Cadence, Google Scale AI Chip Design with ChipStack on Google Cloud

Estimated reading time: 2 minutes

Cadence, an industry leader in AI-driven computational software for semiconductor and system design, announced a strategic collaboration with Google to optimize the Cadence® ChipStack™ AI Super Agent with Gemini on Google Cloud. This collaboration positions Cadence at the forefront of the shift toward agentic design automation, creating an agent-driven, scalable, cloud-native platform for next-generation chip design and verification.

The Cadence ChipStack AI Super Agent integrates advanced agentic reasoning with Cadence’s EDA solutions, delivering up to 10X productivity improvements across digital design and testbench development, verification planning, regression management and automated debug. By combining AI agents with native EDA execution, the platform enables design teams to compress development cycles, improve efficiency and accelerate time to tapeout.

“Our collaboration with Google Cloud represents a major step forward in scaling AI-driven design automation,” said Paul Cunningham, senior vice president and general manager at Cadence. “By integrating the Cadence ChipStack AI Super Agent with Gemini, we’re advancing the next generation of agentic design—combining the reasoning power of large language models with Cadence’s world-class EDA engines to deliver breakthrough productivity and quality of results for our customers.”

At the core of the ChipStack AI Super Agent is its innovative Mental Model technology, which enables sophisticated agentic reasoning through Cadence native skills, driving Cadence EDA tools to improve the quality and correctness of large language model (LLM)-generated content. Through its collaboration with Google Cloud, Cadence is tightening the integration between the Gemini-enabled ChipStack AI Super Agent and Cadence EDA engines, driving significant improvements in both productivity and quality of results.

This collaboration also leverages Google Cloud’s secure, elastic compute infrastructure to deliver the compute needed for Gemini’s LLM reasoning, Cadence EDA tools and the ChipStack AI Super Agent. This enables a “click-to-deploy” end-to-end solution for agent-powered chip design and verification.