Nvidia’s Latest Supercomputer Unveiled: 256 GH200 Superchips, 144TB Of Memory And 1 Eflops Performance
NVIDIA has announced a new type of computing platform DGX GH200 AI Supercomputer for generative AI, processing huge amounts of data and recommender systems.
The Nvidia DGX GH200 uses NVLink Switch System technology to combine 256 GH200 superchips, allowing them to operate as a single GPU. This delivers 1 EFLOPs of performance and 144TB of total memory—nearly 500 times more memory than the previous generation Nvidia DGX A100 introduced in 2020.
The GH200 superchips eliminate the need for traditional PCIe CPU-GPU connectivity by combining an Arm-based Nvidia Grace CPU with an Nvidia H100 Tensor Core GPU in a single package using Nvidia’s NVLink-C2C chip. This increases the throughput between GPU and CPU by 7x compared to the latest PCIe technology, reduces interconnect power consumption by more than 5x, and provides a 600GB Hopper architecture GPU building block for DGX GH200 supercomputers.
Google Cloud, Meta and Microsoft are expected to be among the first to access the DGX GH200 supercomputer to evaluate its capabilities for generative AI workloads.
