And why is Fermi pegged at 530mm2 ? From what's been speculated, it should actually be under 500mm2.
NVIDIA Fermi: Architecture discussion
- Thread starter Rys
- Start date
And why is Fermi pegged at 530mm2 ? From what's been speculated, it should actually be under 500mm2.
It's not, you just seem to be ignoring that info.
~530-550mm2.
don't have any evidence outside of the conference call stating margins for fermi will remain the same as they are now with the gt200b. Or has there been anything solid on that front?
The only "info" I've seen about Fermi size is Charlie's claim of 23.x * 23.x.
You sure about that? I read Kyle's post to mean that they're going to keep things closer to home this time around and that AIB's will be stuck with putting stickers on pre-built boards.
Ok, but what leads you to believe so strongly that A3 will do the trick and/or that clocks will get a boost? According to silent-guy a respin shouldn't impact clocks much. Is it possible that the metal spins also addressed variables that would make the chip play nicer in TSMC's current environment or would that all be at the silicon level too?
You sure about that? I read Kyle's post to mean that they're going to keep things closer to home this time around and that AIB's will be stuck with putting stickers on pre-built boards.
Ok, but what leads you to believe so strongly that A3 will do the trick and/or that clocks will get a boost? According to silent-guy a respin shouldn't impact clocks much. Is it possible that the metal spins also addressed variables that would make the chip play nicer in TSMC's current environment or would that all be at the silicon level too?
GT300 is the same size as GT200, i.e. ~24x24. Any lower (like speculated by some here since before may) is unfounded. Btw, You promised us pics of Fermi back then, still waiting for your sources to show any signs of credibility.
Someone's Twitter said:
Last edited by a moderator:
He just answered... neliz has been telling us this for quite a few months already.
Just need a little clarification on your post. The clockspeeds you stated you mentioned them regarding the target clockspeeds, correct? Not the A2 clocks.
Thanks.
Are there any real sources though?
Until neliz fails us, I don't see any reason to doubt his info.
Hell, even if he does fail, he has been spot on with the vast majority of info he has passed and would still take his word for it.
Edit- You also don't like Charlie's source in Taiwan?
True, you don't know if it is a "real" source until you can verify the info first hand.
Well, like someone at Nvidia or a major OEM, or maybe some reputable reporter. 'Some guy on a forum' is kinda dodgy.
I think you believe him because his predictions are not goot for nVidia. Do you think that GTX380 is a GT212 card?
His track record behind tape-out dates is really bad. Not a great source...
My predictions are not good? or nVidia is dropping the ball? bad choice of words my friend.
uhm what? haven't kept up or selective reading?Do you think that GTX380 is a GT212 card?
For all we know, GT200 was supposed to be pushing the upper reticle limits already. Nvidia's in a kind of difficult situation right now - they're having problems with margins in the high end for about 1.5 yrs now and they are late to the DX11 game. Plus, they've said, Fermi would be much more modular than previous generations.
I for one could imagine a solution to this.
I for one could imagine a solution to this.
This is probably more for the 'signs of strain' topic, but do you reckon that the margins in the consumer high end really matter that much to Nvidia? It's a small volume sector, and Nvidia makes no secret of the fact that most of their profit comes from the professional sector - where margins are still pretty strong.
So, you're saying that no one knows how big the chip is that they have to design their boards for?
hmm no noone knows the exact size kinda like the g80. No one knew the size outside of what nV told them.
I find your G80 part deux very hard to believe.
