gamerk316 :
I think that could help a lot with feeding GCN. My blind shot: +30%?
I doubt it for two reasons. First off, traversal times. L3 is already very inefficient, in terms of space versus performance, and L4 will be even more so. Secondly, it simply isn't big enough to really benefit a GPU. It will help, don't get me wrong, but only about 5-10% or so. And if it takes a significant portion of the die, one needs to wonder if the space could be better utilized by something else (more GPU cores, more CPU cores, specialized logic processors, etc). I do expect the APU as a whole to be ~20-25% faster on average though, simply due to generational gains.
Right, but both L3 and stacked on-die DRAM are more efficent than RAM (it needs a few hundred cycles to get data). Intel used just 40 MB of L4 in Iris. If AMD used the same capacity it could be smaller than L3 (40 MB / 4 layers = 10 MB and DRAM is more dense than SRAM) in FX. Anyway I hope that they know what they're doing.