- Nvidia partners described the new offerings at SC22, where the company released major updates to acceleration libraries.
- A five-year license for Nvidia AI Enterprise, a cloud-native software suite, is included with every H100 PCIe GPU.
- Many of Nvidia’s partners are announcing Nvidia H100-powered servers in a wide variety of configurations.
Nvidia announced broad adoption of its next-generation H100 Tensor Core GPUs and Quantum-2 InfiniBand, including new offerings on Microsoft Azure cloud and over 50 new partner systems for accelerating scientific discovery. At SC22, Nvidia partners described the new offerings. Nvidia also released major updates to its cuQuantum, CUDA, and BlueField DOCA acceleration libraries. Nvidia also announced support for the Omniverse platform on Nvidia A100 and H100-powered systems.
Microsoft Azure cloud and 50+ new partner systems
H100, Quantum-2, and the library updates are part of Nvidia’s HPC platform, which is a full technology stack with CPUs, GPUs, DPUs, systems, networking, and a broad range of AI and HPC software. It enables researchers to efficiently accelerate their work on powerful systems, both on-premises and in the cloud.
Microsoft Azure’s adoption of the Nvidia Quantum-2 InfiniBand networking platform follows news of Nvidia Quantum-2’s general availability. Nvidia’s other partners, including Asus, Atos, Dell, Ingrasys, Gigabyte, HPE, Lenovo, Penguin Solutions, QCT, and Supermicro, are also announcing H100-powered servers with a variety of configurations. With every H100 PCIe GPU, a 5-year license for Nvidia AI Enterprise is included, which is a cloud-native software suite that streamlines the development and deployment of AI.
To help boost scientific discovery, Nvidia has released major updates to its CUDA, cuQuantum, and DOCA acceleration libraries:
- Nvidia CUDA libraries now include a multi-node, multi-GPU Eigensolver enabling unprecedented scale and performance for leading HPC applications like VASP, a package for first-principles quantum mechanical calculations.
- The Nvidia cuQuantum software development kit for accelerating quantum computing workflows now supports approximate tensor network methods. This allows researchers to simulate tens of thousands of qubits, as well as automatically enables multi-node, multi-GPU support for quantum simulation with unparalleled performance using the cuQuantum Appliance.
- Nvidia DOCA, the open cloud SDK and acceleration framework for Nvidia BlueField DPUs, includes advanced programmability, security, and functionality to support new storage use cases.
Jensen Huang, founder and CEO of Nvidia said,
« AI is reinventing the scientific method. Learning from data, AI can predict impossibly complex workings of nature, from the behavior of plasma particles in a nuclear fusion reactor to human impact on regional climate decades in the future. By providing a universal scientific computing platform that accelerates both principled numerical and AI methods, we’re giving scientists an instrument to make discoveries that will benefit humankind. »