A mask-aware Transformer framework for cross-topological thermal prediction in 2.5D chiplet systems

2.5D chiplet heterogeneous integration systems are key for extending Moore's Law and boosting integrated circuit performance. They are widely used in fields such as artificial intelligence training and high-performance computing. However, their dense multi-chip structure creates new and significant thermal management challenges. Current deep learning models based on fixed-grid architectures, such as U-Net, have limited local receptive fields and struggle to explicitly model global, long-range thermal coupling effects across variable topological layouts. To address this, this paper proposes HeatTransUNet, a deep learning framework based on a mask-aware Transformer. The framework combines variable-length sequence modelling with spatial physical field generation, transforming physical heat sources into flexible, discrete-sequence entities. By leveraging global self-attention, the model learns global dependencies among chiplet tokens at the sequence level. A dynamic masking strategy is employed to mathematically isolate irrelevant padding noise. Subsequently, a U-Net spatial decoder utilizes feature smoothing to reconstruct these sequence features, producing high-precision, continuous 2D steady-state temperature fields. HeatTransUNet achieves an average absolute error of 0.028 K on a benchmark dataset of 6000 cases with six distinct topologies, corresponding to only 0.05% of the temperature span across the complete dataset. In few-shot transfer to four target layouts excluded from source-domain pretraining, HeatTransUNet was fine-tuned using 320 pooled target-domain training samples drawn from 100 generated cases per layout, reducing prediction error by approximately 50% compared with training from scratch across five independent target-domain data splits. This study provides a highly adaptable, high-precision, and low-cost electro-thermal co-design solution for modern complex electronic devices during early agile design.

Authors

Institutions

Publication Details

Journal
Case Studies in Thermal Engineering
Published
2026-11-21
DOI
https://doi.org/10.1016/j.csite.2026.108746
Primary Topic
3D IC and TSV technologies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A mask-aware Transformer framework for cross-topological thermal prediction in 2.5D chiplet systems

Ning Xu, Dongfeng Cao, Shiyi Fu, Qingjia Chi et al.
Case Studies in Thermal Engineering
3D IC and TSV technologies
article

A mask-aware Transformer framework for cross-topological thermal prediction in 2.5D chiplet systems

Ning Xu, Dongfeng Cao, Shiyi Fu, Qingjia Chi, Xiaonan Zhang, Fengshuo Liu, Xiaoyu Liang
article en

Abstract

2.5D chiplet heterogeneous integration systems are key for extending Moore's Law and boosting integrated circuit performance. They are widely used in fields such as artificial intelligence training and high-performance computing. However, their dense multi-chip structure creates new and significant thermal management challenges. Current deep learning models based on fixed-grid architectures, such as U-Net, have limited local receptive fields and struggle to explicitly model global, long-range thermal coupling effects across variable topological layouts. To address this, this paper proposes HeatTransUNet, a deep learning framework based on a mask-aware Transformer. The framework combines variable-length sequence modelling with spatial physical field generation, transforming physical heat sources into flexible, discrete-sequence entities. By leveraging global self-attention, the model learns global dependencies among chiplet tokens at the sequence level. A dynamic masking strategy is employed to mathematically isolate irrelevant padding noise. Subsequently, a U-Net spatial decoder utilizes feature smoothing to reconstruct these sequence features, producing high-precision, continuous 2D steady-state temperature fields. HeatTransUNet achieves an average absolute error of 0.028 K on a benchmark dataset of 6000 cases with six distinct topologies, corresponding to only 0.05% of the temperature span across the complete dataset. In few-shot transfer to four target layouts excluded from source-domain pretraining, HeatTransUNet was fine-tuned using 320 pooled target-domain training samples drawn from 100 generated cases per layout, reducing prediction error by approximately 50% compared with training from scratch across five independent target-domain data splits. This study provides a highly adaptable, high-precision, and low-cost electro-thermal co-design solution for modern complex electronic devices during early agile design.

Case Studies in Thermal EngineeringVol. 88
Anhui University (CN), Wuhan University of Technology (CN), Nano Carbon (Poland) (PL), State Key Laboratory of Advanced Technology For Materials Synthesis and Processing (CN)
3D IC and TSV technologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon