Real-Time TCAD: a new paradigm for TCAD in the artificial intelligence era

被引：0

作者：

Myung, Sanghoon ^{[1
]}

Kim, Jinwoo ^{[1
]}

Jeon, Yongwoo ^{[1
]}

Jang, Wonik ^{[1
]}

Huh, In ^{[1
]}

Kim, Jaemin ^{[1
]}

Han, Songyi ^{[1
]}

Baek, Kang-hyun ^{[1
]}

Ryu, Jisu ^{[1
]}

Kim, Yoon-Suk ^{[1
]}

Doh, Jiseong ^{[1
]}

Kim, Jae-ho ^{[1
]}

Jeong, Changwook ^{[1
]}

Kim, Dae Sin ^{[1
]}

机构：

[1] Samsung Elect Co Ltd, Data & Informat Technol Ctr, Device Solut Business, Computat Sci & Engn Team, Gyeonggi Do 18448, South Korea

来源：

2020 INTERNATIONAL CONFERENCE ON SIMULATION OF SEMICONDUCTOR PROCESSES AND DEVICES (SISPAD 2020) | 2020年

关键词：

TCAD; neural network (NN); convolutional neural network (CNN); recurrent neural network (RNN); Real-time prediction; Real-time optimization; active learning;

D O I：

10.23919/sispad49475.2020.9241622

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper presents a novel approach to enable real-time device simulation and optimization. State-of-the-art algorithms which can describe semiconductor domain are adopted to train deep learning models whose input and output are process condition and doping profile / electrical characteristic, respectively. Our framework enables to update automatically deep learning models by estimating the uncertainty of the model prediction. Our Real-Time TCAD framework is validated on 130nm processes for display driver integration circuit (DDI), and 1) prediction time was 530,000 times faster than conventional TCAD, and time spent for process optimization was reduced by 300,000 times compared to human expert, 2) the model achieved average accuracy of 99% compared to TCAD simulation results, and thus, 3) process development time for DDI was reduced by 8 weeks.

引用

页码：347 / 350

页数：4

共 17 条

[1] Ba Jimmy Lei, 2016, LAYER NORMALIZATION, V1050, P21, DOI 10.48550/arXiv.1607.06450
[2] Bartolini A, 2009, DES AUT TEST EUROPE, P1428
[3] Machine Learning Approach for Predicting the Effect of Statistical Variability in Si Junctionless Nanowire Transistors
Carrillo-Nunez, Hamilton
Dimitrova, Nadezhda
Asenov, Asen
Georgiev, Vihar
[J]. IEEE ELECTRON DEVICE LETTERS, 2019, 40 (09) : 1366 - 1369
[4] Powernet: SOI Lateral Power Device Breakdown Prediction With Deep Neural Networks
Chen, Jing
Alawieh, Mohamed Baker
Lin, Yibo
Zhang, Maolin
Zhang, Jun
Guo, Yufeng
Pan, David Z.
[J]. IEEE ACCESS, 2020, 8 (08): : 25372 - 25382
[5] DESIGN OF ION-IMPLANTED MOSFETS WITH VERY SMALL PHYSICAL DIMENSIONS
DENNARD, RH
GAENSSLEN, FH
YU, HN
RIDEOUT, VL
BASSOUS, E
LEBLANC, AR
[J]. IEEE JOURNAL OF SOLID-STATE CIRCUITS, 1974, SC 9 (05) : 256 - 268
[6] Deep Residual Learning for Image Recognition
He, Kaiming
Zhang, Xiangyu
Ren, Shaoqing
Sun, Jian
[J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 770 - 778
[7] Ioffe S, 2015, PR MACH LEARN RES, V37, P448
[8] Lakshminarayanan B, 2017, ADV NEUR IN, V30
[9] Liu R, 2018, ADV NEUR IN, V31
[10] NIX DA, 1994, 1994 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOL 1-7, P55, DOI 10.1109/ICNN.1994.374138

← 1 2 →