EUVIMEDScopri EUVIMED
Open access · CC BY 4.0

ResNet Modeling for 12 nm FinFET Devices to Enhance DTCO Efficiency

Yiming Huang, Bin Li, Zhaohui Wu, Wenchao Liu

Electronics · 2024-10-14 · 13 (20) · 4040

DOI: 10.3390/electronics13204040 ↗

At a glance

Journal article in Electronics, published online on 2024-10-14. Written by Yiming Huang and 3 co-authors. Cited 8 times so far (Crossref); 23 references. The full text is freely available (open access, CC BY 4.0). Funded by: Guangdong S&T Programme, China.

AbstractDati bibliograficiCiteRelated studies

Abstract (original language)

In this paper, a deep learning-based device modeling framework for design-technology co-optimization (DTCO) is proposed. A ResNet surrogate model is utilized as an alternative to traditional compact models, demonstrating high accuracy in both single-task (I–V or C–V) and multi-task (I–V and C–V) device modeling. Moreover, transfer learning is applied to the ResNet model, using the BSIM-CMG compact model for a 12 nm FinFET SPICE model as the pre-trained source. Through this approach, superior modeling accuracy and faster training speed are achieved compared to a ResNet surrogate model initialized with random weights, thereby meeting the rapid and efficient demands of the DTCO process. The effectiveness of the ResNet surrogate model in circuit simulation for 12 nm FinFET devices is demonstrated.

Funding

  • Guangdong S&T Programme, China

Cite

APA

Huang, Y., Li, B., Wu, Z., & Liu, W. (2024). ResNet Modeling for 12 nm FinFET Devices to Enhance DTCO Efficiency. Electronics, 13(20), 4040. https://doi.org/10.3390/electronics13204040

Vancouver

Huang Y, Li B, Wu Z, Liu W. ResNet Modeling for 12 nm FinFET Devices to Enhance DTCO Efficiency. Electronics. 2024;13(20):4040. doi:10.3390/electronics13204040

BibTeX
@article{Huang2024,
  author = {Huang, Yiming and Li, Bin and Wu, Zhaohui and Liu, Wenchao},
  title = {ResNet Modeling for 12 nm FinFET Devices to Enhance DTCO Efficiency},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {20},
  pages = {4040},
  doi = {10.3390/electronics13204040}
}
Start for free →