Too Big to Fail? Active Few-Shot Learning Guided Logic Synthesis
This addresses the scalability issue in logic synthesis for chip design, offering a more efficient solution than existing methods, though it is incremental as it builds on pre-trained models.
The paper tackles the problem of generating sub-optimal synthesis transformation sequences in logic synthesis by proposing Bulls-Eye, which fine-tunes a pre-trained model on past data to predict recipe quality for unseen netlists, achieving 2x-10x run-time improvement and better quality-of-result than state-of-the-art ML approaches.
Generating sub-optimal synthesis transformation sequences ("synthesis recipe") is an important problem in logic synthesis. Manually crafted synthesis recipes have poor quality. State-of-the art machine learning (ML) works to generate synthesis recipes do not scale to large netlists as the models need to be trained from scratch, for which training data is collected using time consuming synthesis runs. We propose a new approach, Bulls-Eye, that fine-tunes a pre-trained model on past synthesis data to accurately predict the quality of a synthesis recipe for an unseen netlist. This approach on achieves 2x-10x run-time improvement and better quality-of-result (QoR) than state-of-the-art machine learning approaches.