Efficient Bilevel Source Mask Optimization

doi:10.1109/tcad.2025.3650385

Efficient Bilevel Source Mask Optimization

2026-01-01

0

PRE

AI

DOI：10.1109/tcad.2025.3650385

Original

Original request for help

Save

Abstract

En 中文

Resolution enhancement techniques (RETs) are critical for meeting the stringent requirements of advanced technology nodes in semiconductor manufacturing. Source mask optimization (SMO), a prominent RET methodology, simultaneously co-optimizes photomask patterns and illumination sources to maximize the lithographic process window; nevertheless, existing SMO approaches typically separate source and mask optimization (MO) into sequential steps, resulting in substantial computational overhead and lacking convergence guarantees. In this work, we present bilevel SMO (BiSMO), a unified bilevel optimization framework that formulates SMO as a nested optimization problem and leverages three novel gradient-based algorithms for efficient and provably convergent solution search. To further enhance practical performance, we introduce BiSMO-reinforcement learning (RL), an RL-driven extension that dynamically adjusts bilevel optimization hyperparameters to accelerate convergence and improve solution robustness. Experimental results on representative lithographic patterns demonstrate that BiSMO-RL reduces critical lithographic error metrics by up to 40% and achieves more than an $8\times $ improvement in computational efficiency compared to state-of-the-art (SOTA) RET methods. All code and experimental settings are open sourced at https://github.com/dekura/BiSMO.git

Keywords:

Electronic design automation and methodology

design methodology

design for manufacture

Efficient Bilevel Source Mask Optimization

Abstract

Journal

Organization