NVIDIA announces AI supercomputer

The NVIDIA AI supercomputer connecting 256 Grace Hopper superchips into a 144TB graphics processing unit (GPU) will be available by the end of the year.

“Generative AI, large language models and recommender systems are the digital engines of the modern economy,” said Jensen Huang, founder and CEO of NVIDIA.

The NVIDIA DGX supercomputer combines 256 GH200 superchips, allowing them to perform as a single GPU.

It has 144TB of shared memory, 500 times more than the previous generation NVIDIA DGX A100.

The company said its supercomputers would be available by the end of the year. Google Cloud, Meta, and Microsoft will be the first ones to start experimenting with it.

NVIDIA also said it intended to provide the DGX GH200 design as a blueprint to cloud service providers and other “hyperscalers.”

“As AI models grow larger, they need powerful infrastructure that can scale to meet increasing demands,” said Alexis Björlin, Vice President of Infrastructure, AI Systems, and Accelerated Platforms at Meta. “NVIDIA’s Grace Hopper design looks to provide researchers with the ability to explore new approaches to solve their greatest challenges.”

According to Microsoft, the new supercomputer would allow developers to conduct research at scale and accelerated speed since training large AI models is a task that consumes time and resources.

NVIDIA is also building DGX GH200-based AI supercomputers for its own researchers and developers. It will be more powerful than the original NVIDIA DGX supercomputer. Dubbed NVIDIA Helios, it will have 1,024 Grace Hopper Superchips.

Bringing game characters to life

NVIDIA is close to becoming a $1 trillion company. Its founder and CEO Jensen Huang, who kicked off the COMPUTEX conference in Taipei, said that 40,000 large companies and 15,000 startups now use NVIDIA technologies.

“We’re now at the tipping point of a new computing era with accelerated computing and AI that’s been embraced by almost every computing and cloud company in the world,” he said.

Among other things, Huang also announced the NVIDIA Avatar Cloud Engine (ACE) for Games, which would help developers bring game characters to life.

“It will give non-playable characters conversational skills so they can respond to questions with lifelike personalities that evolve,” he said.