PALTO: Physics-Informed Active Learning for Tri-Gate FinFET Design Optimization for Vertical Power Delivery

2026-05-31

AI Summary

This study addresses the computational inefficiency of conventional TCAD in optimizing high-dimensional, nonlinear GaN tri-gate FinFET designs by proposing an intelligent optimization framework that integrates physics-informed priors with active learning. The approach dramatically accelerates simulation convergence and enables precise exploration of critical structural parameters, notably the GaN/AlGaN thickness ratio. For the first time, this work systematically elucidates the impact of thickness ratio on multi-fin array performance, transcending traditional design paradigms. Guided by application-oriented metrics, the optimized device D1 achieves, in a 300-fin configuration, a specific on-resistance of 0.49 Ω·mm, an output current of 3.3 A, and a switching figure-of-merit of 5 pC·Ω—representing a two-fold improvement over device D2 and surpassing established industry benchmarks across all key performance indicators.

Abstract

This paper demonstrates the effectiveness of machine learning-driven optimization for designing application-specific GaN tri-gate FinFETs in vertical power delivery systems. Conventional TCAD-based approaches are computationally intensive and insufficient for navigating the high-dimensional, nonlinear design space of advanced GaN devices. To address this, a physics-informed active learning framework is used to intelligently guide simulations, accelerating convergence while preserving accuracy. This ML-guided approach enables the discovery of optimal configurations by efficiently exploring key structural parameters -- most notably the GaN-to-AlGaN thickness ratio -- a long-standing focus of debate in device design. By systematically exploring key structural parameters, two optimized devices with aggressively scaled gate-to-drain lengths are identified. Single-fin, multi-channel simulations show that device~D2, with a thinner GaN channel relative to the AlGaN barrier, achieves higher drive current. However, in a 300-fin configuration, device~D1 outperforms device~D2 by delivering 3.3\,A at 0.49~ohm on-resistance -- approximately 2$\times$ better -- despite slightly higher parasitics. Both devices operate in a normally-off mode. Based on an application-specific figure of merit, device~D1 achieves 5\,pC$\cdot$ohm, demonstrating 2$\times$ greater switching efficiency than device~D2, while both designs outperform industrial benchmarks from different performance standpoints.

Problem

• FinFET design optimization
• vertical power delivery
• GaN devices
• high-dimensional design space
• computational efficiency

Innovation

• physics-informed active learning
• tri-gate FinFET
• vertical power delivery
• GaN/AlGaN heterostructure
• design optimization