Self-Attention to Operator Learning-based 3D-IC Thermal Simulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917023622103040 |
|---|---|
| author | Huang, Zhen Wang, Hong Yang, Wenkai Tang, Muxi Xie, Depeng Lin, Ting-Jung Zhang, Yu Xing, Wei W. He, Lei |
| author_facet | Huang, Zhen Wang, Hong Yang, Wenkai Tang, Muxi Xie, Depeng Lin, Ting-Jung Zhang, Yu Xing, Wei W. He, Lei |
| contents | Thermal management in 3D ICs is increasingly challenging due to higher power densities. Traditional PDE-solving-based methods, while accurate, are too slow for iterative design. Machine learning approaches like FNO provide faster alternatives but suffer from high-frequency information loss and high-fidelity data dependency. We introduce Self-Attention U-Net Fourier Neural Operator (SAU-FNO), a novel framework combining self-attention and U-Net with FNO to capture long-range dependencies and model local high-frequency features effectively. Transfer learning is employed to fine-tune low-fidelity data, minimizing the need for extensive high-fidelity datasets and speeding up training. Experiments demonstrate that SAU-FNO achieves state-of-the-art thermal prediction accuracy and provides an 842x speedup over traditional FEM methods, making it an efficient tool for advanced 3D IC thermal simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15968 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Attention to Operator Learning-based 3D-IC Thermal Simulation Huang, Zhen Wang, Hong Yang, Wenkai Tang, Muxi Xie, Depeng Lin, Ting-Jung Zhang, Yu Xing, Wei W. He, Lei Machine Learning Artificial Intelligence Hardware Architecture Thermal management in 3D ICs is increasingly challenging due to higher power densities. Traditional PDE-solving-based methods, while accurate, are too slow for iterative design. Machine learning approaches like FNO provide faster alternatives but suffer from high-frequency information loss and high-fidelity data dependency. We introduce Self-Attention U-Net Fourier Neural Operator (SAU-FNO), a novel framework combining self-attention and U-Net with FNO to capture long-range dependencies and model local high-frequency features effectively. Transfer learning is employed to fine-tune low-fidelity data, minimizing the need for extensive high-fidelity datasets and speeding up training. Experiments demonstrate that SAU-FNO achieves state-of-the-art thermal prediction accuracy and provides an 842x speedup over traditional FEM methods, making it an efficient tool for advanced 3D IC thermal simulations. |
| title | Self-Attention to Operator Learning-based 3D-IC Thermal Simulation |
| topic | Machine Learning Artificial Intelligence Hardware Architecture |
| url | https://arxiv.org/abs/2510.15968 |