Wei Wu, Huaqiang Wu, B. Gao, Peng Yao, Xiaodong Zhang, Xiaochen Peng, Shimeng Yu, H. Qian
{"title":"A Methodology to Improve Linearity of Analog RRAM for Neuromorphic Computing","authors":"Wei Wu, Huaqiang Wu, B. Gao, Peng Yao, Xiaodong Zhang, Xiaochen Peng, Shimeng Yu, H. Qian","doi":"10.1109/VLSIT.2018.8510690","DOIUrl":null,"url":null,"abstract":"The conductance tuning linearity is an important parameter of analog RRAM for neuromorphic computing. This work presents a novel methodology to improve the conductance tuning linearity of the filamentary RRAM. An electro-thermal modulation layer is designed and introduced to control the distribution of electric field and temperature in the filament region. For the first time, a HfOx based RRAM is demonstrated with linear analog SET, linear analog RESET, 50ns speed, 10× analog tuning window, 100kΩ on-state resistance, and high temperature retention for multilevel states. The excellent performances of the analog RRAM devices enable high accuracy online learning in a neural network.","PeriodicalId":6561,"journal":{"name":"2018 IEEE Symposium on VLSI Technology","volume":"17 1","pages":"103-104"},"PeriodicalIF":0.0000,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"118","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE Symposium on VLSI Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/VLSIT.2018.8510690","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 118
Abstract
The conductance tuning linearity is an important parameter of analog RRAM for neuromorphic computing. This work presents a novel methodology to improve the conductance tuning linearity of the filamentary RRAM. An electro-thermal modulation layer is designed and introduced to control the distribution of electric field and temperature in the filament region. For the first time, a HfOx based RRAM is demonstrated with linear analog SET, linear analog RESET, 50ns speed, 10× analog tuning window, 100kΩ on-state resistance, and high temperature retention for multilevel states. The excellent performances of the analog RRAM devices enable high accuracy online learning in a neural network.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
