Nvidia launches AI supercomputer, with Microsoft, Alphabet-C, and Meta Platforms as first users.

On Monday, Nvidia announced the launch of the new DGX GH200 AI supercomputer powered by 256 GH200 Grace Hopper chips.

According to a Nvidia executive last Friday, the new DGX system has larger memory capacity and larger scale model capabilities, supporting the next generation of generative artificial intelligence applications. The memory of DGX GH200 will be nearly 500 times that of the Nvidia DGX A100 system.

"The DGX GH200 AI supercomputer integrates Nvidia's most advanced acceleration computing and networking technologies to expand the forefront of artificial intelligence," said Nvidia CEO Huang Renxun last week.

Nvidia chips have a great influence in generative AI, and this trend has been popular since OpenAI released ChatGPT at the end of last year.

Nvidia expects its new supercomputer to allow developers to build better language models for AI chatbots, complex recommendation algorithms, and create more effective fraud detection and data analysis.

DGX GH200 integrates 256 GH200 super chips. Each super chip has a GPU, which means that DGX GH200 will have 256 GPUs, while previous models only had 8 GPUs.

There are two types of logic chips: central processing units (CPUs) that serve as the main computing brain for PCs/servers, and graphics processing units (GPUs) used for gaming and AI computing.

Nvidia said that Alphabet-C's Google Cloud, Meta, and Microsoft will be the first companies to use DGX GH200 to explore its generative artificial intelligence capabilities. The system is expected to be put into use by the end of 2023. However, the company did not provide a price.

Nvidia also announced that the GH200 Grace Hopper super chip has entered full production. The super chip uses NVLink connection technology to connect Nvidia's Grace CPU and Hopper GPU together.

Last week, Nvidia's stock price skyrocketed, and management said that the surge in demand came from cloud computing providers, large consumer internet companies, startups, and other companies for their artificial intelligence data center products.