NVIDIA Vera Rubin Supercharges Supercomputing for Science

NVIDIA is introducing the NVIDIA Vera Rubin platform, delivering world-class supercomputers for science and combining native double-precision (FP64) performance, NVIDIA CUDA-X libraries and the full-stack capabilities of the NVIDIA AI platform.

Bringing together NVIDIA’s complete accelerated computing stack—from hardware to software and optimized scientific libraries—Vera Rubin accelerates AI, simulation, and data-intensive research, transforming each system rack into a supercomputer for scientific discovery and industrial innovation, according to NVIDIA.

Built to unite high-precision simulation, AI, and data analytics, the Vera Rubin platform is designed for the era of agents to advance scientific discovery by accelerating workloads such as climate modeling, computational fluid dynamics, quantum chemistry and energy exploration.

With more than 7 exaflops of AI for science, 5 petaflops of native FP64 support and extreme memory bandwidth with up to 144 GPUs, a Vera Rubin supercomputing system can deliver performance on par with systems on the TOP500 list of the world’s most powerful supercomputers. This gives research centers and industrial enterprises the performance to run larger models, improve fidelity, and shorten time to discovery, the company said.

“Scientific discovery is now a race between the complexity of the world’s greatest challenges and the computing systems built to solve them,” said Jensen Huang, founder and CEO of NVIDIA. “NVIDIA Vera Rubin is a new instrument for science—a rack-scale supercomputer that brings simulation, AI and data processing together to help researchers and industries design and discover faster than ever.”

The NVIDIA Vera Rubin platform combines NVIDIA Rubin GPUs and NVIDIA Vera CPUs connected via high-speed NVIDIA NVLink-C2C, NVIDIA ConnectX-9 SuperNICs, and NVIDIA BlueField-4 DPUs in a direct liquid-cooled architecture.

For scientific computing, Vera Rubin provides native FP64 capabilities to accelerate simulations that need the highest accuracy as well as the AI performance needed for surrogate models, scientific foundation models, and AI-assisted analysis.

Researchers can use a single platform to run traditional numerical solvers, train and deploy AI models, stream data from instruments, and couple simulation with real-time analytics, NVIDIA said.

NVIDIA Vera Rubin NVL4-based systems are expected to be available from global system manufacturers in Q4 this year.

For more information about this news, visit www.nvidia.com.