CAMO: Correlation-Aware Mask Optimization with Modulated Reinforcement Learning
This addresses efficiency and performance bottlenecks in VLSI manufacturing for chip designers, though it appears incremental as it builds on existing machine learning approaches with specific optimizations.
The paper tackles the problem of optical proximity correction (OPC) in VLSI manufacturing by proposing CAMO, a reinforcement learning-based system that integrates OPC principles like spatial correlation and modulation, resulting in outperforming state-of-the-art OPC engines on via and metal layer patterns.
Optical proximity correction (OPC) is a vital step to ensure printability in modern VLSI manufacturing. Various OPC approaches based on machine learning have been proposed to pursue performance and efficiency, which are typically data-driven and hardly involve any particular considerations of the OPC problem, leading to potential performance or efficiency bottlenecks. In this paper, we propose CAMO, a reinforcement learning-based OPC system that specifically integrates important principles of the OPC problem. CAMO explicitly involves the spatial correlation among the movements of neighboring segments and an OPC-inspired modulation for movement action selection. Experiments are conducted on both via layer patterns and metal layer patterns. The results demonstrate that CAMO outperforms state-of-the-art OPC engines from both academia and industry.