Ultralow-power in-memory computing based on ferroelectric memcapacitor network.

Bobo Tian, Zhuozhuang Xie, Luqiu Chen, Shenglan Hao, Yifei Liu, Guangdi Feng, Xuefeng Liu, Hongbo Liu, Jing Yang, Yuanyuan Zhang, Wei Bai, Tie Lin, Hong Shen, Xiangjian Meng, Ni Zhong, Hui Peng, Fangyu Yue, Xiaodong Tang, Jianlu Wang, Qiuxiang Zhu, Yachin Ivry, Brahim Dkhil, Junhao Chu, Chungang Duan
Author Information
  1. Bobo Tian: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China. ORCID
  2. Zhuozhuang Xie: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  3. Luqiu Chen: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  4. Shenglan Hao: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  5. Yifei Liu: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  6. Guangdi Feng: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  7. Xuefeng Liu: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  8. Hongbo Liu: School of Materials Science and Engineering Shanghai University of Engineering Science Shanghai China.
  9. Jing Yang: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  10. Yuanyuan Zhang: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  11. Wei Bai: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  12. Tie Lin: State Key Laboratory of Infrared Physics, Chinese Academy of Sciences Shanghai Institute of Technical Physics Shanghai China.
  13. Hong Shen: State Key Laboratory of Infrared Physics, Chinese Academy of Sciences Shanghai Institute of Technical Physics Shanghai China.
  14. Xiangjian Meng: State Key Laboratory of Infrared Physics, Chinese Academy of Sciences Shanghai Institute of Technical Physics Shanghai China.
  15. Ni Zhong: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  16. Hui Peng: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China. ORCID
  17. Fangyu Yue: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  18. Xiaodong Tang: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  19. Jianlu Wang: Frontier Institute of Chip and System Fudan University Shanghai China.
  20. Qiuxiang Zhu: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  21. Yachin Ivry: Department of Materials Science and Engineering Solid-State Institute Technion-Israel Institute of Technology Haifa Israel.
  22. Brahim Dkhil: CentraleSup��lec, CNRS-UMR8580, Laboratoire SPMS Universit�� Paris-Saclay Gif-sur-Yvette France.
  23. Junhao Chu: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.
  24. Chungang Duan: Key Laboratory of Polar Materials and Devices, Ministry of Education, Shanghai Center of Brain-inspired Intelligent Materials and Devices, Department of Electronics East China Normal University Shanghai China.

Abstract

Analog storage through synaptic weights using conductance in resistive neuromorphic systems and devices inevitably generates harmful heat dissipation. This thermal issue not only limits the energy efficiency but also hampers the very-large-scale and highly complicated hardware integration as in the human brain. Here we demonstrate that the synaptic weights can be simulated by reconfigurable non-volatile capacitances of a ferroelectric-based memcapacitor with ultralow-power consumption. The as-designed metal/ferroelectric/metal/insulator/semiconductor memcapacitor shows distinct 3-bit capacitance states controlled by the ferroelectric domain dynamics. These robust memcapacitive states exhibit uniform maintenance of more than 10 s and well endurance of 10 cycles. In a wired memcapacitor crossbar network hardware, analog vector-matrix multiplication is successfully implemented to classify 9-pixel images by collecting the sum of displacement currents ( =  �� d/d) in each column, which intrinsically consumes zero energy in memcapacitors themselves. Our work sheds light on an ultralow-power neural hardware based on ferroelectric memcapacitors.

Keywords

References

  1. Nat Commun. 2022 Mar 31;13(1):1707 [PMID: 35361828]
  2. Nat Commun. 2019 Jul 19;10(1):3239 [PMID: 31324794]
  3. Nanoscale. 2021 Jul 1;13(25):11270-11278 [PMID: 34156059]
  4. Nano Lett. 2019 Mar 13;19(3):2044-2050 [PMID: 30698976]
  5. Nature. 2020 Jan;577(7792):641-646 [PMID: 31996818]
  6. Nat Commun. 2018 Aug 10;9(1):3208 [PMID: 30097585]
  7. Nat Mater. 2019 Apr;18(4):309-323 [PMID: 30894760]
  8. Phys Rev Lett. 2005 Dec 2;95(23):237602 [PMID: 16384347]
  9. Nat Nanotechnol. 2020 Jul;15(7):517-528 [PMID: 32123381]
  10. Science. 2019 Oct 11;366(6462):210-215 [PMID: 31439757]
  11. Nanoscale Adv. 2020 Mar 11;2(5):1811-1827 [PMID: 36132530]
  12. Nat Mater. 2012 Oct;11(10):860-4 [PMID: 22983431]
  13. PLoS One. 2012;7(8):e42772 [PMID: 22880101]
  14. Nanotechnology. 2013 Sep 27;24(38):384004 [PMID: 23999129]
  15. Nat Commun. 2017 Apr 03;8:14736 [PMID: 28368007]
  16. Exploration (Beijing). 2023 May 11;3(3):20220126 [PMID: 37933380]
  17. Adv Mater. 2019 Sep;31(37):e1806424 [PMID: 31379043]
  18. Adv Sci (Weinh). 2022 May;9(15):e2106092 [PMID: 35285175]
  19. Nano Lett. 2012 Nov 14;12(11):5697-702 [PMID: 23039785]
  20. Nature. 2008 May 1;453(7191):80-3 [PMID: 18451858]
  21. Exploration (Beijing). 2022 Jan 14;2(1):20210112 [PMID: 37324580]

Word Cloud

Created with Highcharts 10.0.0memcapacitorferroelectrichardwaresynapticweightsenergyultralow-powerstates10networkmemcapacitorsbasedcomputingAnalogstorageusingconductanceresistiveneuromorphicsystemsdevicesinevitablygeneratesharmfulheatdissipationthermalissuelimitsefficiencyalsohampersvery-large-scalehighlycomplicatedintegrationhumanbraindemonstratecansimulatedreconfigurablenon-volatilecapacitancesferroelectric-basedconsumptionas-designedmetal/ferroelectric/metal/insulator/semiconductorshowsdistinct3-bitcapacitancecontrolleddomaindynamicsrobustmemcapacitiveexhibituniformmaintenanceswellendurancecycleswiredcrossbaranalogvector-matrixmultiplicationsuccessfullyimplementedclassify9-pixelimagescollectingsumdisplacementcurrents =  �� d/dcolumnintrinsicallyconsumeszeroworkshedslightneuralUltralow-powerin-memoryPVDF���TrFEin���memoryultralowpower

Similar Articles

Cited By