Benchmark RadarParasGB
ParasGB evaluates graph neural network predictions of parasitic capacitance and resistance on circuit graphs from analog/mixed-signal designs, with node-level ground capacitance, edge-level resistance, and edge-level coupling capacitance tasks.
- Released
- 2026-07-25
- Readiness
- Runnable
- Primary field
- Industrial & Engineering
Why it matters
ParasGB addresses the lack of public high-fidelity RC benchmarks for early parasitic estimation, enabling reproducible evaluation and development of GNN-based models for parasitic-aware design.
Motivation
As chip manufacturing processes advance to deep submicron nodes, parasitic interconnect effects increasingly dominate the performance of analog and mixed-signal (AMS) circuits and often lead to costly layout iterations.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.