Automated QoR improvement in OpenROAD with coding agents

TL;DR

AuDoPEDA tackles the problem of scarce expert engineering resources in EDA by enabling autonomous, repository-scale code changes guided by graph-based documentation and literature-grounded planning, operated through a Codex-class executor with QoR feedback. The method decomposes into four stages (S0–S3), producing versioned artifacts and safety guardrails to ensure reproducibility. It demonstrates measurable QoR improvements on OpenROAD, including up to 5.9% reductions in routed wirelength and up to 10% reductions in effective clock period across multiple PDks and circuits, without per-design tuning. This approach signals a shift toward self-improving, automated design-automation toolchains for industrial EDA stacks.

Abstract

EDA development and innovation has been constrained by scarcity of expert engineering resources. While leading LLMs have demonstrated excellent performance in coding and scientific reasoning tasks, their capacity to advance EDA technology itself has been largely untested. We present AuDoPEDA, an autonomous, repository-grounded coding system built atop OpenAI models and a Codex-class agent that reads OpenROAD, proposes research directions, expands them into implementation steps, and submits executable diffs. Our contributions include (i) a closed-loop LLM framework for EDA code changes; (ii) a task suite and evaluation protocol on OpenROAD for PPA-oriented improvements; and (iii) end-to-end demonstrations with minimal human oversight. Experiments in OpenROAD achieve routed wirelength reductions of up to 5.9%, and effective clock period reductions of up to 10.0%.

Figures (1)

• Figure 1: The AuDoPEDA pipeline.