Nvidia vGPU software is now available for a broad range of workloads including virtual desktop infrastructure, high-performance graphics, data analytics and AI.
The new release brings support for the latest Nvidia A40 and Nvidia A100 80GB GPUs, as well as Nvidia GPU Operator, a software framework that simplifies GPU deployment and management.
In conjunction with Nvidia RTX vWS software, the A40 provides up to 60% faster virtual workstation performance per user, and up to 100% faster rendering compared with the previous generation RTX 6000 GPUs.
This means Nvidia A40 with the latest vGPU software runs complex graphics workloads in virtualised environments with performance comparable to bare metal, according to the company.
"With support for Nvidia's latest vGPU software, and the new Nvidia A40 with Citrix Hypervisor 8.2 and Citrix Virtual Desktops, we can continue providing the performance customers need to run graphics-intensive visualisation applications as their data and workloads grow," said Citrix vice president of product management Calvin Hsu.
"The combination of Citrix and Nvidia virtualisation technologies provides access to these applications from anywhere, with an experience that is indistinguishable from a physical workstation."
Other new features include simplified GPU management in Kubernetes, and a similar management experience under OpenShift as IT professionals have come to expect with popular hypervisors.
"The combination of Nvidia's latest generation A40 GPU and Nvidia vGPU software, supported with Red Hat Enterprise Linux and Red Hat Virtualisation, offers a powerful platform capable of serving some of the most demanding workloads ranging from AI/ML to visualisation in the oil and gas as well as media and entertainment industries," said Red Hat director of product management Steve Gordon.
"As organisations transform and increasingly use containers orchestrated by Kubernetes as key building blocks for their applications, we see Red Hat OpenShift as a likely destination for containerised and virtualised workloads alike."