Variation-Resilient FeFET-Based In-Memory Computing Leveraging Probabilistic Deep Learning

Manna, Bibhas; Saha, Arnob; Jiang, Zhouhang; Ni, Kai; Sengupta, Abhronil

doi:10.1109/ted.2024.3378223

Variation-Resilient FeFET-Based In-Memory Computing Leveraging Probabilistic Deep Learning

Journal Article · Mon Mar 25 00:00:00 EDT 2024 · IEEE Transactions on Electron Devices

DOI:https://doi.org/10.1109/ted.2024.3378223· OSTI ID:2341283

^[1]; ^[1]; ^[2]; ^[2]; ^[1]

Pennsylvania State Univ., University Park, PA (United States)
University of Notre Dame, IN (United States)

Reliability issues stemming from device level nonidealities of nonvolatile emerging technologies like ferroelectric field-effect transistors (FeFETs), especially at scaled dimensions, cause substantial degradation in the accuracy of in-memory crossbar-based AI systems. Here, in this work, we present a variation-aware design technique to characterize the device level variations and to mitigate their impact on hardware accuracy employing a Bayesian neural network (BNN) approach. An effective conductance variation model is derived from the experimental measurements of cycle-to-cycle (C2C) and device-to-device (D2D) variations performed on FeFET devices fabricated using 28 nm high-k metal gate technology. The variations were found to be a function of different conductance states within the given programming range, which sharply contrasts earlier efforts where a fixed variation dispersion was considered for all conductance values. Such variation characteristics formulated for three different device sizes at different read voltages were provided as prior variation information to the BNN to yield a more exact and reliable inference. Near-ideal accuracy for shallow networks (MLP5 and LeNet models) on the MNIST dataset and limited accuracy decline by ~3.8%–16.1% for deeper AlexNet models on CIFAR10 dataset under a wide range of variations corresponding to different device sizes and read voltages, demonstrates the efficacy of our proposed device-algorithm co-design technique.

🛈

This content will become publicly available on Tue Mar 25 00:00:00 EDT 2025

Research Organization:: Pennsylvania State Univ., University Park, PA (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Basic Energy Sciences (BES)

Grant/Contract Number:: SC0021118

OSTI ID:: 2341283

Journal Information:: IEEE Transactions on Electron Devices, Vol. 71, Issue 5; ISSN 0018-9383

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (24)

Pathways to efficient neuromorphic computing with non-volatile memory technologies Chakraborty, I.; Jaiswal, A.; Saha, A. K. Applied Physics Reviews, Vol. 7, Issue 2 https://doi.org/10.1063/1.5113536	journal	June 2020
Compute in‐Memory with Non‐Volatile Elements for Neural Networks: A Review from a Co‐Design Perspective Haensch, Wilfried; Raghunathan, Anand; Roy, Kaushik Advanced Materials https://doi.org/10.1002/adma.202204944	journal	March 2023
Ferroelectric Field Effect Transistors as a Synapse for Neuromorphic Application Lederer, M.; Kampfe, T.; Ali, T. IEEE Transactions on Electron Devices, Vol. 68, Issue 5 https://doi.org/10.1109/ted.2021.3068716	journal	May 2021
28 nm HKMG-Based Current Limited FeFET Crossbar-Array for Inference Application De, Sourav; Muller, Franz; Thunder, Sunanda IEEE Transactions on Electron Devices, Vol. 69, Issue 12 https://doi.org/10.1109/ted.2022.3216973	journal	December 2022
Variability Analysis for Ferroelectric FET Nonvolatile Memories Considering Random Ferroelectric-Dielectric Phase Distribution Liu, You-Sheng; Su, Pin IEEE Electron Device Letters, Vol. 41, Issue 3 https://doi.org/10.1109/led.2020.2967423	journal	March 2020
Switching Kinetics in Nanoscale Hafnium Oxide Based Ferroelectric Field-Effect Transistors Mulaosmanovic, Halid; Ocker, Johannes; Müller, Stefan ACS Applied Materials & Interfaces, Vol. 9, Issue 4 https://doi.org/10.1021/acsami.6b13866	journal	January 2017
Vortex: variation-aware training for memristor X-bar Liu, Beiye; Li, Hai; Chen, Yiran DAC '15: The 52nd Annual Design Automation Conference 2015, Proceedings of the 52nd Annual Design Automation Conference https://doi.org/10.1145/2744769.2744930	conference	June 2015
On Improving Fault Tolerance of Memristor Crossbar Based Neural Network Designs by Target Sparsifying Jin, Song; Pei, Songwei; Wang, Yu 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE) https://doi.org/10.23919/date48585.2020.9116187	conference	March 2020
Design of Reliable DNN Accelerator with Un-reliable ReRAM Long, Yun; She, Xueyuan; Mukhopadhyay, Saibal 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE) https://doi.org/10.23919/date.2019.8715178	conference	March 2019
Resist: Robust Network Training for Memristive Crossbar-Based Neuromorphic Computing Systems Bi, Yongtian; Xu, Qi; Geng, Hao IEEE Transactions on Circuits and Systems II: Express Briefs, Vol. 70, Issue 6 https://doi.org/10.1109/tcsii.2023.3236168	journal	June 2023
Bayesian Inference Based Robust Computing on Memristor Crossbar Gao, Di; Huang, Qingrong; Zhang, Grace Li 2021 58th ACM/IEEE Design Automation Conference (DAC) https://doi.org/10.1109/dac18074.2021.9586160	conference	December 2021
BRoCoM: A Bayesian Framework for Robust Computing on Memristor Crossbar Gao, Di; Yang, Zeyu; Huang, Qingrong IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Vol. 42, Issue 7 https://doi.org/10.1109/tcad.2022.3215071	journal	July 2023
A Scalable Design of Multi-Bit Ferroelectric Content Addressable Memory for Data-Centric Computing Li, Chao; Muller, Franz; Ali, Tarek 2020 IEEE International Electron Devices Meeting (IEDM) https://doi.org/10.1109/iedm13553.2020.9372119	conference	December 2020
Statistical Training for Neuromorphic Computing using Memristor-based Crossbars Considering Process Variations and Noise Zhu, Ying; Zhang, Grace Li; Wang, Tianchen 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE) https://doi.org/10.23919/date48585.2020.9116244	conference	March 2020
Variational Inference: A Review for Statisticians Blei, David M.; Kucukelbir, Alp; McAuliffe, Jon D. Journal of the American Statistical Association, Vol. 112, Issue 518 https://doi.org/10.1080/01621459.2017.1285773	journal	July 2016
Reliable FeFET-based Neuromorphic Computing through Joint Modeling of Cycle-to-Cycle Variability, Device-to-Device Variability, and Domain Stochasticity Thomann, Simon; Mema, Albi; Ni, Kai 2023 IEEE International Reliability Physics Symposium (IRPS) https://doi.org/10.1109/irps48203.2023.10117810	conference	March 2023
Fundamental Understanding and Control of Device-to-Device Variation in Deeply Scaled Ferroelectric FETs Ni, Kai; Chakraborty, Wriddhi; Smith, Jeffrey 2019 Symposium on VLSI Technology https://doi.org/10.23919/vlsit.2019.8776497	conference	June 2019
Comprehensive Variability Analysis in Dual-Port FeFET for Reliable Multi-Level-Cell Storage Chatterjee, Swetaki; Thomann, Simon; Ni, Kai IEEE Transactions on Electron Devices, Vol. 69, Issue 9 https://doi.org/10.1109/ted.2022.3192808	journal	September 2022
Impact of Extrinsic Variation Sources on the Device-to-Device Variation in Ferroelectric FET Ni, Kai; Gupta, Aniket; Prakash, Om 2020 IEEE International Reliability Physics Symposium (IRPS) https://doi.org/10.1109/irps45951.2020.9128323	conference	April 2020
Intrinsic synaptic plasticity of ferroelectric field effect transistors for online learning Saha, Arnob; Islam, A. N. M. Nafiul; Zhao, Zijian Applied Physics Letters, Vol. 119, Issue 13 https://doi.org/10.1063/5.0064860	journal	September 2021
Hybrid stochastic synapses enabled by scaled ferroelectric field-effect transistors Islam, A. N. M. Nafiul; Saha, Arnob; Jiang, Zhouhang Applied Physics Letters, Vol. 122, Issue 12 https://doi.org/10.1063/5.0132242	journal	March 2023
Reliability-Driven Neuromorphic Computing Systems Design Xu, Qi; Wang, Junpeng; Geng, Hao 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE) https://doi.org/10.23919/date51398.2021.9473929	conference	February 2021
Gradient-based learning applied to document recognition Lecun, Y.; Bottou, L.; Bengio, Y. Proceedings of the IEEE, Vol. 86, Issue 11 https://doi.org/10.1109/5.726791	journal	January 1998
On Information and Sufficiency Kullback, S.; Leibler, R. A. The Annals of Mathematical Statistics, Vol. 22, Issue 1 https://doi.org/10.1214/aoms/1177729694	journal	March 1951

Similar Records

SwitchX: Gmin-Gmax Switching for Energy-efficient and Robust Implementation of Binarized Neural Networks on ReRAM Xbars

Journal Article · Wed May 17 00:00:00 EDT 2023 · ACM Transactions on Design Automation of Electronic Systems · OSTI ID:2422211

Bhattacharjee, Abhiroop; Panda, Priyadarshini

Scaling Deep Learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

Journal Article · Sat May 05 00:00:00 EDT 2018 · Future Generations Computer Systems · OSTI ID:1617450

Gawande, Nitin A.; Daily, Jeff A.; Siegel, Charles; +2 more

Nonvolatile memory cells from hafnium zirconium oxide ferroelectric tunnel junctions using Nb and NbN electrodes

Journal Article · Mon Mar 04 00:00:00 EST 2024 · Journal of Applied Physics · OSTI ID:2331264

Haglund-Peterson, Jessica; Aronson, Benjamin L.; Jaszewski, Samantha T.; +5 more

Related Subjects

97 MATHEMATICS AND COMPUTING
Bayesian Neural Network (BNN)
device-algorithm co-design
ferroelectric field-effect transistor (FeFET) crossbar
in-memory computing
variation-aware design

Variation-Resilient FeFET-Based In-Memory Computing Leveraging Probabilistic Deep Learning

Citation Formats

References (24)

Similar Records

Related Subjects