AutoPPA: Automated Circuit PPA Optimization via Contrastive Code-based Rule Library Learning

TL;DR

AutoPPA introduces an automated framework for circuit PPA optimization that automatically learns and applies effective rules from code pairs, outperforming manual and existing methods.

Contribution

It proposes a novel Explore-Evaluate-Induce workflow to automatically generate and adapt optimization rules, reducing reliance on human knowledge.

Findings

AutoPPA outperforms manual optimization methods.

AutoPPA surpasses state-of-the-art tools SymRTLO and RTLRewriter.

The framework effectively generalizes rules for diverse circuits.

Abstract

Performance, power, and area (PPA) optimization is a fundamental task in RTL design, requiring a precise understanding of circuit functionality and the relationship between circuit structures and PPA metrics. Recent studies attempt to automate this process using LLMs, but neither feedback-based nor knowledge-based methods are efficient enough, as they either design without any prior knowledge or rely heavily on human-summarized optimization rules. In this paper, we propose AutoPPA, a fully automated PPA optimization framework. The key idea is to automatically generate optimization rules that enhance the search for optimal solutions. To do this, AutoPPA employs an Explore-Evaluate-Induce ($E^2I$) workflow that contrasts and abstracts rules from diverse generated code pairs rather than manually defined prior knowledge, yielding better optimization patterns. To make the abstracted rules more generalizable, AutoPPA employs an adaptive multi-step search framework that adopts the most effective rules for a given circuit. Experiments show that AutoPPA outperforms both the manual optimization and the state-of-the-art methods SymRTLO and RTLRewriter.