Considering that G71 has 220 clock cycles of latency hiding, at 650MHz, you'd expect G80 to require in the region of 400+ clock cycles to hide latency at 1350MHz.
Yes, hello and welcome to B3D! The results on R580 are broken, you (if you're the OP at R3D) completely misunderstand the results presented and G80 effectively branches for free. You* were told this by Demi, DC and others over at Rage3D and they were correct then. They'll be correct here again if you* really want to ask again......Lord CorDox said:Greetings
Hold on for a minute. Is the G80 using a fixed function ratio of its unified shaders under DX9 games?
They just do. Unified instruction set has nothing to do with unified hardware execution units. You can always have either one without the other.Matas said:One question: how 128 streaming processores works in DX9 games if they lack of unified shader support?
One question: how 128 streaming processores works in DX9 games if they lack of unified shader support?
So, streaming processors are sorted for example 80pixel and 48vertex(on 8800GTX) in DX9 games?
Actually, you're doing something massively wrong if the drivers have anything to say about it when running realworld applications. And it balances the workload constantly, not just per-frame. I'm not going to write an introduction to the subject however, as plenty of people have summarized it excellently in the past already.Unification of shader hardware is controlled by the drivers and control silicon in the chip, it has nothing to do with the software running on top of the hardware (API or appilication).
Not that I've seen anyone provide evidence of. Why do you think so?