Neuromorphic Computing with Fe-FinFETs in the Presence of Variation

De, Sourav; Baig, Md. Aftab; Qiu, Bo-Han; Le, Hoang‐Hiep; Lee, Yao-Jen; Lu, Darsen D.

doi:10.1109/vlsi-tsa54299.2022.9771015

Cited by 19 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CMOS compatibility and the low process temperature of hafnium zirconium oxide (HZO) make HZO-based ferroelectric (Fe) finFETs an excellent candidate for logic, memory, and neuromorphic devices. This property can be attributed to its superior endurance and write speed compared to flash, significantly higher on-to-off current ratio than that of MRAM, as well as the negligible impact of random telegraphic noise from charge-based operation, unlike RRAM [30][31][32][33][34][35][36][37]. However, the pivotal issue lies in the increasing stochasticity with scaling and the inherent charge-trapping sites that can capture electrons or holes from the channel side (CS) or the gate side (GS).…”

Section: Ferroelectricity In Hafnium Oxidementioning

confidence: 99%

Monolithic-3D Inference Engine with IGZO Based Ferroelectric Thin Film Transistor Synapses

De¹,

Lederer²,

Raffel³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

<p> Instigated by the plethora of data generated by edge devices and IoT devices, machine learning has become the de facto choice of everyone for solving many tasks. Applications such as intelligent healthcare monitoring systems, smart watches, or automatic cars require real-time processing of the data or image, which is done by machine learning algorithms with higher efficiency than humans. There are two possible methods for artificial intelligence?1. non-von-Neumann hardware-based implementation of neural networks 2. traditional computer science based approach for neural networks or traditional von-Neumann architecture?based implementation of neural networks The standard von-Neumann performance of neural networks, where the memory and computation parts are segregated, suffers from severe latency with increasing number of edge devices. However, the multitude of edge devices used in our daily life imposes strict restrictions on latency, device area, and power consumption for hardware. Therefore, we need to take the route beyond the CMOS-based mixed-signal implementation of neural networks, where the memory bandwidth is not limited by the quintessential von-Neumann archi?tecture. The primary motivation of present-day research on the non-von-Neumann computing architecture is to build dedicated hardware modules for implementing low-power, fast-computing units without affecting the recent trend of scaling. This chapter focuses on amorphous indium-gallium-zinc-oxide (α-IGZO) based and their system-level applications. Back-end-of-line (BEoL) compatible indium IGZO based multibit one-time programmable (OTP) ferroelectric thin film transistors (FeTFT) with lifelong retention capability were fabricated. The maximum temperature of the entire fabrication process was limited to 350oC. The gate-stack engineering by varying the thickness ratio of ferroelectric hafnium zirconium oxide (HZO) and IGZO layer fomented excellent data-retention capability and one time programming property. Further, we have evaluated the performance of IGZO-based FeTFT as synaptic devices for an inference engine. The system-level simulation revealed inference accuracy loss of only 1.5% after ten years without re-training for Modified National Institute of Standards and Technology (MNIST) hand-written digits in a multi-layer perceptron (MLP) neural network with a baseline of 97%. The proposed inference engine also showed superior energy efficiency and cell area of 95.33 TOPS/W (binary) and 8F2 , respectively. </p>

show abstract

Section: Ferroelectricity In Hafnium Oxidementioning

confidence: 99%

Monolithic-3D Inference Engine with IGZO Based Ferroelectric Thin Film Transistor Synapses

De¹,

Lederer²,

Raffel³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Among many emerging memory technologies like resistive random access memory (ReRAM) − and phase change memory (PCM), − ferroelectric field effect transistors (FeFETs) seem to be the most promising ones. The pronunciation of ferroelectricity in a single-layer thin film of hafnium oxide (HfO 2 ), fast switching, high on-current ( I ON ) to off-current ( I OFF ) ratio ( I O N I O F F ) , excellent linearity in synaptic weight updates, bidirectional operation, and good endurance are the key technological factors that make FeFET superior to other methods. ,− ,, However, the primary bottleneck in implementing the FeFET-based computing system lies in the intrinsic stochasticity owing to the polycrystalline nature of HfO 2 -based ferroelectric thin film, as well as inherent defect sites that may capture electrons or holes from the channel side (CS) or gate side (GS). − Numerous efforts have been made to reduce the impacts of such nonidealities from the device process, and a circuit point of view. − ,, Previously, it has been reported how the quality of the interface and the READ -Voltage play a pivotal role in the performance of FeFETs, especially for low-frequency noise response, retention, and endurance. ,,,,− In this work, we aim to maximize the reliability and performance of FeFETs by adopting a synergistic approach of READ -voltage optimization and interfacial-layer engineering.…”

Section: Introductionmentioning

confidence: 99%

Synergistic Approach of Interfacial Layer Engineering and READ-Voltage Optimization in HfO₂-Based FeFETs for In-Memory-Computing Applications

Raffel

Lederer

et al. 2022

ACS Appl. Electron. Mater.

Self Cite

View full text Add to dashboard Cite

This article reports an improvement in the performance of the hafnium oxide-based (HfO2) ferroelectric field-effect transistors (FeFET) achieved by a synergistic approach of interfacial layer (IL) engineering and READ-voltage optimization. FeFET devices with silicon dioxide (SiO2) and silicon oxynitride (SiON) as IL were fabricated and characterized. Although the FeFETs with SiO2 interfaces demonstrated better low-frequency characteristics compared to the FeFETs with SiON interfaces, the latter demonstrated better WRITE endurance and retention. Finally, the neuromorphic simulation was conducted to evaluate the performance of FeFETs with SiO2 and SiON IL as synaptic devices. We observed that the WRITE endurance in both types of FeFETs was insufficient ( < 10 8 ) to carry out online neural network training. Therefore, we consider an inference-only operation with offline neural network training. The system-level simulation reveals that the impact of systematic degradation via retention degradation is much more significant for inference-only operation than low-frequency noise. The neural network with FeFETs based on SiON IL in the synaptic core shows 96% accuracy for the inference operation on the handwritten digit from the Modified National Institute of Standards and Technology (MNIST) data set in the presence of flicker noise and retention degradation, which is only a 2.5% deviation from the software baseline.

show abstract

“…ECENT progress in researching hafnium oxide (HfO2) based ferroelectric (Fe) materials has manifested its potential as emerging non-volatile memories. The compatibility of the FeFET process with the CMOS process and the demonstration of 28nm HKMG FeFET [1][2][3][4], ferroelectric finfield effect transistors (Fe-finFET) [5,6], and ferroelectric thin film transistors (Fe-TFT) [7,8] have paved the way for highdensity FeFET based memory array. Amidst many developments, the device-to-device in the drain current (∆Id D2D ) of the FeFETs, especially in the low-threshold voltage (LVT) state, creates a significant bottleneck in the wafer-scale operation of the FeFET-based memory array [9][10][11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Demonstration of Multiply-Accumulate Operation With 28 nm FeFET Crossbar Array

Müller

Laleni

et al. 2022

IEEE Electron Device Lett.

View full text Add to dashboard Cite

Neuromorphic Computing with Fe-FinFETs in the Presence of Variation

Cited by 19 publications

References 7 publications

Monolithic-3D Inference Engine with IGZO Based Ferroelectric Thin Film Transistor Synapses

Monolithic-3D Inference Engine with IGZO Based Ferroelectric Thin Film Transistor Synapses

Synergistic Approach of Interfacial Layer Engineering and READ-Voltage Optimization in HfO₂-Based FeFETs for In-Memory-Computing Applications

Demonstration of Multiply-Accumulate Operation With 28 nm FeFET Crossbar Array

Contact Info

Product

Resources

About

Neuromorphic Computing with Fe-FinFETs in the Presence of Variation

Cited by 19 publications

References 7 publications

Monolithic-3D Inference Engine with IGZO Based Ferroelectric Thin Film Transistor Synapses

Monolithic-3D Inference Engine with IGZO Based Ferroelectric Thin Film Transistor Synapses

Synergistic Approach of Interfacial Layer Engineering and READ-Voltage Optimization in HfO2-Based FeFETs for In-Memory-Computing Applications

Demonstration of Multiply-Accumulate Operation With 28 nm FeFET Crossbar Array

Contact Info

Product

Resources

About

Synergistic Approach of Interfacial Layer Engineering and READ-Voltage Optimization in HfO₂-Based FeFETs for In-Memory-Computing Applications