AWS and NVIDIA focus on AI with upcoming family of GPUs

  • AWS and NVIDIA have announced that will deepen their relationship, continuing to focus on AI.
  • AWS will offer the first cloud AI supercomputer powered by the NVIDIA Grace Hopper Superchip.
  • NVIDIA is also making its DGX Cloud environment available to more customers via AWS.

Amazon Web Services (AWS) has announced a number of collaborations this week at its annual re:Invent 2023 conference. The latest is not a new collaboration, but rather the deepening of a long-running one with NVIDIA.

To that end, the pair confirmed that they will be focusing more heavily on AI. The first example of this will be AWS being set to offer NVIDIA’s GH200 Grace Hopper Superchips as part of a larger AI supercomputer project, with new multi-node NVLink technology for the cloud.

“The NVIDIA GH200 NVL32 multi-node platform connects 32 Grace Hopper Superchips with NVIDIA NVLink and NVSwitch technologies into one instance. The platform will be available on Amazon Elastic Compute Cloud (Amazon EC2) instances connected with Amazon’s powerful networking (EFA), supported by advanced virtualization (AWS Nitro System) and hyper-scale clustering (Amazon EC2 UltraClusters), enabling joint customers to scale to thousands of GH200 Superchips,” AWS explained in a press release.

The collaboration will not stop there though, with NVIDIA also planning to bring its DGX Cloud environment as an AI-training-as-a-service offering to more customers via AWS. “It will be the first DGX Cloud featuring GH200 NVL32, providing developers the largest shared memory in a single instance. DGX Cloud on AWS will accelerate training of cutting-edge generative AI and large language models that can reach beyond 1 trillion parameters,” the silicon maker noted.

“Generative AI is transforming cloud workloads and putting accelerated computing at the foundation of diverse content generation. Driven by a common mission to deliver cost-effective, state-of-the-art generative AI to every customer, NVIDIA and AWS are collaborating across the entire computing stack, spanning AI infrastructure, acceleration libraries, foundation models, to generative AI services,” added Jensen Huang, founder and CEO of NVIDIA, who was present during the second day keynote at re:Invent.

Given that NVIDIA has seen revenues rise significantly on the back of the frenzied need for chips that can power generative AI experiences, it comes at no surprise that it is looking to collaborate even more with one of the world’s leading hyperscalers.


About Author


Related News