VDI Graphics Delivery Options: Pros & Cons

No requirements around virtualization; the application is installed directly in the remote server or blade.

Provides near-native, high-end 3D professional graphics experiences.

Supports remoting protocols like HP RGS, Microsoft RDP, and Citrix HDX 3D Pro via client hardware.

One server or one blade is dedicated to one client OS, resulting in higher costs per user.

Offers the lowest density of all other options, which means the hardware will only be available to one client OS and user.

Virtualization benefits can’t be leveraged as the OS is directly installed.

Using the proper configuration, you can get up to eight workstation-class VMs per host

Best performing solution as the graphics driver resides in the VM, and the virtual machines have full and direct access to a dedicated GPU (not shared).

You can get server blades that already include the native graphics driver, for maximum workstation performance.

Higher cost of ownership per connection as it has a dedicated GPU per virtual machine.

Lower VM density per host when compared to a software-virtualized GPU or non-3D desktop virtualization environment.

Live migration of VM with pass-through devices is not supported.

Scalability to over 50 users per GPU depending on the workload.

It can load balance between multiple installed cards as VMs start, thereby ensuring the right workloads receive the graphics requirements they need.

Lower cost per user compared to other technologies, with high density of VMs per GPU.

Allows users to have “just-like-desktop-PC” with minimal-to-no latency and fast graphics delivery. 

May exhibit unacceptable performance for mid-to high-end 3D workstation user workloads.

The GPU can become a performance bottleneck as many users draw on the resources of one card.

GPU sharing with direct access to the video driver maximizing user density and cost.

Lower cost of ownership when compared to other accelerated graphics for VDI technologies.

Some 3D applications may not work or be certified as published application or multi-user published desktops.

It may exhibit unacceptable performance for the high-end 3D user.

The GPU can become a performance bottleneck as many users draw on the resources of one card; it is possible that one user can consume all of the resources of the GPU.

Increase in the number of graphics-accelerated VMs per host; supporting up to eight users per physical GPU.

The virtual machine has full and direct access to the GPU, including the native graphics driver.

Potential lower overall VM density per GPU as compared to software-virtualized GPU model (depends on applications and workload).

In this model as well, it is possible that one user can consume all of the resources of the GPU, creating a performance bottleneck.