Support NeoGAF

[marsomega]

Why is it when things are presented in smaller sizes they seem cute? Can we one day find one of these inside the next GB? Maybe not, tee hee.

Introducting the 9700 PRO "MINI"

Last PS3/NVIDIA thread some claimed blasphemy at the idea that NVIDIA's next GPU's won't incorporate a unified shader model. Well its nothing new that NVIDIA and ATI are on two different sides considering the tech and a new interview tells no different on their complete lack of interest in the direction. Except this time, they make a argument as to why.


David Kick NVIDIA Guru/Cheif Scientist

As to whether the architectures for vertex and pixel processors should be the same, it's a good question, and time will tell the answer. It's not clear to me that an architecture for a good, efficient, and fast vertex shader is the same as the architecture for a good and fast pixel shader. A pixel shader would need far, far more texture math performance and read bandwidth than an optimized vertex shader. So, if you used that pixel shader to do vertex shading, most of the hardware would be idle, most of the time. Which is better—a lean and mean optimized vertex shader and a lean and mean optimized pixel shader or two less-efficient hybrid shaders? There is an old saying: "Jack of all trades, master of none."

Pretty much considering the development time behind PS3's GPU we can deduce it will retain the distinction between Vertex and Pixel shaders but we don't know (least I don't) how CELL would fit or influence NVIDIA's tech. Also, cancelation of the NV47, 48, 50 were just rumors and speculation. We already know the NV48 was never canceled and in fact will face off ATI's R520 head on. The part is scheduled to debut after ATI shows their hand, showed be interesting.

NV48 Thread

UPDATE: Looks like Beyond 3D summed it all up including ATI's side of which I haven't heard much from. Least not as detailed as Kirk's Take on it.

http://www.beyond3d.com/forum/viewtopic.php?topic=19258&forum=9

xbitlabs take on the whole Distinction versus Unified argument between NVIDIA and ATI.
http://www.xbitlabs.com/news/video/display/20041223075525.html

Not much is known about the architecture and capabilities of the code-named R520 product scheduled for release in Q2 2005 that was initially referred as the R500. What is clear now is that the new graphics chip will sport Shader Model 3.0 – pixel shaders 3.0 and vertex shaders 3.0 – bringing additional programming capabilities to ATI’s future graphics processors as well as some other innovations.

ATI’s R5xx architecture will not resemble that of the previous generation products and NVIDIA’s GeForce 6 architecture known as NV4x, particularly ATI will implement efficient flow-control, a crucial feature for pixel shaders 3.0, that will not bring speed penalty it does on existing SM3.0 hardware, according to sources. The future of the graphics hardware lies in higher number of ALUs ops per texture ops, unified pixel and vertex shaders as well as some other requirements of Microsoft Windows Longhorn operating system, such as virtualisation and context switches. While ATI agrees on the long-term goals for its roadmap, it does not name feature-set of actual products and says all the architectural changes will be implemented gradually, not at once.

Some sources claim that the R500 is a code-name of ATI’s graphics processor that will be submitted for Microsoft’s next Xbox console. The shader core of the R500 was reported to have 48 Arithmetic Logic Units (ALUs) that can execute 64 simultaneous threads on groups of 64 vertices or pixels. ALUs are automatically and dynamically assigned to either pixel or vertex processing depending on load. The ALUs can each perform one vector and one scalar operation per clock cycle, for a total of 96 shader operations per clock cycle. Texture loads can be done in parallel to ALU operations. At peak performance, the GPU can issue 48 billion shader operations per second, it was said.

The R520 is also expected to feature advanced memory interface, presumably supporting GDDR4 memory.

Hmm.. souped up Ultra-fied NV48 at 110nm vs R520 at 90 nm...Can't wait..

 

[doncale]

can't wait to see r520 take on the nv48 (or nv47)

the PS3 GPU remains a big mystery still. other than the fact that nvidia is working on it, and it will be based on nvidia's next architecture...


btw, i dont think that GBA-NEXT will have as much 3D power as the Radeon 9700. maybe half that. maybe something close to gamecube or slightly less even. but then you never know.

 

[Fafalada]

Last PS3/NVIDIA thread some claimed blasphemy at the idea that NVIDIA's next GPU's won't incorporate a unified shader model.

Actually there is a good chance that PS3 GPU will in fact, have a unified shader model, thanks to the possibility that it could end up with nothing but "pixel" shaders, period.
On that same note, the PS3 part may also have a lot less in common with PC parts then people generally assume.

 

[marsomega]

Wow I'm seeing it every where now. Here is XbitLabs take on it.

http://www.xbitlabs.com/news/video/display/20041223075525.html

Not much is known about the architecture and capabilities of the code-named R520 product scheduled for release in Q2 2005 that was initially referred as the R500. What is clear now is that the new graphics chip will sport Shader Model 3.0 – pixel shaders 3.0 and vertex shaders 3.0 – bringing additional programming capabilities to ATI’s future graphics processors as well as some other innovations.

ATI’s R5xx architecture will not resemble that of the previous generation products and NVIDIA’s GeForce 6 architecture known as NV4x, particularly ATI will implement efficient flow-control, a crucial feature for pixel shaders 3.0, that will not bring speed penalty it does on existing SM3.0 hardware, according to sources. The future of the graphics hardware lies in higher number of ALUs ops per texture ops, unified pixel and vertex shaders as well as some other requirements of Microsoft Windows Longhorn operating system, such as virtualisation and context switches. While ATI agrees on the long-term goals for its roadmap, it does not name feature-set of actual products and says all the architectural changes will be implemented gradually, not at once.

Some sources claim that the R500 is a code-name of ATI’s graphics processor that will be submitted for Microsoft’s next Xbox console. The shader core of the R500 was reported to have 48 Arithmetic Logic Units (ALUs) that can execute 64 simultaneous threads on groups of 64 vertices or pixels. ALUs are automatically and dynamically assigned to either pixel or vertex processing depending on load. The ALUs can each perform one vector and one scalar operation per clock cycle, for a total of 96 shader operations per clock cycle. Texture loads can be done in parallel to ALU operations. At peak performance, the GPU can issue 48 billion shader operations per second, it was said.

The R520 is also expected to feature advanced memory interface, presumably supporting GDDR4 memory.