基于12T SRAM的CNN高精度低功耗卷积算子

Tae Seob Oh, Younggun Pu, Kangyoon Lee
{"title":"基于12T SRAM的CNN高精度低功耗卷积算子","authors":"Tae Seob Oh, Younggun Pu, Kangyoon Lee","doi":"10.1109/ICUFN49451.2021.9528655","DOIUrl":null,"url":null,"abstract":"To get high accuracy, various weight should be stored in memory. For this, this paper presents tri-state weight static random access memory(SRAM). 12T SRAM is a form of power gating on the conventional 10T SRAM. By using power gating, the inverter can be turned off. The new weight (0) can be stored in 12T SRAM when inverter is turned off. The operator fabricated in a 0.18-µm CMOS process dissipates 172.3µW with the supply of 1.8V while convolution. Even without sizing, the writing margin is better than the conventional SRAM and the accuracy is improved by 23.2%.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A High Accuracy Low Power Convolution Operator with 12T SRAM for CNN\",\"authors\":\"Tae Seob Oh, Younggun Pu, Kangyoon Lee\",\"doi\":\"10.1109/ICUFN49451.2021.9528655\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"To get high accuracy, various weight should be stored in memory. For this, this paper presents tri-state weight static random access memory(SRAM). 12T SRAM is a form of power gating on the conventional 10T SRAM. By using power gating, the inverter can be turned off. The new weight (0) can be stored in 12T SRAM when inverter is turned off. The operator fabricated in a 0.18-µm CMOS process dissipates 172.3µW with the supply of 1.8V while convolution. Even without sizing, the writing margin is better than the conventional SRAM and the accuracy is improved by 23.2%.\",\"PeriodicalId\":318542,\"journal\":{\"name\":\"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)\",\"volume\":\"17 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-08-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICUFN49451.2021.9528655\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICUFN49451.2021.9528655","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

为了获得较高的精度,需要将各种权重存储在内存中。为此,本文提出了三态权重静态随机存取存储器(SRAM)。12T SRAM是传统10T SRAM上的一种功率门控形式。通过使用功率门控,可以关闭逆变器。当逆变器关闭时,新的权重(0)可以存储在12T SRAM中。在0.18µm CMOS工艺中制造的算子在卷积时功耗为172.3µW,电源为1.8V。即使没有调整大小,写入余量也比传统的SRAM好,精度提高了23.2%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A High Accuracy Low Power Convolution Operator with 12T SRAM for CNN
To get high accuracy, various weight should be stored in memory. For this, this paper presents tri-state weight static random access memory(SRAM). 12T SRAM is a form of power gating on the conventional 10T SRAM. By using power gating, the inverter can be turned off. The new weight (0) can be stored in 12T SRAM when inverter is turned off. The operator fabricated in a 0.18-µm CMOS process dissipates 172.3µW with the supply of 1.8V while convolution. Even without sizing, the writing margin is better than the conventional SRAM and the accuracy is improved by 23.2%.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Augmented Reality Musical Service Part 1 for Non-face-to-face Watching by Multiple Audiences Performance Analysis of Cell-Free mmWave Massive MIMO with Low-Resolution DAC Quantization Efficient Task Offloading for MEC-Enabled Vehicular Networks: A Non-Cooperative Game Theoretic Approach High Efficiency & Low Area DC-DC Buck Converter with the Digital Feedback Loop for the Wireless Applications Interesting Projects To Strenghthen DSP Teaching
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1