DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kang, Yesung | - |
dc.contributor.author | Kwon, Eunji | - |
dc.contributor.author | Lee, Seunggyu | - |
dc.contributor.author | Byun, Younghoon | - |
dc.contributor.author | Lee, Youngjoo | - |
dc.contributor.author | Kang, Seokhyeong | - |
dc.date.accessioned | 2022-03-02T04:46:23Z | - |
dc.date.available | 2022-03-02T04:46:23Z | - |
dc.date.created | 2022-02-20 | - |
dc.date.issued | 2021-02-02 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/109924 | - |
dc.description.abstract | This paper presents a convolutional neural network (CNN) accelerator that can skip zero weights and handle outliers, which are few but have a significant impact on the accuracy of CNNs, to achieve speedup and increase the energy efficiency of CNN. We propose an offline weight-scheduling algorithm which can skip zero weights and combine two non-outlier weights simultaneously using bit-level sparsity of CNNs. We use a reconfigurable multiplier-and-accumulator (MAC) unit for two purposes; usually used to compute combined two non-outliers and sometimes to compute outliers. We further improve the speedup of our accelerator by clipping some of the outliers with negligible accuracy loss. Compared to DaDianNao [7] and Bit-Tactical [16] architectures, our CNN accelerator can improve the speed by 3.34 and 2.31 times higher and reduce energy consumption by 29.3% and 30.2%, respectively. | - |
dc.language | English | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.relation.isPartOf | 2021 Design, Automation and Test in Europe Conference and Exhibition, DATE 2021 | - |
dc.relation.isPartOf | Proceedings -Design, Automation and Test in Europe, DATE | - |
dc.title | Approach to Improve the Performance Using Bit-level Sparsity in Neural Networks | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.identifier.bibliographicCitation | 2021 Design, Automation and Test in Europe Conference and Exhibition, DATE 2021, pp.1516 - 1521 | - |
dc.citation.conferenceDate | 2021-02-01 | - |
dc.citation.conferencePlace | FR | - |
dc.citation.endPage | 1521 | - |
dc.citation.startPage | 1516 | - |
dc.citation.title | 2021 Design, Automation and Test in Europe Conference and Exhibition, DATE 2021 | - |
dc.contributor.affiliatedAuthor | Kang, Yesung | - |
dc.contributor.affiliatedAuthor | Kwon, Eunji | - |
dc.contributor.affiliatedAuthor | Lee, Seunggyu | - |
dc.contributor.affiliatedAuthor | Byun, Younghoon | - |
dc.contributor.affiliatedAuthor | Lee, Youngjoo | - |
dc.contributor.affiliatedAuthor | Kang, Seokhyeong | - |
dc.identifier.scopusid | 2-s2.0-85111015888 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.