MappingEvolve: LLM-Driven Code Evolution for Technology Mapping
For logic synthesis researchers, this work pioneers LLM-driven code evolution for core algorithm enhancement, offering significant area-delay improvements.
MappingEvolve uses LLMs to directly evolve technology mapping code, achieving 10.04% area reduction over ABC and 7.93% over mockturtle, with 46.6%–96.0% overall improvement on EPFL benchmarks.
Technology mapping is a critical yet challenging stage in logic synthesis. While Large Language Models (LLMs) have been applied to generate optimization scripts, their potential for core algorithm enhancement remains untapped. We introduce MappingEvolve, an open-source framework that pioneers the use of LLMs to directly evolve technology mapping code. Our method abstracts the mapping process into distinct optimization operators and employs a hierarchical agent-based architecture, comprising a Planner, Evolver, and Evaluator, to guide the evolutionary search. This structured approach enables strategic and effective code modifications. Experiments show our method significantly outperforms direct evolution and strong baselines, achieving 10.04\% area reduction versus ABC and 7.93\% versus mockturtle, with 46.6\%--96.0\% $S_{overall}$ improvement on EPFL benchmarks, while explicitly navigating the area--delay trade-off. Our code and data are available at https://github.com/Flians/MappingEvolve.