InsightAlign: A Transferable Physical Design Recipe Recommender Based on Design Insights
Hao-Hsiang Hsiao, Sudipto Kundu, Wei Zeng, Wei-Ting Jonas Chan, Deyuan Guo, Sung Kyu Lim · 2025
Physical design tools have complex workflows with many different ways of optimizing power, performance, and area (PPA) out of a large number of options and hyperparameters in different engines and functionalities. Black-box optimization techniques are widely adopted to automate quality-of-result (QoR) exploration. Such exploration often proves impractical in real-world customer environments due to high computational demands, lengthy exploration cycles, and the need for large parallel jobs. To reduce the exploration space for viable compute resource requirements, we propose a novel design methodology to enable transferable learning by incorporating design insights crafted on top of physical design experts’ experience and streamlining QoR exploration as a sequence generation task for best recipe selection. We apply language model-inspired alignment techniques to learn the ranking of different recipe sets, enabling our model to generalize beyond known-good manually tuned expert design recipes. Extensive evaluations demonstrate our method’s superior QoRs and runtime performance on unseen industrial designs and rigorous benchmarks.