NVIDIA Debuts Quadro vDWS Leveraging Tesla GPUs For Virtualized Workstation Rendering And Compute Muscle

Tesla P4
NVIDIA is making its high-powered Tesla GPU servers even more useful today with the launch of what it calls Quadro Virtual Data Center Workstation Software, or Quadro vDWS. Quadro vDWS allows users to run heavy rendering operations and high-performance computing workloads within a virtualized environment.

These applications can then be streamed to a laptop or virtual workstation that otherwise wouldn’t have the compute power necessary to handle such tasks. Quadro vDWS is optimized for Pascal-based Tesla GPU accelerators with up to 24GB of onboard memory, with those resources being divided up amongst multiple users based on their needs.

tesla slide 1

NVIDIA claims that Quadro vDWS offers twice the performance of virtualized solutions using its previous generation Maxwell architecture and three times the amount GPU memory, while providing “reliable, predictable QOS accessible from any device.” 

"The enterprise is transforming. Workflows are evolving to incorporate AI, photorealism, VR, and greater collaboration among employees. The Quadro visualization platform is evolving with the enterprise to provide the performance required," said Bob Pette, NVIDIA’s VP of Professional Visualization. "With Quadro vDWS on Tesla-powered servers, businesses can tackle larger datasets, power the most demanding applications and meet the need for greater mobility."

tesla slide 2
(Click to Enlarge)

NVIDIA boasts that Tesla GPU accelerators backed by Quadro vDWS offer a number of advantages, including:

  • Increased productivity due to additional available GPU memory and compute performance
  • Unified graphics and compute workloads supporting CUDA and OpenCL
  • NVIDIA NVENC support, delivering better performance and user density through the off-loading H.264 video encoding for Linux virtual workstation users

Quadro vDWS will be available from a number of system vendors — including well-known brands like Cisco, Dell, Hewlett-Packard, and Lenovo — beginning September 1st.


Via:  NVIDIA
Show comments blog comments powered by Disqus