Optimization of deep learning-based BSIM-CMG I-V parameter extraction in seconds

Fredo Chavez; Ming-Yen Kao; Chenming Hu; Sourabh Khandelwal

doi:10.1109/RFIT54256.2022.9882451

Optimization of deep learning-based BSIM-CMG I-V parameter extraction in seconds

Fredo Chavez, Ming-Yen Kao, Chenming Hu, Sourabh Khandelwal

School of Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

5 Citations (Scopus)

Abstract

A deep learning-based parameter extraction for industry standard BSIM-CMG compact model is presented in this paper. A Monte-Carlo simulation varying key BSIM-CMG parameters was performed to create the 1 million I-V sweep data for training. A deep Learning model is trained with drain current ID as an input and the BSIM-CMG parameters as the output. The trained neural network was able to successfully model TCAD I-V data. The results show very promising capability of the deep learning-based parameter extraction to develop compact models within seconds with less or comparable error compared to traditional manual parameter extraction.

Original language	English
Title of host publication	2022 IEEE International Symposium on Radio-Frequency Integration Technology (RFIT)
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	124-126
Number of pages	3
ISBN (Electronic)	9781665466493, 9781665466486
ISBN (Print)	9781665466509
DOIs	https://doi.org/10.1109/RFIT54256.2022.9882451
Publication status	Published - 2022
Event	2022 IEEE International Symposium on Radio-Frequency Integration Technology, RFIT 2022 - Busan, Korea, Republic of Duration: 29 Aug 2022 → 31 Aug 2022

Conference

Conference	2022 IEEE International Symposium on Radio-Frequency Integration Technology, RFIT 2022
Country/Territory	Korea, Republic of
City	Busan
Period	29/08/22 → 31/08/22

Keywords

Parameter Extraction
BSIM-CMG
FinFET
deep learning
compact model

Access to Document

10.1109/RFIT54256.2022.9882451

Cite this

@inproceedings{2c14934f0d1e4dba8b370e60ce93a20f,

title = "Optimization of deep learning-based BSIM-CMG I-V parameter extraction in seconds",

abstract = "A deep learning-based parameter extraction for industry standard BSIM-CMG compact model is presented in this paper. A Monte-Carlo simulation varying key BSIM-CMG parameters was performed to create the 1 million I-V sweep data for training. A deep Learning model is trained with drain current ID as an input and the BSIM-CMG parameters as the output. The trained neural network was able to successfully model TCAD I-V data. The results show very promising capability of the deep learning-based parameter extraction to develop compact models within seconds with less or comparable error compared to traditional manual parameter extraction.",

keywords = "Parameter Extraction, BSIM-CMG, FinFET, deep learning, compact model",

author = "Fredo Chavez and Ming-Yen Kao and Chenming Hu and Sourabh Khandelwal",

year = "2022",

doi = "10.1109/RFIT54256.2022.9882451",

language = "English",

isbn = "9781665466509",

pages = "124--126",

booktitle = "2022 IEEE International Symposium on Radio-Frequency Integration Technology (RFIT)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2022 IEEE International Symposium on Radio-Frequency Integration Technology, RFIT 2022 ; Conference date: 29-08-2022 Through 31-08-2022",

}

Chavez, F, Kao, M-Y, Hu, C & Khandelwal, S 2022, Optimization of deep learning-based BSIM-CMG I-V parameter extraction in seconds. in 2022 IEEE International Symposium on Radio-Frequency Integration Technology (RFIT). Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 124-126, 2022 IEEE International Symposium on Radio-Frequency Integration Technology, RFIT 2022, Busan, Korea, Republic of, 29/08/22. https://doi.org/10.1109/RFIT54256.2022.9882451

Optimization of deep learning-based BSIM-CMG I-V parameter extraction in seconds. / Chavez, Fredo; Kao, Ming-Yen; Hu, Chenming et al.
2022 IEEE International Symposium on Radio-Frequency Integration Technology (RFIT). Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2022. p. 124-126.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Optimization of deep learning-based BSIM-CMG I-V parameter extraction in seconds

AU - Chavez, Fredo

AU - Kao, Ming-Yen

AU - Hu, Chenming

AU - Khandelwal, Sourabh

PY - 2022

Y1 - 2022

N2 - A deep learning-based parameter extraction for industry standard BSIM-CMG compact model is presented in this paper. A Monte-Carlo simulation varying key BSIM-CMG parameters was performed to create the 1 million I-V sweep data for training. A deep Learning model is trained with drain current ID as an input and the BSIM-CMG parameters as the output. The trained neural network was able to successfully model TCAD I-V data. The results show very promising capability of the deep learning-based parameter extraction to develop compact models within seconds with less or comparable error compared to traditional manual parameter extraction.

AB - A deep learning-based parameter extraction for industry standard BSIM-CMG compact model is presented in this paper. A Monte-Carlo simulation varying key BSIM-CMG parameters was performed to create the 1 million I-V sweep data for training. A deep Learning model is trained with drain current ID as an input and the BSIM-CMG parameters as the output. The trained neural network was able to successfully model TCAD I-V data. The results show very promising capability of the deep learning-based parameter extraction to develop compact models within seconds with less or comparable error compared to traditional manual parameter extraction.

KW - Parameter Extraction

KW - BSIM-CMG

KW - FinFET

KW - deep learning

KW - compact model

UR - http://www.scopus.com/inward/record.url?scp=85139120197&partnerID=8YFLogxK

U2 - 10.1109/RFIT54256.2022.9882451

DO - 10.1109/RFIT54256.2022.9882451

M3 - Conference proceeding contribution

AN - SCOPUS:85139120197

SN - 9781665466509

SP - 124

EP - 126

BT - 2022 IEEE International Symposium on Radio-Frequency Integration Technology (RFIT)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

T2 - 2022 IEEE International Symposium on Radio-Frequency Integration Technology, RFIT 2022

Y2 - 29 August 2022 through 31 August 2022

ER -

Optimization of deep learning-based BSIM-CMG I-V parameter extraction in seconds

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this