The GT300/Fermi Thread - Part 2!

[LordEC911]

fermi: x*y=z
x = texture units
y = shader clock
z = texture fillrate


fermi:
higher pixel+texture fillrates
higher shader power
higher memory bandwidth/size
higher efficiency across the board

and more but according to ati brilliants here it barely matches 5870 lol

Fail... you need to go read the whitepapers again, unless you like making stuff up.
The only thing you are correct on is pixel fillrate, memory bandwidth and bus size.

Mtriangles/s figure for 5970 is wrong I think, should be double of that.

Yep, should be double the 725, aka 1450.

You can't add bus width like that. AFR mirrors the memory for GPU1 in GPU2 so the bandwidth is still 256-bit effective, iirc.

Yes, but each GPU has access to all the 256bit bus. It isn't like each GPU has to split a 128bit bus.