Futuremark backs down on Nvidia cheat claims

[Spinner]

Benchmark developer Futuremark has dropped its allegation that Nvidia cheated to gain false scores with the use of optimised driver code, ending the dispute between the two companies.

"Futuremark now states that Nvidia's driver design is an application-specific optimisation and not a cheat," said Futuremark in a statement.

Futuremark said its normal practice was to frown on optimised code, but said it may change this practice.
The full report:
http://news.zdnet.co.uk/hardware/chips/0,39020354,2135501,00.htm

Related News:
http://www.short-media.com/forum/showthread.php?s=&threadid=2003&highlight=futuremark
http://www.short-media.com/forum/showthread.php?s=&threadid=2442&highlight=futuremark

[Omega65]

XbitLabs: Futuremark Clarifies its Attitude Towards Driver Optimization (http://www.xbitlabs.com/news/video/display/20030924114535.html)

Futuremark Corporation, a leading developer of benchmarking software, today clarified its position towards driver optimizations for 3DMark benchmarks. Earlier this year both NVIDIA and ATI Technologies were caught on cheating in 3DMark game benchmarks, and even though the latter removed its cheats, the former never confirmed their existence claiming that the industry benchmark had been developed in an attempt to show NVIDIA GeForce FX products in bad light.

In order to clarify its stance on driver optimizations and to help those companies who wish to have their products benchmarked with its industry standard 3DMark benchmark, Futuremark today publishes the following set of guidelines for creating drivers:

* It is prohibited to change the rendering quality level that is requested by 3DMark;
* It is prohibited to detect 3DMark directly or indirectly. In its sole discretion, Futuremark may approve detection in order to fix a specified hardware error;
* Optimizations that utilize the empirical data of 3DMark are prohibited;
* Generic optimizations that do not violate the above rules and benefit applications in general are acceptable only if the rendering is mathematically consistent with that of Microsoft DirectX reference rasterizer.


more here (http://www.xbitlabs.com/news/video/display/20030924114535.html)

[RWB]

Can they say what you can and cannot do with your own software/drivers? Not saying I am against it or anything, but it seems to me from what you said that FutureMark is saying that when anyone dev's some drivers for a HW device, that it cannot do *whatever*