Acquire RTL designs and synthesize them into pre-layout graphs.
npx skills add https://github.com/ShenShan123/agent-r2g --skill rtl-acquire
Please help me install this Agent Skill. Skill: rtl-acquire Source: https://github.com/ShenShan123/agent-r2g/tree/main/r2g-skills/rtl-acquire Command: npx skills add https://github.com/ShenShan123/agent-r2g --skill rtl-acquire
This Skill automates the discovery, screening, and acquisition of RTL designs at scale, followed by synthesis into pre-layout graphs, enabling the creation of large-scale training datasets for RTL graph analysis.
Run the acquisition and synthesis workflow for RTL designs with the command: python3 scripts/run_expansion_round.py --discover --run-retry
High-intent search queries and answers about installing and using this skill.
To acquire RTL designs at scale for graph analysis, you can automate the discovery, screening, and acquisition of RTL designs from local repositories, manifests, or keyword searches. This process systematically builds a large corpus of RTL designs suitable for training graph analysis models.
To convert RTL designs into pre-layout graphs using Yosys and OpenROAD, you run an automated synthesis workflow that processes the acquired RTL designs. This converts the RTL designs into a pre-layout graph format suitable for training graph analysis models with PyG.
Yes, you need PyG, Yosys, and OpenROAD installed to synthesize RTL designs into pre-layout graphs. These dependencies are strictly required for the synthesis process and for converting the RTL designs into the graph format used for training graph analysis models.
The best way to automate RTL corpus expansion and validation is to use dedicated scripts that handle discovery, synthesis, and validation. You can run the acquisition and synthesis workflow with a single command to expand and validate large-scale RTL corpora efficiently.
Yes, you can use locally stored RTL repositories for large-scale corpus acquisition. The acquisition workflow systematically discovers and acquires RTL designs from various sources, including local repositories, manifests, and keyword searches, to build a comprehensive training dataset.
ShenShan123Detect, install, and verify open-source EDA tools for RTL-to-GDS flows.
JosephWoodallBuild and train graph neural networks with PyTorch Geometric.
jackspaceDevelop and train graph neural networks with PyTorch Geometric.
ShenShan123Automate EDA signoff from RTL to GDS with DRC, LVS, and RCX verification.
