• Notice regarding image hosts and attachments. See here.

  • Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

The Ferminator

?

I'm not sure what there is to guess about. 6xxx could potentially be a little more advanced sure but its engineered to teh same targets so its going to be in the same ballpark.

'potentially' and 'ballpark', you're guessing here. I'm not saying your guess is unbelievable however try not to pit non existing hardware against existing hardware, it makes you look a little fanboy-ish.
 
ATI Stole a march on nVidia by bolting DX11 onto a glorified 4870 - I'm not slighting it it works very well - but at the end of the day thats what it is.

Are you basically saying Nvidia has had it's @ss handed to them, because they were dumb and bit off more than they could chew.

Note:
Architecturally Fermi is 'Nvidia's' NEXT gen, not 'next next next' gen that will probably arrive in time to be made redundant by HD6000 or even a 5890.

Seriously Rroff, it's like your in denial.
 
'potentially' and 'ballpark', you're guessing here. I'm not saying your guess is unbelievable however try not to pit non existing hardware against existing hardware, it makes you look a little fanboy-ish.

Yes I'm clarifying what I said before... I'm not guessing within the scope of my original post...................

Are you basically saying Nvidia has had it's @ss handed to them, because they were dumb and bit off more than they could chew.

Note:
Architecturally Fermi is 'Nvidia's' NEXT gen, not 'next next next' gen that will probably arrive in time to be made redundant by HD6000 or even a 5890.

Seriously Rroff, it's like your in denial.

Fermi is nvidias next next gen... I shouldn't have to spell that out on a forum populated by so called enthusiasts... I'm not sure why GT212 is such a mystery to some people.

RV7xx->Evergreen->Northern Islands
GT200b->GT212->GF100
 
Last edited:
Yes I'm clarifying what I said before... I'm not guessing within the scope of my original post...................



Fermi is nvidias next next gen... I shouldn't have to spell that out on a forum populated by so called enthusiasts... I'm not sure why GT212 is such a mystery to some people.

RV7xx->Evergreen->Northern Islands
GT200b->GT212->GF100

It's not because GT212 never existed, besides it just sounds like another re-brand.
 
It's not because GT212 never existed,.

Doesn't make any odds if its actually released or not its still the technology progress going through the motions. The point being we will have similiar architectures going up against each other and aslong as nVidia can get it onto a sub 40nm process in time (doubtful) it will show its real strength rather than being hampered by 40nm where it never belonged.

besides it just sounds like another re-brand.

So basically you don't even know anything about it......
 
Last edited:
Not a major generation shift no - but DX10.1, 40nm and masses of shaders, the evergreen cards aren't really that much different except AMD was on the ball and strapped DX11 functionality in for the ride. Fermi's architecture is significantly more sophisticated than the 58xx cards.
 
The problem with Larrabee isn't hardware... intel doesn't have the mind set to make it a sucess - what they do they do very well but it doesn't translate to high end GPUs.
 
And what nvidia do (and do very well) is spin. But there is only so far you can spin an imminent failure. The whole fermi "incident" could be culled with some honest answers.

Again I will point out that I am 100% brand impartial and would go out and buy a [insert useless video card manufacturer here] card if it outperformed the competition in a price/performance manner.
 
Most people are suggesting closer to the 100 mark for how many dies you can get off a wafer, assuming they all worked, but yield wise as you said, it could quite easily be as bad as around 20 a wafer, and frankly we don't really know if the 20% rumours are 20% including salvaged cores(in which case its an entire disaster) or without, which I'd guess is more likely. The problem is if they do end up doing intesively salvaged cores, I can't see the yields getting "that" high.

As I said before, anyone laughing at AMD for low 5870 numbers, is in for a BIG BIG shock from Nvidia's supply numbers.

But AMD's are largely because, no matter which company is ahead on performance, they aren't usually far enough ahead to stop all sales to the competition, infact not many. This is a strange situation where Nvidia simply aren't producing 260-285gtx's or Fermis for the last several months, they've shifted almost all their production to chucking out zero profit cheap as chips gt210's and the like to keep OEM's off their backs. AMD has basically their normal high/mid end demand, plus all the high/mid end demand that Nvidia usually has, but very little extra production. Twice the normal demand, no extra capacity and worse yields compared to previous gen due to crappy process = less cores available and more than twice the demand, it was never going to be fantastic. But then theres little point making 10 million 5870's one month, and nothing for the next 6 months.

I've worked it out with the cut on centre and hitting the whole of one side. I have no idea how they would arrange the cores and I'm unsure what core spacing is used but even at 110 cores the average is still only 26.

The thing is why would the yeilds be so poor ? They will never hit the same rate as ATI because of the difference in core size, but ATI are seeing improvements over 55nm now. Thats still pritty dam poor considering the extra 2k per wafer cost, but its a mile ahead of what Nvidia are doing which seems to suggests the problem is not all down to TSMC.
 
Last edited:
Fermi's architecture is significantly more sophisticated than the 58xx cards.

I think this is evidence of sophistication turning into complication.

Neither yardstick gives an accurate picture of how good/bad an architecture is as you can have an extremely sophisticated architecture yet badly designed, which appears to be the case with Fermi.
 
Back
Top Bottom