NVIDIA GRID – RDSH licensing (including XenApp)

I’ve had a few questions about what licensing is needed under the GRID 2.0 and up software licensing for the M60/M10/M6 GPUs for RDSH solutions such as XenApp. I think the confusion arises because it’s possible to use a number of GPU/vGPU different profiles for a server OS VM. The key point is to remember that the licensing is always per user.

More Lenovo Servers Support NVIDIA GPUs Including the M60

Lenovo have recently qualified and announced support for more NVIDIA GPUs for several servers including the x3650 M5 (E5-2600 v4), details can be found on Lenovo’s site, here:

• https://lenovopress.com/lp0068-lenovo-system-x3650-m5-e5-2600-v4#gpu-adapters

Also recently listed is the x3500 M5:

• https://lenovopress.com/tips1242-system-x3500-m5#gpu-adapters

This means Lenovo have worked with NVIDIA to test and certify that both parties hardware, firmware and software is fully-compatible, thermally and electrically stable.

Where to find the drivers for NVIDIA GRID 2.0 vGPU and up, including M60 and M6 drivers

Quick blog, to highlight where you get GRID vGPU drivers and software for GRID 2.0 and higher. Whilst unsupported older products are available on the general NVIDIA download sites, newer products need to be obtained via the NVIDIA enterprise licensing portal.

Customers of GRID 2.0 and up NVIDIA products should receive access to an NVIDIA licensing portal account. Drivers for the GRID GPU cards such as the M6 and M60 can be obtained via this portal.

Two types of customers: 90 days evaluation (pre-sales), and paying customers

Evaluation Customers

1. Go to www.nvidia.com/grideval
2. Click “software download”
3. Fill in registration form
4. Get access to the NVIDIA licensing portal that will let you download 128 evaluation licenses and GRID software.

• If you are already registered, and need to return to the licensing portal, follow this link: https://nvidia.flexnetoperations.com/

 Paying Customers

1. The process is documented here: http://images.nvidia.com/content/pdf/grid/guides/quickstartguide.pdf
2. But just to capture the summary from this documentation

• When you purchase GRID, you receive email with PAK and registration link to the licensing portal.
• When you login to the portal, you get access to download all the licenses you have purchased along with GRID software.

Relevant Products:

Enterprise supported GRID vGPU drivers including M60 and M6 GPUs

Benchmarking virtualized NVIDIA GRID GPU cards using HPC methodologies! Don’t wear shiny green high-heels in the farmyard!

Follow GRID team’s @AmandaMSaunders and the adventures of the magical GRID shoes!

I’ve been cc:d on a clutch of strange enquiries recently where people are trying to evaluate the NVIDIA GRID GPU cards using HPC (High-performance computing) methods, benchmarks and comparisons. Hypervisors aren’t usually fully compatible with HPC application architecture and as such, although the newest NVIDIA Tesla cards (M60/M6) can be repurposed between a “compute mode” and a specialist “graphics” mode is provided for virtualized graphics designed with hypervisors and graphical application architecture in mind.

The previous (Kepler) generation of NVIDIAGPUs for virtualized graphics (GRID K1/K2) are designed solely for grahical workloads.

NVIDIA M60 GPUs – how they support CUDA, OpenCL and compute in “graphics” mode

Yesterday I wrote a blog about how to configure the M60 / M6 NVIDIA GPU boards for use for “graphics” mode or “compute” mode and how they were designed for different use cases such as VDI accelerated graphics and HPC (high-performance compute) respectively.

This has led to some questions as to whether “graphics” supports compute and CUDA like technologies. The answer is yes!

Mode switching on NVIDIA M60 (GRID 2.0) cards – modeswitch tool

Update (24th Feb 2016): Jason Southern has published an overview and how-to-guide on this tool: https://www.youtube.com/watch?v=VAQhiNNFXxQ&feature=youtu.be

 

I had an enquiry this week asking what the “modeswitch tool” is and when a user should use it. Basically a GRID 1.0 K1/K2 user had been to a demo of the new GRID 2.0 M60 GPUs. As he hadn’t got M60 boards yet he didn’t have the tool and hadn’t downloaded it (so hadn’t read the very comprehensive documentation that comes with it explain when and why to use it) but he’d remembered some information from the demo and was trying to extrapolate that to his GRID 1.0 K1/K2 cards.