Large-Scale Training in Neural Compact Models for Accurate and Adaptable MOSFET Simulation

We address the challenges associated with traditional analytical models, such as BSIM, in semiconductor device modeling. These models often face limitations in accurately representing the complex behaviors of miniaturized devices. As an alternative, Neural Compact Models (NCMs) offer improved modeli...

Full description

Saved in:
Bibliographic Details
Main Authors: Chanwoo Park, Seungjun Lee, Junghwan Park, Kyungjin Rim, Jihun Park, Seonggook Cho, Jongwook Jeon, Hyunbo Cho
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of the Electron Devices Society
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10566861/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261751433527296
author Chanwoo Park
Seungjun Lee
Junghwan Park
Kyungjin Rim
Jihun Park
Seonggook Cho
Jongwook Jeon
Hyunbo Cho
author_facet Chanwoo Park
Seungjun Lee
Junghwan Park
Kyungjin Rim
Jihun Park
Seonggook Cho
Jongwook Jeon
Hyunbo Cho
author_sort Chanwoo Park
collection DOAJ
description We address the challenges associated with traditional analytical models, such as BSIM, in semiconductor device modeling. These models often face limitations in accurately representing the complex behaviors of miniaturized devices. As an alternative, Neural Compact Models (NCMs) offer improved modeling capabilities, but their effectiveness is constrained by a reliance on extensive datasets for accurate performance. In real-world scenarios, where measurements for device modeling are often limited, this dependence becomes a significant hindrance. In response, this work presents a large-scale pre-training approach for NCMs. By utilizing extensive datasets across various technology nodes, our method enables NCMs to develop a more detailed understanding of device behavior, thereby enhancing the accuracy and adaptability of MOSFET device simulations, particularly when data availability is limited. Our study illustrates the potential benefits of large-scale pre-training in enhancing the capabilities of NCMs, offering a practical solution to one of the key challenges in current device modeling practices.
format Article
id doaj-art-41bd7e5386234739aa8ec28dc5eec43f
institution OA Journals
issn 2168-6734
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of the Electron Devices Society
spelling doaj-art-41bd7e5386234739aa8ec28dc5eec43f2025-08-20T01:55:19ZengIEEEIEEE Journal of the Electron Devices Society2168-67342024-01-011274575110.1109/JEDS.2024.341752110566861Large-Scale Training in Neural Compact Models for Accurate and Adaptable MOSFET SimulationChanwoo Park0https://orcid.org/0000-0001-7321-0269Seungjun Lee1https://orcid.org/0009-0001-4314-0260Junghwan Park2https://orcid.org/0009-0004-4602-9877Kyungjin Rim3Jihun Park4Seonggook Cho5Jongwook Jeon6https://orcid.org/0000-0002-5232-650XHyunbo Cho7https://orcid.org/0009-0006-0425-5301Research and Development Center, Alsemy Inc., Seoul, South KoreaResearch and Development Center, Alsemy Inc., Seoul, South KoreaResearch and Development Center, Alsemy Inc., Seoul, South KoreaResearch and Development Center, Alsemy Inc., Seoul, South KoreaResearch and Development Center, Alsemy Inc., Seoul, South KoreaResearch and Development Center, Alsemy Inc., Seoul, South KoreaSchool of Electronic and Electrical Engineering, Sungkyunkwan University, Suwon-si, South KoreaResearch and Development Center, Alsemy Inc., Seoul, South KoreaWe address the challenges associated with traditional analytical models, such as BSIM, in semiconductor device modeling. These models often face limitations in accurately representing the complex behaviors of miniaturized devices. As an alternative, Neural Compact Models (NCMs) offer improved modeling capabilities, but their effectiveness is constrained by a reliance on extensive datasets for accurate performance. In real-world scenarios, where measurements for device modeling are often limited, this dependence becomes a significant hindrance. In response, this work presents a large-scale pre-training approach for NCMs. By utilizing extensive datasets across various technology nodes, our method enables NCMs to develop a more detailed understanding of device behavior, thereby enhancing the accuracy and adaptability of MOSFET device simulations, particularly when data availability is limited. Our study illustrates the potential benefits of large-scale pre-training in enhancing the capabilities of NCMs, offering a practical solution to one of the key challenges in current device modeling practices.https://ieeexplore.ieee.org/document/10566861/Compact modelDTCOfoundation modelMOSFETneural network
spellingShingle Chanwoo Park
Seungjun Lee
Junghwan Park
Kyungjin Rim
Jihun Park
Seonggook Cho
Jongwook Jeon
Hyunbo Cho
Large-Scale Training in Neural Compact Models for Accurate and Adaptable MOSFET Simulation
IEEE Journal of the Electron Devices Society
Compact model
DTCO
foundation model
MOSFET
neural network
title Large-Scale Training in Neural Compact Models for Accurate and Adaptable MOSFET Simulation
title_full Large-Scale Training in Neural Compact Models for Accurate and Adaptable MOSFET Simulation
title_fullStr Large-Scale Training in Neural Compact Models for Accurate and Adaptable MOSFET Simulation
title_full_unstemmed Large-Scale Training in Neural Compact Models for Accurate and Adaptable MOSFET Simulation
title_short Large-Scale Training in Neural Compact Models for Accurate and Adaptable MOSFET Simulation
title_sort large scale training in neural compact models for accurate and adaptable mosfet simulation
topic Compact model
DTCO
foundation model
MOSFET
neural network
url https://ieeexplore.ieee.org/document/10566861/
work_keys_str_mv AT chanwoopark largescaletraininginneuralcompactmodelsforaccurateandadaptablemosfetsimulation
AT seungjunlee largescaletraininginneuralcompactmodelsforaccurateandadaptablemosfetsimulation
AT junghwanpark largescaletraininginneuralcompactmodelsforaccurateandadaptablemosfetsimulation
AT kyungjinrim largescaletraininginneuralcompactmodelsforaccurateandadaptablemosfetsimulation
AT jihunpark largescaletraininginneuralcompactmodelsforaccurateandadaptablemosfetsimulation
AT seonggookcho largescaletraininginneuralcompactmodelsforaccurateandadaptablemosfetsimulation
AT jongwookjeon largescaletraininginneuralcompactmodelsforaccurateandadaptablemosfetsimulation
AT hyunbocho largescaletraininginneuralcompactmodelsforaccurateandadaptablemosfetsimulation