A Charge-Sharing based 8T SRAM In-Memory Computing for Edge DNN Acceleration
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Kyeongho | - |
dc.contributor.author | Cheon, Sungsoo | - |
dc.contributor.author | Jo, Joongho | - |
dc.contributor.author | Choi, Woong | - |
dc.contributor.author | Park, Jongsun | - |
dc.date.accessioned | 2022-04-19T08:45:16Z | - |
dc.date.available | 2022-04-19T08:45:16Z | - |
dc.date.issued | 2021-12 | - |
dc.identifier.issn | 0146-7123 | - |
dc.identifier.issn | 0146-7123 | - |
dc.identifier.uri | https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/145982 | - |
dc.description.abstract | This paper presents a charge-sharing based customized 8T SRAM in-memory computing (IMC) architecture. In the proposed IMC approach, the multiply-accumulate (MAC) operation of multi-bit activations and weights is supported using the charge sharing between bit-line (BL) parasitic capacitances. The area-efficient customized 8T SRAM macro can achieve robust and voltage-scalable MAC operations due to the charge-domain computation. We also propose a split capacitor structure-based 5/6-bit reconfigurable successive approximation register analog-to-digital converter (SAR-ADC) to reduce the hardware cost of an analog readout circuit while supporting higher precision MAC operations. The proposed reconfigurable SAR-ADC has been exploited to implement layer-by-layer mixed bit-precisions in convolution layer for increasing energy efficiency with negligible accuracy loss. The 256x64 8T SRAM IMC macro has been implemented using 28nm CMOS process technology. The proposed SRAM macro achieves 11.20-TOPS/W with a maximum clock frequency of 125MHz at 1.0V. It also supports supply voltage scaling from 0.5V to 1.1V with the energy efficiency ranging from 8.3-TOPS/W to 35.4-TOPS/W within 1 % accuracy loss. | - |
dc.format.extent | 6 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | IEEE | - |
dc.title | A Charge-Sharing based 8T SRAM In-Memory Computing for Edge DNN Acceleration | - |
dc.type | Article | - |
dc.publisher.location | 미국 | - |
dc.identifier.doi | 10.1109/DAC18074.2021.9586103 | - |
dc.identifier.scopusid | 2-s2.0-85119425447 | - |
dc.identifier.bibliographicCitation | 2021 58TH ACM/IEEE DESIGN AUTOMATION CONFERENCE (DAC), v.2021-December, pp 739 - 744 | - |
dc.citation.title | 2021 58TH ACM/IEEE DESIGN AUTOMATION CONFERENCE (DAC) | - |
dc.citation.volume | 2021-December | - |
dc.citation.startPage | 739 | - |
dc.citation.endPage | 744 | - |
dc.type.docType | Proceedings Paper | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | MACRO | - |
dc.subject.keywordPlus | COMPUTATION | - |
dc.subject.keywordAuthor | In-memory computing (IMC) | - |
dc.subject.keywordAuthor | charge domain compute | - |
dc.subject.keywordAuthor | compute-in-memory (CIM) | - |
dc.subject.keywordAuthor | bit reconfigurable SAR-ADC | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
Sookmyung Women's University. Cheongpa-ro 47-gil 100 (Cheongpa-dong 2ga), Yongsan-gu, Seoul, 04310, Korea02-710-9127
Copyright©Sookmyung Women's 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.