Follow along with the video below to see how to install our site as a web app on your home screen.
Note: This feature may not be available in some browsers.
I think there is a bit of a difference between a vendor supporting the new DX standard and one choosing to support a proprietary feature like PhysX or CUDA.![]()
While I don't disagree with your basic argument, you say this as if DX is somehow not a proprietary standard.
When Is the last time anyone but nVidia had influence on PhysX or CUDA?
How does that relate to the fact that DX is a proprietary standard which only exists on Microsoft operating systems?
oh, yeah, saying the truth now is "nv pr".DegustatoR---> Full time NV PR exclusively for Beyond3d![]()
Multiple vendors have input on directx which sees use across multiple platforms.
How does that relate to the fact that DX is a proprietary standard which only exists on Microsoft operating systems?
IIRC, the register specs since R5xx have been posted....Well if AMD's GPU architecture would be open i'm sure that NV would write CUDA for it, no? In fact we'll see if NV port CUDA to LRB once it'll become avialable. Although now with OpenCL it probably won't happen anyway.
I'd agree with you if I hadn't played a couple a few days ago.DX11 has a tough road ahead. It is definately the future and a welcome change, but i doubt we see any full DX11 titles for a few years yet.
DX10.1 might be considered ATi-only even though it is part of the industry standard DX. Didnt ATi go to microsoft about that one since Nvidia had microsoft cut a bunch of stuff from DX10?
No difference at all. From an ISV point of view it all comes down to the size of the market. PhysX now (and for a couple of years ahead) will have much higher market penetration than DX11 so it makes more sense for an ISV to implement GPU PhysX first and DX11 later.I think there is a bit of a difference between a vendor supporting the new DX standard and one choosing to support a proprietary feature like PhysX or CUDA.![]()
Well, the rest of the world WILL just stop and wait. Not for "them" but for DX11 having some kind of a footprint in a PC h/w space. And even when it will get some footprint the usage of DX11 effects and functions will be pretty minimal at first.Just because nVidia is going to be late to the game with their part, does that mean the rest of the world should just stop and wait for them?
I mean that CUDA is a developement environment and infrastructure first, proprietary runtime environment second.I don't get that at all DegustatoR, what do you mean? :|
I'd agree with you if I hadn't played a couple a few days ago.![]()
i'm quite sure that most of CUDA tools will work with them eventually -- up to the point where you might be able to write a program once and then "compile" it for CUDA+OpenCL+DXCS automatically.