Characterizing Endurance Degradation of Incremental Switching in Analog RRAM for Neuromorphic Systems

Meiran Zhao, Huaqiang Wu, Bin Gao, Xiaoyu Sun, Yuyi Liu, Peng Yao, Yue Xi, Xinyi Li, Qingtian Zhang, Kanwen Wang, Shimeng Yu, He Qian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Resistive random access memory (RRAM) is attractive for neuromorphic computing systems as synaptic weights. In the neural network training, incremental switching occurs between the analog conductance states, thus the analog RRAM devices have unique endurance degradation behaviors compared to the convention digital memory application. In this work, a fast measurement platform is developed to characterize the endurance of incremental switching in analog RRAM. It is found that under weak weight update pulses, the incremental switching cycles of RRAM can be increased for more than 5 orders of magnitude compared with full window switching under strong programming pulses. The 10 11 -cycle endurance of analog RRAM is proved to be sufficient for training neural networks online for various datasets (from MNIST to ImageNet). However, the nonlinearity and dynamic range of analog RRAM degrade during cycling, which may influence the learning accuracy of the neural network when it re-trains with new datasets.

Original languageEnglish (US)
Title of host publication2018 IEEE International Electron Devices Meeting, IEDM 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages20.2.1-20.2.4
ISBN (Electronic)9781728119878
DOIs
StatePublished - Jan 16 2019
Event64th Annual IEEE International Electron Devices Meeting, IEDM 2018 - San Francisco, United States
Duration: Dec 1 2018Dec 5 2018

Publication series

NameTechnical Digest - International Electron Devices Meeting, IEDM
Volume2018-December
ISSN (Print)0163-1918

Conference

Conference64th Annual IEEE International Electron Devices Meeting, IEDM 2018
CountryUnited States
CitySan Francisco
Period12/1/1812/5/18

Fingerprint

endurance
random access memory
Durability
Computer systems
analogs
degradation
Data storage equipment
Degradation
cycles
Neural networks
education
programming
pulses
learning
dynamic range
platforms
nonlinearity

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Electrical and Electronic Engineering
  • Materials Chemistry

Cite this

Zhao, M., Wu, H., Gao, B., Sun, X., Liu, Y., Yao, P., ... Qian, H. (2019). Characterizing Endurance Degradation of Incremental Switching in Analog RRAM for Neuromorphic Systems. In 2018 IEEE International Electron Devices Meeting, IEDM 2018 (pp. 20.2.1-20.2.4). [8614664] (Technical Digest - International Electron Devices Meeting, IEDM; Vol. 2018-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IEDM.2018.8614664

Characterizing Endurance Degradation of Incremental Switching in Analog RRAM for Neuromorphic Systems. / Zhao, Meiran; Wu, Huaqiang; Gao, Bin; Sun, Xiaoyu; Liu, Yuyi; Yao, Peng; Xi, Yue; Li, Xinyi; Zhang, Qingtian; Wang, Kanwen; Yu, Shimeng; Qian, He.

2018 IEEE International Electron Devices Meeting, IEDM 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 20.2.1-20.2.4 8614664 (Technical Digest - International Electron Devices Meeting, IEDM; Vol. 2018-December).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhao, M, Wu, H, Gao, B, Sun, X, Liu, Y, Yao, P, Xi, Y, Li, X, Zhang, Q, Wang, K, Yu, S & Qian, H 2019, Characterizing Endurance Degradation of Incremental Switching in Analog RRAM for Neuromorphic Systems. in 2018 IEEE International Electron Devices Meeting, IEDM 2018., 8614664, Technical Digest - International Electron Devices Meeting, IEDM, vol. 2018-December, Institute of Electrical and Electronics Engineers Inc., pp. 20.2.1-20.2.4, 64th Annual IEEE International Electron Devices Meeting, IEDM 2018, San Francisco, United States, 12/1/18. https://doi.org/10.1109/IEDM.2018.8614664
Zhao M, Wu H, Gao B, Sun X, Liu Y, Yao P et al. Characterizing Endurance Degradation of Incremental Switching in Analog RRAM for Neuromorphic Systems. In 2018 IEEE International Electron Devices Meeting, IEDM 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 20.2.1-20.2.4. 8614664. (Technical Digest - International Electron Devices Meeting, IEDM). https://doi.org/10.1109/IEDM.2018.8614664
Zhao, Meiran ; Wu, Huaqiang ; Gao, Bin ; Sun, Xiaoyu ; Liu, Yuyi ; Yao, Peng ; Xi, Yue ; Li, Xinyi ; Zhang, Qingtian ; Wang, Kanwen ; Yu, Shimeng ; Qian, He. / Characterizing Endurance Degradation of Incremental Switching in Analog RRAM for Neuromorphic Systems. 2018 IEEE International Electron Devices Meeting, IEDM 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 20.2.1-20.2.4 (Technical Digest - International Electron Devices Meeting, IEDM).
@inproceedings{b424f737741e47d0b8451ecc3770ed70,
title = "Characterizing Endurance Degradation of Incremental Switching in Analog RRAM for Neuromorphic Systems",
abstract = "Resistive random access memory (RRAM) is attractive for neuromorphic computing systems as synaptic weights. In the neural network training, incremental switching occurs between the analog conductance states, thus the analog RRAM devices have unique endurance degradation behaviors compared to the convention digital memory application. In this work, a fast measurement platform is developed to characterize the endurance of incremental switching in analog RRAM. It is found that under weak weight update pulses, the incremental switching cycles of RRAM can be increased for more than 5 orders of magnitude compared with full window switching under strong programming pulses. The 10 11 -cycle endurance of analog RRAM is proved to be sufficient for training neural networks online for various datasets (from MNIST to ImageNet). However, the nonlinearity and dynamic range of analog RRAM degrade during cycling, which may influence the learning accuracy of the neural network when it re-trains with new datasets.",
author = "Meiran Zhao and Huaqiang Wu and Bin Gao and Xiaoyu Sun and Yuyi Liu and Peng Yao and Yue Xi and Xinyi Li and Qingtian Zhang and Kanwen Wang and Shimeng Yu and He Qian",
year = "2019",
month = "1",
day = "16",
doi = "10.1109/IEDM.2018.8614664",
language = "English (US)",
series = "Technical Digest - International Electron Devices Meeting, IEDM",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "20.2.1--20.2.4",
booktitle = "2018 IEEE International Electron Devices Meeting, IEDM 2018",

}

TY - GEN

T1 - Characterizing Endurance Degradation of Incremental Switching in Analog RRAM for Neuromorphic Systems

AU - Zhao, Meiran

AU - Wu, Huaqiang

AU - Gao, Bin

AU - Sun, Xiaoyu

AU - Liu, Yuyi

AU - Yao, Peng

AU - Xi, Yue

AU - Li, Xinyi

AU - Zhang, Qingtian

AU - Wang, Kanwen

AU - Yu, Shimeng

AU - Qian, He

PY - 2019/1/16

Y1 - 2019/1/16

N2 - Resistive random access memory (RRAM) is attractive for neuromorphic computing systems as synaptic weights. In the neural network training, incremental switching occurs between the analog conductance states, thus the analog RRAM devices have unique endurance degradation behaviors compared to the convention digital memory application. In this work, a fast measurement platform is developed to characterize the endurance of incremental switching in analog RRAM. It is found that under weak weight update pulses, the incremental switching cycles of RRAM can be increased for more than 5 orders of magnitude compared with full window switching under strong programming pulses. The 10 11 -cycle endurance of analog RRAM is proved to be sufficient for training neural networks online for various datasets (from MNIST to ImageNet). However, the nonlinearity and dynamic range of analog RRAM degrade during cycling, which may influence the learning accuracy of the neural network when it re-trains with new datasets.

AB - Resistive random access memory (RRAM) is attractive for neuromorphic computing systems as synaptic weights. In the neural network training, incremental switching occurs between the analog conductance states, thus the analog RRAM devices have unique endurance degradation behaviors compared to the convention digital memory application. In this work, a fast measurement platform is developed to characterize the endurance of incremental switching in analog RRAM. It is found that under weak weight update pulses, the incremental switching cycles of RRAM can be increased for more than 5 orders of magnitude compared with full window switching under strong programming pulses. The 10 11 -cycle endurance of analog RRAM is proved to be sufficient for training neural networks online for various datasets (from MNIST to ImageNet). However, the nonlinearity and dynamic range of analog RRAM degrade during cycling, which may influence the learning accuracy of the neural network when it re-trains with new datasets.

UR - http://www.scopus.com/inward/record.url?scp=85061791185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061791185&partnerID=8YFLogxK

U2 - 10.1109/IEDM.2018.8614664

DO - 10.1109/IEDM.2018.8614664

M3 - Conference contribution

T3 - Technical Digest - International Electron Devices Meeting, IEDM

SP - 20.2.1-20.2.4

BT - 2018 IEEE International Electron Devices Meeting, IEDM 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -