Peter Lewis (peter.delete@this.notyahoo.com) on June 2, 2022 2:01 pm wrote:
> > At the end of the day, once Apple passes Intel, you'll see this
> > in full force. It will no longer matter that Apple is 1% faster
> > than Intel's best or 30% faster because "Intel runs the apps I want, and Apple doesn't".
>
> You seem to be implying that Apple Macs will eventually be faster than x86 PCs. If Apple Macs
> do become noticeably faster than x86 PCs, a lot of software development will shift to Macs and
> the apps people want will be ported to Macs. This would be a huge change in the PC industry.
>
> The answer is unclear but it’s certainly not ill-posed to ask x86
> market share in personal computing and servers in 5 or 10 years.
>
> > Intel could doubtless do somewhat better if they gave up some compatibility,
> > and a lot better if they abandoned all compatibility.
>
> There was this project called Itanium ...


The rule of thumb in the RISC days was that the cost of switching to a different ISA & OS meant you had to see a 2x performance advantage at product introduction, or a 50% advantage sustained for several years, before you'd see a lot of people switching. I think that's a bit too high today because it switching ISAs is less painful than it was back then due to emulation, and more interpreted code and cloud based apps, but there is still some level of performance difference that has to happen - which is way way larger than "1%".

Sure you might be able to point to a few people who would sell their firstborn to get a 5% performance advantage, but for most that isn't true - and some people want to do things that wouldn't be possible on a Mac and where Windows emulation isn't feasible like gaming that would rule them out from switching even if they don't necessarily care too much what OS they use. Or they simply have a hatred for Apple and wouldn't buy a Mac even if it was twice as fast as any PC and Siri did your taxes for free and found you an extra $500 refund every year.

Apple has always been behind Windows PCs in performance, even after they switched to x86. They updated product lines once every year or two, and rarely if ever made the fastest SKU available even when they did update them. Meanwhile even if a given PC OEM might not switch to the latest and great immediately several of them always had the fastest x86 chip available in one or more of their models the day Intel started shipping it.

Apple was especially bad with updating Macs in the last few years of x86 (in hindsight, they were probably busy getting ARM Macs ready) but they were still gaining market share. If Macs having better performance would cause them to gain share, wouldn't having worse performance cause them to lose share? Its because the performance gap wasn't big enough to induce people to switch platforms, just like if Apple Silicon was able to get a 10% or 20% advantage that wouldn't be enough to switch the other direction.

Apple has gained some market share with the Apple Silicon Macs, though with pent up demand from people not wanting to buy "lame duck" x86 Macs once the transition was announced, covid, work from home, remote schooling and supply chain issues that affected Apple relatively less than most PC OEMs it is impossible to know the reasons why Macs have gained share since the introduction of Apple Silicon Macs. I will say some people probably switched due to power efficiency - i.e. not having fans or having fans that essentially never run, and having very long battery life. That's related to but not the same thing as raw performance.