Chip maker Nvidia has announced a new class of large-memory AI supercomputers — an Nvidia DGX supercomputer powered by its GH200 Grace Hopper Superchips and the NVLink Switch System. According to the company, the AI supercomputer is created to enable the development of giant, next-generation models for generative AI language applications, recommender systems and data analytics workloads.
“Generative AI, large language models and recommender systems are the digital engines of the modern economy,” Jensen Huang, founder and CEO of Nvidia, said in a statement while making the announcement at Computex 2023. “DGX GH200 AI supercomputers integrate NVIDIA’s most advanced accelerated computing and networking technologies to expand the frontier of AI.”
Nvidia claims the DGX GH200 is the only AI supercomputer that offers a massive shared memory space of 144TB across 256 NVIDIA Grace Hopper Superchips, providing developers with nearly 500X more memory to build giant models. DGX GH200 supercomputers include NVIDIA software to provide a turnkey, full-stack solution for the largest AI and data analytics workloads.
Moreover, the chip maker said that Google Cloud, Meta and Microsoft are among the first expected to gain access to the DGX GH200 to explore its capabilities for generative AI workloads. The company also intends to provide the DGX GH200 design as a blueprint to cloud service providers and other hyper scalers so they can further customise it for their infrastructure.
“As AI models grow larger, they need powerful infrastructure that can scale to meet increasing demands,” said Alexis Bjorlin, vice president of Infrastructure, AI Systems and Accelerated Platforms at Meta.
Further, to advance research and development, the company is building its own DGX GH200-based AI supercomputer named — NVIDIA Helio, to power the work of its researchers and development teams.
Nvidia DGX GH200 supercomputers are expected to be available by the end of the year.