Tag
This paper explores using LLM agents for chip design with higher-level abstractions, introducing a workflow called AHRR that combines agent-based HLS design with RTL refinement, achieving a 2.6× speedup over direct RTL design in benchmarks.
XLS is an experimental high-level synthesis toolchain from Google that generates synthesizable hardware designs from high-level descriptions, aimed at accelerating hardware-software co-design in the end-of-Moore's-law era.
AgRefactor is an LLM-based multi-agent workflow for refactoring software into HLS-compatible programs, featuring a self-evolving memory system and automated refactoring tools, achieving significant speedups on real-world benchmarks.