Beyond speed: Opening up the architecture for third party developers
New graphics chips always tend to be faster, prettier and better than the previous generation. At this point in time, consumers ask for more than just more speed, but for innovation that increases the user experience and quality level of gaming and other graphics applications. And ATI brings a couple interesting ideas to the table with its new graphics chip generation.
First, ATI said it integrated Shader Model 3.0 in a more complete way than Nvidia did. The company claims the real estate gained on the silicon through a 90 nm production process enabled the firm to extend the feature set previously offered. Presentations shown by the company in fact showed an amazing level of realism and let us look forward to the next generation of games. Other new features include "Avivo," ATI's video display platform, which promises to increase the quality of video playback. For a detailed look under the hood of the new X1000 family as well as its performance capabilities, you will soon find an in-depth review over at Tom's Hardware Guide.
The real innovation however is just an idea at this time, but promises to have a major impact on the industry, if brought to reality. Heye mentioned that ATI plans to open the hardware architecture of the X1000 to allow third party developers to write non-graphics-related applications to run on the graphics processor. The company calls this feature "dynamic load balancing."
Compared to a Pentium 4 CPU, which delivers a floating point performance of 12 GFLOPs and a bandwidth of just under 6 GByte per second, a graphics processor is a calculation monster: According to ATI, an X1800 XT chip reaches 83 GFlops and 42 GByte per second. The full performance of a graphics may not always be needed - especially in dual-graphics environments - and users will be able to relocate processing power to other applications. According to ATI, these applications could include scientific applications such as fluid dynamics, but also entertainment-related functions such as physics or 3D audio processing. Similar features have been demonstrated by academic projects in the past on ATI and Nvidia platforms, but dynamic load balancing as described by ATI officials promises a whole new use of graphics processors.
The company expects GPU specific third-party API's to become common within a few years - with one of the most promising being physics processing: ATI believes that graphics chips provide enough power to cover the features that are currently promoted by Ageia. If ATI's vision comes true, Ageia's business model of a physics board for every gaming PC may become unnecessary before the startup's technology has reached a critical market penetration.
However, all of ATI's new features and great ideas are somewhat overshadowed by the X1000's late appearance and the somewhat blurry outlook of availability. We will have to wait to see, if ATI will be able to deliver what the market is asking for - at least as far as the retail channels are concerned. Users who are interested in buying a complete computer system before Christmas should not count on finding too many systems that actually carry X1300, X1600 or X1800 cards. The late launch and an expected October 10 availability of the X1800 XL cards for system integrators caused ATI to completely miss the boat for the holiday business, as computer makers already placed their orders for different products.
While the release of the X1000 certainly is not a paper launch in its entirety, the delay of the most attractive versions of the product family may leave not the best impression with end users and OEMs alike. Nvidia, in contrast, has proven with the 7800 family that it is capable of bringing products to market at launch day. There is no question that this fact boosted the industry's and user's perception of Nvidia's credibility and time will tell, if ATI can afford to announce products that are not available at launch day.