• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

NVIDIA GeForceFX interview at Beyond3D

Finally, what would you say that GeForce FX has that R300 doesn't?

Unbelievable levels of programmability that will enable the developers and artist to deliver stunning visual experiences in real time.

ATi is gonna have a hard time adjusting to that with R350!!!

 
I just love all of the excuses for not implementing a 256-bit memory bus! Matrox and ATI are both there already. The color compression engine in the GeForceFX is great stuff, but I sure hope the NV30 refresh has 4x64 memory controllers!!
 
Originally posted by: jeffrey
I just love all of the excuses for not implementing a 256-bit memory bus! Matrox and ATI are both there already. The color compression engine in the GeForceFX is great stuff, but I sure hope the NV30 refresh has 4x64 memory controllers!!

FWIW, contrary to AT's report the R300 fully supports colour compression with FSAA enabled.... it was revealed a few weeks back by one of ATi's developers, I can dig up the linky if you wish.
Granted it lacks colour compression with FSAA disabled, whereas the NV30 seems to support it regardless of AA status... but with it disabled colour compression has precious little to work with anyway so the gain is minimal.

Personally I was shocked with the way nVidia went about implementing the vertex shaders. Granted it may not be as fast clock for clock as the R300 but it's a much more forward looking approach IMHO. Quite similar in many respects to 3DLabs implementation with the P10.
The 128bit memory controller was pretty much expected, virtually all rumours had indicated that.
The 8x1 rendering configuration was another unexpected move though.
 
Originally posted by: jeffrey
I just love all of the excuses for not implementing a 256-bit memory bus! Matrox and ATI are both there already. The color compression engine in the GeForceFX is great stuff, but I sure hope the NV30 refresh has 4x64 memory controllers!!

The Matrox Parhelia has a 256-bit memory bus and it sucks donkey ball in performance. Even a GeForce4 Ti4600 can eat it alive.

SO WHAT'S YOUR POINT?? IT'S NOT THE SIZE THAT MATTERS, IT'S THE MOTION OF THE OCEAN😀
 
I just love all of the excuses for not implementing a 256-bit memory bus! Matrox and ATI are both there already.

Yes, Parhelia sure did a good job with it 😉
Like the guy said, some implementations of 256bit are fast, and some are slow. It's all about balance, and well designed architecture. Throw 256bit bus on GeForce 2 Ultra, and it still won't outperform GeForce3 under stressful conditions.

IT'S NOT THE SIZE THAT MATTERS

I would not go this far...😀
 
Originally posted by: NFS4
Originally posted by: jeffrey
I just love all of the excuses for not implementing a 256-bit memory bus! Matrox and ATI are both there already. The color compression engine in the GeForceFX is great stuff, but I sure hope the NV30 refresh has 4x64 memory controllers!!

The Matrox Parhelia has a 256-bit memory bus and it sucks donkey ball in performance. Even a GeForce4 Ti4600 can eat it alive.

Really?!?!?! (scroll down for benchmarks).
 
Back
Top