Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
maybe Apple should just buy Intel and get it over with.

Maybe people should stop saying Apple should buy anything and everything.

But seriously, it would be interesting if instead of this daft ARM move, Apple would use its money and influence to get a x86 license and work on actually improving the chip designs for power efficiency.
 
1 - It's been a long time since the "intel" switch. In this fast moving technology world it happened like "20 years" ago. A lot of things happened in the meantime.
2 - Thunderbolt it's not a problem. It will suddenly disappear as soon as Apple decides to drop it, no matter how many "customers" may not like this fact
3 - The last Apple's desktops don't seem to care much about "horsepower".
In 2 or 3 years we will barely notice the difference between desktops and other portable devices, at least in Apple's opinion

My 2 cents
 
Who is AMD?

Congrats! You get a lifetime supply of Blackberry Playbooks.





....and that's the ONLY tablet you can use for the rest of your life!:mad:

----------

IBM's Watson?
Power7.
A monster of a chip design; an example of performance at all costs.

Yeah, that's "all" with bold, italics, and underline.

Isn't the Wii U's CPU based on that? If so, then it's more powerful than I thought.

Is Power7 in anyway related to PowerPC?

Maybe we need to go back to the Power ya'll.;)
 
For me I see the benefits as more autonomy for Apple. Sticking with Intel means they follow Intel's release schedule and they cannot ad anything unique to the platform without Intel's consent. Why would Apple allow this to continue now that they are 5x larger than Intel (in Market Cap)?

But Intel has modified their release schedule due to Apple. Intel wouldn't be as focused on on-die graphics without the Apple deal. Intel isn't an inflexible company. They have long adjusted their path depending on clients. I see no reason why Intel wouldn't focus on avenues that are in demand. Haswell is the obvious point to look at. Huge graphics boost, very low TDP, while increasing processing power. Haswell is an extremely scalable architecture. From servers down to <10W applications.

I'll stick to the point of saying, ARM isn't getting to desktop/laptop level processing power in the immediate future. 5-10 years from now we may be talking about a different story, but in the near future I see no reason to move Mac to ARM.
 
Is anyone else worried about software compatibility with this move?

There has been a significant increase in software since Apple moved to Intel some 6 or 7 years ago, and it makes bootcamp etc easy as it supports the same chipsets.

If they go to mobile I won't buy in.

Their current iMac offering with the mobile chipset is a bit of an insult to the 'Pro' user.

I can see their fanbase shrinking over time if they only cater for the casual market.
 
How would this affect one's ability to use Windows through Bootcamp?

Bootcamp/Parallels are nothing more than emulators, akin to a Zsnes or Mega Drive emulator are, they port code from a type of architecture to another. If we have such powerful processors to pull this nowadays, it's highly unlikely we won't have the same in the future, irrespective of the future architecture for Macs may be (Intel, ARM, etc.).
 
Bootcamp/Parallels are nothing more than emulators, akin to a Zsnes or Mega Drive emulator are, they port code from a type of architecture to another. If we have such powerful processors to pull this nowadays, it's highly unlikely we won't have the same in the future, irrespective of the future architecture for Macs may be (Intel, ARM, etc.).
Virtualization is not emulation like back in those VirtualPC days. x86 is x86.

Congrats! You get a lifetime supply of Blackberry Playbooks.

....and that's the ONLY tablet you can use for the rest of your life!
Well I guess that is nice since I do not have a tablet but I do not really need one anyways.
 
Last edited:
I think Mansfield leading Technologies at apple is simply a matter of necessity. All ios models combined, Apple sells far more of them than macs, making it necessary to have a clearly defined leadership structure for semiconductor development within Apple.

Apple making the move from intel to ARM processors would be an undertaking that simply wouldn't be worth their time.
 
Bootcamp/Parallels are nothing more than emulators, akin to a Zsnes or Mega Drive emulator are, they port code from a type of architecture to another. If we have such powerful processors to pull this nowadays, it's highly unlikely we won't have the same in the future, irrespective of the future architecture for Macs may be (Intel, ARM, etc.).

Bootcamp and Parallels are not emulators and do not "port code from a type of architecture to another".

Parallels is a x86 virtualization package that enables sharing a host operating system's hardware ressources with another guest operating system.

Bootcamp simply resizes your disk partition and enables the boot loader to load a 2nd OS directly on your hardware. It's used to install a 2nd OS on your Mac, but that OS needs to be x86-64 or x86 compatible to begin with.

ZSnes is an emulator. It takes graphics/sound/CPU calls from a dump of a cartridge ROM (read only memory) and translates them to calls your Intel Mac understands so it can "playback" the sounds/graphics and let you interact with them like you would with a controller on a SNES.
 
I know. I didn't want to create a link between the Sun Open Source DTrace and LLVM but that may have inadvertently happened. Isn't there a tool now that can see where your app can be broken into threads in Xcode?

----------



I doubt that. While you have a modicum of technical ability you display cognitive issues, delivering extraneous information that is out of context.

When I say "GLkit is available on Intel and ARM" I'm not asking for a treatise on shaders or OpenGL and OpenGL ES differences"

You attempt to overwhelm people with minutiae. I respect your "deep dive" technical knowledge to decline accepting your "unarmed" tag since I don't think you understand fully the scenario here.

The facts of this argument are in the minutaie details. if you choose that you wish to look at it on a surface level and not deep delve into it like Knight is, and are finding yourself "overwhelmed", perhaps you're finding that your breadth of knowledge on this subject is outside of your scope and that he might in fact have more knowledge than you, and perhaps instead of dismissing his attempt to illustrate where you're lacking, you could learn a few things.

Dismissing his commentary as wrong because it's too deep and 'boring' doesn't change the fact that he's more likely correct. unless there is a significant advancement in ARM processor architecture that completely blows intel's advancements out of the water, he's correct.

------------

As for a business aspect of an architecture switch, Apple (or anyone) would be in a big way of trouble to move off the x86 at this current point. Windows, believe it or not is still the number 1 used operating system in the world. While Apple PC sales have improved dramatically since their old incompatible PPC closed garden, one needs to look back and remember that without the ability to run windows or similar applications on Apple hardware, Their market penetration was ~5%. If changing CPU architecture limited people to OSx or even iOS only on the PC side, it would be a sufficient hurt to go back to such days, as developers are more likely than not going to ignore the platform with near zero penetration that would require them to code everything entirely over again.

last time, Apple almost went bankrupt.

---------------
I'll stick to the point of saying, ARM isn't getting to desktop/laptop level processing power in the immediate future. 5-10 years from now we may be talking about a different story, but in the near future I see no reason to move Mac to ARM.

Further emphasis on today''s performance. Currently Google has released a laptop based on an ARM CPU built by samsung in the name of the chromebook. This is running a highly customized OS exclusively built to run on minimal hardware. it is effectively.. a browser OS.

Even on a pretty beefy dual core Samsung CPU that is near the high end of what's available, Reviews have had mixed feelings and results over the performance of simple desktop like tasks. the ARM cpu's are fantastic in embedded platforms, and with code that is highly customized to specifiic tasks with limited use, but as general computing platform they are years behind.
 
Last edited:
Bootcamp/Parallels are nothing more than emulators, akin to a Zsnes or Mega Drive emulator are, they port code from a type of architecture to another. If we have such powerful processors to pull this nowadays, it's highly unlikely we won't have the same in the future, irrespective of the future architecture for Macs may be (Intel, ARM, etc.).

incorrect.

Bootcamp is not an emulator, nor a virtualizer. Bootcamp on modern OSx is more a fancy launcher and installation manager for launching Windows. Windows itself runs completely native on the current intel hardware.

This can be further proven as you can in fact install windows, or even Linux and other OS's on Mac hardware without another "host" os, and I have seen many setups that do this. Blow away OSx and load Win7 on the machine instead.

if you're talking about Parellels. That is in fact Virtualization. it doe not 'emulate' anything either, but allows for direct hardware access to the underlying resources via software level or "host". This is actually a feature that is required to be found as part of the hardware as well as software and does not suffer the overhead impact that true Emulation has.

Emulation is what OSx used to have to do with Old PPC legacy applications. Emulation always takes a significant performance hit as it forces hardware to "pretend" it's acting in a way different than it is designed. Basically, what OSx did (I think it was called Darwin, i honestly drawing a brainfart), was have a layer on the OS pretend it was a different CPU architecture, this layer had to be processed by the real hardware, and then that fake hardware that was being emulated could pretend to emulate the application. Emulation always suffers extreme performance hits.

The reason why OSx was able to emulate the old PPC so well, was that the intel hardware it was based on was lightyears ahead of the PPC architecture at the time, so that there was sufficient hardware power to enable this smoothely. Let me tell you, Emulation isn't efficient. It wasn't till nearly a decade after the NES was out that it was finally able to be emulated accurately or efficiently on x86 hardware, and heck, even the Pentium 4 era had issues with the N64 based hardware.

as it stands today, Intel hardware is in a better place to emulate ARM than vice versa.
 
Ignorance?

Has anyone thought maybe Apple could design a new line of "desktop" computers that fall somewhere between Macs and iPads?

Why would that be so hard to believe? Pretty much everything they've done with Mac OS X has headed in that direction. Especially with all the iOS-like interface elements and features.

How about a computer where the interface is mainly like an iOS device, but has much more computing power, storage, bigger screens, external ports, etc. No touch screen, you'd use a keyboard and trackpad.

Two models only, a 13" laptop and a 21" AIO. $799

And... They would still keep the current Macs around for those who wanted them... Which would probably be most of their current user base (Me included). The new line would be targeted at consumers who don't use their computers for much of anything anyway, but still need an iTunes "hub" for all their media.
 
Agree with above.

I was thinking that an iOS derivative desktop would be a platform for an ARM engine.

But I think users would go else where if they did.
 
Has anyone thought maybe Apple could design a new line of "desktop" computers that fall somewhere between Macs and iPads?

Why would that be so hard to believe? Pretty much everything they've done with Mac OS X has headed in that direction. Especially with all the iOS-like interface elements and features.

How about a computer where the interface is mainly like an iOS device, but has much more computing power, storage, bigger screens, external ports, etc. No touch screen, you'd use a keyboard and trackpad.

Two models only, a 13" laptop and a 21" AIO. $799

And... They would still keep the current Macs around for those who wanted them... Which would probably be most of their current user base (Me included). The new line would be targeted at consumers who don't use their computers for much of anything anyway, but still need an iTunes "hub" for all their media.

I did :p Some companies already did just that. For example, Samsung has just released ARM based Chromebook. Apple may follow suit. What they can't do is to switch to ARM for Macs any time soon. On second though? They can. Given how low share of Apple profits comes from Macs they can abandon all MacPro, Final Cut and all this crap and go ahead with consumer electronics (iPods and such). The risk, of course, would be that profit margins in CE are usually very low. iPhone and iPad were an exception but the fundamentals have not changed. Profit margins in this stuff will drop drastically very soon. Nexu 7/Kindle Fire HD/ iPad Mini show how this works.
 
Let History be your guide

There would be many precedents for switching to a different architecture:
68030/040>PowerPc>Intel.
For the intel switch OS X was ported as early as 2001 and developed alongside the public release on PowerPC. Consider the fact that iOS is based on OS X and has been in development for several years now it's not hard to imagine something similar going on behind the scenes. Granted ARM designed chips aren't powerful enough to be the end all be all, but look what they have achieved on the iPad and iPhone. Since Apple is a licensee and can and have developed their own processor based on the ARM instruction set (A6), it's not hard to see this as being a long term goal for Apple.

Look at the A6 as a first generation product. According to benchmarks it's twice as fast as the A5, and as ARM releases new instruction sets and designs Apple can quickly integrate them. So to think that in 3-5 years time we could be facing a shift to ARM is not unforeseeable, provided that similar gains occur each year. It probably won't replace a high-end user's computer anytime soon, but look how many people use an iPad instead of a laptop now and extrapolate it as the underlying technology advances.
 
With how affordable the "system on a chip" ARMs that Apple uses in the iDevices are, wouldn't it make more sense to add a secondary processing unit to a computer so that it can easily run iOS apps and MacOS Apps? Especially if they engineered a really intelligent controller that will allow system resources to be shared between the two?
 
There would be many precedents for switching to a different architecture:
68030/040>PowerPc>Intel.
For the intel switch OS X was ported as early as 2001 and developed alongside the public release on PowerPC. Consider the fact that iOS is based on OS X and has been in development for several years now it's not hard to imagine something similar going on behind the scenes. Granted ARM designed chips aren't powerful enough to be the end all be all, but look what they have achieved on the iPad and iPhone. Since Apple is a licensee and can and have developed their own processor based on the ARM instruction set (A6), it's not hard to see this as being a long term goal for Apple.

Look at the A6 as a first generation product. According to benchmarks it's twice as fast as the A5, and as ARM releases new instruction sets and designs Apple can quickly integrate them. So to think that in 3-5 years time we could be facing a shift to ARM is not unforeseeable, provided that similar gains occur each year. It probably won't replace a high-end user's computer anytime soon, but look how many people use an iPad instead of a laptop now and extrapolate it as the underlying technology advances.

In all previous switches the new architecture/chips were more powerful than the previous one which indicates that there is very little chance of switching to ARM for Macs any time soon.
 
"Apple's Potential Shift from Intel to ARM for Macs Not Implausible, just dumb"
 
Keeping their options open

Why did Apple switch to Intel in the first place? Because IBM was incapable of providing them with the low power, high speed processors Apple wanted for its computers, especially its laptops, which is where Apple's growth and profits were coming from.

Why would Apple switch from Intel to its own in-house ARM-based designs? Same reason. Intel hasn't proven able to provide the kind of low-power, high speed processors Apples tablets, smartphones and increasingly laptops and desktops require.

At the time when Apple made the Intel switch, they weren't large enough or capable enough to roll their own custom CPUs to meet their needs. That isn't the case anymore. Apple could certainly buy their way to CPU and chipset design success. I don't know if they can do quite as well as Intel when it comes to performance, but on the other hand, they also don't have to subsidize Intel's high margins. And Intel continues to lag far behind ARM when it comes to performance per-watt.

I think we could see ARM-based latptops from Apple in as little as 3 years. Apple will no doubt try to offload as much functionality as possible onto the GPU and other helper chips (PCs are moving in the same direction, anyhow). If they're successful, look for ARM-based iMacs and Mac Minis to launch shortly thereafter.

Assuming Apple stays in the pro desktop market - and I'm not sure they will - they'll probably go for a multi-processor solution that provides similar levels of performance to their contemporary Intel boxes. They'll probably have to eat some of their margins to do it, but on the plus side they won't be forking cash over to a potential competitor and helping the Wintel ecosystem anymore in the process, and they won't need to maintain two code bases anymore.

Now, if Intel does manage to get its act together with performance-per-watt, all bets are off. Apple could just as easily migrate its portable iOS devices to Intel's architecture. I think Apple would rather be more in command of its own platform, but I don't think they'd be willing to sacrifice (much) performance in order to do it.

Apple isn't the only one starting to drift away from Intel. Microsoft's Surface RT devices are also ARM-based. I wouldn't be surprised to see ARM-based Windows laptops crop up over the next couple of years if Intel continues to lag behind in performance-per-watt.
 
Apple is already primarily an ARM-based computer company. x86 is already down to a "hobby" percentage of their business.

Until Intel is capable of taking mobile share from ARM, their PC business with forward-looking companies like Apple is at risk.

IMO, etc.
 
My support for ARM

Although, I love and appreciate my Intel Mac Pro 6-core, I would like to see more development in ARM as Apple's future processor of choice. I feel given what I have read up thus far, ARM would be a likely replacement for Intel.

Even though the CISC vs RISC question is not of a concern today as both architectures use each others technology, I still find RISC based processors much cleaner and more streamlined versus CISC. Its a damn shame the PowerPC G5 was not brought to life as a suitable processor for the laptop division. I sure would have loved to see a PowerBook G5 as many of you also would have.

Its time for Apple to look at the potential for a return of RISC computing and as a welcome sign that Apple prefers to do their own in-house chip fabrication and control what goes into their Macs and iToys.

How do we know that Apple might just be beta testing OS X or iOS on ARM based processors? ARM has a lot of potential, maybe not now, but a few years down the road. I welcome this change from Intel to ARM RISC.

Just my .02
 
Given that MS has their Windows RT now to run on ARM, and they're working closely with Nvidia and Qualcomm on ARM architecture, it's not only not implausible Apple is doing the same (if in different ways), it would be implausible that they're not.
 
Yeah, they're looking out for their customers all right. Be prepared to buy all new hardware and then wait until developers get around to porting your favorite applications. Hope you don't mind re-buying some of them. Hopefully you don't use Bootcamp either, because that will go away too.

Think you missed the sarcasm there
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.