An Error Compensation Technique for Low-Voltage DNN Accelerators
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ji, Daehan | - |
dc.contributor.author | Shin, Dongyeob | - |
dc.contributor.author | Park, Jongsun | - |
dc.date.accessioned | 2021-08-30T03:56:14Z | - |
dc.date.available | 2021-08-30T03:56:14Z | - |
dc.date.created | 2021-06-18 | - |
dc.date.issued | 2021-02 | - |
dc.identifier.issn | 1063-8210 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/50026 | - |
dc.description.abstract | Reducing supply voltages of deep neural network (DNN) accelerators has been of particular interest since it can achieve high energy efficiency for mobile/edge applications. To ensure reliable DNN operations at low voltage, improving the timing error resilience of DNN accelerator is highly required. In this article, we present an error resilient technique to support low-voltage DNN operations by detecting and compensating erroneous computations using the proposed compensation multiply-accumulate (CMAC) unit. First, the timing errors are detected using Razor flip-flops at critical data-path, and erroneous computations are identified and dumped. Using additional multiplier data-path with flip-flops, the dropped computations are compensated in the next CMAC unit without additional clock-cycle penalty. Various bit-precisions of error compensations are analyzed to efficiently tradeoff DNN accuracy and hardware overhead. To improve the DNN accuracy even at low bit-precision of compensation, two types of rounding techniques are presented to effectively reflect the actual distribution of DNN computation results. The low-voltage DNN accelerator based on the proposed error compensation scheme has been implemented using 65-nm CMOS. Post-layout simulations show that the proposed DNN accelerator for ResNet-18 achieves about 47% and 24% energy savings compared with baseline and state-of-the-art error resilient DNN accelerators, respectively. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | An Error Compensation Technique for Low-Voltage DNN Accelerators | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Park, Jongsun | - |
dc.identifier.doi | 10.1109/TVLSI.2020.3041517 | - |
dc.identifier.scopusid | 2-s2.0-85098746753 | - |
dc.identifier.wosid | 000613352000013 | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, v.29, no.2, pp.397 - 408 | - |
dc.relation.isPartOf | IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS | - |
dc.citation.title | IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS | - |
dc.citation.volume | 29 | - |
dc.citation.number | 2 | - |
dc.citation.startPage | 397 | - |
dc.citation.endPage | 408 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Hardware & Architecture | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordAuthor | Error compensation | - |
dc.subject.keywordAuthor | low-voltage DNN accelerator | - |
dc.subject.keywordAuthor | timing error resilient accelerator | - |
dc.subject.keywordAuthor | voltage scaling | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.