NVIDIA Omniverse Opens Portals for Scientists to Explore Our Universe
3D Simulation and Collaboration Platform Now Supports NVIDIA A100 and H100 Systems; Ecosystem Expands Into HPC With Connections to NVIDIA Modulus, NeuralVDB, and IndeX and Kitware’s ParaView to Accelerate Million-X Scale Discovery
SC22 — NVIDIA today announced that NVIDIA Omniverse™ — an open computing platform for building and operating metaverse applications — now connects to leading scientific computing visualization software and supports new batch-rendering workloads on systems powered by NVIDIA A100 and H100 Tensor Core GPUs.
NVIDIA also introduced fully real-time scientific and industrial digital twins for the high performance computing community, enabled by NVIDIA OVX™, a computing system designed to power large-scale Omniverse digital twins, and Omniverse Cloud, a software- and infrastructure-as-a-service offering.
Omniverse now supports batch workloads that AI and HPC researchers, scientists and engineers can run on their existing A100 or H100 systems — including rendering videos and images or generating synthetic 3D data.
To foster more seamless, collaborative workflows for the HPC community, NVIDIA also unveiled connections to popular scientific computing tools such as Kitware’s ParaView, an application for visualization; NVIDIA IndeX® for volumetric rendering; NVIDIA Modulus for developing physics-ML models; and NeuralVDB for large-scale sparse volumetric data representation.
“Today’s scientific computing workflows are extremely complex, involving enormous datasets that are impractical to move and large, global teams that use their own specialized tools,” said Dion Harris, lead product manager of accelerated computing at NVIDIA. “With new support for Omniverse on A100 and H100 systems, HPC customers can finally start to unlock legacy data silos, achieve interoperability in their complex simulation and visualization pipelines, and generate compelling visuals for their batch-rendering workflows.”
Using Omniverse and hybrid-cloud workloads, scientific computing customers can connect legacy simulation and visualization pipelines to achieve distributed, fully interactive, true real-time interaction with their models and datasets. NVIDIA customers such as Argonne National Laboratory, Lockheed Martin and Princeton Plasma Physics Laboratory are already seeing benefits of Omniverse for HPC workloads.
Global Scientific Leaders Support Omniverse
Argonne National Laboratory is using NVIDIA Omniverse on its A100-powered Polaris supercomputer to connect its legacy visualization tools as a first step to developing the foundations for future digital twins.
“Visualization workflows at Argonne National Laboratory are getting increasingly complex — ranging from handling terabytes of cosmology data to photorealistic renderings of engineered devices — and these collaborative projects involve teams of scientists, engineers and artists all using highly specialized tools,” said Michael Papka, deputy associate laboratory director and director at Argonne Leadership Computing Facility. “Omniverse homogenizes such complex workflows, retains the expertise of established tools and opens the opportunity for entirely new workflows, including building digital twins.”
Princeton Plasma Physics Laboratory (PPPL), the U.S. Department of Energy national laboratory for plasma physics and fusion science, is using Omniverse to connect and accelerate state-of-the-art, synthetic, real-time HPC simulators to model fusion devices and control systems, and ultimately improve the operation of the experiment toward a new commercially viable clean-energy source.