• 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.

**AMD Fiji Thread**


Sadly yes it is..

Here's an unmodified box.

CIE4TwqXAAEQUzA.jpg
 
If you are only buying a card to last 2 years then it doesn't make sense to buy a TitanX since the 12GB is overkill for any situation. 12GB may come into effect in 2-3 years time but we will have cards probably twice as powerful then.

I suspect we will be able to buy 2 Fury pro's for the same price as 1 TitanX, and the Fury Pro's in crossfire will be around 50%+ faster when overclocked.

Who cares about overkill? Because the majority of people buying new/flashy tech want it because it is new, overkill or not.
 
Yes but the fact that Nvidia have managed to have the same efficiency and as far back as 9 months ago withOUT HBM is pretty impressive.

They walk a different path, Nv cut the chips, and made them simplier to reach that, AMD gone with the more complicated chips, and given they knew HBM is coming they don't need to cut their chips to reach the same efficiency
 
Last edited:
Fury Nano has a 175 Watt TDP, thats 125 Watts less than the 290X and it will no doubt destroy it in performance, they have doubled performance per watt, thats not down to HBM alone.

yes, well done, but what happens when nvidia have a process improvement AND HBM and AMD have only the process improvement to rely on?
 
yes, well done, but what happens when nvidia have a process improvement AND HBM and AMD have only the process improvement to rely on?

I don't see the point your making?

The new architecture in Fury Nano form is uses well over 100 Watts less than the 290X while having way more Shaders, its probably a cut down Fiji with about 3500 Shaders, thats 700 More than the 290X.

Fiji is a hell of a lot more efficient at the architectural level, probably by about 35% bringing it in line with Maxwell.
 
Last edited:
Back
Top Bottom