Fermi benchmarked? [Fake]

[sxr7171]

A lot of that has to do with newer games and better optimizations hitting for those games. If you look at the games listed, they all have been out for quite a while, it wouldn't be shocking if Fermi had highly optimized drivers for those titles right at launch(again, I think the chart itself is total imaginary BS, just stating high profile games used in almost everyone's bench charts are going to be what any smart GPU maker optimizes for first).

With all the time they've had they better have some good drivers out.

 

[sxr7171]

Possible, but just as likely amd guerrilla marketing building up false expectations. At least nice for nvidia to actually get noticed... Outside of the odd photo of a dumb looking pr guy with a maybe card or answering questions on forums, the nvidia pr has not had much focus lately.

I suspect nVidia is just laying low while they plan for the future. The economy being what it is this isn't a bad time either.

But fake slides are stupid. If this doesn't meet the created expectation it will disappoint but if it is even within 20% it's still a good result but not great considering the lag.

 

[dguy6789]

Possible, but just as likely amd guerrilla marketing building up false expectations. At least nice for nvidia to actually get noticed... Outside of the odd photo of a dumb looking pr guy with a maybe card or answering questions on forums, the nvidia pr has not had much focus lately.

If Keys says it's not made by Nvidia, then I'm inclined to believe him. I don't think there's much point in discussing who made it or the contents of it in that case, it was probably some random person.

 

[T2k]

Obviously these benches can't be taken seriously at all, but I can assure you that nV has working Fermi chips with drivers ready to roll. Since A0 the respins have been about improving yields, they have had working chips for a long while now and even if they didn't

Oh, pleahse. Obviously they didn't otherwise they wouldn't have blown millions on 2 more respins (FYI no new-gen architecture ever worked on fine on A0 AFAIK.)

driver development for new parts starts off on simulators- if it didn't every new architecture would need to be done long before parts were able to ship(which isn't the case). This is not nV specific, ATi does the exact same thing for driver development on new architectures.

Maybe it's me but I think nobody said anything about drivers being impossible to have - IMO it's common knowledge that drivers can be developed on emulators.

 

[T2k]

Excellent point as well.

Interesting, thanks, I didn't know finalized optimizations could occur that early.

He didn't say that and it's not true - they can work on the drivers parallel with chip respins but they have to have working final silicon to do final optimizations - how else they would determine min./max values etc? Emulators run at the fraction of the final clock (like 10% and such), you cannot do final tweaks on them.
FYI there's a reason why most new architecture gets a nice driver boost after launch...

 

[T2k]

These slides aren't real. And they are not from Nvidia.
Seems "pre-mass hysteria" want's to rear it's ugly head.

Probably just some fan having fun with photoshop.

Dunno, I can easily imagine someone at NV "leaking" it, only to officially deny it -while quietly enjoying the hysteria it causes...

 

[BenSkywalker]

Oh, pleahse. Obviously they didn't otherwise they wouldn't have blown millions on 2 more respins (FYI no new-gen architecture ever worked on fine on A0 AFAIK.)

Even Charlie admits they had working chips, the issues with the respins has always been about yields. Since you have claimed Charlie is 100% right about Fermi, were you telling lies then or now? Charlie said they had working chips several months ago, your pick on when you were being dishonest 🙂

 

[T2k]

Even Charlie admits they had working chips, the issues with the respins has always been about yields. Since you have claimed Charlie is 100% right about Fermi, were you telling lies then or now? Charlie said they had working chips several months ago, your pick on when you were being dishonest 🙂

C'mon, this is childish, not funny. You know what I meant and what Charlie meant.

 

[BenSkywalker]

You have a special decoder ring? The most vehemently over the top nV critic on the web admits nV had working chips months ago. You are the only person I have seen anywhere trying to be more rabidly anti nV then Charlie. I don't see how you can consider my comments childish when I am simply pointing out what you have explicitly stated was 100% accurate information. nV had working chips months ago, now you are saying that isn't true. You can argue with yourself about the point if you'd like, but you are claiming the information you said was 100% accurate is now a lie.

 

[Idontcare]

Dunno, I can easily imagine someone at NV "leaking" it, only to officially deny it -while quietly enjoying the hysteria it causes...

I think AMD fabricated them for the same reasons. lol

 

[Nemesis 1]

You have a special decoder ring? The most vehemently over the top nV critic on the web admits nV had working chips months ago. You are the only person I have seen anywhere trying to be more rabidly anti nV then Charlie. I don't see how you can consider my comments childish when I am simply pointing out what you have explicitly stated was 100% accurate information. nV had working chips months ago, now you are saying that isn't true. You can argue with yourself about the point if you'd like, but you are claiming the information you said was 100% accurate is now a lie.

Ben I agree . But can you show us proof NV had working chips . From people outside of NVs corp. arm . I would like to read that if you have a link.

 

[T2k]

You have a special decoder ring? The most vehemently over the top nV critic on the web admits nV had working chips months ago. You are the only person I have seen anywhere trying to be more rabidly anti nV then Charlie. I don't see how you can consider my comments childish when I am simply pointing out what you have explicitly stated was 100% accurate information. nV had working chips months ago, now you are saying that isn't true. You can argue with yourself about the point if you'd like, but you are claiming the information you said was 100% accurate is now a lie.

So you've decided to play this lame, childish, really pathetic nitpicking game, good.

FYI: Charlies was talking about "working" chips in general, eg booting up, being able to perform at some basic levels vs this thread is about BENHCMARKING GAMES WITH CHIPS WORKING AT FULL SPEED, let alone bugfree.

Now after this point if you still act like you don't know WTF is the difference then I must say you have no clue about the entire subject.

PS: I noticed you played this dumb game with BFG on many occasions when you ran out of meaningful arguments - it's really pathetic, cheap and pointless tactic (sans fooling some naive people not following the subject closely.)

 

[T2k]

Ben I agree . But can you show us proof NV had working chips . From people outside of NVs corp. arm . I would like to read that if you have a link.

Bwahahhahah, touché! :awe:

Great post, N1! 😀

 

[ShadowOfMyself]

T2k you need to take a step back and relax, youre sounding too much like the red version of Wreckage, and thats not good, we dont need another rabid fanboy for either team

Even if thats not your intention thats how you come off with your current posts, it seems AMD is perfect in your world and Nvidia does everything wrong (exact opposite of wreckage)

In this case yeah, those slides are obviously fake, even Keys confirmed it, but no need to go overboard ^^ Its perfectly possible that Fermi will have great performance considering all the delays, I mean if AMD had delayed the 5870 by 6 months it would also be alot faster, logically

 

[Keysplayr]

Dunno, I can easily imagine someone at NV "leaking" it, only to officially deny it -while quietly enjoying the hysteria it causes...

That's funny. I was thinking it could have been an ATI fan creating this, or even AMD themselves as IDC hinted at, anonymously posting it as a random leak somewhere, and hoping that it would point the finger at Nvidia for releasing it as a PR slide.

Wow, the possibilities huh? Limitless.

 

[Wreckage]

T2k you need to take a step back and relax, youre sounding too much like the red version of Wreckage

He sounds like the rest of the red team here.

 

[MrK6]

In this case yeah, those slides are obviously fake, even Keys confirmed it, but no need to go overboard ^^ Its perfectly possible that Fermi will have great performance considering all the delays, I mean if AMD had delayed the 5870 by 6 months it would also be alot faster, logically

At least you would hope so. The market is stagnant enough as it is.

 

[Fox5]

What rumors? There are no performance rumors from Fermi whatsoever LOL



Suuuuure... Oh wait, G80 wasnt 6 months late

I predict this to be another G70.
It beats out ATI's first go (X1800 in that case), which was a fairly decent performer, but a bit of a let down to some for a next gen gpu.
However, shortly thereafter, ATI will release the updated version (as they usually do about 9 months after a new architecture) that's good for at least another 50% performance.

 

[ronnn]

If Keys says it's not made by Nvidia, then I'm inclined to believe him. I don't think there's much point in discussing who made it or the contents of it in that case, it was probably some random person.

Nvidia has been dishonest before. Am also sure amd's record is also not unblemished.

 

[cbn]

http://www.guru3d.com/news/geforce-gtx-360-and-380-benchmarks/

originally posted at:
http://www.xtremesystems.org/forums/showthread.php?t=240958

😱 if true!!

BUT the 5870 had amazing performance on PR slides too and that didn't fully pan out. Who knows...maybe someone at NV/a fanboy made them up to get people to wait for Fermi. I was going to wait for Fermi anyway and then decide whether to get a 5XXX or one of the Fermi cards.

In all cases here we are seeing more than double the FPS (on 1920x1200 with 8xAA).

512 stream processors vs 240 stream processors with a ~ 50% grain bandwidth and VRAM.

But how much have the core clocks increased?

 

[cbn]

Deleted.

 

[ShadowOfMyself]

He sounds like the rest of the red team here.

Thats because in your world grey = red

Take a few clues from Keys, he gets free stuff from Nvidia and still manages to be more impartial than you ever were

I predict this to be another G70.
It beats out ATI's first go (X1800 in that case), which was a fairly decent performer, but a bit of a let down to some for a next gen gpu.
However, shortly thereafter, ATI will release the updated version (as they usually do about 9 months after a new architecture) that's good for at least another 50% performance.

You mean G71 right (7900 series), because G70 came out a few months before X1800 ever saw the light of day

But other than that it seems to be following that trend yep... I will be very surprised if AMD doesnt have anything up their sleeves after so long... Dont think they are just gonna watch the spotlight being taken from them, specially when the 5800 series has alot of overclocking potential

 

[Zensal]

I think most people can safely assume that AMD is sitting on/tweaking designs for a 5890, just waiting for Fermi, and if Nvidia chooses to break the ATX specs or Fermi is as fast as these slide say, AMD will also be all over it with a 5990 that will hopefully be in the neighborhood. 6'ish months is a long time.

Personally, I'm hoping that Fermi => Cypress so that we can have another price war.

 

[yh125d]

Obviously PR slides, recommend ignoring them as they're never accurate from either team 😉



Though I do think nvidia surely has working cards in house, but they're just not like the cards we'll see on release day (lower clocks since an older stepping)

 

[BenSkywalker]

But can you show us proof NV had working chips .

That would be rather difficult for a product that hasn't been released yet when you put the 'outside nVidia' condition on it. Can you prove Larrabee was ever anything but emulated from anyone outside of Intel? It's the same sort of question, not really answerable for something that hasn't been released yet(same could have been said about the 5870 at one point too).

FYI: Charlies was talking about "working" chips in general, eg booting up, being able to perform at some basic levels vs this thread is about BENHCMARKING GAMES WITH CHIPS WORKING AT FULL SPEED, let alone bugfree.

What full speed is is normally determined after you start fabbing, and according to Charlie's quoted A2 numbers nV had parts working on the clockrates they were shooting for(not the numbers AMD tried to say they claimed, but the ones they actually stated).

Now after this point if you still act like you don't know WTF is the difference then I must say you have no clue about the entire subject.

You claim Charlie is 100% accurate, dodge the A0 question repeatedly and then fail to acknowledge that even Charlie states they have had working chips for months. I'm not remotely implying they are going to be ready to ship at any point, they could be delayed until 2049 for all I know, but they do have functioning samples in house.

PS: I noticed you played this dumb game with BFG on many occasions when you ran out of meaningful arguments - it's really pathetic, cheap and pointless tactic (sans fooling some naive people not following the subject closely.)

It's not playing dumb, it's throwing your ignorant statements back in your face 🙂

T2k you need to take a step back and relax, youre sounding too much like the red version of Wreckage

I see Wreckage pick on ATi's financial situation, not a whole lot else(certainly not to the level where he is willing to go beyond people like Charlie's ignorance, not even close).