Tag

Dgx Gh200

All articles tagged with #dgx gh200

Nvidia's Latest AI Supercomputers and Modular Server Platform.
technology2 years ago

Nvidia's Latest AI Supercomputers and Modular Server Platform.

Nvidia has announced the DGX GH200 AI supercomputer, powered by NVIDIA GH200 Grace Hopper Superchips and the NVIDIA NVLink Switch System. The supercomputer is expected to be available by the end of 2023 and provides 1 exaflop of performance and 144 terabytes of shared memory. Nvidia is also building NVIDIA Helios, a supercomputer that will feature four DGX GH200 systems interconnected with NVIDIA Quantum-2 InfiniBand networking to supercharge data throughput for training large AI models.

NVIDIA's Grace Hopper-powered supercomputer revolutionizes AI.
technology2 years ago

NVIDIA's Grace Hopper-powered supercomputer revolutionizes AI.

NVIDIA has announced that their Grace Hopper "superchip" has entered full production, combining a Grace CPU and Hopper H100 GPU to deliver a semi-integrated CPU/GPU product for AI models. The Grace CPU packs 72 CPU cores and comes with up to 480GB of LPDDR5X memory, while the Hopper GPU brings just shy of 1 EFLOPS of FP16 matrix math throughput for AI workloads, as well as 80GB of HBM3 memory. NVIDIA is also building its first DGX system around the chip, a full-on multi-rack computational cluster called the DGX GH200 AI Supercomputer, which is a complete, turn-key, 256 node GH200 cluster designed for training large AI models.

NVIDIA's DGX GH200: A Game-Changing Supercomputer for AI.
technology2 years ago

NVIDIA's DGX GH200: A Game-Changing Supercomputer for AI.

NVIDIA has announced its next DGX supercomputer, the DGX GH200, which is designed to help companies develop generative AI models. The supercomputer uses a new NVLink Switch System to enable 256 GH200 Grace Hopper superchips to act as a single GPU, delivering 1 exaflop of performance and 144 terabytes of shared memory. The DGX GH200 offers 10 times more bandwidth than the previous generation, making it a powerful AI supercomputer with the simplicity of programming a single GPU. Google Cloud, Meta, and Microsoft are among the first companies to gain access to the supercomputer to test how it can handle generative AI workloads.