Managing the End User Experience with GPU-Powered Insights

Editor's Notes

• #2: Today you will learn about THREE key to improving the Productivity, Compliance and Security of your Citrix XenMobile Environment.
• #6: eG Innovations is dedicated to helping businesses across the globe transform IT services delivery into a competitive advantage and a center for productivity, growth and profit.
• #9: Founded in 1993Jen-Hsun Huang is co-founder and CEOListed with NASDAQ under the symbol NVDA in 1999 Invented the GPU in 1999 and has shipped more than 1 billion to date FY15: $4.68 billion in revenue 9,100 employees worldwide7,300 patent assetsHeadquartered in Santa Clara, Calif.
• #15: H: Part of the complexity in troubleshooting Citrix environments is driven by the sheer number of silo tools available for monitoring and performance diagnosis. We asked our Citrix professionals how many tools they use to manage their Citrix infrastructure. The answer to this question explains why Citrix admins have to spend so much time troubleshooting issues. 55% of respondents are using two to five management tools to manage Citrix performance. 25% of respondents are even using six to ten tools. Doug, do you have any comments? D: I would say larger the organization, more the number of domain experts and each of them has their own tools. Many organizations are still using administration tools supplied by the vendors for each tier. So even if you had the same expert managing the entire environment, there is still one tool for Citrix XenApp, another for , another for the storage tier, yet another for the network. S: The use of multiple tools by itself is not a problem – the problem is the amount of time needed to review the metrics from each tool and manually correlate and analyze what the tools are telling you to determine what action to take. This is a very slow, manual process and also one that needs the experts to be involved.
• #26: Application and desktop virtualization solutions have been around for a long time, but their number one point of failure tends to be user experience. The reason is very simple. When applications and desktops were first virtualized the technology, GPUs were not a part of the mix. This meant that all of the capture, encode and rendering that was traditionally done on a GPU in a physical device, was being handled by the CPU in the host. While it was functional for some of the more basic applications it never truly met the native experience and performance levels that most users needed. Then 3 years ago, NVIDIA release our GRID solution which allowed you to virtualize a datacenter GPU and share it across multiple VMs. This not only improved performance for existing application and desktop environments, it also opened up a whole new set of use cases that could leverage this technology.
• #27: 2x:Based on Lakeside SysTrack Community data 56%: Based on Lakeside SysTrack Community data 50%: Based on Gartner Strategic Planning Assumptions
• #30: 2x:Based on Lakeside SysTrack Community data 56%: Based on Lakeside SysTrack Community data 50%: Based on Gartner Strategic Planning Assumptions
• #31: NVIDIA GRID comes in three different editions that support different use cases. All editions are sold per concurrent user so you can mix and match to give users the exact performance they need. For customers who are deploying RDSH solutions, like Citrix XenApp, we have the GRID Virtual Applications edition. This enables you to provide graphics acceleration to remote application solutions which enable them to run at full performance. Customer who are deploying virtual desktop solution, like Citrix XenDesktop or VMware Horizon, choose between our GRID Virtual PC and GRID Virtual Workstation products. GRID Virtual PC is for users who run PC applications such as Microsoft Office, high definition or streaming video, browsers, etc. Traditionally if the application runs on a standard PC laptop than it is probably supported by the Virtual PC edition. GRID Virtual Workstation is for organizations who want to put the power of a Quadro workstation in the data center. Users in this group are running profession graphics applications such as Dassault’s CATIA, SolidWorks and 3DExcite, Siemens NX, PTC Creo, Schlumberger Petrel, Autodesk Maya. This product allows users who have traditionally relied high performance workstations sitting at their desk, to get the full benefits of mobility, flexibility and security that come with a centralized, virtual solution.
• #33: The main message is In guest – For the first time, NVIDIA is bringing its vGPU management capability in feature parity with extensive physical GPU management, and NVIDIA is the ONLY company to provide most extensive vGPU visibility in the industry In-host – For the first time, we are providing VM visibility inside a host. This is invaluable to get a cross section view of the hosts and do in-depth scalability planning, help desk use cases etc. In-host – for the first time, we are adding run-time system query capabilities for vGPU profiles, taking manual and guess work out of the deployment scenario. This would accelerate the integration with new hypervisor vendors. For end customers, this is especially important when it comes to some of our competition such as AMD, where there is significant manual work involved while creating virtual functions. NOTE: The in-guest metrics or vGPU metrics in host don’t apply to shared graphics mode such as vSGA (VMware) and RemoteFX (Microsoft). The in-guest metrics and some physical characteristics are already supported in GPU pass through (VMware vDGA, Microsoft DDA, Citrix passthrough etc.) mode. The host level vGPU metrics don’t apply in this case.
• #34: 2x:Based on Lakeside SysTrack Community data 56%: Based on Lakeside SysTrack Community data 50%: Based on Gartner Strategic Planning Assumptions