NVIDIA's detailed slam of 3DMark03

Originally posted by kyleb
first off "cpu limited" is a different thing that does not "need a fast cpu" sence the fastest cards on the market are still cpu limited to begin with i cannot realy fufill your request. however i can say that my tbird@900 does nicely with ut2k3 and anything else i have throw at it. regardless we are not talking about games aleady released here.

i'm talking about game engines, not video cards.

ati and another video card company. also i don't spupose anyone still has a copy of that nvidia release to best-buy empoyees traget which bashed the kryoII t for its lack of t&l among other things?

those look like the original white papers or PR documents from the launch of the Radeon256 and the GeForce256. so i'm not gonna pay heed to them. why? because they were false promises IMO.

look at the facts. the gf2Ultra was way ahead of the Kyro2 when it came out. yet in today's games with a modern CPU the Kyro2 catches and surpasses the gf2Ultra even though the gf2Ultra was much faster when it came out. amazing, isn't it?

http://www.anandtech.com/video/showdoc.html?i=1647&p=6

look at the high detail settings of each resolution.

no devloper in their right mind would just close their options like that. however, to most of them that also means makeing it run well for the wideist userbase possable. also, the wide range imlementation of harware t&l has made the cpu less of an issue; take a look at the recomended system reqirements on any game box you can find, hardly any even come close to half the speed of the top of the line cpus, not to mention they are toughting numbers from architectures 2-3 generations below the top of the line cpus. i doubt you could name any grapicly intensive pre t&l games that were avalable to such a wide range preformace range of cpus at the time of their release.

and yet, 3dmark03 is highly CPU independent. it gains almost nothing from faster CPUs. a 1 GHz CPU and a r9700 will beat a 2GHz CPU and a gf4. as you said, how many games are like this? in how many games will a 1GHz increase not mean much at all, especially when fast video cards are CPU limited as you earlier said?

if there is anything you have not found me fourth comeing about or consider rhetoric and at i have yet to adress to your satistaction, please feel free to reference it directly so i can atempt to rectify the situation.

as i said, i was not referring to you, mainly Skynet, who has ignored my post. and i already stated why, you say and others say "things" without providing game examples, without providing anything but rhetoric.

those documents you linked are poor examples. you said it yourself, Kyro2 was slammed for not having hardware T&L. yet at high detail settings in UT2003, it keeps up with the formerly mighty gf2Ultra.

like i eluded to above above, you are not going to get that from me as i feel that ingoreing a person, or even just one of their openions, is the lowest of the low.

that has nothing to do with what i said. i called out Skynet to show me proof of why he seems so absolutely certain that games will stop being as CPU limited as they are today, and move instead to being video limited. we're talking about raw game performance, no FSAA, no AF, 1024X768, just like 3dmark03 uses.

and then i said, if it was just his opinion, and he is not basing his opinion on anything of substance(ie facts), then he should ignore my challenge to provide evidence.


and i don't even understand what your post is about. i already said numerous times i don't care whether the CPU is being offloaded or not. i already said it is a good thing. but you keep coming back to that instead of responding to my question. is it being offloaded? sure. but who cares. recent games are still CPU limited just as much as before.

it's the reason why some guy with a 2400+ and a gf3 says C&C Generals runs smoothly and why my friend with a 1.4GHz Athlon and a gf4 says the game chops up.

The Question: what makes you think games will not be just as CPU limited tomorrow as they are today?

if you aren't going to bother to respond to the actual question, and instead attack my side arguments, then save us both some time and don't respond at all. because that's all i'm seeing from you.

basically you have said this in your post: a)CPU offloading is good, and has happened since DX7 hardware was released.

b)the CPU will be used in the future and not be idle.

in essence, you have agreed with me without fail....i don't understand why you posted all that if that is the case.

let me propose to you some reasons.

a) you just want to argue.
b) english is not your native language
c) you read too fast or just don't comprehend what you are reading
d) you are trying to find ulterior motives that aren't there

i'm sick of arguing about semantics. the side dish is eaten. let's get to the main course.

[kyleb]

Originally posted by StealthHawk
i'm talking about game engines, not video cards.

well game engines are not very good without video cards are there? so could you please explain to me how you seperate the two?

look at the facts. the gf2Ultra was way ahead of the Kyro2 when it came out. yet in today's games with a modern CPU the Kyro2 catches and surpasses the gf2Ultra even though the gf2Ultra was much faster when it came out. amazing, isn't it?

http://www.anandtech.com/video/showdoc.html?i=1647&p=6

look at the high detail settings of each resolution.

first off, i dont not see any evednece to back your claim that the gf2Ultra was way ahead of the Kyro2 when it came out. as i recal i considerd them both as fairly equal options when my voodoo5 was falling behind and i made choice to get a gefoce3. anyway, look at more than one page of benchmarks from the link you posted; the only thing amazing i am seeing is how amazingly loose your definition of "fact" is. how does that one page prove the point you were atempting to make any less than benchmarks on other pages disprove the same point?


can i get a clear answer on this questions before going into the rest of it? or a simple apolige would be be wonderful as well.

[Chalnoth]

Originally posted by Sazar
that would seem to be the case

whoever was saying 20ghz systems in 10 years or so... that depends ENTIRELY on economic situations..

No, it depends more on the physics. Depending on the size of the processor, too high of a frequency will cause the processor to radiate like crazy. If I did my calcs right, it would be impossible to make a processor that runs at 20GHz larger than about 1.5cm in size (note that this is not a rigorous calculation, meaning that it doesn't matter what "size" means here...this should be accurate to within a factor of two if you take the diameter of the chip). This becomes a problem particularly when you consider that the amount the processor radiates is not a step function, so this problem will start to have an effect long before the limit is reached. That and the "square wave" nature of digital technology means that all chips will have much higher frequency components than the frequency that the chips run at. This may help to explain why chips have been getting so hot lately...

[Chalnoth]

Originally posted by StealthHawk
look at the facts. the gf2Ultra was way ahead of the Kyro2 when it came out. yet in today's games with a modern CPU the Kyro2 catches and surpasses the gf2Ultra even though the gf2Ultra was much faster when it came out. amazing, isn't it?

If I remember correctly, the Kyro II got such high scores because it didn't render the cubemaps that the other cards had to deal with.

[kyleb]

Originally posted by Chalnoth
No, it depends more on the physics. Depending on the size of the processor, too high of a frequency will cause the processor to radiate like crazy. If I did my calcs right, it would be impossible to make a processor that runs at 20GHz larger than about 1.5cm in size (note that this is not a rigorous calculation, meaning that it doesn't matter what "size" means here...this should be accurate to within a factor of two if you take the diameter of the chip).

but that assumes that no one ever finds a beter way to do things than the method you are cacluateing. that just comes off like a silly think to assume for me.

[Chalnoth]

Originally posted by kyleb
but that assumes that no one ever finds a beter way to do things than the method you are cacluateing. that just comes off like a silly think to assume for me.

There are obviously many factors, but the idea is very simple. If the circuit size approaches the wavelength of light of the frequency the curcuit is operating at, it radiates.

Granted, processors are highly-complex devices, and it may be possible to reduce the amount of EM radiation by intelligent circuit routing, but that can only go so far.

The main point here is that very high frequencies are going to be much, much more challenging to attain than more parallelism. Thus, if companies focus on more parallelism, they'll be able to put out overall faster processors.

Originally posted by Chalnoth
If I remember correctly, the Kyro II got such high scores because it didn't render the cubemaps that the other cards had to deal with.

hmm, you could be right about that. Kyro2 doesn't support cube maps AFAIK. Sweeney complained about that a long while back.

Originally posted by kyleb
well game engines are not very good without video cards are there? so could you please explain to me how you seperate the two?

3dmark03 vs 3dmark2001. in 3dmark03 people with the same video card but with different CPU speeds have almost the same score. not true of 3dmark2001.

first off, i dont not see any evednece to back your claim that the gf2Ultra was way ahead of the Kyro2 when it came out. as i recal i considerd them both as fairly equal options when my voodoo5 was falling behind and i made choice to get a gefoce3.

http://www6.tomshardware.com/graphic...kyroII-12.html

kyro2 loses almost all tests to the original gf2. kyro2 wins some at high resolution and 32bit. the gf2Ultra was a good 30% than the gf2 in such situations. so extrapolate the results yourself.

anyway, look at more than one page of benchmarks from the link you posted; the only thing amazing i am seeing is how amazingly loose your definition of "fact" is. how does that one page prove the point you were atempting to make any less than benchmarks on other pages disprove the same point?

that kyro2 wins at all is the point. although as Chalnoth has suggested, this could be due to cubemaps not being used.

can i get a clear answer on this questions before going into the rest of it?

you want it, you got it.

[jbirney]

The question of weather or not the games will be more/less CPU dependent is a true unknown. If the game is a multi-player only then the likely hood that its more CPU limited is smaller then it beeing held back by other bottlenecks. Any single player game has a higher chance of being CPU limited. Lots of them can be CPU limited if you tweak the settings (like take UT2k3 and turn up the phyics detial to high and you stress your CPU more).

Also dont forgot some of these timedemos that they use to record benchmarks (JK2 for example) are used with bots = more of a CPU limitation.

UT2k3 is less CPU limited than UT ever was. Remember UT was basically the Unreal Engine with bot support and a few tweaks. It was design for software rendering. And that software rendering stole much of the CPUs power. So that is ONE game that has moved away from being CPU limited. Which makes me happy as know I can work on getting my AI stuff more complicated to make the bots "fight" better

Personally I think we will see a mix. Some games will use more of your CPU others less

[kyleb]

exactly jbirney, and i recal Sweeny bitching about cube maps on the kryo as well so i stand by Chalnoth argument there.

Originally posted by jbirney
The question of weather or not the games will be more/less CPU dependent is a true unknown. If the game is a multi-player only then the likely hood that its more CPU limited is smaller then it beeing held back by other bottlenecks. Any single player game has a higher chance of being CPU limited. Lots of them can be CPU limited if you tweak the settings (like take UT2k3 and turn up the phyics detial to high and you stress your CPU more).

hmm, but the botmatch scores in UT2003 ARE more CPU limited than the other timedemos, doesn't that mean in multiplayer UT2003 becomes more CPU limited?

Also dont forgot some of these timedemos that they use to record benchmarks (JK2 for example) are used with bots = more of a CPU limitation.

that explains a lot.

UT2k3 is less CPU limited than UT ever was. Remember UT was basically the Unreal Engine with bot support and a few tweaks. It was design for software rendering. And that software rendering stole much of the CPUs power. So that is ONE game that has moved away from being CPU limited. Which makes me happy as know I can work on getting my AI stuff more complicated to make the bots "fight" better

true enough. but the original UT was a bad example of a 3d accelerated game. the engine was coded the way it was because Sweeney did not forsee the advent of 3d accelerators.

Personally I think we will see a mix. Some games will use more of your CPU others less

undoubtedly true. the question is how much of a mix. will we see many games that go to the extent of 3dmark03? will that be the norm? or the exception to the rule?

these are the questions that need to be answered as 3dmark03 is "the gamer's benchmark."

[kyleb]

StealthHawk, i sweer you must have taken lessons from johnny cochran in the oj trial.