Welcome to Overclockers Forums! Join us to reply in threads, receive reduced ads, and to customize your site experience!
IIRC, the 96c monsters only boost to around 3.7 GHz with all-core around 3.5 GHz. The only ones that reach 4Ghz+ are on boost is the 48c chip (and less). The 32c chip (and less) does 4GHz+ all-core.
The 9XXXF are faster than the non 9XXXF parts, anyway I did hear 4.3GHZ
4.4 even..The 9XXXF are faster than the non 9XXXF parts, anyway I did hear 4.3GHZ
Great question, but would it really matter? as long as they are the same impedance and ohms the electrical impulses will travel at the same "Speed" or the information will get there at the same time with no impedance.
I don't know the answer, but if what you say is true, it seems logical to think you'd have to have the same lengths so the signals arrive at the same time. If all speeds are the same, a longer path takes longer for the pulse to get there. Does the CPU have some kind of logic for that baked in?
My guess is that every wire and every connection is absolutely perfect right down to the nano wire.I don't know the answer, but if what you say is true, it seems logical to think you'd have to have the same lengths so the signals arrive at the same time. If all speeds are the same, a longer path takes longer for the pulse to get there. Does the CPU have some kind of logic for that baked in?
No idea. But it FEELS like these are built symetrically for a reason.
I'm not sure about the inside of the CPU but on the outside it matters like from the CPU to the ram, the copper traces for the ram socket closes to the CPU have to be the same leanth as the traces to the ram socket farthest from the CPU. It all has to do with timing.
I just learned this the other day, so I was looking at that big conglomeration of chiplets and wondering if the same was true for a CPU substrate and even on die cache.
The electric bill on that would be enormous.About the same as 192 single core CPU folding farm
