Adding GPU to a VM instance

Leverage GPUs on Google Cloud for complex processing and scientific computing

Reisbel Machado avatar
Written by Reisbel Machado
Updated over a week ago

Some companies that are working with high level design applications, science software or system engineers may need access to massively parallel computational power.
GPU's (Graphics Processing Units) can rapidly increase the speed of complex processing of workloads. 

There are two options for high performance virtual workstations:

1. itopia allows delivering of high performance workstations powered by NVIDIA® P100 GPU accelerators through Teradici’s PCoIP to designers, multimedia companies and engineers.

2. There is also an option of adding GPUs to your existing virtual machines directly from GCP.

GPU Restrictions

GPU's are available in some US Zones and they have certain restrictions that make them behave differently than other VM instance types. Click here for more details about restrictions and availability.

Deploying a server with attached GPU

You can deploy a new environment via itopia and then attach GPU directly from Google or add GPU to your existing server that you deployed via itopia.

This detailed guide will explain exactly how to attach GPU to a VM instance.
More information about manually installing the drivers for Windows can be found here.

Server integration with itopia

There shouldn't be any compatibility issues with the itopia software if you add GPU's to yur existing VM instances created with itopia software.
If you're adding new servers with GPU's, they must be deployed in the same zone as the rest of servers in the deployment (pdc, fbu, etc.)

If you're interested in this option, please contact the support for more details.

Next steps:

Did this answer your question?