Nvidia announces DGX GH200 AI supercomputer

NVIDIA announces new large-memory AI supercomputer DGX GH200, offering 1 exaflop of performance and 144 terabytes of shared memory

DGX GH200 uses NVLink interconnect technology with the NVLink Switch System to combine 256 GH200 superchips as a single GPU

GH200 superchips eliminate need for traditional CPU-to-GPU PCIe connection and increases bandwidth between GPU and CPU by 7x

Save time.  Stay Informed with FYI: A short news app for working professionals.

DGX GH200 is the first supercomputer to pair Grace Hopper Superchips with the NVIDIA NVLink Switch System, providing 48x more NVLink bandwidth

Google Cloud, Meta, and Microsoft are expected to gain access to DGX GH200 for generative AI workloads and large-scale AI initiatives

NVIDIA DGX GH200 supercomputers are expected to be available by the end of the year