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
Citrix Virtual Apps and Desktops VDI Reference Architecture for Dell EMC PowerFlex family
Executive summary Product overview Solution architecture Test and performance analysis Testprofile1 – Login VSI Task Worker Testprofile2 – Login VSI Knowledge Worker Testprofile3 – Login VSI Power Worker Testprofile4 – Login VSI Multimedia Worker Best practices
Management infrastructure
Windows 10 optimization
Scaling guidelines
NVDIA vGPU considerations
Conclusion References Configuration details

NVDIA vGPU considerations

Home > Storage > PowerFlex > White Papers > Citrix Virtual Apps and Desktops VDI Reference Architecture for Dell EMC PowerFlex family > NVDIA vGPU considerations

NVDIA vGPU considerations

  • NVIDIA vGPU supports various scheduling policies that allow VMware vSphere Shared Direct (passthrough graphics) feature to share the vGPU resources optimally with multiple workload VMs.

    • Best effort scheduler – default policy in vSphere, allows a vGPU virtual machine to use the GPU processor cycles are not used by other vGPUs virtual machines.
    • Equal share scheduler – shares the GPU processing equally to all the vGPU virtual machines are running.
    • Fixed share scheduler – each vGPU has the fixed share of the GPU allocated to the virtual machine.

    Equal share scheduler or Fixed share scheduler is recommended for VDI solutions, which reduces the overall CPU overhead to handle the vGPU scheduling for the virtual machines running in the ESXi host and improves the end-user graphics performance equivalently.