GPUs and flash memory are used in numerous VDI applications today and the number is rapidly growing. The need to store and transcribe huge amounts of data through image and data processing is becoming overwhelming. The more GPUs and flash memory available, the quicker the data can be used. GPU appliances supporting multiple NVIDIA GPUs and Intel Phi coprocessors and Flash memory appliances supporting multiple Fusion-io flash memory cards are quickly becoming the best and most economical way of accomplishing this tremendous feat.
VDI or Virtual Desktop Infrastructure helps companies save money, time and resources. Instead of large bulky machines on every desk in the office, companies can connect multiple workstations to a single computer using thin clients. Instead of replacing individual desktops every year, companies only have to replace thin clients every 5 years. And when it comes time to do updates, the IT staff updates the one computer instead of spending time updating every individual workstation.
VDI is a great solution for most companies. But if every employee in the company has to process large amounts of data, that one computer may not be powerful enough. For example, if there are 8 employees and each employee’s workstation requires two GPUs to process data quickly enough, will switching to a Virtual Desktop Infrastructure still work? After all, there are still only a small number of open slots for GPUs in most computers.
For some companies, the number of GPUs needed would require multiple computers increasing not only the upfront cost but also the long term costs of maintaining and running multiple computers in a VDI environment. But what if there was a way to get 16 GPUs to attach to one computer to provide that extra power to all 8 employees? Well, there is. One Stop Systems builds Compute Accelerators that support from two to sixteen GPUs and that can be easily attached to the computer in the field or in the data center, adding thousands of additional compute cores. Compute Accelerators are equipped with their own power, cooling, and system monitoring so it does not depend on the resources of the main computer.
There are many applications that can benefit from using the parallel structure of a GPU to process large amounts of data. However, the original function of a GPU is in the name, Graphics Processing Unit. The technology was designed to process graphics so gaming has been an application that has benefited from GPUs since games have a huge graphic component.
For avid individual consumers, using a GPU that’s already integrated into their system is not powerful enough for graphically demanding games. Some gamers will build their own systems so they can put more powerful GPUs (integrated on video cards) into their system. Some individual gamers are willing to spend a good amount of money on these products. But this is not possible for all consumers.
For gaming companies, the idea of gaming in the cloud has been around for a while. There are plenty of games that can be played in the cloud. These games are also able to be played on devices other than computers. But there are still games that cannot be played on a phone or a tablet, because these devices do not have the graphic processing power to support these games. So there has been somewhat of a delay in bringing the gaming industry 100% into the cloud. Virtualization and cloud computing hosts have been enhanced for computing power, but not for graphics processing. But by using GPUs, these hosts can now achieve the processing power needed to bring gaming into the cloud. One Stop System offers the densest solution with our High Density Compute accelerator that can accommodate up to 16 high end GPUs. Our products can provide more compute power to gaming virtualization.
Computer-aided design (CAD) utilizes computers to generate, revise, evaluate and improve designs. CAD software is used to help designers be more productive. CAD drawings are very complex. In addition to the design, the files must contain the materials that should be used, the processes for creating the object(s), the dimension of the object(s), and the tolerances based on the regulations of the application for which the item is being designed. CAD drawings can be two-dimensional but they also can be three-dimensional.
CAD is used in a wide variety of industries, including industrial and architectural design, aerospace, automotive, prosthetics, shipbuilding and many others. CAD is also utilized in the movie industry for computer animation and special effects. The more complex a drawing is, the more compute power is needed. Some CAD systems can do graphically and computationally intensive tasks, so GPUs are very helpful in adding the necessary compute power.
For a company that has multiple CAD users, there are several ways to go about ensuring everyone has enough compute power for graphically intensive tasks. If everyone has their own system, a GPU can be added to each system. However, most computers are not capable of holding more than one low-end GPU. High end GPUs require more power and cooling and most computers cannot handle these requirements. This is where virtualization comes in. Each employee can connect to a single server, or multiple servers using a thin client. A server can accommodate slightly more GPUs, and some can accommodate the higher end GPUs. If more than one server is used, the number of GPUs can increase. However, such infrastructure would start to take up a lot of rack space and get more expensive to purchase and maintain.
The One Stop Systems High Density Compute Accelerator (HDCA) can accommodate up to 16 high end NVIDIA GPUs and connect to a single server. And it only takes up 3U of rack space. It’s the densest solution on the market and can add the much needed compute power to a CAD virtualization environment without taking up a large amount of space. Porr, an Austrian architectural and civil engineering design firm successfully used one server and one of OSS's compute accelerators to virtualize CAD for multiple users.
Here are some CAD applications that can be sped up by using GPUs:
Our compute accelerators support from one to sixteen double-wide PCIe cards and can be cabled up to four host computers through PCIe x16 Gen3 connections each operating at 128Gb/s. The all-steel construction chassis house power supplies, fans, and a system monitor that monitors the fans, temperature sensors and power voltages. Front panel LEDs signal minor, major or critical alarms. The compute accelerators are transparent and do not require software except for the drivers required by the PCIe add-in cards. Compute accelerators are the best appliance for applications that require a large amount of compute power.Learn More
Our flash storage arrays support from one to thirty-two single-wide PCIe cards and can be cabled up to four host computers through PCIe x16 Gen3 connections each operating at 128Gb/s. The light-weight, compact chassis house power supplies, fans, and a system monitor that monitors the fans, temperature sensors and power voltages. Flash storage arrays are the best appliance for applications that require a large amount of fast, flexible storage.
To read an independent review of the 3U FSA done by Tom's IT Pro, click here.Learn More