Wednesday , 18 July 2018
Home >> C >> Chips >> Nvidia’s new virtualisation software turns its GPUs into workstations

Nvidia’s new virtualisation software turns its GPUs into workstations

NVIDIA has announced a new software suite which will allow users to virtualise an operating system to turn the company’s ridiculously powerful Tesla GPU servers into powerful workstations.

Quadro vDWS runs graphic and compute workloads in a virtualised environment, offering the ability to create increased productivity, unified graphic and compute workloads and significantly raised performance for Linux users, aimed at users working on 3D, photorealistic rendering, virtual reality (VR) and deep learning projects.

Nvidia recommends Pascal-based Tesla GPU accelerators, which when combined with the new vDWS suite, offers up to 24GB of GPU memory, perfect for complex modelling.

It also boasts double performance compared to previous GPU architecture, access to CUDA and Open CL workflows to streamline design and computer-aided engineering and as mentioned a performance boost for Linux users by offloading the H.264 graphics work to the cloud.

“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, vice president of Professional Visualization at NVIDIA.

“With Quadro vDWS on Tesla-powered servers, businesses can tackle larger datasets, power the most demanding applications and meet the need for greater mobility.”

The news comes alongside improvements to the NVIDIA GRID virtual PC (vPC) line which offers up to 24 instances of 1GB virtual desktop (double the previous offering), with greater vGPU insight via a range of dashboards including VMware vRealize Operations (bROps), Citrix Director and XenCenter.

The whole thing combines to offer the system managers of the world a better service with more equilibrium, even if there’s a resource hog in the chain.

Alongside all this comes the Tesla P6, a new blade server GPU which joins the P4, P40 and P100, offering 16GB of memory which can be split down to 16x1GB machines.

At this years GTC conference in San Jose, Nvidia announced the Volta based GPU range, which it claims has the performance of 100 CPUs.

The software is available now at 100 server locations worldwide, including offerings from Cisco, Citrix, Dell, HP, Lenovo and VMWare. New Pascal-based feature and function follows on September 1st. µ



  • <!–

  • Save this article

  • –>

==[ Click Here 1X ] [ Close ]==