AI-enhanced applications, photorealistic rendering, simulation, and other technologies are helping professionals get business-critical results from multi-app workflows faster than ever.
Workstations with high-end CPUs, GPUs, and advanced networking are needed to run these data-heavy, complex workflows, share data, and work together across geographically separate teams.
Intel and NVIDIA are making new platforms with the latest Intel Xeon W and Intel Xeon Scalable processors, NVIDIA RTX 6000 Ada Generation GPUs, and NVIDIA ConnectX-6 SmartNICs to help meet these needs.
With the highest levels of AI computing, rendering, and simulation power, these new workstations can handle demanding workloads in fields like data science, manufacturing, broadcast, media and entertainment, healthcare, and more.
Bob Pette, vice president of professional visualization at NVIDIA, said, “Professionals need advanced power and performance to run the most intensive workflows, like using AI, rendering in real-time, or running multiple apps at the same time.” “The new Intel- and NVIDIA-Ada-powered workstations offer speed, power, and efficiency that has never been seen before. This lets professionals in all industries handle the most complex workflows.”
Roger Chandler, vice president and general manager of Creator and Workstation Solutions in Intel’s Client Computing Group, said, “The latest Intel Xeon W processors, with their groundbreaking new compute architecture, are designed to help professional users handle the most difficult workloads of today and tomorrow.” “By putting together our new Intel Xeon workstation processors and the latest NVIDIA GPUs, professional creators, artists, engineers, designers, data scientists, and power users worldwide will be able to use their creativity and innovation to the fullest.”
Metaverse apps and the rise of generative AI require the hardware to have a new computing power. NVIDIA Omniverse Enterprise is a platform for making and running metaverse applications. It lets you create digital twins in a simulated photorealistic environment that obeys the laws of physics and plant factories.
BMW Group, for instance, is using NVIDIA Omniverse Enterprise to create a digital twin of a whole factory from start to finish. This requires working 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 built or a new product is used in the real world.
Due to the explosion of AI-enhanced workflows, the need for faster computing power is growing exponentially. This includes traditional R&D and data science tasks, edge devices on factory floors or security offices, and generative AI solutions for text conversations and text-to-image apps.
Solutions for collaborative work that use extended reality (XR) also need much computing power. XR applications include
- design reviews,
- testing the design of a product, training for maintenance and support,
- interactive digital twins, and
- entertainment based on where you are.
All of these need high-resolution, photorealistic images to make the most intuitive and engaging immersive experiences, whether they are available locally or streamed to wireless devices.
The Xeon W-3400 and Xeon W-2400, series of processors, have a new computing architecture that makes each CPU core run faster, and a new embedded multi-die interconnect bridge packaging makes it possible to scale up workloads in ways that have never been done before. The top-of-the-line Intel Xeon w9-3495X processor has up to 56 cores in a single socket, a redesigned memory controller, and an enormous L3 cache. This gives it up to 28% more single-threaded(1) performance and 120% more multi-threaded(2) performance than the previous generation of Xeon W processors.
The latest NVIDIA RTX 6000 is based on the NVIDIA Ada Lovelace GPU architecture and gives the new workstations outstanding power efficiency and performance. It has 142 third-generation RT Cores, 568 fourth-generation Tensor Cores, 18,176 latest-generation CUDA cores, and 48GB of high-performance graphics memory. This gives it up to 2x the performance of the previous generation in ray tracing, AI, graphics, and computing.
With line-speed network connectivity based on two 25Gbps ports and GPUDirect technology, NVIDIA ConnectX-6 Dx SmartNICs can increase GPU bandwidth by 10x compared to standard NICs, allowing professionals to handle demanding, high-bandwidth 3D rendering and computer-aided design tasks as well as traditional office work. High-speed, low-latency networking and streaming make it possible for teams to move and import large datasets or for people in different places to work together on design and visualization across applications.
The new generation of workstations powered by the latest Intel Xeon W and Intel Scalable processors and NVIDIA RTX Ada Generation GPUs will be available for preorder from BOXX and HP, with more coming soon from other workstation system integrators.
You must log in to post a comment.