A Fully Differential 4-Bit Analog Compute-In-Memory Architecture for Inference Application

D. Kushwaha, Rajat Kohli, Jwalant Mishra, R. Joshi, S. Dasgupta, B. Anand
{"title":"A Fully Differential 4-Bit Analog Compute-In-Memory Architecture for Inference Application","authors":"D. Kushwaha, Rajat Kohli, Jwalant Mishra, R. Joshi, S. Dasgupta, B. Anand","doi":"10.1109/AICAS57966.2023.10168599","DOIUrl":null,"url":null,"abstract":"A robust, fully differential multiplication and accumulate (MAC) scheme for analog compute-in-memory (CIM) architecture is proposed in this article. The proposed method achieves a high signal margin for 4-bit CIM architecture due to fully differential voltage changes on read bit-lines (RBL/RBLBs). The signal margin achieved for 4-bit MAC operation is 32 mV, which is 1.14×, 5.82×, and 10.24× higher than the state-of-the-art. The proposed scheme is robust against the process, voltage, and temperature (PVT) variations and achieves a variability metric (σ/µ) of 3.64 %, which is 2.36× and 2.66× lower than the reported works. The architecture has achieved an energy-efficiency of 2.53 TOPS/W at 1 V supply voltage in 65 nm CMOS technology, that is 6.2× efficient than digital baseline HW [25]. Furthermore, the inference accuracy of the architecture is 97.6% on the MNIST data set with a LeNet-5 CNN model. The figure-of-merit (FoM) of the proposed design is 355, which is 3.28×, 3.58×, and 17.75× higher than state-of-the-art.","PeriodicalId":296649,"journal":{"name":"2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AICAS57966.2023.10168599","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

A robust, fully differential multiplication and accumulate (MAC) scheme for analog compute-in-memory (CIM) architecture is proposed in this article. The proposed method achieves a high signal margin for 4-bit CIM architecture due to fully differential voltage changes on read bit-lines (RBL/RBLBs). The signal margin achieved for 4-bit MAC operation is 32 mV, which is 1.14×, 5.82×, and 10.24× higher than the state-of-the-art. The proposed scheme is robust against the process, voltage, and temperature (PVT) variations and achieves a variability metric (σ/µ) of 3.64 %, which is 2.36× and 2.66× lower than the reported works. The architecture has achieved an energy-efficiency of 2.53 TOPS/W at 1 V supply voltage in 65 nm CMOS technology, that is 6.2× efficient than digital baseline HW [25]. Furthermore, the inference accuracy of the architecture is 97.6% on the MNIST data set with a LeNet-5 CNN model. The figure-of-merit (FoM) of the proposed design is 355, which is 3.28×, 3.58×, and 17.75× higher than state-of-the-art.
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
用于推理应用的全差分4位模拟内存计算体系结构
本文提出了一种鲁棒的全微分乘法累积(MAC)方案,用于模拟内存计算(CIM)体系结构。由于读位线(RBL/ rblb)上的完全差分电压变化,该方法实现了4位CIM结构的高信号裕度。在4位MAC操作中实现的信号裕度为32 mV,比最先进的高1.14倍、5.82倍和10.24倍。该方案对过程、电压和温度(PVT)变化具有鲁棒性,变异性度量(σ/µ)为3.64%,分别比现有方法低2.36倍和2.66倍。该架构在65纳米CMOS技术下,在1 V电源电压下实现了2.53 TOPS/W的能效,比数字基准HW[25]效率高6.2倍。此外,该架构在MNIST数据集上使用LeNet-5 CNN模型的推理准确率为97.6%。该方案的优点系数(FoM)为355,分别比现有方案高3.28倍、3.58倍和17.75倍。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Synaptic metaplasticity with multi-level memristive devices Unsupervised Learning of Spike-Timing-Dependent Plasticity Based on a Neuromorphic Implementation A Fully Differential 4-Bit Analog Compute-In-Memory Architecture for Inference Application Convergent Waveform Relaxation Schemes for the Transient Analysis of Associative ReLU Arrays Performance Assessment of an Extremely Energy-Efficient Binary Neural Network Using Adiabatic Superconductor Devices
×
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