Going Virtual with the BOXX ProVDI 8401R-V

Virtualization has enabled companies to host multiple users running business office applications on a single server. But until recently, these virtual machines lacked the power to meet the graphics-intensive needs of designers and engineers.

Virtual desktop infrastructure (VDI) is a recent variation on the client-server computing model. It hosts a desktop operating system – such as Microsoft Windows – on a centralized server. That desktop image is then delivered over a network to an end-point device, most often a traditional PC. The user then interacts with the OS and its applications as if they were running locally.

This approach can have many benefits. Because little actual computing takes place at the endpoint, you no longer need a powerful workstation at your desk. With the applications and user files all residing on a central server, data is stored securely in the data center. You can login remotely from anywhere with a LAN or internet connection. And because everything stays in the server room and runs on the server, users don’t need to transfer large files – only keyboard and mouse input is sent to the server and pixels streamed back to the user.

 
BOXX Breaks New Ground

BOXX has been quite active in the VDI arena for many years, having previously released both PCoIP- and GRID- (GPU virtualization) based solutions. Last fall, BOXX introduced its ProVDI 8401R-V, the world’s first overclocked VDI system. BOXX claimed that its new ProVDI solution provided enough power to fully support graphics-intensive 3D modeling applications. By overclocking the CPU, the BOXX ProVDI hardware significantly boosts performance over that of competing VDI systems. And by relying on individual professional-grade NVIDIA graphics cards rather than GRID technology, the BOXX ProVDI solution delivers faster frame rates on the endpoint device while eliminating the licensing costs associated with GRID software.

At least, that’s the promise. To see for ourselves, we undertook one of the most intensive hands-on reviews ever conducted at DE, extending over several months. BOXX initially configured a ProVDI system for our use at their headquarters in Austin, TX. We logged on to this system remotely and ran an extensive suite of tests, including industry-standard benchmarks as well as several mainstream CAD applications. BOXX then shipped the hardware to our offices where we repeated all of those tests a second time to compare the difference in performance caused by latency. We reasoned – quite logically – that performance would improve when accessing the virtual machines over a LAN with the server sitting a few feet from the clients rather tha over the internet to a server located more than 2,000 miles away. The results surprised us.

 

READ THE FULL ARTICLE FROM DIGITAL ENGINEERING

In It for the Long Haul

How a 3-year-old BOXX workstation is faster than your brand new Dell or HP.

 “Kaby Lake” is the latest processor from Intel, introduced in early 2017, and features a top clock speed of 4.2GHz. That sounds impressive, until you realize that BOXX offered safely overclocked 4.3GHz workstations as far back as late 2013. While Dell and HP brag about their new 4.2GHz machines, BOXX offers expertly-engineered solutions – with speeds up to 4.9GHz currently – to boost 3D design & modeling performance.

Taking this concept a step further, BOXX has also introduced overclocked multi-core systems that bridge the gap between single-threaded and multi-threaded tasks. Thanks to Intel’s new line of Extreme-series processors, safe overclocking of multi-core CPUs is now possible. Imagine how much faster you can compile a 3D scene using the speed of a single, high-speed overclocked core, and then render your scene in record time with additional overclocked CPU cores. Now your creativity doesn’t have to wait on your hardware!

BOXX workstations are built to last, and they will likely be the most relevant piece of hardware your organization uses for years to come. While cheap, throw-away PCs are just now catching up, BOXX is introducing systems that will outpace those other systems for another 3 or 4 years, and maybe longer. Some BOXXers have even reported using their BOXX workstation for up to 12 years before needing to upgrade. Talk about return on your investment!

The DEVELOP3D Review: BOXX APEXX 2 + BOXX renderPRO 2

Ray trace rendering is arguably the most computationally intensive process in any product development workflow. It is highly multi-threaded so it absolutely hammers all of a workstation’s CPU cores. It is also extremely scalable, so doubling the number of cores can, in many cases, halve the render time.

CAD software is very different in that it is a single threaded process, so the majority of tasks are performed on one CPU core. This means it thrives on a high frequency (GHz) CPU. Performance will not increase if you add more CPU cores.

This presents a big challenge when choosing a workstation for both CAD and rendering. The highest frequency CPUs have the least number of cores, while the ones with the most cores tend to have the lowest frequencies. As a result, designers and engineers must accept that there will always be a trade off. Or must they?

Custom workstation manufacturer BOXX offers an alternative solution by dedicating separate machines to each process. CAD work is done on the BOXX APEXX 2, a high frequency Intel Core i7 desktop workstation, while the rendering is handled by the BOXX renderPRO 2, a networked, dual Intel Xeon rendering machine with lots of cores.

As both machines work completely independently of each other, it also means that the BOXX APEXX 2 workstation will be able to dedicate almost all of its resources to CAD modelling when the BOXX renderPRO 2 is rendering.

In contrast, when a traditional desktop workstation is set to render flat out, it will often become sluggish, making it almost impossible to do any meaningful CAD work.

To get round this, users have to reduce the number of cores assigned to the rendering task, either by changing processor affinity in Windows Task manager (so specific applications use specific CPU cores) or by applying more granular control of CPU core usage inside the rendering application. And that means renders come back slower.

CLICK HERE to read the full article from DEVELOP3D!