The largest NDv2 deployments rank among the world's fastest supercomputers, according to Nvidia officials, enabling customers for the first time to rent an entire AI supercomputer on demand that matches the capabilities of large-scale, on-premises supercomputers that can take months to deploy.
NDv2 instances are said to be ideal for complex AI, machine learning and HPC workloads.
For example, AI researchers needing fast solutions can quickly spin up multiple NDv2 instances and train
complex conversational AI models in just hours.
Microsoft and Nvidia engineers used 64 NDv2 instances on a pre-release version of the cluster to train the popular conversational AI model Bert in roughly three hours.
All NDv2 instances benefit from the GPU-optimized HPC applications, machine learning software and deep learning frameworks such as TensorFlow, PyTorch and MXNet from the Nvidia NGC container registry and Azure Marketplace, according to Nvidia officials.
"Until now, access to supercomputers for AI and high performance computing has been reserved for the world's largest businesses and organisations," said Nvidia vice president and general manager of accelerated computing Ian Buck.
"Microsoft Azure's new offering democratises AI, giving wide access to an essential tool needed to solve some of the world's biggest challenges."
Microsoft corporate vice president of Azure Compute Girish Bablani said "As cloud computing gains momentum everywhere, customers are seeking more powerful services.
"Working with NVIDIA, Microsoft is giving customers instant access to a level of supercomputing power that was previously unimaginable, enabling a new era of innovation."
NDv2 is available now in preview.