POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization

📰 ArXiv cs.AI

POET is a framework for power-oriented evolutionary tuning of LLM-based RTL PPA optimization

advanced Published 23 Mar 2026

Action Steps

Identify the key challenges in applying LLMs to RTL code optimization, including functional correctness and power reduction
Develop a framework that addresses these challenges, such as POET
Implement evolutionary tuning to systematically prioritize power reduction within the multi-objective PPA trade-off space
Evaluate the effectiveness of the framework in optimizing PPA and ensuring functional correctness

Who Needs to Know This

This research benefits AI engineers and ML researchers working on large language models and hardware optimization, as it provides a novel approach to addressing challenges in functional correctness and power reduction

Key Insight

💡 POET addresses the challenges of functional correctness and power reduction in LLM-based RTL code optimization

Key Takeaways

POET is a framework for power-oriented evolutionary tuning of LLM-based RTL PPA optimization

Full Article

Title: POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization

Abstract:
arXiv:2603.19333v1 Announce Type: cross Abstract: Applying large language models (LLMs) to RTL code optimization for improved power, performance, and area (PPA) faces two key challenges: ensuring functional correctness of optimized designs despite LLM hallucination, and systematically prioritizing power reduction within the multi-objective PPA trade-off space. We propose POET (Power-Oriented Evolutionary Tuning), a framework that addresses both challenges. For functional correctness, POET introd

Read full paper → ← Back to Reads