Search papers, labs, and topics across Lattice.
The authors developed HLSFactory-Agent, an autonomous LLM agent pipeline designed to discover, isolate, and validate standalone High-Level Synthesis (HLS) designs from complex academic and open-source repositories. Scaling training and evaluation datasets for hardware-generation LLMs and Quality-of-Result (QoR) surrogate models has long been bottlenecked by the labor-intensive engineering needed to extract synthesizable C/C++ hardware modules. Executing in containerized environments via the Pi agent framework, the system successfully extracts turnkey, synthesizable HLS designs from structured codebases to systematically expand training corpora beyond conventional benchmark suites.
Hardware dataset curation no longer requires manual code refactoring, thanks to an agentic pipeline that autonomously trawls academic repositories to carve out synthesizable HLS designs for LLM training.
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.
