2D-ThermAl: Physics-Informed Framework for Thermal Analysis of Circuits using Generative AI

TL;DR

ThermAl is a physics-informed generative AI framework that rapidly and accurately predicts thermal distributions in integrated circuits, significantly reducing computation time compared to traditional FEM methods.

Contribution

The paper introduces ThermAl, a novel hybrid U-Net based AI model with physical regularization for efficient thermal analysis of circuits, outperforming FEM in speed and accuracy.

Findings

ThermAl achieves an RMSE of 0.71°C in temperature prediction.

The model runs up to 200 times faster than conventional FEM simulations.

It maintains high accuracy across a wide temperature range, including elevated stress scenarios.

Abstract

Thermal analysis is increasingly critical in modern integrated circuits, where non-uniform power dissipation and high transistor densities can cause rapid temperature spikes and reliability concerns. Traditional methods, such as FEM-based simulations offer high accuracy but computationally prohibitive for early-stage design, often requiring multiple iterative redesign cycles to resolve late-stage thermal failures. To address these challenges, we propose 'ThermAl', a physics-informed generative AI framework which effectively identifies heat sources and estimates full-chip transient and steady-state thermal distributions directly from input activity profiles. ThermAl employs a hybrid U-Net architecture enhanced with positional encoding and a Boltzmann regularizer to maintain physical fidelity. Our model is trained on an extensive dataset of heat dissipation maps, ranging from simple logic gates (e.g., inverters, NAND, XOR) to complex designs, generated via COMSOL. Experimental results demonstrate that ThermAl delivers precise temperature mappings for large circuits, with a root mean squared error (RMSE) of only 0.71{\deg}C, and outperforms conventional FEM tools by running up to ~200 times faster. We analyze performance across diverse layouts and workloads, and discuss its applicability to large-scale EDA workflows. While thermal reliability assessments often extend beyond 85{\deg}C for post-layout signoff, our focus here is on early-stage hotspot detection and thermal pattern learning. To ensure generalization beyond the nominal operating range 25-55{\deg}C, we additionally performed cross-validation on an extended dataset spanning 25-95{\deg}C maintaining a high accuracy (<2.2% full-scale RMSE) even under elevated temperature conditions representative of peak power and stress scenarios.