Largest Array of NVIDIA-Certified Systems Will Leverage High-Speed Communication Capabilities Built into the NVIDIA Grace CPU Superchip
Super Micro Computer, Inc., a global leader in enterprise computing, storage, networking, and green computing technology, will deploy the NVIDIA Grace CPU Superchip in a wide range of servers optimized for AI, HPC, data analytics, digital twins, and compute-intensive applications. As artificial intelligence (AI) technologies transcend multiple industries, Supermicro servers will use the NVIDIA Grace CPU Superchip to enable a broader range of developers and IT administrators to take advantage of this new technology. Supermicro servers will be optimized for energy efficiency, reducing operating costs, which will become the norm for all data centers. In addition, with a memory bandwidth of up to 1 TB/second, applications will not be limited by communication speeds. Initially, a limited number of servers will be available, starting with a 2U 2 Node portfolio and then followed by product line expansion.
“Supermicro is developing new server platforms incorporating the NVIDIA Grace CPU Superchip,” said Charles Liang, president, and CEO of Supermicro. “Leveraging our innovative Building Block Solutions®, we plan to offer a wide range of servers optimized for specific workloads. Based on our green computing DNA, Supermicro offers the most advanced energy-efficient servers available to meet demanding data center requirements. Our first-to-market new systems can quickly address the rapidly expanding AI, HPC, and data analytics markets.”
Also Read: FullStory Redefines Product Analytics Allowing Brands To Find, Validate
“NVIDIA has been working with Supermicro to quickly bring innovative products to market,” said Paresh Kharya, senior director of accelerated computing at NVIDIA. “The release of Supermicro’s servers with NVIDIA Grace CPU Superchips will optimize a wide variety of workloads to meet the needs of modern data centers.”
Supermicro’s Total IT solutions are designed to deliver customers a one-stop experience for their IT needs. Supermicro tests and integrates combinations of hardware and software that ensure server or rack-level designs meet the current and future needs of IT professionals. As part of this ongoing practice, Supermicro will incorporate the NVIDIA Grace CPU Superchip in solutions that are optimized for HPC, AI, and data analytics workloads. Specifically, the NVIDIA Grace CPU Superchip interfaces with the latest PCIe Gen5 protocol, enabling optimum 400Gb/s connectivity with the NVIDIA Quantum-2 InfiniBand platform or NVIDIA Spectrum Ethernet, including NVIDIA ConnectX®-7 smart network interface cards and NVIDIA BlueField-3 DPUs, enabling secure and accelerated HPC and AI workloads.
Supermicro has collaborated with NVIDIA for many years, delivering the most advanced graphics, HPC, and AI accelerators to a wide range of users. With the new NVIDIA Grace CPU Superchip, the entire NVIDIA software stack, including NVIDIA AI Enterprise, will run seamlessly on upcoming Supermicro servers. Supermicro will also continue to support NVIDIA Omniverse Enterprise, helping to accelerate 3D design collaboration and simulation of industrial virtual worlds and digital twins.