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

2026-04-24

AI Summary

This work addresses the limitations of conventional electronic design automation (EDA) tools, which rely on fixed heuristics and require extensive manual tuning to achieve high-quality global routing across diverse chip designs. To overcome this, the paper introduces a novel adaptive EDA paradigm by integrating large language models (LLMs) into the internal algorithmic evolution of EDA tools. Specifically, it presents GR-Evolve, an LLM-driven code evolution framework that couples an open-source global router with the OpenROAD evaluation flow, using post-routing quality-of-results (QoR) as feedback to dynamically generate and iteratively refine routing algorithms. Evaluated on seven benchmark circuits, the approach significantly outperforms baseline methods, achieving up to an 8.72% reduction in post-detailed-routing wirelength and demonstrating the potential to transcend the constraints of traditional static tool architectures.

Technology Category

• Machine Learning: Evolutionary Learning
• Search and Optimization: Evolutionary Computation
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

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.

Problem

• design-adaptive EDA
• global routing
• algorithm evolution
• quality of results (QoR)
• ASIC design

Innovation

• design-adaptive EDA
• LLM-driven code evolution
• global routing
• algorithm specialization
• QoR optimization