Self-Attention to Operator Learning-based 3D-IC Thermal Simulation
Quick summary
arXiv:2510.15968v2 Announce Type: replace-cross 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 effectivel
Key takeaways
- arXiv:2510.15968v2 Announce Type: replace-cross 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.
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments