Speeding delivery of low-power GPUs using AI

Cadence Design Systems, Inc. has announced that Imagination Technologies successfully used the AI-driven Cadence Cerebrus Intelligent Chip Explorer and the complete RTL-to-GDS digital full flow to speed up the delivery of its latest low-power 5nm GPUs. By using the Cadence Cerebrus generative AI capabilities in the Cadence OnCloud platform, which allows pay-for-use flexibility and massive scalability, Imagination automatically lowered leakage power by 20% and total power by 6% while at the same time improving area and performance.

Using AI-driven solution in a SaaS model provided the company's design team with the following benefits:

Improved productivity enables the team to achieve power, performance and area goals faster and accelerate tape-out time to tapeout.

Quick ramp-up with an EDA-optimised, ready-to-use, multi-cloud-enabled SaaS model that is security-compliant

A cost-efficient, pay-for-use SaaS business model that offers massive compute and software license capacity to serve AI-driven peak demands.

Cost savings because no extra capital expenditures or IT efforts were required.

Pre-trained Cadence Cerebrus AI models are available to both companies' customers as a warm start for their design projects.

"Our low-power 5nm GPUs had an aggressive delivery schedule, and the AI-driven Cadence Cerebrus using a SaaS model gave us rapid access to a tailored Cadence-managed cloud environment on AWS—all without any CAPEX investment and the long wait times associated with on-premises hardware procurement and IT setup," said Tim Mamtora, chief of innovation and engineering at Imagination Technologies. "With the powerful combination of Cadence Cerebrus and the complete Cadence digital full flow, our team was able to automate processes that were previously manual, which saved us time and helped us achieve our PPA goals."

"The AI-driven Cadence Cerebrus and the broader Cadence digital full flow are specifically designed for complex, next-generation designs like Imagination's low-power 5nm GPUs," said Dr Venkat Thanvantri, corporate vice president of AI R&D in the Digital and Signoff Group at Cadence. "Through our collaboration with Imagination, they successfully leveraged AI-driven automation and the flexibility of our SaaS model to dramatically improve PPA and deliver a high-quality GPU design faster."

The Cadence Cerebrus Intelligent Chip Explorer and the broader digital full flow deliver optimal PPA and faster turnaround time, supporting Cadence's Intelligent System Design strategy, which enables SoC design excellence.