By: Richard S (rsa73.delete@this.iinet.net.au), June 2, 2022 5:14 pm
Room: Moderated Discussions
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 ...
Itanium had to do more than be purely about high performance or technical excellence though. It also had to be patentable, keep Intel's very high margins (by being difficult to clone) and was foundered on wrong assumptions about the increasing complexity of processors and the ability of compilers to create near perfect code. Unbelievably, they also appeared to think you could over take a market from the high end down when the history of processors is the low end maturing and growing into higher end markets, not the other way around (as x86 did, and ARM appear to be doing now).
Arguably the technical foundations were compromised by the assumptions they made and the need for as much as possible to be patentable.
Intel misused their chance to redo everything and suffered because of it.
Also the first generation of Itanium also had an x86 compatibility capability, so it wasn't even that much of a clean break.
> > 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 ...
Itanium had to do more than be purely about high performance or technical excellence though. It also had to be patentable, keep Intel's very high margins (by being difficult to clone) and was foundered on wrong assumptions about the increasing complexity of processors and the ability of compilers to create near perfect code. Unbelievably, they also appeared to think you could over take a market from the high end down when the history of processors is the low end maturing and growing into higher end markets, not the other way around (as x86 did, and ARM appear to be doing now).
Arguably the technical foundations were compromised by the assumptions they made and the need for as much as possible to be patentable.
Intel misused their chance to redo everything and suffered because of it.
Also the first generation of Itanium also had an x86 compatibility capability, so it wasn't even that much of a clean break.