There's very little doubt they've worked on porting OS X to ARM. Why wouldn't they? I'm sure there are much more interesting projects they are working on that will never see the light of day.
Maybe someday it will become slightly viable, sensible, and beneficial to transition Macs to ARM, but that day is so far off into the future that it's not even worth thinking about.
Given that iOS is OS X, it's fair to say that Apple ported to ARM quite some time ago.
If you plot the increase in performance of the A-Series over time, it's growing faster than X86. Intel's expertise may be more in process than in architecture. I think there is some room for architecture, particularly one optimized by the same company that fields the OS and rest of the hardware, to match Intel's advantage in process. Remember that Apple's elimination of Intel also eliminates Intel's hefty margins. That immediately places Apple at a cost advantage against other PC manufacturers.
Apple is pulling into the same league as Intel on number of CPUs manufactured each year, and they're doing it across far fewer variants. The latest geekbench scores for the dual core A6 place it at about 1/8th the speed of the MacBook Pro's quad core i7. That's only 4x better per core. ARM is claiming 3x improvement from the first generation of their 64 bit design. I think Apple can get within striking distance over the next few years.
It will obviously happen one day, it's pretty well inevitable. However it's so far into the future that there's no point in discussing it in the present.
If this rumor is true, it would also indicate to me that Apple are going to abandon the creative pro market. There is no way ARM will be competitive with Intel big iron for applications like Photoshop and video editing.
Maybe at the moment. In 5 years? It'll be fast enough for anything anybody is going to do in Photoshop. Video editing might or might not be a problem, depending on the rest of the chipset. In theory, Apple could offload a lot of specialized processing for dedicated tasks like video editing onto other chips / the video card. It would allow them to unify X and iOS onto a single CPU architecture while still supporting Intel-like performance for key high-power tasks on desktop and high-end laptop devices.
Even on the PC there's already been movement toward utilizing GPUs to take over some of the functionality traditionally handled by CPUs, since when you're running a productivity app the GPU is usually just sitting there idling, even though in theory it's actually better at performing many tasks than a CPU typically is.
I see ultralight laptops like the Air adopting ARM CPUs first, maybe within as little as 2-3 years. Larger laptops and the iMac and Mac Mini would follow. If Apple stays in the desktop business the Pro would probably get a bunch of ARM CPUs and built-in high-powered graphics chips and other dedicated helpers for targeted tasks.
But we'll see. Maybe Intel will finally get it together in the low-power space and none of this will be necessary. At this point I'd imagine Apple is just hedging its bets. If Intel comes thru with low-power chips, Apple could just as easily go in the opposite direction and switch over to using Intel chips in iOS devices.
It will also lead to a massive decrease in performance - which would not be acceptable to most people.
We're a long way from ARM even reaching current levels of Intel performance - and by the time they do, Intel will be much faster than they are now.
At best, I could see an iPad Pro with something like a MBA form factor (and regular keyboard) which is intended to be between the MBA and iPad. This could run on ARM. Replacing MBP and iMac and Mac Pro processors with ARM? Nope.
There is, of course, always the possibility of using AMD chips, though.
Absolutely! This isn't understood, it seems. I imagine it comes from the recent report that the iPhone 5 is more powerful than the most powerful G4 Powermac Apple produced.
Of course engineers working on chips will think, and hope, that what they are doing will supplant something else. I don't blame them for that, and it likely will result in much better SoC's. But x86 will remain a magnitude more powerful than ARM. I don't see how that will change any time in the foreseeable future.
The problem is OS X. All of us who are old enough remember the problems we had with Virtual PC, and other older emulation software. You simply can't successfully emulate an OS, and software, from an entirely different chip family with a chip in the same power range. It must be five times as powerful to come close.
So while x86 can do an excellent job in emulating iOS, there will be no way for ARM to successfully emulate OS X.
If Apple eventually abandons OS X the way Microsoft is abandoning the Desktop, that would be a different story. But otherwise it's not going to happen.
I see ARM taking a greater role in Apple's lineup, but it won't be replacing Intel for a good long while, if ever.
I see a 13" and 15" iPad replacing the laptops Apple sells (maybe with iOS' second real UI change) and different sizes of multitouch desktop computers replacing OS X, but I'm pretty sure the latter won't be ARM.
Honestly, I think this is more of a Worst-Case-Scenerio than where they are headed. Much like what they did with PowerPC. They kept with the PowerPC Version until it made no sense for them to continue supporting it. They made the transition to Intel, and life carried on (even though my wife said it was the end of the Mac). I see them keeping a version of OS X running on their Ax Series of chips, and probably have an idea what it would take to make it work well with them. I still think it is just a matter of if Intel drops the ball, and then Apple has to respond.
I have no idea about any of this stuff (hardware), would somebody fill me in? I mean, I know the basics, don't treat me like a child. Give me 10 (or as much as you can) reasons why switching to an ARM architecture would be bad on a Mac...
Thanks.
Since you admit you don't understand any of this "stuff", what makes you come up with ten reasons?
One reason should suffice, and that's processing power. If you feel that going back seven years in computer development is enough for your needs, then it can be done. But not quite.
The problem is emulation, as I wrote about in my previous response. Emulation requires a computer that's at least five times as powerful as the one being emulated (according to studies), if the processors are of a different family. As ARM will always be significantly less powerful, that can't be done.
It's why developers can use Apple's iOS emulation program in an x86 machine to emulate iOS and it's apps, but not the other way around.
This isn't going to change. Intel isn't standing still. While, for a while, the gap will narrow, there will always be a vast difference in power between the two technologies.
Of course, if Apple either abandons OS X the way Microsoft is doing with the Desktop, then there will only be iOS left. They could incorporate many of the OS X API's into iOS, but nevertheless a powerful program that runs on x86 will not be happy on ARM.
Absolutely! This isn't understood, it seems. I imagine it comes from the recent report that the iPhone 5 is more powerful than the most powerful G4 Powermac Apple produced.
Of course engineers working on chips will think, and hope, that what they are doing will supplant something else. I don't blame them for that, and it likely will result in much better SoC's. But x86 will remain a magnitude more powerful than ARM. I don't see how that will change any time in the foreseeable future.
The problem is OS X. All of us who are old enough remember the problems we had with Virtual PC, and other older emulation software. You simply can't successfully emulate an OS, and software, from an entirely different chip family with a chip in the same power range. It must be five times as powerful to come close.
So while x86 can do an excellent job in emulating iOS, there will be no way for ARM to successfully emulate OS X.
If Apple eventually abandons OS X the way Microsoft is abandoning the Desktop, that would be a different story. But otherwise it's not going to happen.
ARM runs OS X natively already, so emulation is pointless. I believe you meant that ARM would have difficulty emulating the X86 instruction set. As Apple is designing the processor, emulation of the X86 instruction set is probably more a legal problem than a technological one. The PA Semi folks have already implemented two different instruction sets, PowerPC and ARM. X86 would not be beyond their grasp. However, they can't get a license to run X86 by purchasing AMD (there's a caveat in AMD's license that prevents inheritance of the license). There may be another way for Apple to emulate X86 efficiently and legally, or it may be that by the time they envision making the switch, they also envision X86 compatibility being unnecessary.
I think it's important to consider the leverage Apple gains by removing Intel's 60% gross margin from the bill of materials.
Maybe at the moment. In 5 years? It'll be fast enough for anything anybody is going to do in Photoshop. Video editing might or might not be a problem, depending on the rest of the chipset. In theory, Apple could offload a lot of specialized processing for dedicated tasks like video editing onto other chips / the video card. It would allow them to unify X and iOS onto a single CPU architecture while still supporting Intel-like performance for key high-power tasks on desktop and high-end laptop devices.
Even on the PC there's already been movement toward utilizing GPUs to take over some of the functionality traditionally handled by CPUs, since when you're running a productivity app the GPU is usually just sitting there idling, even though in theory it's actually better at performing many tasks than a CPU typically is.
I see ultralight laptops like the Air adopting ARM CPUs first, maybe within as little as 2-3 years. Larger laptops and the iMac and Mac Mini would follow. If Apple stays in the desktop business the Pro would probably get a bunch of ARM CPUs and built-in high-powered graphics chips and other dedicated helpers for targeted tasks.
But we'll see. Maybe Intel will finally get it together in the low-power space and none of this will be necessary. At this point I'd imagine Apple is just hedging its bets. If Intel comes thru with low-power chips, Apple could just as easily go in the opposite direction and switch over to using Intel chips in iOS devices.
Extrapolations of ARM performance 5 years down the road are difficult.
What we know now, today, is that the latest ARM 15 dual core cpus clocked at 1.7 ghz are slower than Intel's 3 year old core 2 duos at a slightly slower clock speed.
And creative pros are always looking for more speed because that translates into greater productivity and more revenue.
When people say ARM will be "good enough" to replace Intel, thats code for "good enough" for consumer use. A move to ARM on Macs is a move away from professional markets.
I forgot to add that Microsoft's forking of Windows into both ARM (RT) and X86 variants may open the door for Apple ARM hardware to virtualize Win RT. That brings Office to iOS, which is a pretty big deal.
Unless ARM can do Intel i7 emulation FASTER than an Intel i7 CPU, then this is a fool's dream.
Any transition has to be with a much faster CPU to do decent emulation. All the years of Intel code won't run on ARM since ARM is too whimpy.
Who says it has to do Intel emulation? Apple surprised the tech world when it revealed it had a working verso of OS X running on Intel processors. Who says they don't have OS X running on custom, Apple designed ARM in the labs? And I don't agree that leaving Windows behind would be a big problem.
ARM runs OS X natively already, so emulation is pointless. I believe you meant that ARM would have difficulty emulating the X86 instruction set. As Apple is designing the processor, emulation of the X86 instruction set is probably more a legal problem than a technological one. The PA Semi folks have already implemented two different instruction sets, PowerPC and ARM. X86 would not be beyond their grasp. However, they can't get a license to run X86 by purchasing AMD (there's a caveat in AMD's license that prevents inheritance of the license). There may be another way for Apple to emulate X86 efficiently and legally, or it may be that by the time they envision making the switch, they also envision X86 compatibility being unnecessary.
I think it's important to consider the leverage Apple gains by removing Intel's 60% gross margin from the bill of materials.
Are you claiming to actually know something here? I have no doubt that they could write OS X to run directly on ARM, but that doesn't help the many thousands of programs out there that will not.
And running, doesn't translate to running well. As the iPhone five can just beat an old G4 laptop, it isn't going to be very useful. How many people are willing to drop back to that now pathetic level of performance? Not very many.
Why would they want their own x86 license? That would be a waste for them. There is no way they could keep pace with Intel. AMD is so far behind, it's hardly worthwhile thinking about it. Without a state of the art factory, it's impossible to keep up with Intel on their own turf. That's not a useful suggestion.
There's very little doubt they've worked on porting OS X to ARM. Why wouldn't they? I'm sure there are much more interesting projects they are working on that will never see the light of day.
Maybe someday it will become slightly viable, sensible, and beneficial to transition Macs to ARM, but that day is so far off into the future that it's not even worth thinking about.
Flying pork aside, thinking about the future is exactly what Apple is doing. It's how they will stay ahead of the curve. Besides, Microsoft has already ported Windows and Windows Server 2012 to ARM. And ARM just developed a 64-bit core. This is going to happen and it won't seem so strange when it does. The question is: where will Apple be in the adoption curve? Leading or trailing edge?
Of course they are mulling it. They would be stupid not to. Just like they are mulling if they can ever have an iPad with enough processor etc to run even an 'express' version of Final Cut or Logic
They will be mulling these things for the next ten years or so. And then we will see what comes of it.
And now that the 'experts' said there would be a second iPad in the fall for three years and it finally turned out to be true, they will say this for the next decade until they can say 'told ya so'. Perhaps
I forgot to add that Microsoft's forking of Windows into both ARM (RT) and X86 variants may open the door for Apple ARM hardware to virtualize Win RT. That brings Office to iOS, which is a pretty big deal.
I'm not so certain it is such a big deal. Apple has been stating that business sales are driving iPad sales. A recent report for one of the business computer publications stated that about 50% of iPads are bought by business. As Office isn't on iPads now, and they seem to be used successfully, it's very likely that those commercial users are finding that for tablet use, Office isn't required after all. How daunting for Microsoft that could be.
I'm reading about the problems of using RT overall, and the difficulties of the Home Student version.
If Apple is smart, and upgrades their iWork suite, something they haven't been doing, for some reason, they could own the space. In addition, another report says that Apple and VMware are working on an online suite together. This could be interesting.
Comments
Quote:
Originally Posted by astrosmash
When pigs fly.
There's very little doubt they've worked on porting OS X to ARM. Why wouldn't they? I'm sure there are much more interesting projects they are working on that will never see the light of day.
Maybe someday it will become slightly viable, sensible, and beneficial to transition Macs to ARM, but that day is so far off into the future that it's not even worth thinking about.
Given that iOS is OS X, it's fair to say that Apple ported to ARM quite some time ago.
If you plot the increase in performance of the A-Series over time, it's growing faster than X86. Intel's expertise may be more in process than in architecture. I think there is some room for architecture, particularly one optimized by the same company that fields the OS and rest of the hardware, to match Intel's advantage in process. Remember that Apple's elimination of Intel also eliminates Intel's hefty margins. That immediately places Apple at a cost advantage against other PC manufacturers.
Apple is pulling into the same league as Intel on number of CPUs manufactured each year, and they're doing it across far fewer variants. The latest geekbench scores for the dual core A6 place it at about 1/8th the speed of the MacBook Pro's quad core i7. That's only 4x better per core. ARM is claiming 3x improvement from the first generation of their 64 bit design. I think Apple can get within striking distance over the next few years.
Quote:
Originally Posted by backtomac
If this rumor is true, it would also indicate to me that Apple are going to abandon the creative pro market. There is no way ARM will be competitive with Intel big iron for applications like Photoshop and video editing.
Maybe at the moment. In 5 years? It'll be fast enough for anything anybody is going to do in Photoshop. Video editing might or might not be a problem, depending on the rest of the chipset. In theory, Apple could offload a lot of specialized processing for dedicated tasks like video editing onto other chips / the video card. It would allow them to unify X and iOS onto a single CPU architecture while still supporting Intel-like performance for key high-power tasks on desktop and high-end laptop devices.
Even on the PC there's already been movement toward utilizing GPUs to take over some of the functionality traditionally handled by CPUs, since when you're running a productivity app the GPU is usually just sitting there idling, even though in theory it's actually better at performing many tasks than a CPU typically is.
I see ultralight laptops like the Air adopting ARM CPUs first, maybe within as little as 2-3 years. Larger laptops and the iMac and Mac Mini would follow. If Apple stays in the desktop business the Pro would probably get a bunch of ARM CPUs and built-in high-powered graphics chips and other dedicated helpers for targeted tasks.
But we'll see. Maybe Intel will finally get it together in the low-power space and none of this will be necessary. At this point I'd imagine Apple is just hedging its bets. If Intel comes thru with low-power chips, Apple could just as easily go in the opposite direction and switch over to using Intel chips in iOS devices.
Absolutely! This isn't understood, it seems. I imagine it comes from the recent report that the iPhone 5 is more powerful than the most powerful G4 Powermac Apple produced.
Of course engineers working on chips will think, and hope, that what they are doing will supplant something else. I don't blame them for that, and it likely will result in much better SoC's. But x86 will remain a magnitude more powerful than ARM. I don't see how that will change any time in the foreseeable future.
The problem is OS X. All of us who are old enough remember the problems we had with Virtual PC, and other older emulation software. You simply can't successfully emulate an OS, and software, from an entirely different chip family with a chip in the same power range. It must be five times as powerful to come close.
So while x86 can do an excellent job in emulating iOS, there will be no way for ARM to successfully emulate OS X.
If Apple eventually abandons OS X the way Microsoft is abandoning the Desktop, that would be a different story. But otherwise it's not going to happen.
I see ARM taking a greater role in Apple's lineup, but it won't be replacing Intel for a good long while, if ever.
I see a 13" and 15" iPad replacing the laptops Apple sells (maybe with iOS' second real UI change) and different sizes of multitouch desktop computers replacing OS X, but I'm pretty sure the latter won't be ARM.
Quote:
Originally Posted by apersona
Cue the chorus of oldsters tiring of innovation and the effort it takes to wipe the slate clean and change paradigms.
Oldsters? Please. I'm almost 57. Put your overly-broad paintbrush away.
Since you admit you don't understand any of this "stuff", what makes you come up with ten reasons?
One reason should suffice, and that's processing power. If you feel that going back seven years in computer development is enough for your needs, then it can be done. But not quite.
The problem is emulation, as I wrote about in my previous response. Emulation requires a computer that's at least five times as powerful as the one being emulated (according to studies), if the processors are of a different family. As ARM will always be significantly less powerful, that can't be done.
It's why developers can use Apple's iOS emulation program in an x86 machine to emulate iOS and it's apps, but not the other way around.
This isn't going to change. Intel isn't standing still. While, for a while, the gap will narrow, there will always be a vast difference in power between the two technologies.
Of course, if Apple either abandons OS X the way Microsoft is doing with the Desktop, then there will only be iOS left. They could incorporate many of the OS X API's into iOS, but nevertheless a powerful program that runs on x86 will not be happy on ARM.
Quote:
Originally Posted by melgross
Absolutely! This isn't understood, it seems. I imagine it comes from the recent report that the iPhone 5 is more powerful than the most powerful G4 Powermac Apple produced.
Of course engineers working on chips will think, and hope, that what they are doing will supplant something else. I don't blame them for that, and it likely will result in much better SoC's. But x86 will remain a magnitude more powerful than ARM. I don't see how that will change any time in the foreseeable future.
The problem is OS X. All of us who are old enough remember the problems we had with Virtual PC, and other older emulation software. You simply can't successfully emulate an OS, and software, from an entirely different chip family with a chip in the same power range. It must be five times as powerful to come close.
So while x86 can do an excellent job in emulating iOS, there will be no way for ARM to successfully emulate OS X.
If Apple eventually abandons OS X the way Microsoft is abandoning the Desktop, that would be a different story. But otherwise it's not going to happen.
ARM runs OS X natively already, so emulation is pointless. I believe you meant that ARM would have difficulty emulating the X86 instruction set. As Apple is designing the processor, emulation of the X86 instruction set is probably more a legal problem than a technological one. The PA Semi folks have already implemented two different instruction sets, PowerPC and ARM. X86 would not be beyond their grasp. However, they can't get a license to run X86 by purchasing AMD (there's a caveat in AMD's license that prevents inheritance of the license). There may be another way for Apple to emulate X86 efficiently and legally, or it may be that by the time they envision making the switch, they also envision X86 compatibility being unnecessary.
I think it's important to consider the leverage Apple gains by removing Intel's 60% gross margin from the bill of materials.
Quote:
Originally Posted by sunspot42
Maybe at the moment. In 5 years? It'll be fast enough for anything anybody is going to do in Photoshop. Video editing might or might not be a problem, depending on the rest of the chipset. In theory, Apple could offload a lot of specialized processing for dedicated tasks like video editing onto other chips / the video card. It would allow them to unify X and iOS onto a single CPU architecture while still supporting Intel-like performance for key high-power tasks on desktop and high-end laptop devices.
Even on the PC there's already been movement toward utilizing GPUs to take over some of the functionality traditionally handled by CPUs, since when you're running a productivity app the GPU is usually just sitting there idling, even though in theory it's actually better at performing many tasks than a CPU typically is.
I see ultralight laptops like the Air adopting ARM CPUs first, maybe within as little as 2-3 years. Larger laptops and the iMac and Mac Mini would follow. If Apple stays in the desktop business the Pro would probably get a bunch of ARM CPUs and built-in high-powered graphics chips and other dedicated helpers for targeted tasks.
But we'll see. Maybe Intel will finally get it together in the low-power space and none of this will be necessary. At this point I'd imagine Apple is just hedging its bets. If Intel comes thru with low-power chips, Apple could just as easily go in the opposite direction and switch over to using Intel chips in iOS devices.
Extrapolations of ARM performance 5 years down the road are difficult.
What we know now, today, is that the latest ARM 15 dual core cpus clocked at 1.7 ghz are slower than Intel's 3 year old core 2 duos at a slightly slower clock speed.
And creative pros are always looking for more speed because that translates into greater productivity and more revenue.
When people say ARM will be "good enough" to replace Intel, thats code for "good enough" for consumer use. A move to ARM on Macs is a move away from professional markets.
I forgot to add that Microsoft's forking of Windows into both ARM (RT) and X86 variants may open the door for Apple ARM hardware to virtualize Win RT. That brings Office to iOS, which is a pretty big deal.
Who says it has to do Intel emulation? Apple surprised the tech world when it revealed it had a working verso of OS X running on Intel processors. Who says they don't have OS X running on custom, Apple designed ARM in the labs? And I don't agree that leaving Windows behind would be a big problem.
Are you claiming to actually know something here? I have no doubt that they could write OS X to run directly on ARM, but that doesn't help the many thousands of programs out there that will not.
And running, doesn't translate to running well. As the iPhone five can just beat an old G4 laptop, it isn't going to be very useful. How many people are willing to drop back to that now pathetic level of performance? Not very many.
Why would they want their own x86 license? That would be a waste for them. There is no way they could keep pace with Intel. AMD is so far behind, it's hardly worthwhile thinking about it. Without a state of the art factory, it's impossible to keep up with Intel on their own turf. That's not a useful suggestion.
This is just rumor and speculation. Nothing more.
This rumor has the same validity as WMD.
Flying pork aside, thinking about the future is exactly what Apple is doing. It's how they will stay ahead of the curve. Besides, Microsoft has already ported Windows and Windows Server 2012 to ARM. And ARM just developed a 64-bit core. This is going to happen and it won't seem so strange when it does. The question is: where will Apple be in the adoption curve? Leading or trailing edge?
They will be mulling these things for the next ten years or so. And then we will see what comes of it.
And now that the 'experts' said there would be a second iPad in the fall for three years and it finally turned out to be true, they will say this for the next decade until they can say 'told ya so'. Perhaps
I'm not so certain it is such a big deal. Apple has been stating that business sales are driving iPad sales. A recent report for one of the business computer publications stated that about 50% of iPads are bought by business. As Office isn't on iPads now, and they seem to be used successfully, it's very likely that those commercial users are finding that for tablet use, Office isn't required after all. How daunting for Microsoft that could be.
I'm reading about the problems of using RT overall, and the difficulties of the Home Student version.
If Apple is smart, and upgrades their iWork suite, something they haven't been doing, for some reason, they could own the space. In addition, another report says that Apple and VMware are working on an online suite together. This could be interesting.
Some day.