The official GT300/Fermi Thread

[trinibwoy]

The point was that it does not need to. You do know that PhysX works on the CPU.

Yep. Unfortunately that doesn't tell us much. Unless of course you assume it's the same code base and they don't have a GPU optimized path which is highly unlikely given the vast differences in the architectures. Actually, I'm almost certain that's the case becaues they have a CUDA 1.3 optimized PhysX implementation, i.e. different paths for G80 and GT200 based cards.

Nvidia would have loved to have one there, regardless of whether there is any software there, because it would be good PR pure and simple. Not having it might not be a big deal in the end, but you bet your $$ that if they could choose between having it ready at launch or not ready, they'd choose the former every single time.

Yeah there's no doubt they aimed for the Win7 launch and missed. Now they're hoping to tread water for a few months and then make nice with Fermi.

[Final8ty]

Yep. Unfortunately that doesn't tell us much. Unless of course you assume it's the same code base and they don't have a GPU optimized path which is highly unlikely given the vast differences in the architectures. Actually, I'm almost certain that's the case becaues they have a CUDA 1.3 optimized PhysX implementation, i.e. different paths for G80 and GT200 based cards.



Yeah there's no doubt they aimed for the Win7 launch and missed. Now they're hoping to tread water for a few months and then make nice with Fermi.

NV needs to sort it out as people who have bought an NV card should be allowed to use it as they see fit.
What's the point of Fermi that has no display output & its purposes is to be a number cruncher but may have issues with what GPU you have in your system.