用进化算法优化芯片设计，既保证正确性又优先省电。
POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization
- 通过差分测试生成验证用例，避免LLM出错影响设计正确性。
- 在40个电路设计上实现100%功能正确，功耗全最优。
- 适合芯片设计自动化、低功耗优化方向的研究者和工程师。
将大语言模型（LLMs）应用于RTL代码优化以提升功耗、性能和面积（PPA）面临两大挑战：确保优化后设计的功能正确性（避免LLM幻觉），以及在多目标权衡中系统性地优先考虑功耗降低。本文提出POET（面向功耗的进化调优框架），解决上述问题。为保障功能正确性，POET引入基于差分测试的测试平台生成流程，将原始设计作为功能基准，通过确定性仿真生成黄金参考，消除验证过程中的LLM幻觉。针对PPA优化，采用基于LLM的进化机制，结合非支配排序、功耗优先的层级内排序及比例存活选择策略，无需手动调节权重即可引导搜索趋向帕累托前沿的低功耗区域。在涵盖40个不同RTL设计的RTL-OPT基准上评估，POET实现100%功能正确性，所有设计功耗最优，且面积与延迟改善具有竞争力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。