Too Big to Fail? Active Few-Shot Learning Guided Logic Synthesis

TL;DR

This paper introduces Bulls-Eye, a fine-tuning approach for pre-trained models that significantly improves the efficiency and quality of logic synthesis recipe prediction for large netlists, addressing scalability issues in existing ML methods.

Contribution

The paper presents Bulls-Eye, a novel fine-tuning method that enhances scalability and prediction accuracy in logic synthesis, outperforming current state-of-the-art ML approaches.

Findings

Achieves 2x-10x run-time improvement

Provides better quality-of-result (QoR)

Scales effectively to large netlists

Abstract

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.