Indexed by: Journal paper

First Author: Ruihan Li

Correspondence Author: Xingsheng Wang

Co-author: Haowen Luo,Yichen Wang,Zhengwu Yuan,Asen Asenov,Xiangshui Miao

Journal: Semiconductor Science and Technology

Included Journals: SCI、EI

Affiliation of Author(s): Huazhong University of Science and Technology

Discipline: Engineering

First-Level Discipline: Electronic Science And Technology

Document Type: J

Volume: 37

Issue: 9

Page Number: 095010

ISSN No.: 0268-1242

Key Words: 5 nm nanosheet transistor, compact model extraction, statistical variability, artificial neural network, SRAM

DOI number: 10.1088/1361-6641/ac836d

Date of Publication: 2022-08-02

Impact Factor: 2.66

Abstract: In this paper, we look at how artificial neural networks (ANNs) may be used to improve compact model extraction of statistical variability in 5-nm nanosheet transistors (NSTs) and how it can be applied to 6NST-SRAM simulations. To begin, both the TCAD simulation platform and compact model of 3D n-type and p-type NST have been rigorously validated against the experimental data. The transfer characteristics curves of 1104 NST samples generated by metal gate granularity (MGG), random discrete dopants (RDD) and line edge roughness (LER) are used to extract the important figures of merit (FoM) including ON-current (ION), OFF-current (IOFF), threshold voltage (VTH) and subthreshold slope (SS). Meanwhile, we can collect the main compact model parameters of these NST samples using our automatic extraction technique. Furthermore, a multi-layer artificial neural network (ANN) engine is trained to anticipate the important compact model parameters by entering FoMs, which significantly speeds up the automatic extraction. When we compare the prediction results to the genuine values, we discover that their correlation coefficients are all larger than 0.99. Finally, we simulated the 6NST-SRAM circuit and obtained its stability variation, with the help of extracted NST variability by the aforementioned speedup techniques.