Microsoft backs Nvidia for AI supercomputer in the cloud : Page 2 of 2

August 20, 2020 // By Nick Flaherty
Microsoft is using Nvidia's A100 graphics processing unit and AMD's Rome processor connected via Infiniband for its AI supercomputer in the cloud
Microsoft is using Nvidia's A100 graphics processing unit and AMD's Rome processor connected via Infiniband for its AI supercomputer in the cloud

requires large clusters of hundreds of machines with specialized AI accelerators interconnected by high-bandwidth networks inside and across the machines.

“We have been building such clusters in Azure to enable new natural language generation and understanding capabilities across Microsoft products, and to power OpenAI on their mission to build safe artificial general intelligence,” said Finder.

This builds on the previous public cloud offering clusters of VMs with Nvidia’s V100 Tensor Core GPUs, connected by a Mellanox InfiniBand network. “Most customers will see an immediate boost of 2x to 3x compute performance over the previous generation of systems based on NVIDIA V100 GPUs with no engineering work,” said Finder, with certain applications seeing a 20x speed up.

The ND A100 v4 VM series and clusters are now in preview and will become a standard offering in the Azure portfolio.

www.nvidia.com; www.microsoft.com; www.amd.com

Related AI supercomputer articles

Other articles on eeNews Europe


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.