This web-site has posted a link to the x3dfx Forum, where they discovered some interesting news on the upcoming NVIDIA baby aka NV30. Here is what we managed to sum up:

• 73 million transistors;
• 0.13micron manufacturing technology;
• 450MHz chip clock frequency;
• External T&L unit and TT&L unit (True Time and Lighting) implemented in a companion chip (supposedly working at 450MHz);
• 8 rendering pipelines (about the same amount of pipelines is expected to be implemented in ATI R300);
• 4 TMUs per pipeline capable of laying up to 8 textures in a single pass (loopback);
• 4 Vertex Shaders units;
• 2 Pixel Shaders units;
• 256bit memory access;
• Up to 750MHz DDR memory working frequency;
• 370MHz RAMDAC;
• Quad cache for vertex, primitive and pixel textures;
• Dual (dounble-level, like Hyper-Z?) Z-Buffer for better lossless data compression;
• 12nvx – new anisotropic filtering mode (12x4=48, 48 texture samples?);
• NVAutoShaper prediction unit also responsible for preliminary saving of data samples in caches, which allows operating the data location manually;
• NvBlur: API Glide compatibility;
• DirectX9.x compatible;
• OpenGL 2.0 support.

Well, what can we say about these “specs”? First, these are none other but rumors without any evidence to prove. Second, the relatively small number of transistors in the chip arouses some doubts, even despite the fact that the T&L unit has been moved to a companion chip (I wonder if it would be possible to design graphics cards without this chip at all, because the today’s CPUs can cope pretty well with the T&L functions, too). Take for instance, GeForce4 Ti chips: they feature "only" 63 million transistors, though their specifications look more modest than those of NV30. Thirdly, I can’t quite understand why they needed to support the old API Glide (though it might be x3dfx’ personal contribution, as people very often see what they want to see :) And fourth, I should admit the 8 rendering pipelines with 4 TMUs on each and with the loopback look too monster-like to me at least. So, it turns out the upcoming ATI R300, which has been regarded as a competitor No.1 to NVIDIA NV30, is no longer that dangerous. Frankly speaking, this is all too hard to believe. Anyway, time will come when we learn the truth, and in the meanwhile, let’s be happy with what we know.

By the way, as we have already mentioned here, NVIDIA NV30 is expected to come in September at the earliest.