Replies to post #36019 on Intel Corp (INTC)

[wbmw]

Re: Tx for your calculations. This is the data i referred to when I said it must have been a product where SRAM is not sent to sleep in idle operation, which you confirmed in a previous post for desktop products.

Actually, I said that Core 2 had >2x as many LOGIC transistors, which actually shows that the cache has LITTLE or NOTHING to do with higher idle power.

Also, I have already said that desktop parts most likely have identical cache structures as the mobile parts. I have also said that the biggest KNOWN differentiator is that desktop parts DO NOT have the sleep states enabled, as do their mobile cousins, which substantially affects idle power.

Therefore, the most likely explanation for higher power in Intel desktop parts relative to Intel mobile parts is the lack of extra sleep states. The most likely explanation for higher power in Intel desktop parts relative to AMD desktop parts is a larger number of logic transistors; although there are additional unknowns, such as whether AMD implements sleeps states, a lower halt state voltage, process differences, etc.