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

Zhen Huang, Hong Wang, Wenkai Yang, Muxi Tang, Depeng Xie, Ting Jung Lin, Yu Zhang, Wei W. Xing, Lei He

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

Abstract

Thermal management in 3D ICs is increasingly challenging due to higher power densities. Traditional PDESolving 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 UNet Fourier Neural Operator (SAU-FNO), a novel framework combining self-attention and U-Net with FNO to capture longrange 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 SAUFNO achieves state-of-the-art thermal prediction accuracy and provides an 842 × speedup over traditional FEM methods, making it an efficient tool for advanced 3D IC thermal simulations.

Original languageEnglish
Title of host publication2025 62nd ACM/IEEE Design Automation Conference, DAC 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331503048
DOIs
Publication statusPublished - 2025
Externally publishedYes
Event62nd ACM/IEEE Design Automation Conference, DAC 2025 - San Francisco, United States
Duration: 22 Jun 202525 Jun 2025

Publication series

NameProceedings - Design Automation Conference
ISSN (Print)0738-100X

Conference

Conference62nd ACM/IEEE Design Automation Conference, DAC 2025
Country/TerritoryUnited States
CitySan Francisco
Period22/06/2525/06/25

Keywords

  • Fourier Neural Operator
  • Self-Attention
  • Thermal modeling
  • Transfer Learning

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'Self-Attention to Operator Learning-based 3D-IC Thermal Simulation'. Together they form a unique fingerprint.

Cite this