Litcius/Paper detail

Bulls-Eye: Active Few-Shot Learning Guided Logic Synthesis

Animesh Basak Chowdhury, Benjamin Tan, Ryan M. Carey, Tushit Jain, Ramesh Karri, Siddharth Garg

2022IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems23 citationsDOI

Abstract

Generating suboptimal 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 pretrained model on past synthesis data to accurately predict the quality of a synthesis recipe for an unseen netlist. Our approach achieves <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2\times $ </tex-math></inline-formula> – <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$30\times $ </tex-math></inline-formula> runtime improvement and generates synthesis recipes achieving close to 95% quality-of-result (QoR) compared to conventional techniques using actual synthesis runs. We show our QoR beat state-of-the-art approaches on various benchmarks.

Topics & Concepts

Shot (pellet)Computer scienceArtificial intelligenceMaterials scienceMetallurgyVLSI and Analog Circuit TestingMachine Learning and AlgorithmsAdvancements in Photolithography Techniques
Bulls-Eye: Active Few-Shot Learning Guided Logic Synthesis | Litcius