Microsoft Offers GPU-Accelerated Virtual Machines in Azure

Microsoft announced preview availability of its N-Series Virtual Machines in Azure today. Microsoft will offer state-of-the-art GPU visualization infrastructure and GPU compute infrastructure through the N-Series, enabled by our NVIDIA Tesla M60 platform with GRID and Tesla K80 GPU accelerators.

For the first time, businesses will have the ability to deploy NVIDIA Quadro-grade professional graphics applications and accelerated computing on-premises, in the cloud through Azure, or via a hybrid of the two using both Windows and Linux virtual machines.

windows_azure_nvidia

Professional Graphics in the Cloud

Azure N-Series now offer NVIDIA Tesla M60 GPUs with NVIDIA GRID software for professional graphics users with visually intensive applications. This solution allows organizations to get the full power of a workstation from Azure cloud, enabling workforce productivity, security and workspace mobility.

Supercomputing-Class Performance

Azure also offers customers supercomputing-class performance, with the addition of the NVIDIA Tesla Accelerated Computing Platform’s K80 GPU for the most computationally demanding data center and high performance computing applications.

By deploying the Tesla K80 GPU accelerator in its N-Series virtual machines, Azure dramatically expands access to supercomputing-class performance. Enterprises can rent a supercomputer in the cloud, whenever needed, to accelerate their most demanding workloads.

Cloud-Based GPUs

We’ve spent years and thousands of engineering man-hours adding cloud-based capabilities to our GPUs. At the same time, we’ve been intensely focused on improving the energy efficiency of GPUs to meet the requirements of hyperscale data centers.

We’re also focused on the need for the shortest possible latency. Graphics or computation are instantly transmitted to the user through any connected device. Furthermore, we’ve virtualized the software stack and integrated into the Azure cloud, allowing complete compatibility with almost any application.

For more details or to register for the preview, see Microsoft’s blog.

 

Similar Stories

  • Bob Johnson

    “We’re also focused on the need for the shortest possible latency” – then why don’t you support VESA Adaptive-Sync which reduces latency?

  • Mexor

    Quote mining? I think you’re out of context.