[Bouncing Zabaglione Bros.]

Originally Posted by MfA

It wouldn't be so bad if people just approached it as what it is, funny ... nothing wrong with using a mockup, why waste a card a tester/developer could be using? Don't let people take close up pictures though ... DUH.

For exactly the reason that people see it and think that you're lying to them when you're waving it about and saying "here it is" instead of "here's a mockup". The internet doesn't let you get away with that kind of stuff now. There was nothing to stop Nvidia using a real card (if they had them) to wave in front of the cameras for a few hours and then send it to somewhere more useful. Even a polished mockup would have been preferable to the crude thing they allowed to be photographed and the images sent all over the world.

I suspect Nvidia really do have very poor yields, at least off that first batch, and they didn't have any spare chips whatsoever. The cards running that one demo were probably ugly engineering prototypes, so they mocked up a prettier looking fake that is what Nvidia intends the finished product to look like. They just didn't do it very well and got caught.

I think Nvidia is really much further off from a finished product than they would like us to believe, but they had to have their spoiler out no matter what, because now is the 58xx launch, and now is when Nvidia need the spoiler event.

[loekf]

Originally Posted by LordEC911

Maybe pathetic is being used to refer to Nvidia's sad attempts to hoodwink enthusiasts?

Actually it's common practice in the industry to once and a while pull off a fake demo. That's why I always love to look under tables when I'm at some show visiting a booth. Just the panic in the people's eyes

However, it rarely occurs that CEOs wave with demo boards in front of an audience with this amount of publicity....

Honestly if Nvidia only got 7 working dies out of 4 wafers they must have serious issues like timing in the logic or perhaps TSMC did a bad job on memory (there's a large L2 on this IC). Usually you keep wafers out of your hot lot on hold, before metalization, so 4 weeks later they could have repaired samples in the lab..... but not in time for this show.

[Scrat]

Originally Posted by LordEC911

Maybe pathetic is being used to refer to Nvidia's sad attempts to hoodwink enthusiasts?

Exactly

[Jawed]

Originally Posted by Scali

I do wonder though... is it an accurate mockup? As in, is this the actual reference cooler design of the new generation, so will the actual card look the same and be the same size?

Why would the "accuracy" of a mock-up be interesting?

Jawed

[stevem]

Is there a reason other than aliteracy for "Jensen" instead of Jen-Hsun (Huang)? 'Cos it's pissing me off...

[Slappi]

Originally Posted by apoppin

i forgot to mention .. i asked about the videocard that Jensen was holding up for us to see
(yes, i am that rude)

- "it is a production mock-up"


. . . but they do have working Fermi silicon
(the closest anyone could get from any Nvidia official - as far as i can ascertain - for a firm Firmi GTX "number" comparison, was 1.6-1.8 times faster than the current GT 285 GTX; that is not confirmed, however)

WTF!!! It was a mock up!!!

That's it, they are frauds!! I will never buy their card again!!!!

If I do happen to buy their Fermi card I will open it up right when I get it and measure that huge ass chip of theirs under super magnification... and if it's so much as a flea pubic hair longer than the HD5870 then I am selling that humongous POS even if it is 300% faster than anything out. I mean wtf!!! How can I game knowing that the chip inside my case..... inside the cooler.... is a few ant butt hairs longer than the competitions???

HOW??

[Kaotik]

This is just ridicilous, I picked this from another board and I'm still waiting for link, but I'll throw the quote in right away

Nvidia PR was asked to comment on the faked cards earlier this evening. Their reply was, "I'm glad you're asking us before you write. That statement is false. The product that we displayed was an actual Fermi board. The demo ran on Fermi silicon." We do not believe all of that statement.

How stupid they can think people are?

edit:
http://www.semiaccurate.com/2009/10/...mi-boards-gtc/

[nAo]

Originally Posted by Kaotik

This is just ridicilous, I picked this from another board and I'm still waiting for link, but I'll throw the quote in right away


How stupid they can think people are?

edit:
http://www.semiaccurate.com/2009/10/...mi-boards-gtc/

Do you *really* care about a fake board? Please..

[Kaotik]

Originally Posted by nAo

Do you *really* care about a fake board? Please..

Showing fake board, not a big thing as itself. It however becomes big when it's first presented as the real thing and then even when asked specificly due fake claims if it's fake or not, it's told to be the real thing while it's obviously not.

[Bouncing Zabaglione Bros.]

Originally Posted by Kaotik

Showing fake board, not a big thing as itself. It however becomes big when it's first presented as the real thing and then even when asked specificly due fake claims if it's fake or not, it's told to be the real thing while it's obviously not.

If Nvidia had initially come out and said it was a mock-up, there would be no problem, and no one would care. Instead they lied about it, and when caught in the lie, they continue to insist on the lie, despite what everyone can obviously see in the photos. It's just trying to fool us that there's a finished product on the near horizon, when the product is nowhere near that ready.

This is the sort of BS that Nvidia pulls all the time, and it's why a lot of people don't like them as a company. Even after being caught out, how difficult would it be for them to hold their hands up and say it was a mockup? It makes you wonder what else they are bs-ing about so far in advance of shipping product.

[thatdude90210]

Originally Posted by Kaotik

edit:
http://www.semiaccurate.com/2009/10/...mi-boards-gtc/

Saw someone mentioned that he's wrong about the A1 label, and that Nvidia uses the A0 for first silicon. So which is it?

Originally Posted by DegustatoR

That's the problem. I don't have any bias. You're seeing what doesn't exist.

Thanks a lot, I almost choked on a sandwich.

[digitalwanderer]

Oh gods, some arsehat is now hinting that they only have one working Fermi prototype.

[jaredpace]

[dnavas]

Originally Posted by digitalwanderer

Oh gods, some arsehat is now hinting that they only have one working Fermi prototype.

If there was only one prototype, you TAPE the demo and show the prototype. I wouldn't waste your time. It seems more likely that what they have in-house isn't terribly photogenic at the moment.

-Dave

EDIT: Oh, I see, that's what you say earlier in that thread. Err, nm

[fellix]

Originally Posted by jaredpace

http://i33.tinypic.com/k4ug5j.jpg

Wow!
Dimensional Compression(TM) tech with infinite die stacking?!

[wishiknew]

well I'm not related to xbitlabs but it looks like nvidia pr finally got together and made a response for the Fermi board that makes sense.

[apoppin]

Originally Posted by Arty

If you can correct Rys, then please do!

Friday being the last day of the week is weird, two contradicting replies by Nvidia PR. Fermi Tesla board is a mock-up

What is written at Fudzilla is accurate

Fudo and i were both there with Drew Henry and Jason Paul (my company is AlienBabelTech [no links posted to there by me]; not Fudzilla)
- they said what Jensen showed "is a production mock-up"

However, they have working silicon of Fermi ... is in their testing setups 'black box', so it is not really "presentable" in a finished videocard

Who really cares if it was a "mock up" or not ?
- Fermi is real and according to the aforementioned Nvidia officials - "It will ship this year" (2009)

[MfA]

Originally Posted by apoppin

Who really cares if it was a "mock up" or not ?

It's always funny to see that when pushed PR people grab for lies even when truth is more convenient ... kinda clarifies what PR really is.

PS. just for reference, it was Drew Henry which said that apoppin?

[apoppin]

Originally Posted by MfA

It's always funny to see that when pushed PR people grab for lies even when truth is more convenient ... kinda clarifies what PR really is.

i am not following you.

i did not believe - at the time - what Jensen had in his hand was a "finished" videocard

When i asked that question, there was no hesitation whatsoever on the official's response that it was a mockup

it isn't like they are hiding something. Femi is working and they demoed by using it

EDIT: i think it was actually Jason Paul; but i need to go over my video

[Richard]

Originally Posted by MfA

It's always funny to see that when pushed PR people grab for lies even when truth is more convenient ... kinda clarifies what PR really is.

This could be an example of how "a little inaccuracy saves a ton of explanation".

[MfA]

Originally Posted by Richard

This could be an example of how "a little inaccuracy saves a ton of explanation".

Did it?

[Richard]

You know the answer to that, and NV PR ought to have known too.

[fehu]

Originally Posted by thop

Forum poster claims to know quite a bit about Fermi.

recursive!

[Mize]

As I've alluded to in this thread, my bet is nominally = Cypress but 20% faster with PhysX or some other special conditions. Their marquee bench will be B:AA with PhysX and AA and, under those circumstances, they'll say X% faster than Cypress.

My prediction at least.

[neliz]

Originally Posted by hatter

I doubt that Anand will put something in his piece after hearing it from people whispering in a crowd. You can say many things about AnandTech but I have found that mostly they don't pay heed to rumours. He must have got the figure from someone reliable or connected to Fermi.

The 20-30% number has been going around the net since October (if not earlier.) It's not from people "connected to fermi", it's AMD's competitive analysis team and nv's own presentations.