Xbox console spec points to NVIDIA's next steps
Dr. Dobb's Journal has a very interesting article
by Michael Abrash (graphics god of id Software and Microsoft fame) about the MS Xbox console, which will be using an NVIDIA-produced chip. Abrash mentions in the article that the Xbox's graphics chip will be very similar to NVIDIA's next PC chip:
Also, the GPU has the same pipeline features as NVIDIA's upcoming next-generation PC chip, so information about that chip (at http://www.nvidia.com/ developer/) will be applicable to Xbox as well. There's already considerable information on the aforementioned web site about GeForce and GeForce 2 GTS, which contain a subset of the Xbox GPU's pixel and vertex shaders.
Fair enough. We've all expected that. But elsewhere in the article, he lets slip what sounds like some very interesting details while discussing the chip's potential fill rate:
The GPU's raw fill rate at 250 MHz will be 1 Gpix/sec. To provide some context for that number, at a resolution of 640×480, it is sufficient to draw every pixel on the screen more than 50 times per frame, at a frame rate of 60 Hz. . . There's also occlusion-detection circuitry that can increase fill rate by up to 4X [emphasis mine]; the effect varies depending on whether pixels are occluded when they're drawn, but tends to be greatest exactly when it's needed most -- when there's a lot of overdraw.
Occlusion detection circuitry could potentially endow the new NVIDIA chips (including the Xbox's) with the advatanges of tile-based renderers like the PowerVR series (used in the Dreamcast and the upcoming Kyro card for the PC). This feature could go a long way toward easing the memory bandwidth bottleneck
currently holding back the GeForce cards (among others). Good news!