Nvidia and Intel team up on chips for metaverse workstations

Nvidia and Intel have teamed up to provide processors and graphics chips for a new generation of creator workstations. You might think of them as metaverse workstations.

Those workstations will be launching with anywhere from one Nvidia graphics processing unit (GPU) to four in a system powered by Intel’s latest Xeon W and Intel Xeon Scalable processors, said Bob Pette, vice president of Nvidia’s professional visualization business in an interview with GamesBeat.

“I think this will really unlock the number of GPUs that are in a workstation because now we can fully drive multiple GPUs,” Pette said.

At a time when Nvidia is pitching Omniverse as a tool for building virtual worlds, enterprise digital twins, and eventually the metaverse, these workstations are likely to be in high demand. Intel said there are more than 50 designs using the Xeon processors coming to the market.

AI-augmented applications, photorealistic rendering, simulation and other technologies are helping professionals achieve business-critical results from multi-app workflows faster than ever, the companies said.

Running these data-intensive, complex workflows, as well as sharing data and collaborating across geographically dispersed teams, requires workstations with high-end CPUs, GPUs and advanced networking.

The Intel Xeon processors will be paired with Nvidia RTX 6000 Ada generation GPUs, as well as Nvidia
ConnectX-6 SmartNICs. The latter networking card will have a cooling system — a sign of the times of where the heat in a system can be, Pette said.

“We’ve got some customers that are testing it out. And anywhere, anytime you’re moving gigabytes or terabytes of data, it’s going to have a huge impact. So we spent the money because we believe there is a large opportunity to refit this with an actively cooled card,” Pette said.

These new workstations bring together the highest levels of AI computing, rendering and simulation
horsepower to tackle demanding workloads across data science, manufacturing, broadcast, media and
entertainment, healthcare and more, Nvidia said.

“Professionals require advanced power and performance to run the most intensive workflows, like using
AI, rendering in real time or running multiple applications simultaneously,” said Pette. “The new Intel- and Nvidia-Ada powered workstations deliver unprecedented speed, power and efficiency, enabling professionals everywhere to take on the most complex workflows across all industries.”

“The latest Intel Xeon W processors — featuring a breakthrough new compute architecture — are
uniquely designed to help professional users tackle the most challenging current and future workloads,”
said Roger Chandler, vice president and general manager of creator and workstation solutions in the
client computing group at Intel, in a statement. “Combining our new Intel Xeon workstation processors with the latest Nvidia GPUs will unleash the innovation and creativity of professional creators, artists, engineers, designers, data scientists and power users across the world.”

Serving new workloads

Metaverse applications and the rise of generative AI require a new level of computing power from the
underlying hardware.

“These are purpose-built for things like Nvidia Omniverse and Nvidia AI,” Pette said.

Creating digital twins in a simulated photorealistic environment that obeys the laws of physics and planning factories are just two examples of workflows made possible by Nvidia Omniverse Enterprise, a platform for creating and operating metaverse applications.

BMW Group, for example, is using Nvidia Omniverse Enterprise to design an end-to-end digital twin of an entire factory. This involves collaboration with thousands of planners, product engineers and facility managers in a single virtual environment to design, plan, simulate and optimize highly complex manufacturing systems before a factory is actually built or a new product is integrated into the real world.

(I’m going to moderate a session on the enterprise metaverse at Nvidia’s GTC event coming on March 22).

The need for accelerated computing power is growing exponentially due to the explosion of AI-augmented workflows, from traditional R&D and data science workloads to edge devices on factory floors or in security offices, to generative AI solutions for text conversations and text-to-image applications, the companies said.

Extended reality (XR) solutions for collaborative work also require significant computing resources. Examples of XR applications include design reviews, product design validation, maintenance and support training, rehearsals, interactive digital twins and location-based entertainment. All of these demand high-resolution, photoreal images to create the most intuitive and compelling immersive experiences, whether available locally or streamed to wireless devices.

Next-generation platform features

With a breakthrough new compute architecture for faster individual CPU cores and new embedded multi-die interconnect bridge packaging, the Xeon W-3400 and Xeon W-2400 series of processors enable scalability for increased workload performance. Available with up to 56 cores in a single socket, the top-end Intel Xeon w9-3495X processor features a redesigned memory controller and larger L3 cache, delivering up to 28% more single-threaded and 120% more multi-threaded performance over the previous-generation Xeon W processors.

Based on the Nvidia Ada Lovelace GPU architecture, the latest Nvidia RTX 6000 brings power efficiency and performance to the new workstations. It features 142 third-generation RT Cores, 568 fourth-generation Tensor Cores and 18,176 latest-generation CUDA cores combined with 48GB of high-performance graphics memory to provide up to 2x ray-tracing, AI, graphics and compute performance over the previous generation.

And Nvidia’s ConnectX-6 Dx SmartNICs enable professionals to handle demanding, high-bandwidth 3D
rendering and computer-aided design tasks, as well as traditional office work with line-speed network
connectivity support based on two 25Gbps ports and GPUDirect technology for increasing GPU bandwidth by 10x over standard NICs. The high-speed, low-latency networking and streaming capabilities enable teams to move and ingest large datasets or to allow remote individuals to collaborate across applications for design and visualization.

The new workstations will be available in the coming months, and you can preorder from Boxx and HP starting today.

While it’s unusual to see competitors like Intel and Nvidia teaming up, Nvidia also partners with AMD around its CPU families as well, Pette said.

“We just tend to try to focus on what the customer experience is going to be,” Pette said. “Even though we may be competing with somebody on the GPU side, the best experience is putting in a Sapphire Rapids (Intel) or Threadripper (AMD), then we want to make sure those workloads are tuned.”