Battle of ATI and NVIDIA: where are fair duels?

Dom · Jul 4, 2003, 05:22 AM

No sooner had the disputes around the 3DMark2003 and Detonator FX drivers faded away than www.tech-report.com published some information about new cheats for this benchmark in the same Detonator FX, namely about the aggressive optimization of anisotropic filtering with the name of an active application being the criterion of its activation. The ShaderMark from ToMMTi-Systems also had its shader code slightly modified which noticeably affected the performance; it indicates that the Detonator FX plays tricks on it as well. Since this hunting is acquiring the mass character we decided to investigate this issue ourselves. But we realize that to reveal the driver's tricks with benchmarks we need to cooperate with developers of given applications in 99% of cases. Moreover, even the developers are not always able to find and eliminate such optimizations because drivers often use very sophisticated methods of detection of one or another application. That is why we decided to look at the problem differently and to analyze the driver inside to locate and lock all ways of detection of one or another Direct3D application. It will disarm the driver and bring to minimum the risk of getting wrong benchmark results.

So, the starting point in our investigation was that the driver reacts to renaming of an executable file of at least one benchmark. It means that its code must contain an algorithm that analyzes names of active Direct3D applications. The first our step was to look for it. The research showed that the Detonator FX really contains a base of applications detectable with a command line that covers about 70 elements...

Read More...

hjs · Jul 4, 2003, 07:00 AM

Ah, i just wonder why this news isn't on the frontpage of all hardware sites? for example nvnews, i know that Muya guy knows of this article (mailed with him last week)

here a nice thread at beyond3d with some screenies and a quickbenchmark at ut-2003 with the use of the anti-scripts.

http://www.beyond3d.com/forum/viewto...=137300#137300

Quote:

I've done one quick benchmark run at 1600x1200 no AA/AF:

Normal Anti
Flyby 145.0 93.6
Bot 69.22 63.69

digitalwanderer · Jul 4, 2003, 04:05 PM

...'cause I didn't put it there yet since the story is still very much developing.

Unwinder only tested 3dm2k1se and Wavey Dave is just having a field day ripping apart UT2k3 with Unwinder's script. That's the thing, there are so many people right now using Unwinder's script to find out just what the what is on both sides that I feel it's a little premature for a frontpage story, I'd rather wait a day or two and have better content than to just be first up with the news.

Jul 4, 2003, 04:05 PM	#3
digitalwanderer Colour Commentator Join Date: May 2002 Location: Highland, IN USA Posts: 5,619 Rep Power: 0	Well, mebbe it wasn't on the front page... ...'cause I didn't put it there yet since the story is still very much developing. Unwinder only tested 3dm2k1se and Wavey Dave is just having a field day ripping apart UT2k3 with Unwinder's script. That's the thing, there are so many people right now using Unwinder's script to find out just what the what is on both sides that I feel it's a little premature for a frontpage story, I'd rather wait a day or two and have better content than to just be first up with the news. __________________ WTF is up with the sigs?

Jul 4, 2003, 05:22 AM	#1
Dom DriverHeaven Extreme Member Join Date: Jun 2002 Posts: 12,940 Rep Power: 0	Battle of ATI and NVIDIA: where are fair duels? No sooner had the disputes around the 3DMark2003 and Detonator FX drivers faded away than www.tech-report.com published some information about new cheats for this benchmark in the same Detonator FX, namely about the aggressive optimization of anisotropic filtering with the name of an active application being the criterion of its activation. The ShaderMark from ToMMTi-Systems also had its shader code slightly modified which noticeably affected the performance; it indicates that the Detonator FX plays tricks on it as well. Since this hunting is acquiring the mass character we decided to investigate this issue ourselves. But we realize that to reveal the driver's tricks with benchmarks we need to cooperate with developers of given applications in 99% of cases. Moreover, even the developers are not always able to find and eliminate such optimizations because drivers often use very sophisticated methods of detection of one or another application. That is why we decided to look at the problem differently and to analyze the driver inside to locate and lock all ways of detection of one or another Direct3D application. It will disarm the driver and bring to minimum the risk of getting wrong benchmark results. So, the starting point in our investigation was that the driver reacts to renaming of an executable file of at least one benchmark. It means that its code must contain an algorithm that analyzes names of active Direct3D applications. The first our step was to look for it. The research showed that the Detonator FX really contains a base of applications detectable with a command line that covers about 70 elements... Read More...