Yes http://www.nvidia.com/object/cloud-gaming.html I'd love to read a more technical breakdown on what is happening behind the scenes, if anyone has something please link it up.
-
Competitor rules
Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
AMD Multiuser GPU – World’s First Hardware-Based Virtualized GPU
- Thread starter shankly1985
- Start date
Yes http://www.nvidia.com/object/cloud-gaming.html I'd love to read a more technical breakdown on what is happening behind the scenes, if anyone has something please link it up.
- Joined
- 25 Nov 2011
- Posts
- 20,679
- Location
- The KOP
AMD say Grid is software base not hardware.
Virtualization method - AMD Hardware - Nvidia Software
OpenCL™ 2.0 acceleration support - AMD Yes - Nvidia No
Stable, predictable performance - AMD Yes - Nvidia No
Dedicated share of local memory for increased security - AMD Yes - Nvidia No
Maximum users per physical GPU - AMD 15 - Nvidia 8
Soldato
- Joined
- 20 Apr 2004
- Posts
- 4,410
- Location
- Rugby
They had shader based AA methods first but kinda went away after the likes of FXAA came on to the scene
Last edited:
Associate
- Joined
- 3 Jan 2010
- Posts
- 1,379
Imagine if R&D department of AMD could have had more funding all these years and dominant market share to support it .Could have been years ahead of where we are now and with some other stuff coming out the wings. Nvidia make generally the best all round cards but AMD are definitely the ones pushing stuff forward. It's kind of sad they miss a few steps here and there and we get people act like it's the end of the world.
- Joined
- 25 Nov 2011
- Posts
- 20,679
- Location
- The KOP
Virtualization
VDI and Virtualized Workstations
For companies considering centralized computing solutions, AMD FirePro™ S-series server cards make it easy for IT to choose one flexible, scalable solution to meet various employee needs. It’s now possible to take advantage of the processing power of the GPU to create virtual machines for users – all managed from one central, secure location.
Benefits for IT:
Flexible configuration options
Support for leading virtualization technologies from Citrix®, Microsoft® and VMware®
GPU-accelerated applications in virtualized environments
Ability to move more specialized professionals away from physical PCs and into the cloud
More easily manage employee hardware and software from one central location
The world's first hardware-based virtualized GPU solution
Quite a Big copy and paste! Read more here http://www.amd.com/en-us/solutions/professional/virtualization#
Enable consistent, predictable, and secure performance from your virtualized workstation with the world’s first hardware-based virtualized GPU solution, the AMD Multiuser GPU.* This new virtualization solution from AMD will enable users to have workstation-class experiences with full ISV certifications and local desktop-like performance.
Predictable performance
An AMD graphics card equipped with our Multiuser GPU technology offers consistent, predictable performance. IT managers can easily configure these solutions to allow for up to 16 users on a single GPU. When the card is appropriately configured to meet the needs of the organization, users expect the same access to the GPU no matter their workload. There is no worry about any one user tying up the entire GPU while other users experience slow and unresponsive systems. Each user now has an equal share of the GPU to allow them to design, create, and execute their
2-6 USERS
Workstation Performance Use Cases (Graphics intensive design applications)
6-10 USERS
Power User Use Cases (Enterprise GPU applications and CAD viewer only support)
UP TO 16 USERS
Knowledge Worker Use Cases (Office-type applications)
Full-featured virtual GPU
Software virtualization has traditionally been a limiting factor for those who want to fully utilize GPU hardware acceleration for compute tasks under Open CL. With AMD’s implementation of the new Multiuser GPU, users are no longer as limited to what they can or can’t do in a virtualized environment. Users will have access to native AMD display drivers for OpenGL, DirectX®, and OpenCL acceleration, enabling them to work with few if any restrictions. Whatever users were able to do on a local machine they can now do using our new virtualization technology.
Data secure
Users will have peace of mind knowing that their valuable work and data cannot be viewed by other prying eyes. Unlike software virtualization, AMD’s hardware-based virtualization solution makes it extremely difficult for a hacker to break in at the hardware level, whereas with software virtualization, any breaches or holes in the underlying driver can be exploited to access a guest virtual machine in an unauthorized fashion. For organizations that highly value security, the new AMD Multiuser GPU is the clear option for their virtualized workstation needs.
The AMD Multiuser GPU works with hypervisors to provide ease of installation. IT managers and system administrators setting up a central server within an enterprise environment can easily implement and configure the AMD Multiuser GPU with a hypervisor driver no bigger than a typical word processing document. The same graphics driver used for local workstations equipped with AMD FirePro™ graphics cards can be installed and used in this virtualized environment.
AMD Multiuser GPU is designed to work on environments using VMWare vSphere/ESXi 5.5 and up, with support for remote protocols such as Horizon View, Citrix Xen Desktop, Teradici Workstation Host Software, and others.
One solution for knowledge workers and power users
VDI and Virtualized Workstations
For companies considering centralized computing solutions, AMD FirePro™ S-series server cards make it easy for IT to choose one flexible, scalable solution to meet various employee needs. It’s now possible to take advantage of the processing power of the GPU to create virtual machines for users – all managed from one central, secure location.
Benefits for IT:
Flexible configuration options
Support for leading virtualization technologies from Citrix®, Microsoft® and VMware®
GPU-accelerated applications in virtualized environments
Ability to move more specialized professionals away from physical PCs and into the cloud
More easily manage employee hardware and software from one central location
The world's first hardware-based virtualized GPU solution
Quite a Big copy and paste! Read more here http://www.amd.com/en-us/solutions/professional/virtualization#
Enable consistent, predictable, and secure performance from your virtualized workstation with the world’s first hardware-based virtualized GPU solution, the AMD Multiuser GPU.* This new virtualization solution from AMD will enable users to have workstation-class experiences with full ISV certifications and local desktop-like performance.
Predictable performance
An AMD graphics card equipped with our Multiuser GPU technology offers consistent, predictable performance. IT managers can easily configure these solutions to allow for up to 16 users on a single GPU. When the card is appropriately configured to meet the needs of the organization, users expect the same access to the GPU no matter their workload. There is no worry about any one user tying up the entire GPU while other users experience slow and unresponsive systems. Each user now has an equal share of the GPU to allow them to design, create, and execute their
2-6 USERS
Workstation Performance Use Cases (Graphics intensive design applications)
6-10 USERS
Power User Use Cases (Enterprise GPU applications and CAD viewer only support)
UP TO 16 USERS
Knowledge Worker Use Cases (Office-type applications)
Full-featured virtual GPU
Software virtualization has traditionally been a limiting factor for those who want to fully utilize GPU hardware acceleration for compute tasks under Open CL. With AMD’s implementation of the new Multiuser GPU, users are no longer as limited to what they can or can’t do in a virtualized environment. Users will have access to native AMD display drivers for OpenGL, DirectX®, and OpenCL acceleration, enabling them to work with few if any restrictions. Whatever users were able to do on a local machine they can now do using our new virtualization technology.
Data secure
Users will have peace of mind knowing that their valuable work and data cannot be viewed by other prying eyes. Unlike software virtualization, AMD’s hardware-based virtualization solution makes it extremely difficult for a hacker to break in at the hardware level, whereas with software virtualization, any breaches or holes in the underlying driver can be exploited to access a guest virtual machine in an unauthorized fashion. For organizations that highly value security, the new AMD Multiuser GPU is the clear option for their virtualized workstation needs.
The AMD Multiuser GPU works with hypervisors to provide ease of installation. IT managers and system administrators setting up a central server within an enterprise environment can easily implement and configure the AMD Multiuser GPU with a hypervisor driver no bigger than a typical word processing document. The same graphics driver used for local workstations equipped with AMD FirePro™ graphics cards can be installed and used in this virtualized environment.
AMD Multiuser GPU is designed to work on environments using VMWare vSphere/ESXi 5.5 and up, with support for remote protocols such as Horizon View, Citrix Xen Desktop, Teradici Workstation Host Software, and others.
One solution for knowledge workers and power users
Knowledge workers
The most common type of employee. They require a PC to do their job, usually a basic desktop or laptop system with office productivity applications and Internet connectivity.
Knowledge workers are the most typical type of employee found in every business. While the work they do is valuable, they don’t need a powerful PC to get the job done. With the latest advancements in computing hardware, software and communication technologies, it’s now possible to give every employee a robust computing experience, on par with a physical system, from the cloud.
One GPU, multiple virtual machines
In a shared GPU model every employee still feels like they have their own PC, but in fact all of the applications and processing hardware are centrally located in the data center. The employees are actually working on a virtual machine that they access via a compatible thin or zero client.
Power users
Requires everything a knowledge worker needs and more. They need more powerful PCs to run more specialized applications used for design, 3-D modeling, simulation and more. Power users are typically professionals in the design, engineering and simulation industries.
GPU-accelerated applications on virtual machines
Thanks to the tremendous processing power of the GPU, power users working with specialized applications can be transitioned from a physical tower or mobile workstation to a virtual machine that resides in the data center. These power users are working with more graphics-intensive applications than the typical knowledge worker, applications that perform best on a discrete GPU.
The ideal type of power user who can easily transition to virtual machine is an engineer, designer or modeler currently working on a tower or mobile workstation. Depending on the applications and workload, these professionals can be transitioned via a shared GPU model (one GPU for many users) or to a dedicated GPU model (one GPU per user).
However, there are various levels of power users, with some needing more processing horsepower than others. With AMD FirePro™ S-series graphics cards, and virtualization technologies from Citrix®, Microsoft® and VMware®, IT can find the right mix of hardware and software to meet a variety of end-user needs.
For companies looking to take advantage of the shared GPU model to support multiple midrange power users, AMD FirePro S-series server cards support Microsoft ® RemoteFX and VMware ESX 5.5.
For companies looking to take advantage of the dedicated GPU model to support midrange to ultrahigh power users, AMD FirePro S-series server cards support VMware ESXi 5.1 and Citrix XenDesktop® and XenApp.
The most common type of employee. They require a PC to do their job, usually a basic desktop or laptop system with office productivity applications and Internet connectivity.
Knowledge workers are the most typical type of employee found in every business. While the work they do is valuable, they don’t need a powerful PC to get the job done. With the latest advancements in computing hardware, software and communication technologies, it’s now possible to give every employee a robust computing experience, on par with a physical system, from the cloud.
One GPU, multiple virtual machines
In a shared GPU model every employee still feels like they have their own PC, but in fact all of the applications and processing hardware are centrally located in the data center. The employees are actually working on a virtual machine that they access via a compatible thin or zero client.
Power users
Requires everything a knowledge worker needs and more. They need more powerful PCs to run more specialized applications used for design, 3-D modeling, simulation and more. Power users are typically professionals in the design, engineering and simulation industries.
GPU-accelerated applications on virtual machines
Thanks to the tremendous processing power of the GPU, power users working with specialized applications can be transitioned from a physical tower or mobile workstation to a virtual machine that resides in the data center. These power users are working with more graphics-intensive applications than the typical knowledge worker, applications that perform best on a discrete GPU.
The ideal type of power user who can easily transition to virtual machine is an engineer, designer or modeler currently working on a tower or mobile workstation. Depending on the applications and workload, these professionals can be transitioned via a shared GPU model (one GPU for many users) or to a dedicated GPU model (one GPU per user).
However, there are various levels of power users, with some needing more processing horsepower than others. With AMD FirePro™ S-series graphics cards, and virtualization technologies from Citrix®, Microsoft® and VMware®, IT can find the right mix of hardware and software to meet a variety of end-user needs.
For companies looking to take advantage of the shared GPU model to support multiple midrange power users, AMD FirePro S-series server cards support Microsoft ® RemoteFX and VMware ESX 5.5.
For companies looking to take advantage of the dedicated GPU model to support midrange to ultrahigh power users, AMD FirePro S-series server cards support VMware ESXi 5.1 and Citrix XenDesktop® and XenApp.
Last edited:
That is quite a lot of somewhat shameful FUD being presented there, for example a single user cannot tie up a GPU in the way they are claiming 'could' happen.
The thing I really do take umbridge with is this:
With GRID you have a virtualised GPU sitting in the Hypervisor, memory management and partitioning is handled there, and has been proven as more than secure and stable for many organisations. At no point does a user have direct access to the underlying GPU or GPU memory space.
AMD's approach to this market shows a lack of class. Stepping up and trashing a solution that is proven and secure enough for the worlds largest enterprise IT company does you no favours in the eyes of those who will be planning on using this technology/ Explain why it actually is better (if it is), rather than how everything else is worse.
Edit: GRID 2.0 based upon Maxwell increases users per GPU to 16 amongst other features: http://images.nvidia.com/content/pdf/grid/data-sheet/NVIDIA-GRID20-DS.pdf
The thing I really do take umbridge with is this:
With GRID you have a virtualised GPU sitting in the Hypervisor, memory management and partitioning is handled there, and has been proven as more than secure and stable for many organisations. At no point does a user have direct access to the underlying GPU or GPU memory space.
AMD's approach to this market shows a lack of class. Stepping up and trashing a solution that is proven and secure enough for the worlds largest enterprise IT company does you no favours in the eyes of those who will be planning on using this technology/ Explain why it actually is better (if it is), rather than how everything else is worse.
Edit: GRID 2.0 based upon Maxwell increases users per GPU to 16 amongst other features: http://images.nvidia.com/content/pdf/grid/data-sheet/NVIDIA-GRID20-DS.pdf
Last edited:
- Joined
- 25 Nov 2011
- Posts
- 20,679
- Location
- The KOP
lol
AMD is always wrong, a forum user on OCUK told you so.. Yeah yeah... Man they wouldn't write up an article if it was all rubbish.. That would be plain lying and would be classed has false advertisement.
AMD is always wrong, a forum user on OCUK told you so.. Yeah yeah... Man they wouldn't write up an article if it was all rubbish.. That would be plain lying and would be classed has false advertisement.
Last edited:
Our council tried to switch to a VDI infrastructure with BT doing the design and implementation. Was an absolute 100% failure of epic proportions, and resulted in complete loss of service for front line staff for days on end (not to mention several million £ wasted).
We found that most bespoke apps couldn't be virtualised, and a mish-mash of VDIs and workstations created more hassle than it was worth.
Does anyone here use VDI infrastructure across a large organisation with many employees? I've only ever seen it done successfully with relatively small organisations and a small number of apps.
In short, esp for their "knowledge" class users, I'm not sure why you wouldn't just have a workstation with integrated graphics on CPU. It's all these guys need, and it's much less hassle than going VDI.
We found that most bespoke apps couldn't be virtualised, and a mish-mash of VDIs and workstations created more hassle than it was worth.
Does anyone here use VDI infrastructure across a large organisation with many employees? I've only ever seen it done successfully with relatively small organisations and a small number of apps.
In short, esp for their "knowledge" class users, I'm not sure why you wouldn't just have a workstation with integrated graphics on CPU. It's all these guys need, and it's much less hassle than going VDI.
The only reason AMD is first is they ignore all the other markets that beat them to it. For example AMD was 2nd or 5th in low level API's depending how you count, 2nd in homogenius CPU's, 2nd in hardware virtualization GPU's. But they conveniently forgot we have GPU's and CPU's outside the desktop market and all they did was copy the other GPU's and CPU's.
EDIT: I know this is a desktop section but AMD didn’t say desktop first. They said world first and industry first which doesn’t look true to me.
Last edited: