NVIDIA Grace Hopper Superchip
The breakthrough accelerated CPU for giant-scale AI and HPC applications.
Take a Closer Look at the Superchip
The NVIDIA GH200 Grace Hopper Superchip combines the Grace and Hopper architectures using NVIDIA® NVLink®-C2C to deliver a CPU+GPU coherent memory model for accelerated AI and HPC applications.
- CPU+GPU designed for giant-scale AI and HPC
- New 900 gigabytes per second (GB/s) coherent interface, 7X faster than PCIe Gen5
- 30X higher aggregate system memory bandwidth to GPU compared to NVIDIA DGX™ A100
- Runs all NVIDIA software stacks and platforms, including the NVIDIA HPC SDK, NVIDIA AI, and NVIDIA Omniverse™
Breakthrough accelerated performance for giant scale AI-HPC applications
QuantaGrid S74G-2U
QuantaGrid S74G-2U is the first server to introduce the NVIDIA Grace Hopper Superchip in conjunction with NVIDIA MGX architecture.
1 x NVIDIA GH200 Grace Hopper Superchip, with: NVIDIA Grace 72 Arm Neoverse V2 cores NVIDIA Hopper H100 NVIDIA Chip-2-Chip (C2C) Interconnect 900GB/s
576GB total of Memory, including:
480GB LPDDRX Grace CPU Memory 96GB HBM3 (up to 4TB/s) Hopper GPU Memory Memory coherency via NVLINK C2C
3 x PCIe 5.0 x16 FHFL Dual Width slots
4 x E1.S NVMe SSD
1+1 High efficiency hot-plug 2000W PSU, 80 Plus Titanium
READ MORE
ASUS ESC NM1-E1
ASUS ESC NM1-E1 is an NVIDIA® MGX-powered 2U, 19-inch rack server with the NVIDIA Grace GH200 Grace Hopper™ Superchip CPU, NVIDIA NVLink-C2C technology, PSU and air-cooling support
1 x NVIDIA GH200 Grace Hopper Superchip, with: NVIDIA Grace 72 Arm Neoverse V2 cores NVIDIA Hopper H100 NVIDIA Chip-2-Chip (C2C) Interconnect 900GB/s
576GB of Memory, including: 480GB LPDDRX Grace CPU Memory 96GB HBM3 ( 4TB/s) Hopper GPU Memory Memory coherency via NVLINK C2C
3 x PCIe 5.0 x16 FHFL Dual Width slots
4 x U.2 NVMe SSD
1+1 High efficiency hot-plug 2000W PSU, 80 Plus Titanium
READ MORE
Supermicro GPU ARS-111GL-NHR
Supporting NVIDIA BlueField-3 or NVIDIA ConnectX-7High Performance Computing, AI/Deep Learning Training, Large Language Model (LLM) and Generative AI, and more.