AI Chip Studio: A Cloud-Native, AI-Assisted Platform for Browser-Based RTL-to-GDSII Digital Design Automation
This paper presents AI Chip Studio, a cloud-native, browser-accessible EDA platform that integrates open-source tools — Verilator, Icarus Verilog, Yosys, OpenSTA, SymbiYosys, and OpenROAD — into a single guided RTL-to-GDSII flow, augmented with an LLM copilot for RTL review, bug detection, testbench generation, and natural-language-to-RTL synthesis. The system is implemented as a six-phase, microservice-oriented architecture spanning a FastAPI/Celery core platform, a browser-based Verification Studio, a Yosys-based Synthesis Studio, an OpenROAD-based Physical Design Studio, a natural-language AI Copilot with an explicit generated-versus-verified correctness contract, and a job-queue-based cloud architecture for scalable, isolated execution of untrusted RTL.
Authors
- mohit Mohit (ORCID: https://orcid.org/0009-0004-8156-4656)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-08-14
- DOI
- https://doi.org/10.5281/zenodo.21939109
- Primary Topic
- Software System Performance and Reliability
- Type
- article
- Field-Weighted Citation Impact
- 0.00