Researchers “have open questions that they just can’t get answered with the compute resources that they have available to them.”

The Fugaku cluster has more than 150,000 processors and roughly 2.8 times the performance of the second-fastest supercomputer, US DoE's Summit.

Future machine learning models will be enormous. The OpenAI system shows that hyperscale cloud platforms can take them on.

“You can just plug it into a server and run it at room temperature.”

Other Nvidia announcements at SC19 include a GPU-accelerated Arm server design and software that makes GPU clusters faster.

Google claims "quantum supremacy" in a paper published in Nature, but IBM researchers dispute the claim.

Charlie Boyle, the man in charge of Nvidia’s AI supercomputer line, on AI hardware and data centers today and in the future.

Announce tight collaboration on supercomputers for scientists and enterprises

Move further fuels challenge to Intel’s dominance in large-scale computing