Nvidia's G80 (aka NV50) uses Unified Shader approach

  • Thread starter Thread starter Guest
  • Start date Start date
G

Guest

remember G70 (GeForce 7800 GTX) is an NV4X architecture (a refresh of the
NV40) - basicly it's the NV48 with a few changes, no matter what Nvidia
tells you or how they spin it as a totally new GPU.


G80 is most likely going to be Nvidia's first -completely- new architecture
since the NV40 - GeForce 6800

G80 is therefore, probably the NV50.



http://www.techspot.com/news/18126-NVIDIA-G80-uses-Unified-Shader-approach.html

NVIDIA G80 uses Unified Shader approach
by Derek Sooman on Sun 24 Jul 2005, 10:42 AM
David Kirk, Chief Architect for NVIDIA says that there's plenty of mileage
left in the G70 architecture, but that one day, when it makes sense to do
so, NVIDIA will move to using a unified architecture in hardware. The design
of NVIDIA G80 is based on unified shader architecture, which we should
hopefully see appear as soon as next year.

G70 already supports Longhorn WGF 1.0 API so most likely G80 will support
WGF 2.0 with improved virtualization techniques and new pipeline stages. The
likely process technology choice for G80 is 90nm and the architecture is
made for high core speed (~1GHz). G80 design is completed and waiting for
ATI R580 when the time comes.
ATI has beaten NVIDIA to it, using the unified approach for their R500 Xenon
within the XBox 360, which has 48 unified pipelines.

_______________________________________________________________


http://www.nforcershq.com/article3503.html
VR-Zone - The future is actually pretty near where NVIDIA G80 design is
based on unified shader architecture slated to appear in 2006. ATI has
already taken the unified approach for their R500 Xenon within the XBox 360
and has 48 unified pipelines. As we know, in an unified shader architecture,
there are no dedicated vertex and pixel shader engines but unified shader
engine capable of executing both types of instructions.

G70 already supports Longhorn WGF 1.0 API so most likely G80 will support
WGF 2.0 with improved virtualization techniques and new pipeline stages. G80
design is completed and waiting for ATI R580 when the time comes.
 
We'll see how that works out. This kind of "flexible" or "unified"
architecture was attempted with the FX5xxx series. The end result is that
games required a lot more tweaking/shader-replacement to take advantage of
this kind of flexibility. And remember, "unified" shaders are more
complicated than dedicated vertex- or pixel-shaders, so die size grows
again, and we pay for it in the form of lower clock speeds and dustbuster
cooling solutions.

Also, recall the 7800GTX isn't that much faster than the 6800Ultra in
applications requiring lots of memory bandwidth (e.g. Doom3), for the
obvious reason that memory technology hasn't advanced much between the two
cards: same 256-bit interface, similar clock speed.
 
Back
Top