A Readout Scheme for PCM-Based Analog In-Memory Computing With Drift Compensation Through Reference Conductance Tracking

Alessio Antolini;Andrea Lico;Francesco Zavalloni;Eleonora Franchi Scarselli;Antonio Gnudi;Mattia Luigi Torres;Roberto Canegallo;Marco Pasotti
{"title":"A Readout Scheme for PCM-Based Analog In-Memory Computing With Drift Compensation Through Reference Conductance Tracking","authors":"Alessio Antolini;Andrea Lico;Francesco Zavalloni;Eleonora Franchi Scarselli;Antonio Gnudi;Mattia Luigi Torres;Roberto Canegallo;Marco Pasotti","doi":"10.1109/OJSSCS.2024.3432468","DOIUrl":null,"url":null,"abstract":"This article presents a readout scheme for analog in-memory computing (AIMC) based on an embedded phase-change memory (ePCM). Conductance time drift is overcome with a hardware compensation technique based on a reference cell conductance tracking (RCCT). Accuracy drop due to circuits mismatch and variability involved in the computational chain are minimized with an optimized iterative program-and-verify algorithm applied to the phase-change memory (PCM) devices. The proposed AIMC scheme is designed and manufactured in a 90-nm STMicroelectronics CMOS technology, with the aim of adding a signed multiply-and-accumulate (MAC) computation feature to a Ge-Rich GeSbTe (GST) embedded PCM array. Experimental characterizations are performed under different operating conditions and show that the mean MAC decrease in time is approximately null at room temperature and reduced by a factor of 3 after 64-h bake at \n<inline-formula> <tex-math>$85~{^{\\circ }}$ </tex-math></inline-formula>\nC. Based on several MAC operations, the estimated \n<inline-formula> <tex-math>$512\\times 512$ </tex-math></inline-formula>\n matrix-vector-multiplication (MVM) accuracy is 97.4%, whose decrease in time is less than 3% in the worst case.","PeriodicalId":100633,"journal":{"name":"IEEE Open Journal of the Solid-State Circuits Society","volume":"4 ","pages":"69-82"},"PeriodicalIF":0.0000,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10609348","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Open Journal of the Solid-State Circuits Society","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10609348/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

This article presents a readout scheme for analog in-memory computing (AIMC) based on an embedded phase-change memory (ePCM). Conductance time drift is overcome with a hardware compensation technique based on a reference cell conductance tracking (RCCT). Accuracy drop due to circuits mismatch and variability involved in the computational chain are minimized with an optimized iterative program-and-verify algorithm applied to the phase-change memory (PCM) devices. The proposed AIMC scheme is designed and manufactured in a 90-nm STMicroelectronics CMOS technology, with the aim of adding a signed multiply-and-accumulate (MAC) computation feature to a Ge-Rich GeSbTe (GST) embedded PCM array. Experimental characterizations are performed under different operating conditions and show that the mean MAC decrease in time is approximately null at room temperature and reduced by a factor of 3 after 64-h bake at $85~{^{\circ }}$ C. Based on several MAC operations, the estimated $512\times 512$ matrix-vector-multiplication (MVM) accuracy is 97.4%, whose decrease in time is less than 3% in the worst case.
通过参考电导跟踪进行漂移补偿的基于 PCM 的模拟内存计算读出方案
本文介绍了一种基于嵌入式相变存储器(ePCM)的模拟内存计算(AIMC)读出方案。基于参考单元电导跟踪 (RCCT) 的硬件补偿技术克服了电导时间漂移。计算链中涉及的电路不匹配和可变性导致的精度下降,通过应用于相变存储器 (PCM) 设备的优化迭代编程和验证算法得以最小化。所提出的 AIMC 方案采用 90 纳米意法半导体 CMOS 技术设计和制造,目的是为锗富硒钴 (GST) 嵌入式 PCM 阵列增加有符号乘法累加 (MAC) 计算功能。在不同的工作条件下进行了实验鉴定,结果表明,在室温下,MAC 的平均时间减少率近似为零,而在 85~{^{\circ }}$ C 温度下烘烤 64 小时后,时间减少率为 3 倍。基于若干 MAC 运算,512/times 512$ 矩阵-向量乘法(MVM)的估计精度为 97.4%,在最坏情况下,时间减少率不到 3%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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