TherMapNet Attention-Guided Runtime Full-Chip Thermal Map Prediction from Performance Metrics

Qin Gu; Chaofang Ma; Mingyu Yang; Yipu Zhang; Jiliang Zhang; Wei Zhang; Lin Jiang

cs.ARAug 22, 2026

TherMapNet Attention-Guided Runtime Full-Chip Thermal Map Prediction from Performance Metrics

Authors: Qin Gu, Chaofang Ma, Mingyu Yang, Yipu Zhang, Jiliang Zhang, Wei Zhang, Lin Jiang

Organizations: College of Information Science and Engineering, Northeastern University, Shenyang, China · Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong

Abstract

Runtime thermal management of high-performance chips depends on fast and accurate full-chip thermal maps. Conventional simulators typically estimate power traces from performance metrics first, which adds overhead. This work proposes TherMapNet, an attention-guided thermal simulator that predicts full-chip thermal maps directly from performance metrics. A Transformer encoder captures temporal evolution by treating the time series of each metric as a token, improving modeling of dynamic workloads. A CNN then extracts fine-grained spatial features. For the CNN, a dual-branch channel-spatial attention convolution module (DACM) and a triplet loss are used to improve spatial learning and reconstruction accuracy. TherMapNet is applied to a multi-core CPU (AMD Ryzen 7 4800U) and a many-core GPU (NVIDIA GeForce RTX 4060). Experiments show that it outperforms prior thermal simulators, with RMSE below 0.26 C and inference under 2.4 ms on an NVIDIA GeForce RTX 3090 GPU. These results indicate that TherMapNet can support high-quality runtime thermal management of modern multi-core chips.

Explore similar work

WarPGNN: A Parametric Thermal Warpage Analysis Framework with Physics-aware Graph Neural Network
Mar 19, 2026Haotian Lu, Jincong Lu, Sachin Sachdeva +1Graph Neural Networks Physics-Informed ML
Department of Electrical and Computer Engineering · University of California, Riverside · Riverside, CA, USA
Active Imitation Learning for Thermal- and Kernel-Aware LFM Inference on 3D S-NUCA Many-Cores
Apr 13, 2026Yixian Shen, Chaoyao Shen, Jan Deen +3LLM Inference Scheduling Imitation Learning
University of Amsterdam, Netherlands · Southeast University, China · University of Thessaly, Greece
ThRIve: Thermally Robust CNN Inference via Low-Rank Adaptation in Heterogeneous PIM Architectures
Jul 19, 2026Vibhanshu Sharma, Pratyush Dhingra, Janardhan Rao Doppa +1Efficient Neural Network Inference Compute-in-Memory
Washington State University

Mar 19, 2026J/K move · Enter open · S save

WarPGNN: A Parametric Thermal Warpage Analysis Framework with Physics-aware Graph Neural Network

Haotian Lu, Jincong Lu, Sachin Sachdeva, Sheldon X. -D. Tan

Department of Electrical and Computer Engineering · University of California, Riverside · Riverside, CA, USA

Graph Neural Networks Physics-Informed ML

Open paper AskPDF arXiv

With the advent of system-in-package (SiP) chiplet-based design and heterogeneous 2.5D/3D integration, thermal-induced warpage has become a critical reliability concern. While conventional numerical approaches can deliver highly accurate results, they often incur prohibitively high computational costs, limiting their scalability for complex chiplet-package systems. In this paper, we present WarPGNN, an efficient and accurate parametric thermal warpage analysis framework powered by Graph Neural Networks (GNNs). By operating directly on graphs constructed from the floorplans, WarPGNN enables fast warpage-aware floorplan exploration and exhibits strong transferability across diverse package configurations. Our method first encodes multi-die floorplans into reduced Transitive Closure Graphs (rTCGs), then a Graph Convolution Network (GCN)-based encoder extracts hierarchical structural features, followed by a U-Net inspired decoder that reconstructs warpage maps from graph feature embeddings. Furthermore, to address the long-tailed pattern of warpage data distribution, we developed a physics-informed loss and revised a message-passing encoder based on Graph Isomorphic Network (GIN) that further enhance learning performance for extreme cases and expressiveness of graph embeddings. Numerical results show that WarPGNN achieves more than 205.91x speedup compared with the 2-D efficient FEM-based method and over 119766.64x acceleration with 3-D FEM method COMSOL, respectively, while maintaining comparable accuracy at only 1.26% full-scale normalized RMSE and 2.21% warpage value error. Compared with recent DeepONet-based model, our method achieved comparable prediction accuracy and inference speedup with 3.4x lower training time. In addition, WarPGNN demonstrates remarkable transferability on unseen datasets with up to 3.69% normalized RMSE and similar runtime.

Abstract

Explore similar work

WarPGNN: A Parametric Thermal Warpage Analysis Framework with Physics-aware Graph Neural Network

Active Imitation Learning for Thermal- and Kernel-Aware LFM Inference on 3D S-NUCA Many-Cores

ThRIve: Thermally Robust CNN Inference via Low-Rank Adaptation in Heterogeneous PIM Architectures