R2G: A Multi-View Circuit Graph Benchmark Suite from RTL to GDSII

TL;DR

R2G is a comprehensive benchmark suite for circuit graph learning, standardizing multi-view representations across stages from RTL to GDSII to facilitate controlled evaluation of GNNs in physical design.

Contribution

It introduces R2G, a multi-view circuit-graph benchmark with standardized representations and an end-to-end pipeline, enabling systematic GNN evaluation in physical design tasks.

Findings

View choice significantly impacts GNN performance.

Node-centric views generalize well across design stages.

Deeper decoder heads improve prediction accuracy to over 99%.

Abstract

Graph neural networks (GNNs) are increasingly applied to physical design tasks such as congestion prediction and wirelength estimation, yet progress is hindered by inconsistent circuit representations and the absence of controlled evaluation protocols. We present R2G (RTL-to-GDSII), a multi-view circuit-graph benchmark suite that standardizes five stage-aware views with information parity (every view encodes the same attribute set, differing only in where features attach) over 30 open-source IP cores (up to $10^6$ nodes/edges). R2G provides an end-to-end DEF-to-graph pipeline spanning synthesis, placement, and routing stages, together with loaders, unified splits, domain metrics, and reproducible baselines. By decoupling representation choice from model choice, R2G isolates a confound that prior EDA and graph-ML benchmarks leave uncontrolled. In systematic studies with GINE, GAT, and ResGatedGCN, we find: (i) view choice dominates model choice, with Test R$^2$ varying by more than 0.3 across representations for a fixed GNN; (ii) node-centric views generalize best across both placement and routing; and (iii) decoder-head depth (3--4 layers) is the primary accuracy driver, turning divergent training into near-perfect predictions (R$^2$$>$0.99). Code and datasets are available at https://github.com/ShenShan123/R2G.