NVIDIA announces world's largest GPU-accelerated cloud-based supercomputer

NDv2 supercomputer is designed to handle demanding AI and high-performance computing applications.

Update: 2019-11-22 02:59 GMT
E2E Networks GPU instances can help in optimizing operational costs by as much as 70 per cent compared to the other leading Public Cloud providers.

NVIDIA has announced a new kind of GPU-accelerated supercomputer in the cloud on Microsoft Azure.

NDv2 supercomputer is designed to handle demanding AI and high-performance computing applications, using up to 800 NVIDIA V100 Tensor Core GPUs interconnected on a single

Mellanox InfiniBand backend network, making it the world's largest GPU-accelerated cloud-based supercomputer, the official press release notes.

It enables customers to rent an AI supercomputer on-demand from their desk, and match the capabilities of large-scale on-premises supercomputers. NDv2 is available in preview.

Tags:    

Similar News