HLSFactory-Agent：从学术和开源项目中构建大规模智能体化HLS数据集
HLSFactory-Agent: Large-Scale Agentic HLS Dataset Construction from Academic and Open-Source Projects
浏览论文内容
中文总结 AI 辅助
针对HLS数据集构建依赖人工的难题，提出HLSFactory-Agent，利用LLM智能体在Docker中自动从代码库提取独立HLS设计，并提供论文索引脚本，初步实验验证了其有效性。
中文摘要 AI 辅助
构建超出常见社区基准的大规模、多样化高层次综合（HLS）设计数据集仍然是一个未解决的挑战。随着深度学习和大型语言模型（LLMs）在硬件设计中的兴起，这一挑战变得尤为紧迫，因为这些技术需要此类数据集来训练QoR模型并在HLS任务上对LLMs进行基准测试。尽管在拓宽数据来源方面已有持续努力，数据集整理仍依赖于人工操作：在学术出版物和开源项目中定位HLS设计，然后从更大的代码库中提取独立设计。这一过程容易出错，且需要专业知识、迭代测试以及大量针对每个仓库的工程工作。为解决这一问题，我们提出了HLSFactory-Agent，一个通过从较大代码库中提取独立设计来自动化大规模HLS数据集整理的LLM智能体。HLSFactory-Agent在Docker容器内运行开源的Pi智能体框架，以构建和评估每个提取的设计。这种交钥匙自动化允许用户将GitHub链接或代码目录传递给HLSFactory-Agent，并收到一个包含提取的HLS设计的文件夹，这些设计可直接集成到HLSFactory数据集框架中。此外，我们提供了开源脚本，用于从计算机体系结构、EDA和FPGA会议中抓取和索引可能实现或使用HLS设计的论文，从而加速人类对HLS设计的发现和整理，以供HLSFactory-Agent使用。我们报告了在索引仓库的一小部分子集上运行HLSFactory-Agent的初步结果，展示了从结构化代码库中成功提取可综合设计的能力。我们在以下网址开源了HLSFactory-Agent和索引脚本：此https URL。
英文摘要
Building large, diverse datasets of high-level synthesis (HLS) designs beyond common community benchmarks remains an open challenge. This challenge is made urgent by the rise of deep learning and LLMs for hardware design, which demand such datasets to train QoR models and benchmark LLMs on HLS tasks. Despite ongoing efforts to broaden sources, dataset curation still depends on manual work: locating HLS designs across academic publications and open source, then extracting standalone designs from larger codebases. The process is error-prone and demands expert knowledge, iterative testing, and substantial per-repository engineering. To address this, we present HLSFactory-Agent, an LLM agent that automates large-scale HLS dataset curation by extracting standalone designs from larger codebases. HLSFactory-Agent runs the open-source Pi agent framework inside Docker containers to build and evaluate each extracted design. This turnkey automation allows users to pass a GitHub link or code directory to HLSFactory-Agent and receive a folder of extracted HLS designs ready to be integrated into the HLSFactory dataset framework. Additionally, we provide open-source scripts to scrape and index papers from computer architecture, EDA, and FPGA conferences that possibly implement or use HLS designs, allowing for faster human discovery and curation of HLS designs for HLSFactory-Agent. We report initial results from running HLSFactory-Agent across a small subset of our indexed repositories, demonstrating successful extraction of synthesizable designs from structured codebases. We open source HLSFactory-Agent and indexing scripts at https://github.com/sharc-lab/hlsfactory-agent.
发表机构
- Georgia Institute of Technology（佐治亚理工学院）
- Georgia Tech Research Institute（佐治亚理工研究院）
机构由 AI 辅助整理，请以论文原文为准。
