Skip to main content

How to watch Nvidia’s Computex 2022 keynote

Nvidia just wrapped its Computex 2022 keynote, which was packed with announcements about the company’s enterprise business. Although the presentation was light on next-gen GPU news, Nvidia still shared some announcements related to liquid-cooled GPUs in the data center and the processors that could power next-gen cloud gaming.

The keynote happened late Monday night in the U.S., lining up with the morning in Taiwan,where Computex takes place. To get you up to speed, we have a replay of the keynote here, as well as all of Nvidia’s announcements.

How to watch Nvidia’s Computex 2022 keynote

NVIDIA Keynote at COMPUTEX 2022

Six different Nvidia executives spoke at Nvidia’s keynote, which mostly covered the company’s data center and AI efforts. The presentation aired during late in the U.S., so if you missed the live keynote, you can catch a replay of it above.

Nvidia’s keynote came just half a day after AMD kicked off Computex with its executive keynote (where it officially revealed Ryzen 7000 CPUs). Intel skipped this year’s show, where we expected to hear about Arc Alchemist GPUs.

What Nvidia announced at Computex 2022

Nvidia A100 liquid-cooled data center GPU.

Although we hoped to hear about next-gen RTX 40-series graphics cards, Nvidia focused on its data center GPUs and Grace CPU during its Computex 2022 keynote. It appears we’ll have to wait on next-gen GPU announcements until the fall, when Nvidia has been long-rumored to launch its next-gen GPUs.

We still got some GPU news, though. Nvidia launched liquid-cooled versions of its A100 and H100 data center GPUs in an attempt to reduce energy consumption in mainstream servers. These GPUs will be available as add-in PCIe cards, as well as in Nvidia’s HGX server racks. The A100 is arriving in the second half of the year, while Nvidia expects the H100 in early 2023.

Nvidia says the new GPUs can cut power consumption by 30% in the data center, as well as free up 66% of the space a normal GPU would take up. The cooler uses a direct-to-chip connection, which Nvidia says provides the best cooling potential possible. Liquid cooling is common in supercomputers, but this is the first time we’re seeing it on mainstream servers.

Nvidia also revealed reference designs for its Grace and Grace Hopper processors. These chips are built to handle massive AI workloads, as well as power the next generation of cloud gaming technology. Nvidia announced the Grace Hopper chip, its first-ever dual CPU/GPU chip, at GTC earlier this year.

Nvidia says dozens of models will be available from Asus, Gigabyte, and Supermicro, among others, and they’ll arrive in the first half of 2023. Hopefully by the end of next year, we’ll start to see what these chips can do with platforms like GeForce Now.

Computex wasn’t the most exciting show for PC enthusiasts this year, as Intel skipped it and Nvidia focused mostly on its enterprise business. The show brought news of AMD’s upcoming AM5 platform, though, including the new X670 chipset.

Editors' Recommendations