Futuremark releases 3DMark03 patch - alleges NVIDIA cheats

Originally posted by Behemoth
i think what ati did was very similar to what nvidia did, except the results were different, both companies substituted its own IHV specific method to get deceptive PS2 score, ati was not using PS2 shaders on the sky and water, ati was not showing its PS2 performance, so i also consider its a cheat.

What? ATI is and was using PS2.0 on the water. ATI did not omit any effects or lines of code. ATI shuffled the order of the code, which could be considered cheating by some people.

[Behemoth]

Originally posted by StealthHawk
What? ATI is and was using PS2.0 on the water. ATI did not omit any effects or lines of code. ATI shuffled the order of the code, which could be considered cheating by some people.

Our shaders are mathematically and functionally identical to Futuremark's and there are no visual artifacts; we simply shuffle instructions to take advantage of our architecture.

To my understanding, those shaders are just mathematically, functionally and visually identical to PS2 shaders in this futuremark situration, if they work identically internally in every situration, it is just a better implementation of PS2 shaders, ati do not need to remove it in the next driver, ati needs to USE it, coz it is exactly a better PS2 shader implemenation, but as far as i understand, mathermatically, functionally and visually identical shaders imply they are not the same as PS2 shaders otherwise ati would just use it.

[Nemesis77]

Originally posted by A-KO
[b]If anything, Futuremark ought to be god damn slapped for what they did with this patch.

YEAH! How dare they to expose NV as cheaters that they are! Poor NV, being mistreated by evil Futuremark!

[conscript]

Originally posted by StealthHawk
If they cheated in 3dmark03, why can't they cheat in game benchmarks too?

they have, and you're going to be seeing that news over the next few days I bet. I believe they've already seen the same types of issues with Serious Sam 2 benches.

[Adagio]

Nvidia yesterday responded to claims of cheating in 3dmark2003 saying this:

A representative at Nvidia questioned the validity of Futuremark's conclusions. "Since Nvidia is not part of the Futuremark beta program (a program which costs of hundreds of thousands of dollars to participate in), we do not get a chance to work with Futuremark on writing the shaders like we would with a real applications developer," the representative said. "We don't know what they did, but it looks like they have intentionally tried to create a scenario that makes our products look bad."

But how much does it cost to enter the Beta plan, I mean what are the actual minimum costs involved per year? is it $300,000 a year? $200,000 a year? maybe even $100,000 a year?

I'll tell you - it's $5000.

http://discuss.futuremark.com/forum/...=1#Post2288998

"hundreds of thousands of dollars" -> $5000? nVidia's staff isn't even able to count

What's $5000 to a company like nVidia? Nothing ... all they just say now is pure nonesense and blabla ...

[Scorched 2.0]

It's quite apparent that Nvidia is the victim here. ATI and FutureMark have created an evil collaboration in an attempt to destroy. Nvidia had no choice but to cheat.

Seriously people, FutureMark makes its money off the competition of different companies. If ATI was the only company around, they would lose a lot of business.

[Behemoth]

Originally posted by Adagio
Nvidia yesterday responded to claims of cheating in 3dmark2003 saying this:

A representative at Nvidia questioned the validity of Futuremark's conclusions. "Since Nvidia is not part of the Futuremark beta program (a program which costs of hundreds of thousands of dollars to participate in), we do not get a chance to work with Futuremark on writing the shaders like we would with a real applications developer," the representative said. "We don't know what they did, but it looks like they have intentionally tried to create a scenario that makes our products look bad."

But how much does it cost to enter the Beta plan, I mean what are the actual minimum costs involved per year? is it $300,000 a year? $200,000 a year? maybe even $100,000 a year?

I'll tell you - it's $5000.

http://discuss.futuremark.com/forum/...=1#Post2288998

"hundreds of thousands of dollars" -> $5000? nVidia's staff isn't even able to count

What's $5000 to a company like nVidia? Nothing ... all they just say now is pure nonesense and blabla ...

you can put it this way.
that hundreds of thousands of dollars could easily add up from the man hours paid for the staffs doing any futuremark related work if nvidia continued to participate in futuremark beta program.

[Onde Pik]

I don't get this "HA HA ATI CHEATED TOO" thing.

I thought everybody knew that both ATI and Nvidia has been optimizing for individual games and benchmarks for a long time. The drop in performance of both Nvidia and ATI cards doesn't == cheating. The cheating becomes aparent when this drop in performanec also shows that the drivers of a specific company were sacrificing IQ.

I think that fact has been established for the Nvidia drivers, but lets hold the verdict against ATI. As far as I am concerned there is nothing that impies that ATI are cheating as of yet. It IS possible to make optimizations that produce better performance withour cutting corners.

And as I said, who here didnt think tha both ATI and Nvidia were optimizing for 3Dmark03 ... or 3dmark01, Quake3 ... etc.???



PS.

And to the "Optimization is cheating. Cheating is cheating nomatter how much u cheat isnt important" argument is rather silly. If this becomes the general atttitude we are in for a bad swtich in the 3D industry.




EDIT:

I didnt seethis thread before posting. So ATI has made a statement that makes sense. They said that they shuffle the instructions to best suit their architecture, which would be stupid not to actually. I remember giving and example of how this kinda shuffling can improve performance(in a very simplyfie enviroment).

[Onde Pik]

Originally posted by Behemoth
you can put it this way.
that hundreds of thousands of dollars could easily add up from the man hours paid for the staffs doing any futuremark related work if nvidia continued to participate in futuremark beta program.

Nobody is forcing Nvidia to pay more than 5K. That is not what Nvidia tries to make it look like.

[Behemoth]

Originally posted by Onde Pik
I don't get this "HA HA ATI CHEATED TOO" thing.

I thought everybody knew that both ATI and Nvidia has been optimizing for individual games and benchmarks for a long time. The drop in performance of both Nvidia and ATI cards doesn't == cheating. The cheating becomes aparent when this drop in performanec also shows that the drivers of a specific company were sacrificing IQ.

I think that fact has been established for the Nvidia drivers, but lets hold the verdict against ATI. As far as I am concerned there is nothing that impies that ATI are cheating as of yet. It IS possible to make optimizations that produce better performance withour cutting corners.

And as I said, who here didnt think tha both ATI and Nvidia were optimizing for 3Dmark03 ... or 3dmark01, Quake3 ... etc.???



PS.

And to the "Optimization is cheating. Cheating is cheating nomatter how much u cheat isnt important" argument is rather silly. If this becomes the general atttitude we are in for a bad swtich in the 3D industry.




EDIT:

I didnt seethis thread before posting. So ATI has made a statement that makes sense. They said that they shuffle the instructions to best suit their architecture, which would be stupid not to actually. I remember giving and example of how this kinda shuffling can improve performance(in a very simplyfie enviroment).

ati altered how sky and water shaders worked in GT4, if it worked in all siturations, why dont ati implement this technique into next driver instead of getting rid of it? the only reason i can think of is that, its siturational, it also only works "on the rail"

[Behemoth]

Originally posted by Onde Pik
Nobody is forcing Nvidia to pay more than 5K. That is not what Nvidia tries to make it look like.

yep, just about every business man, sales, marketing representive make this kind of exaggeration.

Originally posted by Behemoth
To my understanding, those shaders are just mathematically, functionally and visually identical to PS2 shaders in this futuremark situration, if they work identically internally in every situration, it is just a better implementation of PS2 shaders, ati do not need to remove it in the next driver, ati needs to USE it, coz it is exactly a better PS2 shader implemenation, but as far as i understand, mathermatically, functionally and visually identical shaders imply they are not the same as PS2 shaders otherwise ati would just use it.

You're making an assumption as well as accusing ATI of lying. Notice that nvidia never officially said they weren't cheating. They just went off on a tirade about how Futuremark is evil and is trying to make them look bad

In a game, what ATI did was clearly optimizing. However, in a benchmark, some people consider it cheating if the driver touches anything.
Discussion
Discussion
There are other examples where people consider reordering the instructions cheating, look in other threads.

ATI has come clean with what's going on, we have to assume they are telling the truth. As you can see, people consider this cheating, so to appease them, they are removing the optimizations.

Originally posted by Behemoth
ati altered how sky and water shaders worked in GT4, if it worked in all siturations, why dont ati implement this technique into next driver instead of getting rid of it? the only reason i can think of is that, its siturational, it also only works "on the rail"

I can't tell if you're being sarcastic here

I'll assume you aren't.

a) There are no clipping planes in ATI drivers. This has been verified by both B3D and Futuremark.
b) There is no drop in IQ on ATI cards. What would they even fallback to? They support one FP precisions, unlike nvidia.
Visual Poof