Linked by Thom Holwerda on Mon 5th Nov 2012 23:40 UTC
Apple Another Apple-to-switch-Macs-to-ARM post. "Apple engineers have grown confident that the chip designs used for its mobile devices will one day be powerful enough to run its desktops and laptops, said three people with knowledge of the work, who asked to remain anonymous because the plans are confidential. Apple began using Intel chips for Macs in 2005." No idea when Apple will make the switch, but they will do it. I'm thinking 5-10 year timeframe.
Thread beginning with comment 541113
To view parent comment, click here.
To read all comments associated with this story, please click here.
kovacm
Member since:
2010-12-16

Considering that Apple was a co-inventor of ARM from the days of Next computer, and that iOS is basically a stripped down version of OSX, it is very likely that Apple has had this in the works for a very long time.

Apple was not CO-INVENTOR of ARM !!


anyway, it would be great if someone make deep analyze of using ARM instead of intel ivy bridge.


looking from side, all premises that it could be done are there:

1. Apple control third party developers through AppStore
2. Apple control developing tools (language, framework, compiler...)
3. Apple investing heavy in GPGPU & multiprocessing (OpenCL/GDC...)

my question is:

how much faster could professional application* run on ARM + GPGPU chips (vs intel chips) if you optimize everything (metal, compilers, frameworks)?

*FinalCut, Logic, Aperture, Adobe Suit, Cubase, Cinema 4D...?

Is Apple in position to do this:

- potentially leap frog x86 in terms of performances optimizing everything I already mention (metal, compilers, frameworks...)?

Reply Parent Score: 1

MOS6510 Member since:
2011-05-12

That sounds like making something that's slower go faster than something that goes faster.

Why no optimize for the faster option and make it even faster?

iOS devices can do impressive stuff speed wise, but when it comes to certain desktop applications it's hard to beat raw power.

Still, it would be interesting to see if Apple comes with an ARM Mac and how they'd do it.

Reply Parent Score: 2

Laurence Member since:
2007-03-26

That sounds like making something that's slower go faster than something that goes faster.

Why no optimize for the faster option and make it even faster?

Actually that's how x86 has been operating for the last decade. Intel has had to employ a number of 'cheats' to keep up with Moores law and as a result the x86 CPUs have gotten very long in the tooth.


iOS devices can do impressive stuff speed wise, but when it comes to certain desktop applications it's hard to beat raw power.

Few people run applications that need that kind of raw power, and the few times it is required, a switch to multiple RISC cores over fewer CISC cores might pay dividend in the long run. Admittedly there's still a software hurdle to over come there (teaching developers to write god multi-threaded code isn't a small task). But for DAWs, video editors, and image manipulation software; having dedicated RISC cores for filters and fx makes a lot of sense for low latency work.


I genuinely think if we want to sustain the exponential growth in processing power we've enjoyed thus far, then we need to learn to better parallel process rather than rely on clever processor tricks to mimic such effects (eg out of order execution). And to do that, it makes more sense to have more dedicated RISC cores: it's easier to stack cores on one die and the lower draw on power means the CPUs run cooler (as cooling top end multi-core monsters is always a bit of a battle).

Reply Parent Score: 5

Nikato Member since:
2005-12-17

Imagine a computer with twenty or so ARM Chips working in tandem. AMD has already developed such a system based upon ARM, using dozens of ARM cpu's. Megahertz will not be an issue. This will ultimately lead to a MacOS with full compatibility with iOS apps. Effectively the two operating systems will be merged this way. As for Compatibilty with legacy windows Apps... Microsoft doesnt seem to care anyome, so why should Apple. for Microsoft it's do or die. For Apple it's evolve and fly. I was mistaken in my Assertion that Apple "Invented" ARM. I can say that they saw the future coming, almost twenty years in advance....Wow.

Reply Parent Score: 1

Neolander Member since:
2010-03-08

Apple was not CO-INVENTOR of ARM !!


anyway, it would be great if someone make deep analyze of using ARM instead of intel ivy bridge.


looking from side, all premises that it could be done are there:

1. Apple control third party developers through AppStore
2. Apple control developing tools (language, framework, compiler...)
3. Apple investing heavy in GPGPU & multiprocessing (OpenCL/GDC...)

my question is:

how much faster could professional application* run on ARM + GPGPU chips (vs intel chips) if you optimize everything (metal, compilers, frameworks)?

*FinalCut, Logic, Aperture, Adobe Suit, Cubase, Cinema 4D...?

Is Apple in position to do this:

- potentially leap frog x86 in terms of performances optimizing everything I already mention (metal, compilers, frameworks...)?

I don't understand: even if Apple could get that much of a performance boost by using GPGPU on ARM, couldn't they also get the very same perf boost with GPGPU on x86?

Unless I'm missing something, GPGPU does not sound like a major area of differentiation between x86 and ARM, since GPUs must work similarly on both architectures (there's only so many ways to compute a matrix product in silicon).

Edited 2012-11-06 18:16 UTC

Reply Parent Score: 1

kovacm Member since:
2010-12-16

I don't understand: even if Apple could get that much of a performance boost by using GPGPU on ARM, couldn't they also get the very same perf boost with GPGPU on x86?

simple answer: if they want to switch to ARM than they could use GPU to compensate speed difference between ARM and intel x86 chips!


and even on desktop x86 you will need to utilize GPU in future if you want real impressive speed gain!
at the end speed of x86 would be less and less relevant! - "it should be only fast enough for "Office-like" jobs..." and real speed (where it is needed) will come from GPU.

even AMD bet entire company on this premise! - CPU part could be anything (ARM/x86); it does not matter. GPU is one that count. look at latest AMD GPUs - they go so far that you can pass pointers from x86 directly to GPU, they add exception support, virtual memory and page tables, calls and conditional branches, integer operations with 256 GPR. it looks like complete CPU and still massive SIMD monster.

they only need "fast enough" x86 execution since real speed will come from SIMD GPU.

Reply Parent Score: 1