SiMul: An Algorithm-Driven Approximate Multiplier Design for Machine Learning
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, Zhenhong | - |
dc.contributor.author | Yazdanbakhsh, Amir | - |
dc.contributor.author | Park, Taejoon | - |
dc.contributor.author | Esmaeilzadeh, Hadi | - |
dc.contributor.author | Kim, Nam Sung | - |
dc.date.accessioned | 2021-06-22T11:43:02Z | - |
dc.date.available | 2021-06-22T11:43:02Z | - |
dc.date.created | 2021-01-21 | - |
dc.date.issued | 2018-07 | - |
dc.identifier.issn | 0272-1732 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/5810 | - |
dc.description.abstract | The need to support various machine learning (ML) algorithms on energy-constrained computing devices has steadily grown. In this article, we propose an approximate multiplier, which is a key hardware component in various ML accelerators. Dubbed SiMul, our approximate multiplier features user-controlled precision that exploits the common characteristics of ML algorithms. SiMul supports a tradeoff between compute precision and energy consumption at runtime, reducing the energy consumption of the accelerator while satisfying a desired inference accuracy requirement. Compared improves the energy efficiency of multiplication by 11.6x to 3.2x while achieving 81.7-percent to 98.5-percent precision for individual multiplication operations (96.0-, 97.8-, and 97.7-percent inference accuracy for three distinct applications, respectively, compared to the baseline inference accuracy of 98.3, 99.0, and 97.7 percent using precise multipliers). A neural accelerator implemented with our multiplier can provide 1.7x (up to 2.1x) higher energy efficiency over one implemented with the precise multiplier with a negligible impact on the accuracy of the output for various applications. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | SiMul: An Algorithm-Driven Approximate Multiplier Design for Machine Learning | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Park, Taejoon | - |
dc.identifier.doi | 10.1109/MM.2018.043191125 | - |
dc.identifier.scopusid | 2-s2.0-85051440088 | - |
dc.identifier.wosid | 000441410600007 | - |
dc.identifier.bibliographicCitation | IEEE MICRO, v.38, no.4, pp.50 - 59 | - |
dc.relation.isPartOf | IEEE MICRO | - |
dc.citation.title | IEEE MICRO | - |
dc.citation.volume | 38 | - |
dc.citation.number | 4 | - |
dc.citation.startPage | 50 | - |
dc.citation.endPage | 59 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Hardware & Architecture | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Software Engineering | - |
dc.subject.keywordAuthor | approximate computing | - |
dc.subject.keywordAuthor | hardware | - |
dc.subject.keywordAuthor | machine learning | - |
dc.subject.keywordAuthor | multiplier | - |
dc.subject.keywordAuthor | neural network | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/8430625?arnumber=8430625&SID=EBSCO:edseee | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
55 Hanyangdeahak-ro, Sangnok-gu, Ansan, Gyeonggi-do, 15588, Korea+82-31-400-4269 sweetbrain@hanyang.ac.kr
COPYRIGHT © 2021 HANYANG 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.