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.

翻译：三维集成电路中日益增加的功率密度使得热管理愈发具有挑战性。传统的基于偏微分方程求解的方法虽然精确，但迭代设计过程过于缓慢。像傅里叶神经算子这样的机器学习方法提供了更快的替代方案，但存在高频信息丢失和高保真数据依赖性强的问题。我们提出了自注意力U-Net傅里叶神经算子，这是一种新颖的框架，它将自注意力机制和U-Net结构与傅里叶神经算子相结合，以有效捕获长程依赖关系并建模局部高频特征。我们采用迁移学习对低保真数据进行微调，从而最大限度地减少对大量高保真数据集的需求并加速训练。实验表明，SAU-FNO在热预测精度上达到了最先进的水平，并且相比传统的有限元方法实现了842倍的加速，使其成为先进三维集成电路热仿真的高效工具。