Guys keep in mind that performance is in BF3 at high res, ultra textures + 4xmsaa. That is memory hog. so it will bottleneck GTX 580/590 1.5 gb easy
other bench show closer results...
That graph has to be fake because NVIDIA said they will only be using a single clock for geometry + shader processing. So no more 800 core/1600 shader figures. But to compensate their base clocks will be a lot higher than 1000 MHz. That slide there is showing traditional Fermi/Tesla type clocks...
Yeah AMD bitched a lot about Fermi being compute and now they're adopting it :) It's clear the performance hit AMD has suffered with 7970 (I mean 10%-18% total average better performance than GTX 580 at 1080p and 1600p res) is because of this move. but NVIDIA has already suffered through...
That is because AMD's so called performance was theoretical performance. VLIW5 and VLIW 4 give you mad projected performance if u assume that the compiler can optimize perfectly by packing every instruction with 5 or 4 (respectively) meaningful ops. This is rarely the case. Hence NVIDIA's SIMD...
Somehow I'm a little skeptical about Maxwell being 16x... Leaked slides etc show Kepler to be a max of 2x faster and for Maxwell to be 16x that would require an 8x jump in just one more generation. I think 4x performance for Maxwell is more realistic...
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.