Fermi underpowered?

Whilst I agree with Rast, what you have to remember is that OC3D HAS to put up some sort of article about this as it's on every tech site out there. I think it's pretty balanced and leaves the reader to make up their own mind as to the validity of the claims. At the end of the day it's about the site looking fresh and the hits coming in with new news or rumours. Perhaps articles like this could be marked with 'rumour'?
 
name='Kempez' said:
Whilst I agree with Rast, what you have to remember is that OC3D HAS to put up some sort of article about this as it's on every tech site out there. I think it's pretty balanced and leaves the reader to make up their own mind as to the validity of the claims. At the end of the day it's about the site looking fresh and the hits coming in with new news or rumours. Perhaps articles like this could be marked with 'rumour'?
Click to expand...

Would probably be a good idea. Whilst I'd still disagree with the basis of 'as every1 else is doing it'....

name='Kempez' said:
.... and leaves the reader to make up their own mind as to the validity of the claims.
Click to expand...

Cos up to this point, I see very little evidence of this.
 
Got to remember mate that those commenting are only a few of the hundreds (thousands maybe), who will read the article. They are also usually the most vociforous.

From a purely business perspective, news like this brings hits which brings revenue. 'nuff said frankly.

Soz for typos, am on iPhone.
 
TBH I dont really mind waiting. I think its fair that ATI have got there first and are taking the money for it. It's a shame they arent producing enough really because I would like to see some real competition going on, that way the prices would drop quicker and performance would increase quicker too
 
name='Rastalovich' said:
Still think the yields are better than 2% myself.
Click to expand...

A 400mm^2 (I think) die is what Fermi involves, add that to the fact that it's on an already problematic and relatively new process. Yields are bound to be terrible.
 
name='Zoot' said:
A 400mm^2 (I think) die is what Fermi involves, add that to the fact that it's on an already problematic and relatively new process. Yields are bound to be terrible.
Click to expand...

Thats a massive size, like the size of the side of a case
 
name='Zoot' said:
A 400mm^2 (I think) die is what Fermi involves, add that to the fact that it's on an already problematic and relatively new process. Yields are bound to be terrible.
Click to expand...

I've highlighted the other error.
 
name='sammytomjohn' said:
think he means 40nm :)
Click to expand...

name='siravarice' said:
I thought he might ><
Click to expand...

name='monkey7' said:
And 400mm^2 is just 20*20mm, or below 1*1 inch for you imperials out there.
Click to expand...

^^This is what I meant. 400mm^2 isn't very big physically but its enormous for a die size. They're asking a lot of TSMC on this one, I'm not surprised in the least that there's issues.

That said, Semiaccurate ain't the most credible of sources at times best to take it with a grain of salt none the less.

name='Rastalovich' said:
I've highlighted the other error.
Click to expand...

Error?
 
name='sammytomjohn' said:
where you said in the comment of yours he quoted you said fact! it is not fact just speculation and rumours!!
Click to expand...

Well Fermi is on a 40nm process which thus far only has ATi and Nvidia's GPUs (I think).

And also, the process is relatively new; there's bound to be issues with it especially with a rather large die size.

It's the way the IC fabrication process works, die shrinks on the deep sub-micron level always present issues. The leakage current that intel encountered upon switching from 65nm to 45nm is one such example which they sorted with the use of High-K Gate Dielectrics is one such example.

(Look up intel's website if you want more info)

Also the shortages of the 5XXX series is another indication that the process is not completely solid yet. However we haven't seen irrefutable proof yet, but IMO you can bet there are big issues with a new state of the art process with a colossal die size.
 
Zoot 40nm process has been used by other companies in the past, not for gpus tho. Ti are doing 2xnm processes with tsmc atm.
 
name='Rastalovich' said:
Zoot 40nm process has been used by other companies in the past, not for gpus tho. Ti are doing 2xnm processes with tsmc atm.
Click to expand...

Fair enough, that I didn't know. What sort of parts?

Also you can safely say a GPU is a more complex part than most of TI's parts. (DSP's, Microcontrollers etc.)

With a die size as big as Fermi there's bound to be issues. Granted though that 400mm^2 is hearsay at the moment but if the past GT200 series is any indication the die size is going to be rather large in comparison, yields can't be good in the beginning.
 
That's the biggest problem, it's pretty much all hearsay.

Texas Instruments have chips everywhere, their mostly known these days for their firewire presence. But I'm sure if u sat down with a Ti rep, they could talk for days about their other interests. Mainly data conversion, comms and the like afaic. Don't forget the calculators :p
 
They do indeed. Must do a bit of digging to see that they have on the lower processes.

I'm working with a 32bit Floating Point 225MHz DSP from them at the moment. Quite a nice part I must say, very easy to work with.
 
You must log in or register to reply here.

Similar threads

FragTek
The Definitive Seven Year GPU History Guide
Replies
6
Views
11K
FarFarAway
F
Back
Top