Self-Attention to Operator Learning-based 3D-IC Thermal Simulation

By Zhen Huang ^1,2, Hong Wang ¹, Wenkai Yang ^3,5, Muxi Tang ⁴, Depeng Xie ⁵, Ting-Jung Lin ², Yu Zhang ¹, Wei W. Xing ⁶, Lei He ^2,7
1 School of Computer Science and Technology, University of Science and Technology of China, Hefei, China
² Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China
³ ShanghaiTech University, Shanghai, China 4 Tsinghua University, Beijing, China
⁵ BTDTechnology, Ningbo, China 6 University of Sheffield, Sheffield, UK
⁷ University of California, Los Angeles, USA

Abstract

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.

To read the full article, click here