A single neural network global I-V and C-V parameter extractor for BSIM-CMG compact model.

• A single neural network parameter extractor for BSIM-CMG IV and CV model is developed. • A global I-V and C-V parameter extraction for a large range of gate length is achieved. • A high fitting accuracy is demonstrated on TCAD simulated data calibrated to 10 nm node. A global I-V and C-V BSIM-CMG parameter extraction methodology based on deep learning is proposed. 100 k training datasets were generated through Monte Carlo simulation varying 28 IV and CV model parameters in the industry-standard BSIM-CMG FinFET model. For each of the 100 k Monte Carlo-selected BSIM-CMG parameter dataset, the I D -V G and C GG -V G characteristics of seven Monte Carlo-selected gate lengths ranging from 14 nm to 110 nm were generated as the input to train the parameter extraction neural network. The neural network outputs for training are the 28 model parameters' values. The neural network's capability to extract BSIM-CMG model parameters that accurately fit TCAD-generated I D -V G and C GG -V G data over a range of gate lengths was demonstrated. This marks the first time a deep learning compact model parameter extraction flow, employing a single neural network for both I-V and C-V parameters and for a range of gate length, is presented. [ABSTRACT FROM AUTHOR]