Abstract
We propose to use a 3D convolutional neural network to accelerate three-dimensional device simulation by generating an electrostatic potential profile. In the training phase, the deep neural network is trained with the simulation results for various 3D MOSFETs in a supervised manner. The generated potential profile is used as an initial guess at a non-equilibrium condition, while carrier densities are estimated by the frozen field simulation. By numerical examples for three-dimensional MOSFETs, we show that the proposed method significantly reduces the number of the Newton iterations.
Original language | English |
---|---|
Title of host publication | SISPAD 2021 - 2021 International Conference on Simulation of Semiconductor Processes and Devices, Proceedings |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 52-55 |
Number of pages | 4 |
ISBN (Electronic) | 9781665406857 |
DOIs | |
Publication status | Published - 2021 Sep 27 |
Event | 26th International Conference on Simulation of Semiconductor Processes and Devices, SISPAD 2021 - Dallas, United States Duration: 2021 Sep 27 → 2021 Sep 29 |
Publication series
Name | International Conference on Simulation of Semiconductor Processes and Devices, SISPAD |
---|---|
Volume | 2021-September |
Conference
Conference | 26th International Conference on Simulation of Semiconductor Processes and Devices, SISPAD 2021 |
---|---|
Country/Territory | United States |
City | Dallas |
Period | 21/9/27 → 21/9/29 |
Bibliographical note
Funding Information:ACKNOWLEDGEMENT This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (NRF-2019R1A2C1086656 and NRF-2020M3H4A3081800). This work was also supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIT) (No.2019-0-01351, Development of Ultra Low-Power Mobile Deep Learning Semiconductor with Compression/Decompression of Activation/Kernel Data, 30 %)
Publisher Copyright:
© 2021 IEEE.
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering
- Computer Science Applications
- Modelling and Simulation