But performance per TDP is what matters. Battery technology is getting better much slower than CPU technology. We're already at the point where CPU speed is "good enough," but we're not at the point where battery life is "good enough."
I've downsized from a Core 2 MBP to an iPad. It has 1/4 the RAM and runs at half the clock speed. Do I care? No! Web browsing is fast and fluid, photos load plenty fast, editing documents in pages is plenty fast. And it lasts through my whole 12+ hour workday, letting me leave the charger at home and often not even bothering to charge it every night. That's huge and much more important to me, and I'd imagine most people, than whether it can be imperceptibly faster.
I agree for typical single-user applications, but it's hard to call that the end of x86 as in the article. If ARM were matching x86 cycle-by-cycle in performance for less power that might be a credible claim that servers were next. Also high-end x86 devices run higher clock speeds with more cores so the gap in absolute performance is at least 1000% percent wide. I just don't see ARM displacing Intel when batteries or at least small form factor aren't involved. I don't expect to have an x86-based phone or tablet either.
My opinion (and I suspect the authors) is that the market for chips where batteries or form factor are not a concern will no longer be large enough to support a company of the size of Intel. RIM makes the finest high security physical keyboard phones anywhere. That is now a market sized for a company 1/10th their current size.
I've downsized from a Core 2 MBP to an iPad. It has 1/4 the RAM and runs at half the clock speed. Do I care? No! Web browsing is fast and fluid, photos load plenty fast, editing documents in pages is plenty fast. And it lasts through my whole 12+ hour workday, letting me leave the charger at home and often not even bothering to charge it every night. That's huge and much more important to me, and I'd imagine most people, than whether it can be imperceptibly faster.