POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization
This work solves the problem of automated, reliable RTL optimization for hardware designers, though it is incremental in improving existing LLM-based methods.
The paper tackled the problem of applying large language models (LLMs) to optimize RTL code for power, performance, and area (PPA) by addressing challenges in functional correctness and power prioritization, achieving 100% functional correctness and the best power on all 40 designs in the benchmark.
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 introduces a differential-testing-based testbench generation pipeline that treats the original design as a functional oracle, using deterministic simulation to produce golden references and eliminating LLM hallucination from the verification process. For PPA optimization, POET employs an LLM-driven evolutionary mechanism with non-dominated sorting, power-first intra-level ranking, and proportional survivor selection to steer the search toward the low-power region of the Pareto front without manual weight tuning. Evaluated on the RTL-OPT benchmark across 40 diverse RTL designs, POET achieves 100% functional correctness, the best power on all 40 designs, and competitive area and delay improvements.