用大模型系统生成可复用的硬件设计优化策略，提升调度效率
RAG-Enhanced Kernel-Based Heuristic Synthesis (RKHS): A Structured Methodology Using Large Language Models for Hardware Design
- 结合检索增强生成与模板化启发式框架，迭代优化调度策略
- 在高阶综合中降低11%平均任务时延，仅增加1.3倍运行开销
- 方法可推广至其他EDA优化问题，适合芯片设计工程师参考
启发式设计支撑现代电子设计自动化（EDA）工具，但构建有效的布局、布线和调度策略需大量专业经验。本文研究大语言模型（LLMs）如何系统性合成可复用的优化启发式，而不仅是单次代码生成。提出RAG增强的基于核函数的启发式合成方法（RKHS），融合检索增强生成（RAG）、紧凑的核启发式模板及受迭代自反馈启发的LLM驱动优化循环。应用于高阶综合中的最小化延迟列表调度，原型系统相比基线调度器平均缩短11%的任务时延，仅带来1.3倍运行开销，且该结构化检索-合成循环可泛化至其他EDA优化问题。
原文摘要 · Abstract (English)
Heuristic design upholds modern electronic design automation (EDA) tools, yet crafting effective placement, routing, and scheduling strategies entails substantial expertise. We study how large language models (LLMs) can systematically synthesize reusable optimization heuristics beyond one-shot code generation. We propose RAG-Enhanced Kernel-Based Heuristic Synthesis (RKHS), which integrates retrieval-augmented generation (RAG), compact kernel heuristic templates, and an LLM-driven refinement loop inspired by iterative self-feedback. Applied to latency-minimizing list scheduling in high-level synthesis (HLS), a prototype reduces average schedule length by up to 11 percent over a baseline scheduler with only 1.3x runtime overhead, and the structured retrieval-synthesis loop generalizes to other EDA optimization problems.
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。