Your Browser is Out of Date

Nytro.ai uses technology that works best in other browsers.
For a full experience use one of the browsers below
VDI Design Guide—Dual VDI and AI on Dell 15G vSAN Ready Nodes in a Healthcare Environment
Introduction Solution Architecture
Architecture overview
Solution architecture
Physical architecture overview
Nodes front and rear views NVIDIA L40 GPUs Physical network components Storage options Data center infrastructure Client components
Software
Overview VMware vSphere VMware Horizon Horizon clone technology vSAN software-defined storage NVIDIA vGPU AI components
Validation Sizing the Solution Summary References

Software

Home > Workload Solutions > Virtual Desktop Infrastructure > Design and Implementation Guides > VDI Design Guide—Dual VDI and AI on Dell 15G vSAN Ready Nodes in a Healthcare Environment > Software

Software

  • NVIDIA vGPU

    NVIDIA vGPU is the industry's most advanced technology for virtualizing true GPU hardware acceleration. The GPUs can be shared between multiple virtual desktops or aggregated to a single virtual desktop without compromising the graphics experience.

    NVIDIA vGPU offers three software variants to enable graphics for different virtualization techniques:

    • NVIDIA Virtual Applications (vApps)—Designed to deliver graphics accelerated applications using RDSH.
    • NVIDIA Virtual PC (vPC)—Designed to provide workstation-grade performance in a virtual environment with support for up to four quad 4K or 5K monitors or up to two 8K monitors. The VDI Solutions team used this software to support a VDI workload with the appropriately sized frame buffer and features, and an AI workload that could take advantage of CUDA. CUDA is a parallel computing platform and programming model developed by NVIDIA that enables dramatic increases in computing performance by harnessing the power of GPUs. This effort uses the NVIDIA Virtual Workstation (vWS).

    The image below outlines the NVIDIA GRID architecture for a dual VDI and AI solution. When sharing the compute and graphics resources, one L40 GPU was used with 2 GB vGPU framebuffers for each VDI VM to support up to 24 users. The AI guest VM was assigned the other L40 GPU, and the entire 48 GB framebuffer was mapped to the vGPU on that VM.

    Figure 7. NVIDIA GRID architecture for dual VDI and AI solution

    The NVIDIA License System is used to provide software licenses to licensed NVIDIA software products. The licenses that the NVIDIA License System provides are obtained from the NVIDIA Licensing Portal. To activate licensed functionalities, a licensed client must obtain a software license when it is booted.