> I don't know the size of the teams (and I expect Apple will never release this info) but we do know the rate
> of Apple's progress, and we also know the data point I have stated many times --- a desktop Intel CPU takes about
> 7 years to get from concept to shipping.

You're off by about 1-2 years.

>We saw this confirmed pretty much in Atom, where (apparently without
> the benefit of parallel design teams) it took them about six years to get from one micro-architecture to the
> next, with the intervening years spent on annual spins that improved the packaging or shrank the die.

Uh, you really weren't paying attention. It took them a long time because there were other problems that were more important to tackle than the microarchitecture. The most important thing was getting a single chip solution.

> We have AMD's constant failure in this area to meet Intel's performance levels as a >second data point.

That has little to do with x86 complexity, and everything to do with the complexity of achieving the level of performance that Intel consistently provides. AMD has no problem designing and validating x86.

> Look, if you want to insist on the (IMHO insane) claim that it is every bit as easy to design
> a high performance x86 device as to design a high-performance AArch64 device, be my guest; I
> don't give damn. Tech seems to bring out crazy delusions in people, you are welcome to yours.

For Intel and AMD, it is probably easier to do x86 than ARM. After all, they have ~20 years of accumulated knowledge, tools, and expertise. ARMv8 may be simpler, but that is a second order issue when it comes to laptop levels of performance.

Moreover, there are a lot of areas where Intel and AMD are vastly ahead of the entire ARM ecosystem, e.g., power management. What passes for DVFS at most ARM vendors is a brain dead embarrassment to engineers and computer architects everywhere.

David