Saved in:
Bibliographic Details
Main Authors: Huang, Zhen, Xin, Haiyang, Yang, Wenkai, Wei, Yangbo, Yu, Zhiping, Zhang, Yu, Xing, Wei W., Lin, Ting-Jung, He, Lei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.22663
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910255527493632
author Huang, Zhen
Xin, Haiyang
Yang, Wenkai
Wei, Yangbo
Yu, Zhiping
Zhang, Yu
Xing, Wei W.
Lin, Ting-Jung
He, Lei
author_facet Huang, Zhen
Xin, Haiyang
Yang, Wenkai
Wei, Yangbo
Yu, Zhiping
Zhang, Yu
Xing, Wei W.
Lin, Ting-Jung
He, Lei
contents Data-driven thermal predictors for 3D-ICs are often trained from scratch for each chip design using many high-fidelity finite-element simulations, leading to high data-generation cost and costly cross-design reuse. We propose Therm-FM, a neural operator framework that adapts a pretrained partial differential equation (PDE) foundation model to steady-state and transient 3D-IC thermal simulation. The motivation is that steady-state and transient chip-level heat conduction respectively share elliptic and parabolic operator structures with diffusion-type PDEs, allowing pretrained diffusion priors to provide an effective initialization for thermal-field prediction under heterogeneous materials, dense TSV/microbump interconnects, and package-level boundary conditions. To further reduce data-generation cost, Therm-FM incorporates a thermal-equivalent multi-fidelity training strategy that uses low-cost approximate simulations for thermal-domain adaptation and limited high-fidelity samples for calibration. Experiments on public HotSpot benchmarks and industrial 3D-IC package benchmarks show that Therm-FM achieves up to a 10.6x reduction in mean error and surpasses prior best accuracy with less than 20% of the training data. In cross-chip adaptation, it matches or surpasses full-data baselines in several metrics using only 10--30 target samples. We release datasets, source code, and pretrained models at https://github.com/haiyangxin/Therm-FM.
format Preprint
id arxiv_https___arxiv_org_abs_2605_22663
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Therm-FM: Foundation Model is ALL YOU NEED for 3D-ICs Thermal Simulation
Huang, Zhen
Xin, Haiyang
Yang, Wenkai
Wei, Yangbo
Yu, Zhiping
Zhang, Yu
Xing, Wei W.
Lin, Ting-Jung
He, Lei
Computational Engineering, Finance, and Science
Data-driven thermal predictors for 3D-ICs are often trained from scratch for each chip design using many high-fidelity finite-element simulations, leading to high data-generation cost and costly cross-design reuse. We propose Therm-FM, a neural operator framework that adapts a pretrained partial differential equation (PDE) foundation model to steady-state and transient 3D-IC thermal simulation. The motivation is that steady-state and transient chip-level heat conduction respectively share elliptic and parabolic operator structures with diffusion-type PDEs, allowing pretrained diffusion priors to provide an effective initialization for thermal-field prediction under heterogeneous materials, dense TSV/microbump interconnects, and package-level boundary conditions. To further reduce data-generation cost, Therm-FM incorporates a thermal-equivalent multi-fidelity training strategy that uses low-cost approximate simulations for thermal-domain adaptation and limited high-fidelity samples for calibration. Experiments on public HotSpot benchmarks and industrial 3D-IC package benchmarks show that Therm-FM achieves up to a 10.6x reduction in mean error and surpasses prior best accuracy with less than 20% of the training data. In cross-chip adaptation, it matches or surpasses full-data baselines in several metrics using only 10--30 target samples. We release datasets, source code, and pretrained models at https://github.com/haiyangxin/Therm-FM.
title Therm-FM: Foundation Model is ALL YOU NEED for 3D-ICs Thermal Simulation
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2605.22663