By James Hsu, Director of Technical Marketing at Citrix
One of the great experiences in our industry is to see products from different vendors—hardware and software—come together to solve real customer problems. That’s what’s been happening with Citrix and Intel for the last two years as we worked together to apply Intel Graphics Virtualization Technology (Intel GVT) to the Citrix XenServer virtualization platform. The result of that effort is Citrix XenServer 7.0, which we are announcing at Citrix Synergy 2016 in Las Vegas. It’s the first commercial hypervisor product to leverage Intel GVT-g, Intel’s virtual graphics processing unit that can power multiple VMs with one physical GPU. As well as announcing XenServer 7.0, Citrix is also announcing XenDesktop 7.9 offering industry-leading remote graphics delivery supported by Intel. Let me tell you what that does for users running graphics-intensive virtualized desktop applications, and then I’ll tell you how we used Intel GVT-g to do it.
Citrix XenApp and XenDesktop lets you deliver virtualized desktop and applications hosted on a server to remote workstations. Many desktop applications—like computer-aided design and manufacturing apps and even accelerated Microsoft Office—require the high-performance graphics capabilities of a graphics processing unit (GPU). In XenDesktop 7.9 Citrix also added support for Intel Iris Pro graphics in the HDX 3D Pro remote display protocol.
Earlier versions of XenServer enabled Intel GPU capabilities on virtualized desktops in a pass-through mode that allocated the GPU to a single workstation. Now, XenServer 7.0 expands our customers’ options by using Intel GVT-g to virtualize access to the Intel Iris Pro Graphics GPU integrated onto select Intel Xeon processor E3 family products , allowing it to be shared by as many as seven virtual workstations.
With Intel GVT-g, each virtual desktop machine has its own copy of Intel’s native graphics driver, and the hypervisor directly assigns the full GPU resource to each virtual machine on a time-sliced basis. During its time slice, each virtual machine gets a dedicated GPU, but the overall effect is that a number of virtual machines share a single GPU. It’s an ideal solution in applications where high-end graphics are required but shared access is sufficient to meet needs. Using the Intel Xeon processor E3 family, small single-socket servers can pack a big graphics punch. It’s an efficient, compact design that enables a new scale-out approach to virtual application delivery. And it’s a cost-effective alternative to high-end workstations and servers with add-on GPU cards.
The advantages go beyond just cost efficiency. Providing shared access by remote users to server-based data and applications enhances worker productivity and improves collaboration. It also tightens security and enables compliance, because critical intellectual property, financial data, and customer information stays in the data center rather than drifting out to individual workstations and mobile devices. And security is further enhanced, because Intel Xeon processors contain Intel Trusted Execution Technology (Intel TXT) to let you create trusted computing pools. Intel TXT attests to the integrity and trust of the platform, assures nothing has been tampered with, and verifies that the platform is running the authorized versions of firmware and software when booting up.
At Citrix, our goal is to provide our customers with the computing experience they need to innovate and be productive—on a range of platforms and usage models and in a way that enhances the security of their business. And we want to give them the flexibility to access the computing resources they need anywhere, any time, and from any device. Our collaboration with Intel has let us deliver on that promise, and it lets us provide even more options for platform choice and deployment configurations. It’s been a great experience for us, and now it will enable a great experience for our mutual customers.