http://www.beyond3d.com/forum/viewtopic.php?t=20938
and
http://www.beyond3d.com/forum/viewtopic.php?t=20937
before this, I was think PS3 graphics architecture would be of the Shader Model 4 generation. definitally ahead of Xbox2's Shader Model 3.0 ++. because (1.) Nvidia has been ahead of ATI in getting out more advanced feature sets including shader model generations. and (2.) the PS3 is coming out a little later than Xbox2.
but now it seems that there is at least a GOOD chance that Xbox2 and PS3 will both have some form of extended Shader Model 3.0 implemenation.
that's not to say that PS3 will not have Shader Model 4.0, but it looks less likely.
and
http://www.beyond3d.com/forum/viewtopic.php?t=20937
Earlier NVIDIA held a Financial Analysts Session at Credit Suisses First Boston Semiconductor & Capital Equipment Conference, and as is often the case a few details could be gleaned on their upcoming parts. When asked of the high end refreshes for both Spring and Fall NVIDIA's Vice President of Investor Relations and Communications, Michael Hara had this to say:
....... Well, from an architecture standpoint were just still at the beginning of shader model 3.0. And we need to give the programmers out there some time to continue to really learn about that architecture. So in the spring refresh what youll see is a little bit faster versions...
...... I think youll see the industry move up a little bit in performance. But I dont think youll see any radical changes in architecture. I doubt youll see any radical changes in architecture even in the fall. When we came out with GeForce 6, we tend to create a revolutionary architecture about every actually two years. And then we derive from it for the following time. So even the devices that we announced this fall, that will be I think a lot more powerful than the ones we actually had a year ago. Architecturally were still in the shader model three type era.
Although it appears that NVIDIA have been tweaking their codenames, and we dont yet know exactly how they are internally classifying these new parts we can surmise that the Spring part mentioned is what has previously been rumoured to be NV47 whilst the fall product could be what was previously thought to be known as NV50. NVIDIA have said before that the GeForce 6 generation could last for 3 years in the low end, whilst there will be a slightly greater architectural shift in the high end in the intervening time period and, given these timescales, we had previously surmised that this high end refresh would still be Shader Model 3.0 based, possibly bring more flexibility, architectural performance benefits and being more orthogonal, and at present this would still appear to be the case.
On the discussion of silicon process nodes Mike later mentioned this: If you look at when we go to 90, my guess will be is well have one or two products this year going from 90 in the second half. On the face of it this would tend to confirm our suspicions that the Spring refresh will be 110nm based, as much of the GeForce 6 product line is now, whilst the high end fall product will likely be 90nm.
One question that does remain is that of the graphics for Playstation 3 as NVIDIA have already stated that the graphics is an alteration on their next generation part. Given that the design for a console part must be finished many months before the product is due to ship should Sony be seeking an early 2006 ship date the feature capabilities may match up with the Fall product which would suggest Shader Model 3.0 equivelent capabilities.
before this, I was think PS3 graphics architecture would be of the Shader Model 4 generation. definitally ahead of Xbox2's Shader Model 3.0 ++. because (1.) Nvidia has been ahead of ATI in getting out more advanced feature sets including shader model generations. and (2.) the PS3 is coming out a little later than Xbox2.
but now it seems that there is at least a GOOD chance that Xbox2 and PS3 will both have some form of extended Shader Model 3.0 implemenation.
that's not to say that PS3 will not have Shader Model 4.0, but it looks less likely.