Cadence to Power the Fourth Industrial Revolution in Collaboration with NVIDIA

The convergence of artificial intelligence (AI), robotics, and the internet of things (IoT) has brought about the fourth industrial revolution. It's reshaping how we design, manufacture, and interact with the world. At the heart of this era lies a powerful catalyst: artificial intelligence—particularly infrastructure AI, which encompasses hardware and software systems essential for the development, deployment, and maintenance of AI, and physical AI, which bridges the digital and physical worlds, bringing intelligence to machines.

While AI algorithms have been around for a good 50-60 years, it's only recently that they've been in the spotlight. NVIDIA Blackwell architecture builds upon generations of accelerated computing technologies by using 208 billion transistors. It features transformative technologies for accelerated computing, which will help unlock breakthroughs in data processing, fusion energy, engineering simulation, electronic design automation, computer-aided drug design, and quantum computing.

NVIDIA Blackwell Ultra Tensor Cores accelerate inference and training for large language models (LLMs) and diffusion models that heavily rely on transformer architecture with improved mixed-precision support. The latest iteration of NVIDIA NVLink™ enables high-speed communication with 1.8TB/s bidirectional throughput per GPU. What's more, Blackwell adds intelligent resiliency with a dedicated Reliability, Availability, and Serviceability (RAS) Engine to identify potential faults that may occur early on to minimize downtime.

It goes without saying that it takes complex technology to make such a complex system, namely, the Cadence dynamic duo—Palladium Z3 Emulation Platform and Protium X3 Prototyping Platform. To verify the 208 billion transistors in the NVIDIA Blackwell GPU, as well as the entire system, the dynamic duo played a key role. They're designed to work in tandem, but each excels at different types of workloads. The Palladium Z3 system accelerates hardware verification, and through functional and interface congruency, models can be quickly brought up onto the Protium X3 system for accelerated software validation.

The Palladium Z3 and Protium X3 systems can scale from job sizes of 16 million gates up to 48 billion gates, so the largest systems-on-chip (SoCs) can be tested as a whole rather than just partial models, ensuring proper functionality and performance.

"Designed with Cadence" is a series of videos that showcases creative products and technologies that are accelerating industry innovation using Cadence tools and solutions. For more Designed with Cadence videos, check out the Cadence website and YouTube channel.'