Image

Description

NVIDIA GH200 Grace Hopper Superchip has been successfully installed on the SURF Experimental Technologies Platform and is available for the broader Dutch research community.

The GH200 combines the NVIDIA Grace and Hopper architectures using NVIDIA NVLink-C2C to deliver a CPU+GPU coherent memory model for accelerated AI and HPC applications. With 900 gigabytes per second (GB/s) of coherent interface, the superchip is 7X faster than PCIe Gen5. And with HBM3 and HBM3e GPU memory, it supercharges accelerated computing and generative AI. GH200 runs all NVIDIA software stacks and platforms, including NVIDIA AI Enterprise, the HPC SDK, and Omniverse.