Originally posted by: rahvin
Interesting quote from the paper.Precision: support for 64-bit and 128-bit color to eliminate artifacts and
processing errors and increase the range and robustness of effects.
And here's another:
The inherent 16- and 32-bit floating point formats (FP16 and FP32) of the NVIDIA "CineFX" architecture give developers the flexibility to create the highest quality graphics. FP32 offers the ultimate image quality, delivering true 128bit colour.
They also go on to state that developers can use both modes at the same time. If all this is true we could be seeing some amazing stuff late this year.
