Tuesday, May 15th 2012

NVIDIA Introduces First Virtualized GPU, Accelerating Graphics for Cloud Computing

NVIDIA today unveiled the NVIDIA VGX platform, which enables IT departments to deliver a virtualized desktop with the graphics and GPU computing performance of a PC or workstation to employees using any connected device.

With the NVIDIA VGX platform in the data center, employees can now access a true cloud PC from any device -- thin client, laptop, tablet or smartphone -- regardless of its operating system, and enjoy a responsive experience for the full spectrum of applications previously only available on an office PC.

NVIDIA VGX enables knowledge workers for the first time to access a GPU-accelerated desktop similar to a traditional local PC. The platform's manageability options and ultra-low latency remote display capabilities extend this convenience to those using 3D design and simulation tools, which had previously been too intensive for a virtualized desktop.

Integrating the VGX platform into the corporate network also enables enterprise IT departments to address the complex challenges of "BYOD" -- employees bringing their own computing device to work. It delivers a remote desktop to these devices, providing users the same access they have on their desktop terminal. At the same time, it helps reduce overall IT spend, improve data security and minimize data center complexity.

"NVIDIA VGX represents a new era in desktop virtualization," said Jeff Brown, general manager of the Professional Solutions Group at NVIDIA. "It delivers an experience nearly indistinguishable from a full desktop while substantially lowering the cost of a virtualized PC."

The NVIDIA VGX platform is part of a series of announcements NVIDIA is making today at the GPU Technology Conference (GTC), all of which can be accessed in the GTC online press room.

The VGX platform addresses key challenges faced by global enterprises, which are under constant pressure both to control operating costs and to use IT as a competitive edge that allows their workforces to achieve greater productivity and deliver new products faster. Delivering virtualized desktops can also minimize the security risks inherent in sharing critical data and intellectual property with an increasingly internationalized workforce.

NVIDIA VGX is based on three key technology breakthroughs:
  • NVIDIA VGX Boards. These are designed for hosting large numbers of users in an energy-efficient way. The first NVIDA VGX board is configured with four GPUs and 16 GB of memory, and fits into the industry-standard PCI Express interface in servers.
  • NVIDIA VGX GPU Hypervisor. This software layer integrates into commercial hypervisors, such as the Citrix XenServer, enabling virtualization of the GPU.
  • NVIDIA User Selectable Machines (USMs). This manageability option allows enterprises to configure the graphics capabilities delivered to individual users in the network, based on their demands. Capabilities range from true PC experiences available with the NVIDIA standard USM to enhanced professional 3D design and engineering experiences with NVIDIA Quadro or NVIDIA NVS GPUs.
The NVIDIA VGX platform enables up to 100 users to be served from a single server powered by one VGX board, dramatically improving user density on a single server compared with traditional virtual desktop infrastructure (VDI) solutions. It sharply reduces such issues as latency, sluggish interaction and limited application support, all of which are associated with traditional VDI solutions.

With the NVIDIA VGX platform, IT departments can serve every user in the organization -- from knowledge workers to designers ---with true PC-like interactive desktops and applications.

NVIDIA VGX boards are the world's first GPU boards designed for data centers. The initial NVIDIA VGX board features four GPUs, each with 192 NVIDIA CUDA® architecture cores and 4 GB of frame buffer. Designed to be passively cooled, the board fits within existing server-based platforms.

The boards benefit from a range of advancements, including hardware virtualization, which enables many users who are running hosted virtual desktops to share a single GPU and enjoy a rich, interactive graphics experience; support for low-latency remote display, which greatly reduces the lag currently experienced by users; and, redesigned shader technology to deliver higher power efficiency.

The NVIDIA VGX GPU Hypervisor is a software layer that integrates into a commercial hypervisor, enabling access to virtualized GPU resources. This allows multiple users to share common hardware and ensure virtual machines running on a single server have protected access to critical resources. As a result, a single server can now economically support a higher density of users, while providing native graphics and GPU computing performance.
This new technology is being integrated by leading virtualization companies, such as Citrix, to add full hardware graphics acceleration to their full range of VDI products.

NVIDIA User Selectable Machines
NVIDIA USMs allow the NVIDIA VGX platform to deliver the advanced experience of professional GPUs to those requiring them across an enterprise. This enables IT departments to easily support multiple types of users from a single server.

USMs allow better utilization of hardware resources, with the flexibility to configure and deploy new users' desktops based on changing enterprise needs. This is particularly valuable for companies providing infrastructure as a service, as they can repurpose GPU-accelerated servers to meet changing demand throughout the day, week or season.

Leading Businesses Endorse NVIDIA VGX
"Jaguar Land Rover is a global company with an international workforce. The 'holy grail' for us is to deliver virtualized desktop to engineers overseas so we can harness the best engineering talent on the planet without risking the security of our new car designs. The NVIDIA VGX platform is the most promising step we've seen in addressing the user experience for our virtualized workforce. With NVIDIA VGX, engineers for the first time can run all of the office productivity and technical applications they need in a virtualized environment. This will dramatically improve the productivity of our global workforce."
-- Gordon McMullan, interim CTO, Jaguar Land Rover

"Larson Design Group is a growing company that teams with our clients to provide responsive, innovative solutions for facility, transportation, land development and environmental needs. We therefore look to deploy technologies that will help sustain our growing geographic reach, ease administration and allow our engineers to reach their creative maximum and be more connected to client needs. With NVIDIA VGX, our engineers can now take any mobile device to the client's site, work interactively with them on a fully virtualized desktop and still maintain the industry's highest productivity levels."
-- Keith S. Kuzio, CEO, Larson Design Group

Leading Virtualization Companies Endorse NVIDIA VGX
"Desktop virtualization is rapidly becoming mainstream for enterprises. By leveraging the NVIDIA VGX platform, combined with XenDesktop and HDX technologies, we are enabling enterprise customers to virtually deliver graphics-intensive apps beyond power users and designers. Now, they can also serve users who require only occasional access to graphics-intensive apps, which previously would have been cost-prohibitive. The combined virtual desktop solution for serving these users can be reduced by up to 80 percent, while enabling users to securely access GPU-accelerated apps from any device."
-- Sumit Dhawan, vice president and general manager of Receivers and Gateways, Citrix

Leading OEMs Endorse NVIDIA VGX
"NVIDIA virtualized GPU technology aligns with Cisco's vision of cloud and delivery of desktop and rich-media applications. GPU virtualization is the one major technology challenge that has been holding back deeper adoption of VDI in the enterprise. We believe NVIDIA's breakthrough will deliver the unique user experience and ease of management customers have been demanding."
-- David Yen, senior vice president and general manager of Data Center Business Group, Cisco

"Virtual desktop environments can enable mobile workforces to perform tasks more efficiently. With HP VirtualSystem utilizing HP Blade Servers and the NVIDIA VGX platform, clients can easily deploy a simplified virtualized environment that quickly delivers the information or applications users need."
-- Chuck Smith, vice president of Worldwide Industry Standard Servers, HP

Availability and Pricing
The NVIDIA VGX platform, including new NVIDIA VGX boards, the NVIDIA GPU Hypervisor and NVIDIA USMs, is planned to be available for deployment across the enterprise through NVIDIA's hardware OEM and VDI partners later this year.
Add your own comment

12 Comments on NVIDIA Introduces First Virtualized GPU, Accelerating Graphics for Cloud Computing

would be cool if I can play a game on the cloud with full graphics acceleration :D
Posted on Reply
"First"?! Well... I'd normally complain here about the use of "first", but any vGPU progress made is very much appreciated and I'll let it slide. Especially with such an aggressive, respectable push! :D
Posted on Reply
As someone who works for an engineering firm whom has begun using VMs in mass this is fantastic news.
Posted on Reply
by: suraswami
would be cool if I can play a game on the cloud with full graphics acceleration :D
Posted on Reply
by: Leon2ky
As someone who works for an engineering firm whom has begun using VMs in mass this is fantastic news.
How often do we need a GPU in a office machine, so TCO and performance unless you are running fiber to each desktop is going to suck.

A 1080 60FPS stream at 32bit depth is almost 30gigabits per second unless you start using compression, and if you want to do that you might as well run a dedicated hardware/client system with capable hardware.

Or if you are doing accounting and need some performance the same energy a thin client consumes will be outperformed by a few more watts in a low profile system.

Do they have apps that allow for direct control of the rendering API from the network as that is a huge security hole just waiting to be infected.
Posted on Reply
Nick [D]vB
It would be cool if a game studio like EPIC or Crytek could use this for a service like Onlive but using their next-generation engines, with graphics way beyond what could be done in real-time even on a current high-end gaming rig. These same games could then be released a few years later to run locally when the next-gen consoles are out or the PC hardware is fast enough to run them, but if they can sort out the latency issue the next-next-gen consoles will probably render everything in the cloud anyway...
Posted on Reply
by: Nick [D]vB
but if they can sort out the latency issue the next-next-gen consoles will probably render everything in the cloud anyway...
Latency and Bandwidth. Doubt any standard (or even premium) connection can carry a true colour, 1920*1080 @30 (60?)FPS without -very- heavy compression (and a noticeable loss in quality). The issue wasn't the hardware as much as it was the connection.

But I see game publishers loving this idea. Would completely wipe out piracy if the industry completely switched to Cloud gaming.
Posted on Reply
by: Shihabyooo
Would completely wipe out piracy if the industry completely switched to Cloud gaming.
You serious?! :laugh::laugh::roll:
Posted on Reply

4 GPUs and one power connector.? :eek: :toast:
Posted on Reply
by: Shihabyooo
Would completely wipe out piracy if the industry completely switched to Cloud gaming.
Would also completely wipe out the industry. few are those who desire to be chained to a "cloud" 24/7; more and more people are going to realise its downsides once they become mroe aware of what is happening with "their" data.
Posted on Reply
by: Recus

4 GPUs and one power connector.? :eek: :toast:
Not really surprising. Those aren't GK104's, are likely clocked lower than desktop cards, and that might be an 8-pin connector
Number of Users Up to 100
GPU Specifications
Number of GPUs 4
Total NVIDIA CUDA® Cores 768
Shader Perf (TFLOPS) 1.3
Power (W) 150
Memory Specs
Memory Size (GB) 16
Memory Type DDR3
Memory Perf (GB/sec) 115
Form Factor
Length 10.5"
Height 4.4"
Width Dual slot
Posted on Reply
Add your own comment