Obsessed with technology?
Subscribe to the latest tech news as well as exciting promotions from us and our partners!
By subscribing, you indicate that you have read & understood the SPH's Privacy Policy and PDPA Statement.
News
News Categories

NVIDIA’s new vGPUs make remote work easier to deploy and manage

By Ken Wong - on 1 Jul 2020, 3:22pm

NVIDIA’s new vGPUs make remote work easier to deploy and manage

The new vGPUs can be used almost anywhere. Image courtesy of NVIDIA.

With Covid-19 changing the way we work, many businesses and workers are continuing to have staff working away from the office. In an IDC survey, 31% of businesses with staff working from home said that employee productivity was their primary concern, followed by security.

Virtualisation isn’t a new technology, but its common usage so far has been mainly within the data centre with server virtualisation. But in an online conference this week, NVIDIA’s new virtual GPU software, vGPU July 2020 enables remote work, access to any application from any device, anywhere and with a better user experience, and IT admin manageability.

 

Looking back at NVIDIA’s vGPU

How the vGPUs work. Image courtesy of NVIDIA.

When deploying a remote or virtual desktop in the past, it was particularly difficult to render and deliver complex graphics to endpoints with adequate performance as it used to use CPU power. In desktops and PCs, GPUs were originally developed to offload processing calculations from the CPU for graphics-intensive applications. And in 2012, NVIDIA introduced the first virtual GPU to help reduce lag time when delivering graphics to remote users and providing the same performance they would get from a desktop.

In a VDI environment powered by NVIDIA virtual GPU, the NVIDIA virtual GPU software is installed at the virtualization layer along with the hypervisor. The NVIDIA virtual GPU software creates virtual GPUs that enable every virtual machine (VM) to share a physical GPU installed on the server or allocate multiple GPUs to a single VM to power the most demanding workloads. Because work that was typically done by the CPU is offloaded to the GPU, users get a better experience and demanding engineering and creative applications can be supported in a virtualised and cloud environment.

During their research for the previously mentioned study, when IDC interviewed NVIDIA customers using GPU-accelerated virtual desktops, it found organisations with 500-1,000 users experienced a 13 percent increase in productivity, resulting in approximately more than US$1 million in annual savings.

Alex Herrera, an analyst with Jon Peddie Research/Cadalyst said:

“In a centralised computing environment with virtualised GPU technology, users no longer have to be tied to their physical workstations. As proven recently through remote work companies can turn on a dime, enabling anywhere/anytime access to big data without compromising on performance.”

And that brings us back to vGPU July 2020.

 

And the new release brings…

Even graphics-intensive workloads are no problem. Image courtesy of NVIDIA.

NVIDIA began development of vGPU July 2020 months into the Covid-19 lockdown period.

The latest version of vGPU adds support for more workloads and provides workers from designers to data scientists with a “…flexible way to collaborate on projects which require advanced graphics and computing power without the need for their organizations to outfit everyone with their own workstation”.

We asked NVIDIA how much more efficient the new vGPUs were, how many more VDIs could be supported, and how does this compared to current CPU based VDI?

They told us that for users who wanted to run 3D-applications on a virtual machine (such as Catia), they still needed GPU power as these heavy applications typically required a GPU. But for knowledge workers, NVIDIA has seen up to a 33% better performance than a CPU-only VDI. With the typical workload for today’s knowledge workers including, video, office productivity apps, web browsing as well as using multiple high-res monitors.

Collaboration in VR is also getting a boost as Nvidia CloudXR technology uses Nvidia RTX and vGPU software to deliver VR and augmented reality across both 5G and Wi-Fi networks. The latest version of vGPU adds 120Hz vSync support at resolutions up to 4K and this gives CloudXR users an even smoother immersive experience on untethered devices.

Matt Coppinger, Director of AR/VR at VMware said, “Streaming AR/VR over Wi-Fi or 5G enables organisations to truly take advantage of its benefits, enabling immersive training, product design and architecture and construction.”

Other improvements include better user experience and manageability for demanding workloads such as Omniverse AEC Experience for real-time photorealistic rendering of architectural and engineering models.

For IT admins, it comes with features that improve operational efficiencies. They can expect to see reduced deployment time of new VMs and increased manageability. Some of the new features include:

  • cross-branch support, where the host and guest vGPU software can be on different versions, easing upgrades and large deployments
  • support for the latest hypervisor versions to pick up fixes, security patches and new features, while staggering deployments for end-user images
  • improved compatibility for data centres running VMware vSphere will see improved operational efficiency by having the ability to manage vGPU powered VMs with the latest release of VMware vRealize Operations
  • vSphere 7 introduces a new feature called “Assignable Hardware,” which enhances initial placement so that a VM can be automatically “placed” on a host that has exactly the right GPU and profile available before powering it on.

According to NVIDIA, the global rollout and pricing of the new vGPU July 2020 are coming soon.