One of the many exciting new features to the Microsoft Azure cloud platform that Microsoft announces at AzureCon 2015 is the all new Azure GPU Compute. This allows for Virtual Machines (VMs) to utilize GPU’s hosted in the cloud. Now, even graphics processing and video rendering can be brought to “cloud scale” within Microsoft Azure.

You can bring your own custom applications, Operating System images, as well as VM Images from the Azure Marketplace to GPU Compute. The GPU virtualization is done via utilizing DDA (Discrete Device Assignment) within Hyper-V on the host operating system within Azure. This allows the GPU to be brought through to the guest OS with minimal performance impact.

The qraphics hardware in the Azure GPU Compute offering is powered by NVidia Tesla M60 and K80 GPU hardware. The all new N-Series virtual machines sizes are being offers to bring support for GPU Compute to Azure Virtual Machine hosting.

The “Applications that scale using GPU Compute” session by Mark Staveley from AzureCon 2015 covers the all new Azure GPU Compute in greater detail.

Azure_GPUCompute_NSeries_VM_SizesCredit: The N-Series VM size chart above is from the AzureCon 2015 session.

2 thoughts on “Azure GPU Computing in the Cloud

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s