View Single Post
Old 01-23-12, 12:26 PM   #121
Registered User
Join Date: Jul 2003
Posts: 1,526
Default Re: next gen kepler to support dx 11.1, also take a year to rollout all cards

Originally Posted by ninelven View Post
I'm not the one who needs pictures. Either answer the questions or admit you have no actual evidence for your claims.

Exactly, how much die space do the ROPs take on Fermi? What is the percentage of the total area of Fermi? How much die space do the ROPs take on Tahiti, and what percentage of the total area?
That would be information that would only be known for the reasons i mentioned earlier, assuming Nvidia itself allows the information to be released, so stop with the stupid argument if you please.


Exactly, how should the ROPs and texture units be "enhanced?"

Like i said earlier and you didn't bother to understand at all, they need to do more work for every clock cycle in practical real world terms, meaning adding more memory bandwith would help, but adding even more of same ROPS is pointless, as it was proven with the 32 ROPS on tahiti wich is 50% less than on Fermi, and Fermi gets it's ass kicked hard.....This is not hard to understand either...

No, just like nvidia. Texture units are tied to SIMD engines in GCN; it is clear you don't have a clue what you are talking about.
Connected together and integrated into the shader block are 2 different things....The first allows to futher enhance the texturing output without needing to mess with the shader block itself, and the second option does not wich is the option Nvidia took....
shadow001 is offline   Reply With Quote