GR-Evolve: Design-Adaptive Global Routing via LLM-Driven Algorithm Evolution

TL;DR

GR-Evolve introduces an LLM-driven framework that automatically adapts global routing algorithms to specific designs, significantly improving wirelength reduction in ASIC design.

Contribution

This work pioneers design-adaptive EDA tooling by using an LLM to iteratively evolve routing code based on quality feedback, a novel approach in the field.

Findings

Achieved up to 8.72% reduction in wirelength over baseline routers.

Demonstrated effectiveness across seven benchmark designs and three technology nodes.

Showcased the potential of LLM-driven code evolution for design-specific optimization.

Abstract

Modern ASIC design is becoming increasingly complex, driving up design costs while limiting productivity gains from existing EDA tools. Despite decades of progress, current tools rely on fixed heuristics and offer limited control via tool hyperparameters, requiring extensive manual tuning to achieve an acceptable quality of results (QoR). While prior work has explored learning-based optimization and design-specific hyperparameter tuning, these approaches operate within the constraints of static tool algorithm implementations and do not adapt the underlying algorithms to individual designs. To address this limitation, we introduce the concept of design-adaptive EDA tooling, in which the internal algorithms of EDA tools are automatically specialized to the characteristics of a given design. We instantiate this paradigm through GR-Evolve, a code evolution framework that leverages an agentic large language model (LLM) to iteratively modify global routing source code using QoR-driven feedback. The framework equips the LLM with persistent contextual knowledge of open-source global routers along with an integrated toolchain for QoR evaluation within the OpenROAD infrastructure. We evaluate GR-Evolve across seven benchmark designs across three technology nodes and demonstrate up to 8.72% reduction in post-detailed-routing wirelength over existing baseline routers, highlighting the potential of LLM-driven EDA code evolution for design-adaptive global routing.