HLSFactory-Agent automates extraction of hardware designs from code
HLSFactory-Agent: Large-Scale Agentic HLS Dataset Construction from Academic and Open-Source Projects
Hardware ArchitectureSoftware Engineering
Summary
It is hard and time-consuming for experts to find and prepare collections of hardware design projects from academic papers and open-source sites. The authors created HLSFactory-Agent, a software helper that uses AI to automatically pick out standalone hardware designs from big code collections. This tool can test and build each design to make sure it works, saving lots of manual effort. They also made scripts to search and organize papers to find projects faster. Their results show it can successfully extract usable hardware modules from some example repositories.
What this means in practice
- •For hardware design engineers: Automatically gather and test standalone hardware modules from large codebases to build diverse training datasets for machine learning.
- •For software repository managers: Use indexing scripts to quickly find papers containing hardware design projects that can be extracted and reused.
Authors
Kaushik Chandana, Jay Imperatori, Tanmay Shukla, Justin Zhou, Stefan Abi-Karam, Callie Hao
Abstract
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.