The Silicon Integration Initiative (Si2) AI/ML Schema/Ontology Working Group is introducing a public release of their AI for EDA Ontology. The goal of this public release of the Si2 AI/ML Schema Ontology Repository is to provide a strong example ontology and use cases to enable EDA agentic system experimentation for broader industry progress and collaboration.
With the rise of agentic AI systems, the semiconductor design industry is at an inflection point: moving from point tools to autonomous workflows. Agentic EDA enables multi-step reasoning systems across design flows, and requires context awareness, causal understanding, and workflow orchestration.
What is an Ontology in EDA? A formal representation of:
- Concepts (e.g. nets, cells, timing paths)
- Relationships (e.g., “affects,” “depands on,” “constrains”)
- Rules and constraints
In EDA context Ontology provides the reasoning backbone for agentic systems, capturing:
- Workflow steps and dependencies
- Cause-effect relationships
- Design tradeoffs
- Domain vocabulary
Release on Github with Apache 2.0 license: https://github.com/si2org/aiml_schema_ontology
Contents:
- The EDA ontology (TTL/OWL)
- Documented, validated use-cases (ASU & Drexel)
- Ontology validation collateral
- MCP server – agent discovery & reasoning
- Full documentation package
The Si2 AI/ML in EDA Schema/Ontology Working Group is a collaboration between Siemens EDA, Arizona State University Drexel University, IBM, NC State University, NXP, Qualcomm, and Synopsys.
We welcome your comments and questions, and we are looking for companies and universities to join the collaborative work. Contact us on the Github site or through in**@*i2.org with the title “Ontology WG”.