发表机构
KU Leuven; Nokia Bell Labs（鲁汶大学; 诺基亚贝尔实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ARES是一款面向PPA和成本感知的LLM智能体RTL优化框架，通过自适应调控推理力度，在相同成本下提升优化效果，缩小了LLM生成与手工优化单元的差距。
AI 中文摘要
大型语言模型（LLM）智能体通过迭代编辑、综合及PPA分析来优化寄存器传输级（RTL）设计的功耗、性能和面积（PPA），每次LLM调用需支付美元成本。现有智能体仅报告达到的质量却不报告其归一化成本，将该质量归因于工程化的跨设计记忆，且每次调用的推理力度固定。我们提出Ares，包含三项对应创新：（1）我们引入每次LLM调用的归一化美元成本，并与品质因数（FoM）一同报告，实现不同力度水平和优化器间的公平比较；（2）基于该核算，我们发现长期记忆的构建作用不大，工程化记忆相比相同经验的普通拼接并无可靠增益；（3）我们转而通过耐心计数器调整每次调用的推理力度：仅当较低力度下的进展停滞时，才升级到更深层次的推理，该计数器基于21个训练设计拟合，将推理资源分配给能产生收益的环节，而非在所有迭代中均匀分配。在训练期间未见过的3个测试设计上，该力度策略在归一化成本相同时，将FoM从最佳固定力度达到的16-23%降低了23-27%；Ares缩小了LLM生成的乘累加单元与高度手工优化对应单元之间高达83%的差距，且在仅为最先进的Dr. RTL 12%的token用量下，达到比其高25%的FoM。
英文摘要
Large language model (LLM) agents optimize the power, performance, and area (PPA) of register-transfer-level (RTL) designs by iterating over edits, synthesis, and PPA analysis, paying a dollar cost for every LLM call. Prior agents report the quality reached without its normalized cost, attribute that quality to an engineered cross-design memory, and hold the reasoning effort of every call fixed. We propose Ares with three corresponding innovations. (1) We introduce a normalized dollar cost per LLM call reported alongside the figure of merit (FoM), enabling fair comparison across effort levels and optimizers. (2) Using this accounting, we find the construction of the long-term memory matters little. An engineered memory brings no dependable gain over a plain concatenation of the same experience. (3) We instead adapt the per-call reasoning effort by escalating to deeper reasoning only once progress at a lower effort stalls, via a patience counter fit on 21 training designs, allocating reasoning where it pays rather than uniformly across all iterations. On three test designs unseen during training, the effort policy lowers the FoM by 23-27% where the best fixed effort reaches 16-23%, at equal normalized cost. Ares closes up to 83% of the gap from an LLM-drafted multiply-accumulate unit to its highly hand-optimized counterpart, and reaches a 25% deeper FoM than state-of-the-art Dr. RTL at 12% of its tokens.
Comments7 pages, 6 figures
