Read ET's article and JUDGE FOR YOURSELF!
One of the reasons many are up in arms about this isn't because it's
just another syntethic benchmark, but because a lot of OEM deals center around the perfomance of a card in these benchmarks...
So when a company cheats in 3dmark (which is a very well known benchmark for OEM's) it can sway deals worth millions, based on a
fake result...
I, personally, think Nvidia is cheating in 3dmark03 with their latest drivers based on the fact that the "clipping" trick used
doesn't just insert itself like this by itself...
Had it been happening where everyone could see it, yes then it would most likely be a bug, but as it only happens when you "go off the rail" the chances are
extremly slim...
As far as [H] goes, yes his post is valid... Kyle does state the facts known to him,
but the way it's stated removes all claims of objectivity! Nor has he tried to find out more about this himself, or substantiated the "ET is pissed since they didn't get to benchmark D3" remark...
But let's split it up:
1. Yes, it was released 2 days after the D3 benchmarks...
But it was also released two days after the DetFX was released...
And if you take a look at B3D, you'll find Wavey and Reverend talking about this article
one week ago...
Wavey sent pictures of what was happening to Nvidia asking them for an explanation,
but has yet to receive any official explanations.
2. Nvidia doesn't have access to the beta/debug version of 3dmark03. Quite correct.
But they were a beta member for (over) 16 months before they left... So it was their own decision not to have access to the build...
"They don't want to pay the tens of thousands of dollars to be a beta member"....
Isn't this the company which has around a billion of cash lying around?!?
To optimize for 3dmark03 the way they've done also costs them quite a lot of money....
3. Kyle can post anything he wants on [H], as he owns the site... Salvator (sp?) is an employee of
Ziff-Davis and
can not just post whatever he fancies...
ZD is a
large IT company, and stand to loose quite a lot if these are baseless charges, but still they decided to publish them.
4. "Nvidia is doing this do discredit 3dmark/futuremark"
This could very well be the case,
but why don't Nvidia say that openly?!?
There is no mention of this in the readme, and the drivers are published like regular drivers!
Thus it does not seem to me like they're doing this to discredit 3dmark, but just to boost their score...
5. "Only fanATIcs are shouting abuse at this"... Errr, where did he get this idea...
Take a look at B3D (as the discussion is running very hot there), strip away the obvious fanboys (at both sides), and you'll see that most (if not all) of the "in betweens" are outraged as well...
This is because it this could be further reaching than most people think about...
Yes, it's only been noticed in 3dmark so far. But who's to say that Nvidia aren't doing this in any other benchmark which "runs on rails"?
They could very well be doing the same thing for Q3's Timedemo 1,2,3... Yes, it's an actual game,
but with the timedemos
it is only a benchmark...
There is
no way to "jump into" the demo and look around...
Or take the flyby in UT2k3... the FX scores way above the 9800pro, but not in the botmatch... Could this be because of similar culling/clipping?
And before you tell you me you can fly around by yourself, it's not that hard to do a "listen" for a key being pressed, and stop doing the optimization....
Or how about RightMark, AquaMark etc?
NOTE: I'm not saying Nvidia are cheating in all the benchmarks, but that it is a possibility based on what ET discovered!
IF Nvidia
really wanted to stop people using 3dmark as a benchmark,
why not add some code omt the drivesr which makes it impossible to run 3dmark?
That would've been a fair way to tell the world about Nvidias dislike for 3dmark, since "it doesn't test the way we think it should do"...
Why all this optimizing/cheating,
if you don't want people to use the benchmark?
According to B3D and ET there has been a noticeable increase in bugs with nvidia drivers, that seem to correspond with increased scores...
I think I'll stop now before I start raving...
I just got pissed of at Kyle's "fact post" (which i'm posting at the end of this post, so you can see the entire one for yourself...
One last thing before I shut up (for now), read ET's article for yourself, and think about it...
Kyle never had a proper rebuttal of what they found, he only talked about the circumstances they posted it...
.02$ (and thank you for reading so far)
Originally posted by Kyle on [H]ard|OCP:
Two days after Extremetech was not given the opportunity to benchmark DOOM3, they come out swinging heavy charges of NVIDIA intentionally inflating benchmark scores in 3DMark03. What is interesting here is that Extremetech uses tools not at NVIDIA's disposal to uncover the reason behind the score inflations. These tools are not "given" to NVIDIA anymore as the will not pay the tens of thousands of dollars required to be on the "beta program" for 3DMark "membership".
nVidia believes that the GeForceFX 5900 Ultra is trying to do intelligent culling and clipping to reduce its rendering
workload, but that the code may be performing some incorrect operations. Because nVidia is not currently a member of FutureMark's beta program, it does not have access to the developer version of 3DMark2003 that we used to uncover these issues.
I am pretty sure you will see many uninformed sites jumping on the news reporting bandwagon today with "NVIDIA Cheating" headlines. Give me a moment to hit this from a different angle.
First off it is heavily rumored that Extremetech is very upset with NVIDIA at the moment as they were excluded from the DOOM3 benchmarks on Monday and that a bit of angst might have precipitated the article at ET, as I was told about their research a while ago. They have made this statement:
We believe nVidia may be unfairly reducing the benchmark workload to increase its score on 3DMark2003.
nVidia, as we've stated above, is attributing what we found to a bug in their driver.
Finding a driver bug is one thing, but concluding motive is another.
Conversely, our own Brent Justice found a NVIDIA driver bug last week using our UT2K3 benchmark that slanted the scores heavily towards ATI. Are we to conclude that NVIDIA was unfairly increasing the workload to decrease its UT2K3 score? I have a feeling that Et has some motives of their own that might make a good story.
Please don't misunderstand me. Et has done some good work here. I am not in a position to conclude motive in their actions, but one thing is for sure.
3DMark03 scores generated by the game demos are far from valid in our opinion. Our reviewers have now been instructed to not use any of the 3DMark03 game demos in card evaluations, as those are the section of the test that would be focused on for optimizations. I think this just goes a bit further showing how worthless the 3DMark bulk score really is.
The first thing that came to mind when I heard about this, was to wonder if NVIDIA was not doing it on purpose to invalidate the 3DMark03 scores by showing how the it could be easily manipulated.
Thanks for reading our thoughts; I wanted to share with you a bit different angle than all those guys that will be sharing with you their in-depth "NVIDIA CHEATING" posts. While our thoughts on this will surely upset some of you, especially the fanATIics, I hope that it will at least let you possibly look at a clouded issue through from a different perspective.
