Pixel‐Level Hardware Strategy for Large‐Scale Convolution Calculation in Neuromorphic Devices

IF 18.5 1区 材料科学 Q1 CHEMISTRY, MULTIDISCIPLINARY
Xianghong Zhang, Di Liu, Jianxin Wu, Enping Cheng, Congyao Qin, Changsong Gao, Liuting Shan, Yi Zou, Yuanyuan Hu, Tailiang Guo, Huipeng Chen
{"title":"Pixel‐Level Hardware Strategy for Large‐Scale Convolution Calculation in Neuromorphic Devices","authors":"Xianghong Zhang, Di Liu, Jianxin Wu, Enping Cheng, Congyao Qin, Changsong Gao, Liuting Shan, Yi Zou, Yuanyuan Hu, Tailiang Guo, Huipeng Chen","doi":"10.1002/adfm.202420045","DOIUrl":null,"url":null,"abstract":"For convolution neural networks, increasing the performance of hardware computer systems is crucial in the era of big data. Benefiting from the neuromorphic devices, producing the convolutional calculation at the crossbar array circuit has become a promising approach for high‐performance hardware computer systems. However, as computation scales, this hardware system faces the challenge of low resource utilization efficiency and low power efficiency. Here, a novel pixel‐level strategy, leveraging the dynamic change of electron concentration as the process of convolution calculation, is proposed for high‐performance hardware computer systems. Compared with the crossbar array circuit‐based strategy, instead of at least four devices, raised the power efficiency to 413% and decreased the training epochs to 38%. This work presents a novel physics‐based approach that enables highly efficient convolutional calculation, improves power efficiency, speeds up convergency, and paves the way for building complex convolution neural networks with large‐scale convolutional computation capabilities.","PeriodicalId":112,"journal":{"name":"Advanced Functional Materials","volume":"2 1","pages":""},"PeriodicalIF":18.5000,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advanced Functional Materials","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1002/adfm.202420045","RegionNum":1,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

For convolution neural networks, increasing the performance of hardware computer systems is crucial in the era of big data. Benefiting from the neuromorphic devices, producing the convolutional calculation at the crossbar array circuit has become a promising approach for high‐performance hardware computer systems. However, as computation scales, this hardware system faces the challenge of low resource utilization efficiency and low power efficiency. Here, a novel pixel‐level strategy, leveraging the dynamic change of electron concentration as the process of convolution calculation, is proposed for high‐performance hardware computer systems. Compared with the crossbar array circuit‐based strategy, instead of at least four devices, raised the power efficiency to 413% and decreased the training epochs to 38%. This work presents a novel physics‐based approach that enables highly efficient convolutional calculation, improves power efficiency, speeds up convergency, and paves the way for building complex convolution neural networks with large‐scale convolutional computation capabilities.
求助全文
约1分钟内获得全文 求助全文
来源期刊
Advanced Functional Materials
Advanced Functional Materials 工程技术-材料科学:综合
CiteScore
29.50
自引率
4.20%
发文量
2086
审稿时长
2.1 months
期刊介绍: Firmly established as a top-tier materials science journal, Advanced Functional Materials reports breakthrough research in all aspects of materials science, including nanotechnology, chemistry, physics, and biology every week. Advanced Functional Materials is known for its rapid and fair peer review, quality content, and high impact, making it the first choice of the international materials science community.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信