AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance
Quick summary
arXiv:2606.30949v2 Announce Type: replace Abstract: High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but converting real-world software into synthesizable HLS code remains challenging due to restrictive language support and the gap between software and hardware programming practices. Existing automated and LLM-based refactoring approaches partially address this problem, yet they often lack flexibility, struggle to scale, and incur high computational costs. We introduce AgRefactor, an LLM-based multi-agent workflow for refactoring software into HLS-compatible programs.
Key takeaways
- arXiv:2606.30949v2 Announce Type: replace Abstract: High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but converting real-world software into synthesizable HLS code remains challenging due to restrictive language support and the gap between software and hardware programming practices.
- Existing automated and LLM-based refactoring approaches partially address this problem, yet they often lack flexibility, struggle to scale, and incur high computational costs.
- We introduce AgRefactor, an LLM-based multi-agent workflow for refactoring software into HLS-compatible programs.
Why it matters
The importance of “AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments