Living life as a Senior Systems Engineer Packet by Packet.
Friday, 18 December 2015
Graphics have gone off the GRID!
Hopefully by now, when you see or hear the words ‘NVIDIA GRID’…you know, this is all about delivering centrally managed, accelerated graphics to virtualised desktop infrastructures, right?
I’m guessing possibly not – anyone who uses VDI, knows that the biggest Achilles heel of the solution is delivering feature rich content and high end graphics to their power users. So what do IT Managers do, they resort to buying custom built workstations or MacPro’s and just accept that there is no alternative.
Interestingly, I think the lack of rapid deployments for NVIDIA GRID comes from the lack of market knowledge. Whomever I speak to about delivering Siemens NX, AutoDesk or CATIA (to name a few) through their VDI estate, tells me it’s not possible. It’s at that point I take great pride in having the ability to say ‘actually, it is possible and here’s why!’
Axess were one of Three partners in the UK chosen to take the solution to market in late 2013 and to be honest, for me, it’s been a rapid learning curve about Computational Fluid Dynamics and Thermal Transition Simulation – I never thought I’d be learning about the way liquid densities are affected by outside temperatures on a Boeing 747 and thus fuel economies are reduced! But the reason this is all important, generally engineers and designers are the people who feel the pain of not using VDI. These are the guys who have to work on desktop PCs, who can’t work from home, who are still susceptible to viruses and software corruption and those who have to beg for new desktops after 18 months.
For me, understanding these challenges is important – it means that when you’re talking to an IT manager about how you can make his life easier and reduce his costs, you can also talk to the designers and the engineers about how to make their lives easier and how much of an impact a system like this can have!
Alas however – I’m off on a tangent because recently announced by NVIDIA, is their new GRID 2.0 (sounds like Skynet, right?). Almost a dozen fortune 500 companies in the states are completing trials of GRID 2.0 right now - and with 125 approved server models supporting the technology– it looks like this solution could start opening some big doors.
Employees can work from almost anywhere without delays in downloading files, increasing their productivity. IT departments can equip workers with instant access to powerful applications, improving resource allocation. And data can be stored more securely by residing in a central server rather than individual systems.
"NVIDIA GRID technology enables employees to do their best work regardless of the device they use or where they are located. This is the future of enterprise computing." said Jen-Hsun Huang, co-founder and CEO of NVIDIA.
The ability to virtualise high end desktops from the datacentre has not been possible until now due to low performance, poor user experience and limited server and application support. NVIDIA GRID 2.0 integrates the GPU into the datacentre and clears away these barriers by offering:
Doubled user density: The original GRID solution introduced last year has been doubled, allowing up 128 users per server. This enables enterprises to scale more cost-effectively, expanding service to more employees at a lower cost per user.
Doubled application performance: Using the latest version of NVIDIA’s award-winning Maxwell™ GPU architecture, NVIDIA GRID 2.0 delivers twice the application performance as before — exceeding the performance of many native clients.
Blade server support: Enterprises can now run GRID-enabled virtual desktops on blade servers — not simply rack servers — from leading blade server providers (especially important for clients with Green initiatives).
Linux support: No longer limited to the Windows operating system, NVIDIA GRID 2.0 now enables enterprises in industries that depend on Linux applications and workflows to take advantage of graphics-accelerated virtualisation.