Hmmmm, I guess they really do want to drive every pixel on the planet.
http://www.xbitlabs.com/news/story.html?id=1045147250
Can anyone verify this?
http://www.xbitlabs.com/news/story.html?id=1045147250
Can anyone verify this?
NV33 Rumours, if anyone is interested
- Thread starter elroy
- Start date
Well if we are playing rumours - trump time with information I in no way vouch for - NV40 
http://www.quake.co.il/modules/news/article.php?storyid=117
Inside source gave some new details about nVidia's card, that is due to come out in the second half of next year (2004).
Same source was the one to give pre-release details about the current high-end card - NV30, even before Geforce4 was released.
Details were correct, about 90% of the data about NV30.
This information stands for only as a roadmap, and some of it might still change due to market requirements.
Read More For the NV40 Specs.
S2K
Here are the NV40 specs:
300-350 Million Transistors on 90-nm process
750-800 MHz Core
16MB Embedded DRAM (134M trans.)
1.4 GHz 256-512MB DDR-II Memory
8 Pixel Rendering Pipelines (4 texels each)
16 Vertex Shader Engines
204.8 GB/sec Bandwidth (eDRAM)
44.8 GB/sec Bandwidth (DDR-II)
25.6 GigaTexels per Second
3 Billion Vertices per Second
DirectX 10 (or extended 9.1)
Release H2 2004
We will release more data as soon as it comes available to us.
***The data above is not offical, and shouldnt be treated as such.
To compare, here are the NV30 Specs
0.13u process
500 MHz core clock speed
500(1Ghz) MHz 128-256MB DDR-II
125 M transistors
8 pixel pipelines with 2 texturing units each
16 texture layers per rendering pass
3.2 gigapixels per second
6.4 gigatexels per second
360-400 million vertices per second
16 gigabytes/sec
DirectX 9.0+ features (Pixel Shader 2.0+, Vertex Shader 2.0+, etc.)
128 and 64-bit Floating-Point Pixel Processing
Quad Vertex Shader Engine
Improved FSAA (Programmable Grid AA or Adaptive AA)
Improved HSR (Lightspeed Memory Architecture III)
AGP 3.0 (AGP 8x)
http://www.quake.co.il/modules/news/article.php?storyid=117
Inside source gave some new details about nVidia's card, that is due to come out in the second half of next year (2004).
Same source was the one to give pre-release details about the current high-end card - NV30, even before Geforce4 was released.
Details were correct, about 90% of the data about NV30.
This information stands for only as a roadmap, and some of it might still change due to market requirements.
Read More For the NV40 Specs.
S2K
Here are the NV40 specs:
300-350 Million Transistors on 90-nm process
750-800 MHz Core
16MB Embedded DRAM (134M trans.)
1.4 GHz 256-512MB DDR-II Memory
8 Pixel Rendering Pipelines (4 texels each)
16 Vertex Shader Engines
204.8 GB/sec Bandwidth (eDRAM)
44.8 GB/sec Bandwidth (DDR-II)
25.6 GigaTexels per Second
3 Billion Vertices per Second
DirectX 10 (or extended 9.1)
Release H2 2004
We will release more data as soon as it comes available to us.
***The data above is not offical, and shouldnt be treated as such.
To compare, here are the NV30 Specs
0.13u process
500 MHz core clock speed
500(1Ghz) MHz 128-256MB DDR-II
125 M transistors
8 pixel pipelines with 2 texturing units each
16 texture layers per rendering pass
3.2 gigapixels per second
6.4 gigatexels per second
360-400 million vertices per second
16 gigabytes/sec
DirectX 9.0+ features (Pixel Shader 2.0+, Vertex Shader 2.0+, etc.)
128 and 64-bit Floating-Point Pixel Processing
Quad Vertex Shader Engine
Improved FSAA (Programmable Grid AA or Adaptive AA)
Improved HSR (Lightspeed Memory Architecture III)
AGP 3.0 (AGP 8x)
Um, I think they got their times a little mixed up. NV40 is supposed to be released late this year, or early next year. I can't see it slipping to H2 next year (unless the 90 nm process won't be ready). 16 mb eDRAM would be sweet though! Don't know how feasible it is, but if they can pull it off.....
Thank you Google! Of course, that doesn't mean they're not accurate...
chairmansteve said:
EDIT: for those who didn't follow the link...the "chairmansteve" in the quote above is also the guy who posted those NV40 "specs". In other words, 2 posts later he admitted they were just made up.
I've heard the opposite--that yields have been pretty sucky on .13u.
Joe DeFuria
Legend
Actually, it seems to be somewhere "between" PDAs and Notebooks? They talk about the so-called "Tablet" PCS, which are basically between PDAs (like the Palm) and notebooks. (I think ATI already has chips in Tablet PCs).
At this time, most (all?) of the limited number of tablet PCs out there are powered by notebook chips. (If you've ever seen "screen rotation" features in video drivers, that's why....users of tablet PCs should be able to look at their screen, and then "flip" or rotated it to show the guy "across the table", by pushing a button.
Something like an NV33 seems MUCH to power hungry and needlessly expensive (feature rich) for PDAs / hand-helds. nVidia looks like they are getting their feet wet in this "potentially growing market" of tablet PCs, by trying to design a chip specifically for it.
Joe DeFuria
Legend
Here's a couple relevant links from ATI:
http://www.ati.com/companyinfo/press/2001/4427.html
http://www.ati.com/companyinfo/press/2001/4426.html
http://www.ati.com/companyinfo/press/2001/4427.html
http://www.ati.com/companyinfo/press/2001/4426.html
Joe DeFuria
Legend
Yes, though keep in mind the release about ATI's DX7 tablet display is about a year and a half old.
I'm not sure what ATI is currently marketing for that segment....