ATI has been alarmed by the intensity with which accusations against its drivers have been flying around the net and has decided to do something which is unprecedented in the chronicles of the graphics hardware industry.
In response to the various accusations, the Canadian graphics giant will hold a live web chat, in a short while, hoping to put an end to the speculation once and for all. If this venture proves a success it will definitely set a precedent which other companies may have to follow.
The statement on ATIs website reads:
There has been a lot of discussion about our trilinear filtering recently. In an effort to clear this up, ATI is holding a live web chat today, May 19, 2004 at 3pm EST, 9pm CET.
Speakers:
- Andy Pomianowski, Staff Engineer, and architect of our image analysis and compression algorithms.
- Raja Koduri, Engineering manager, graphics architecture and performance tools, one of ATI's experts on performance and image quality.
The link to the web chat is available by following the download tab above.
A variety of recent reports in hardware sites claim that ATI may be using some nefarious methods in order to achieve optimal results in benchmark tests. The need to achieve that impressive score has led many astray, including the much publicized nVidia cheat story which, at its peak, led to an intense war of words between Futuremark and the graphics manufacturer.
The problem with covert optimizations, according to experts, is that while benchmark scores go up and up, image quality suffers, meaning that a game may run faster but at a high price since certain features which add depth to an image are, neglected by the drivers. This very basic explanation is the essence of the problem since such cheats have created the Real-World and benchmark performance divide, shaking consumer trust in the onslaught of tests which floods the web whenever a new chip is released.
The most significant evidence suggesting that ATI have been dipping their hand in the nVidia comment box in order to develop their marketing strategy comes from claims that ATI beta drivers and the ati3duag.dll target specific applications. The latest information claims that the .dll file goes after SplinterCell.exe, SplinterCell2.exe, CT3.exe, pop.exe and RaceDriver.exe. The choice of games may make sense on some levels i.e. Prince of Persia and SC 2 but has experts puzzling as to the exclusion of some high profile titles such as Far Cry.
Until some further light is shed on the intricacies of ATIs drivers and before we rush to discredit the X800's recent benchmark victories we will have to accept ATIs side of the story which, as quoted in the inquirer.net, is as follows:
There has been a lot of discussion about our trilinear filtering algorithms recently.
The objective of trilinear filtering is to make transitions between mipmap levels as near to invisible as possible. As long as this is achieved, there is no "right" or "wrong" way to implement the filtering.
We have added intelligence to our filtering algorithm to increase performance without affecting image quality. As some people have discovered, it is possible to show differences between our filtering implementations for the RADEON 9800XT and RADEON X800. However, these differences can only be seen by subtracting before and after screenshots and amplifying the result. No-one has claimed that the differences make one implementation "better" than another.
Our algorithm for image analysis-based texture filtering techniques is patent-pending. It works by determining how different one mipmap level is from the next and then applying the appropriate level of filtering. It only applies this optimization to the typical case - specifically, where the mipmaps are generated using box filtering. Atypical situations, where each mipmap could differ significantly from the previous level, receive no optimizations. This includes extreme cases such as colored mipmap levels, which is why tests based on color mipmap levels show different results. Just to be explicit: there is no application detection going on; this just illustrates the sophistication of the algorithm.
We encourage users to experiment with moving the texture preference slider from "Quality" towards "Performance" - you will see huge performance gains with no effect on image quality until the very end, and even then, the effect is hardly noticeable. We are confident that we give gamers the best image quality at every performance level.
Microsoft does set some standards for texture filtering and the company's WHQL process includes extensive image quality tests for trilinear filtering and mipmapping. CATALYST passes all these tests - and without application detection, which could be used if you wanted to get a lower-quality algorithm go undetected through the tests.
Finally, ATI takes image quality extremely seriously and we are confident that we set the bar for the whole industry. We don't undertake changes to our filtering algorithms lightly, and perform considerable on-line and off-line image analysis before implementing changes. This algorithm has been in public use for over a year in our RADEON 9600 series products, and we have not received any adverse comments on image quality in that time. If anyone does find any quality degradation as a result of this algorithm, they are invited to report it to ATI. If there is a problem, we will fix it.
