on-chip training or an iterative procedure, and is thus very fast. Also our method does not require a nonideality model or a training dataset, hence very easy to apply. Our experimental results using ternary neural networks with binary and 4-bit activations demonstrate that our OBNC can recover the baseline performance in many variability settings and that our method outperforms a previously known method (VCAM) by large margins when input distribution is asymmetric or activation is multi-bit. | - |
dc.identifier.bibliographicCitation | IEEE International Conference on Computer Design, pp.269 - 276 | - |
dc.identifier.doi | 10.1109/iccd53106.2021.00051 | - |
dc.identifier.issn | 1063-6404 | - |
dc.identifier.scopusid | 2-s2.0-85123953511 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/76796 | - |
dc.identifier.url | https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9643837 | - |
dc.identifier.wosid | 000763821700040 | - |
dc.publisher | IEEE | - |
dc.title | Fast and Low-Cost Mitigation of ReRAM Variability for Deep Learning Applications | - |
dc.type | Conference Paper | - |
dc.date.conferenceDate | 2021-10-24 | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.