NVIDIA "Pascal" GPUs to be Built on 16 nm TSMC FinFET Node

[medi01]

The combination of a less efficient architecture but more transistors for same die size and assuming that AMD uses a design, layout, and instruction sets that are slightly inferior to Nvidia's for GAMING purposes, then I can see, overall, AMD competing equally with Nvidia.

Fury X is 8.9 billion transistors.
980 Ti is 8 billion.

The "architecture" difference in terms of efficiency is marginal at best and not even clear which company has the upper hand especially if you take the whole DX11/DX12 optimization into account.

 

[ironcerealbox]

I hope you realize that you said, in-the-end, the same thing as I did.

 

[mcraygsx]

Lower fab processes will most likely bring lower power, so maybe WC will not be required?

Not everyone like the idea of WC in their system. I am hoping that these next gen chips don't require a massive coolers and like one of the member said that is exactly the point of die shrink.