用推理大模型自动优化硬件设计，提升效率与质量
Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective
- 构建智能代理框架，自动重写代码并插入优化指令
- 在基准测试中成功率超传统模型，降低延迟并节省面积
- 首次展示开源推理模型的思考过程，适合芯片设计研究者
近期大型语言模型（如 OpenAI o3-mini、DeepSeek-R1）通过思维链（Chain-of-Thought, CoT）实现增强推理，其在依赖专家迭代优化的硬件设计中的潜力尚未被探索。本文研究推理型大模型能否解决高层次综合（HLS）设计空间探索与优化中的挑战。在HLS过程中，工程师需手动设置指令以平衡性能与资源约束。本文提出一种基于大模型的优化智能体框架，能自动重构代码、插入指令，并通过HLS工具反馈和整数线性规划（ILP）求解器识别最优设计点。实验对比了推理模型与传统LLMs在基准测试中的表现，采用成功率、效率及设计质量（面积/延迟）作为指标，首次揭示了如DeepSeek-R1等强大开源推理模型所产生的思维链过程。
原文摘要 · Abstract (English)
Recent Large Language Models (LLMs) such as OpenAI o3-mini and DeepSeek-R1 use enhanced reasoning through Chain-of-Thought (CoT). Their potential in hardware design, which relies on expert-driven iterative optimization, remains unexplored. This paper investigates whether reasoning LLMs can address challenges in High-Level Synthesis (HLS) design space exploration and optimization. During HLS, engineers manually define pragmas/directives to balance performance and resource constraints. We propose an LLM-based optimization agentic framework that automatically restructures code, inserts pragmas, and identifies optimal design points via feedback from HLs tools and access to integer-linear programming (ILP) solvers. Experiments compare reasoning models against conventional LLMs on benchmarks using success rate, efficiency, and design quality (area/latency) metrics, and provide the first-ever glimpse into the CoTs produced by a powerful open-source reasoning model like DeepSeek-R1.
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。