No, because what that doesn't consider is the added logic cost in going unified, or any potential differences in usage patterns that may reduce the efficiency of the pipelines in a unified design.Jawed said:From earlier in the thread:
http://personals.ac.upc.edu/vmoya/docs/vmoya-ShaderPerformance.pdf
You can be sure NVidia is busily working on a unified architecture for real, now
That said, given nVidia's softened stance on unified pipelines, it would seem that they have indeed started work on a unified design.