If you haven’t heard of cloud computing by now, I’m wondering how you managed to find this site since it’s a buzzword that’s on every news site BEFORE this humble little geek news blog. If you have, you know how much the concept has been taking off in the IT industry and computing world in general.

Nvidia intends to take it a step further. Their latest move takes the rendering process for images, moves it off the client-side and puts it on a series of high-quality servers that process the raw numbers and streams back the image data to whatever device requested it, supposedly in near real-time. At the very least, they claimed it would be able to render:

“images of photorealistic scenes at rates approaching an interactive gaming experience”.

From the article:

Here’s the eye-opener: NVIDIA claims that the combination of RealityServer and its Tesla hardware can deliver those photorealistic scenes on your workstation or your cell phone, with no difference in speed or quality. Instead of relying on a client PC to handle the task of 3D rendering, NVIDIA wants to move the capability into the cloud, where the task of rendering an image or scene is handed off to a specialized Tesla server. Said server performs the necessary calculations and fires back the finished product, which theoretically allows for the aforementioned frame rates that approach an “interactive gaming experience.”

NVIDIA has designed a series of rackable Tesla servers, as shown above. The categories above are meant to represent various size possibilities—based on NVIDIA’s comments, one could host a RealityServer 3.0 project on a single GPU, and could possibly scale up past 100 GPUs. A key part of the new software architecture is Mental Image’s new iray rendering engine, which has been designed to take advantage of GPU acceleration. Iray was built to take advantage of the tremendous parallel processing capabilities of a modern GPU—according to the FAQ (PDF),  iray is an “interactive, consistent, high-performance global illumination rendering technology that generates photorealistic imagery by simulating the physical behavior of light…iray does not depend on complex renderer-specific shaders and settings to approximate global illumination. iray generates photorealistic imagery without introducing rendering algorithm-specific artifacts.”

The pros here: like other cloud-rendering services such as Gaikai or OnLive, the Nvidia cloud renderer obviates the need for powerful client-side hardware and thus allows a supremely frugal option for gamers. Not having to purchase expensive video cards and not having to worry about compatible hardware configurations is always a plus, not to mention secondary but still critical issues such as heat ventilation and power consumption are rendered moot by the absence of power-hungry components. It also allows developers to write for and optimize code for this particular platform alone, streamlining development time by cutting out testing for odd consumer hardware configurations, much like console development goes.

Not to mention: smartphones are even capable of displaying good quality video. This option allows anything capable of streaming data at a respectable speed to receive the image data in real-time and display it.

The cons though: odds are, this will be a subscription or pay-per-render service– it’s hard to imagine that on initial adoption this service will be anything resembling a free service. Also, the reliance on a centralized server system means there will be consumers picking at a central supply of rendering power and supply, possibly leading to queues if demand gets high enough at a certain point (although Nvidia should have more than enough GPUs in reserve to quickly construct more servers).

Most of all though, this service relies on an internet connection, something which may not be available or practical for the bandwidth speeds available in certain places. Lacking that internet connection means absolutely no rendering capability if you’re running a device lacking a capable GPU.

Are there any pros I missed? Cons I missed? What are your thoughts on the issue?

See the original article here.