An isolated symmetrical 2T2R cell enabling high precision and high density for RRAM-based in-memory computing

被引:4
作者
Ling, Yaotian [1 ]
Wang, Zongwei [1 ]
Yang, Yuhang [1 ]
Bao, Lin [2 ]
Bao, Shengyu [1 ]
Wang, Qishen [1 ]
Cai, Yimao [1 ]
Huang, Ru [1 ]
机构
[1] Peking Univ, Beijing Adv Innovat Ctr Integrated Circuits, Sch Integrated Circuits, Beijing 100871, Peoples R China
[2] Beijing Univ Posts & Telecommun, State Key Lab Informat Photon & Opt Commun, Beijing 100876, Peoples R China
基金
中国国家自然科学基金; 北京市自然科学基金;
关键词
RRAM; multi-level storage; weight asymmetry; in-memory computing;
D O I
10.1007/s11432-023-3887-0
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In-memory computing (IMC), leveraging emerging memories, holds significant promise in overcoming memory limitations and improving energy efficiency. However, the prevailing IMC array structure based on serially connected transistors and memory cells (1T1R/2T2R), along with the signed weight mapping scheme, can lead to asymmetrical weight sensing issues (AWS) due to electrical asymmetry within the 1T1R/2T2R structure, particularly in highly scaled cells where the transistor's resistance becomes significant. In this paper, we propose and fabricate an electrically symmetric memory cell based on a physically isolated 2T2R structure for IMC. This design aims to enhance the precision and density of RRAM-based IMC arrays. The 2T2R cells are manufactured using the back-end-of-line (BEOL) process of a commercial 40 nm technology platform. The feasibility of this design is verified through measured and simulated results, showcasing its capability to address the issue of AWS. Compared to conventional 2T2R cells, this design achieves a considerably smaller transistor footprint without compromising accuracy, while also improving integration density by 42.2%. These innovative memory cell advancements have the potential to further advance high-energy-efficient IMC technology.
引用
收藏
页数:8
相关论文
共 25 条
[1]   High Density Embedded PCM Cell in 28nm FDSOI Technology for Automotive Micro-Controller Applications [J].
Arnaud, F. ;
Ferreira, P. ;
Piazza, F. ;
Gandolfo, A. ;
Zuliani, P. ;
Mattavelli, P. ;
Gomiero, E. ;
Samanni, G. ;
Jasse, J. ;
Jahan, C. ;
Reynard, J. P. ;
Berthelon, R. ;
Weber, O. ;
Villaret, A. ;
Dumont, B. ;
Grenier, J. C. ;
Ranica, R. ;
Gallon, C. ;
Boccaccio, C. ;
Souhaite, A. ;
Desvoivres, L. ;
Ristoiu, D. ;
Favennec, L. ;
Caubet, V ;
Delmedico, S. ;
Cherault, N. ;
Beneyton, R. ;
Chouteau, S. ;
Sassoulas, P. O. ;
Clement, L. ;
Boivin, P. ;
Turgis, D. ;
Disegni, F. ;
Ogier, J. L. ;
Federspiel, X. ;
Kermarrec, O. ;
Molgg, M. ;
Viscuso, A. ;
Annunziata, R. ;
Maurelli, A. ;
Cappelletti, P. ;
Ciantar, E. .
2020 IEEE INTERNATIONAL ELECTRON DEVICES MEETING (IEDM), 2020,
[2]   Homogeneous 3D Vertical Integration of Parylene-C Based Organic Flexible Resistive Memory on Standard CMOS Platform [J].
Chen, Qingyu ;
Wang, Zongwei ;
Lin, Min ;
Qi, Xin ;
Yu, Zhizhen ;
Wu, Lindong ;
Bao, Lin ;
Ling, Yaotian ;
Qin, Yabo ;
Cai, Yimao ;
Huang, Ru .
ADVANCED ELECTRONIC MATERIALS, 2021, 7 (02)
[3]  
Chen WH, 2018, ISSCC DIG TECH PAP I, P494, DOI 10.1109/ISSCC.2018.8310400
[4]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[5]   In-memory computing with resistive switching devices [J].
Ielmini, Daniele ;
Wong, H. -S. Philip .
NATURE ELECTRONICS, 2018, 1 (06) :333-343
[6]  
Krizhevsky A, 2009, LEARNING MULTIPLE LA
[7]   Deep learning [J].
LeCun, Yann ;
Bengio, Yoshua ;
Hinton, Geoffrey .
NATURE, 2015, 521 (7553) :436-444
[8]   Deep Learning Face Attributes in the Wild [J].
Liu, Ziwei ;
Luo, Ping ;
Wang, Xiaogang ;
Tang, Xiaoou .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :3730-3738
[9]  
Ramesh A., 2022, arXiv, DOI DOI 10.48550/ARXIV.2204.06125
[10]  
Razavi B., 2002, Design of Analog CMOS Integrated Circuits