I don't know why you're being downvoted. A 5nm version of the AMD stuff should be reasonably close to the M1.
The main bottleneck is the production capacity, we badly need more manufacturers of high end chipsets.
The main bottleneck is the production capacity, we badly need more manufacturers of high end chipsets.
But do you think that Apple stopped innovating after releasing the M1 last year? Don't you think the M2 (or M1X whatever it's called) is well into design and prototyping at this point?
Just because it matters on Android, which is a COMPLETELY different system, doesn't mean it matters as much on iOS.
Yes, it matters a bit when switching between multiple apps, but app suspend is handled in a completely different way on iOS than on Android.
Apples to Oranges.
Eh, I'm not sure that's true. They did with the original PPC, and also the G3 and G5.
It's difficult to compare the Apple Silicon versus PowerPC, because the new Apple hardware is far more ambitious, the whole platform. I would expect that the memory SSD controllers are to some degree licensed from other industry players. The CPU architecture is something else again. Issues eight instructions per clock -- per core. The M1 core design has more in common with IBM mainframe POWER9 than with a typical x86 core. It's remarkable to see this design ina low end consumer device. A mobile.
There have been just so many genuine tech news articles of the form, "Future Apple Competitor Product Beats Current, Widely Successful Apple Product".
It's the twin brother of all the "Currently, successful Apple product feature technically existed on [not-Apple] Product years ago (even though basically nobody used it)."
People read those articles and conclude it's all marketing hype but never ask themselves why it seems to happen again and again where simply checking off the box for having a specific feature never seems to actually lead to broad adoption. And if it truly is ONLY marketing hype leading to those ecosystem effects, then maybe you should start thinking of marketing hype as a feature?
I see what you did there. Really casting shade on Intel!
I can answer why _I_ downvoted the comment. It was this part:
> [...] it's really surprising to me how many eagerly lap up the angle Apple is pushing without much reflection, even on HN. Like the good old Apple hype days.
You can make a point without implying that anybody who doesn't agree with you is incompetent (the "Apple hype" meme is really stale).
Chips like the M1 (or ideally, something similar made available to other device manufacturers) is still really interesting. The ARM architecture can scale down better than x86/x64 can, allowing a device maker to hit low end performance targets with less cost than x86 chips can manage. For the low end, it also tends to provide better power consumption for a fixed performance target than the x86 offerings.
This makes M1 type chips really interesting for any manufacturer who want to make devices that span a huge scale of performance requirements, from slow kiosks performance range to the decent laptop range. All being the same ISA makes sharing firmware and applications across the lineup easier than having to switch to x86/x64 above some threshold.
It also does not hurt that M1 means that the really popular for development Apple devices are now running on ARM, which helps ensure that more software has been ported to (and/or tested on) ARM devices. ARM's weak memory model for example is something that can trip up a lot of software that tries to implement low lock algorithms, but whose designers were only familiar with the x86/x64 memory model.
This is purely theoretical. Apple will <<never>> sell its chips to other companies.
So if you were expecting Apple Silicon on its own to start a revolution, that's never going to happen.
Microsoft already have a Surface product with an ARM chip that didn't get updated in this round AFAIK. It already has solid ARM performance, but it's not as good as M1. It was let down with how well x86 emulation worked, but there seem to have been improvements including x64 support. If they focused on improvements with the chip design then they could see improvements along the lines of Apple. It's a question of whether the investment is made rather than whether it's possible.
The team that built the M1 is a collection of top tier ASIC designers that came from several acquisitions, from PA Semi forward. The Qualcomms and Caviums and so on just aren't in the same league. Lord spare me another tarball of garbage and random kernel patches called an "SDK." They don't really have the same bench and don't pay top dollar and it shows.
It is unlikely that there will be an M1 equivalent from any of those guys. Intel? AMD? Absolutely.
Back in the 90s, when Jobs was gone, Apple licensed its OS and almost went bankrupt as you could simply get a cheaper clone of Apple's computers with the OS on them. They won't repeat that mistake again.
Also, saying that people are "lapping up" the Apple marketing suggests that it's more sizzle than steak. But it's completely undeniable that the A chips, and by extension, the M1 is a beast.
Reasonably close only counts in horseshoes and hand grenades. Until a 5nm version of the AMD stuff can run MacOS, there’s no point comparing the 2.
If the AMD stuff blows past the M1 (or the M-whatever), Apple’s marketing will turn on a dime.