Why Apple might consider leaving Intel's x86 for its own ARM chips in future Macs

124678

Comments

  • Reply 61 of 150
    wizard69wizard69 Posts: 13,377member
    kkerst wrote: »
    I agree with you, and "good enough" is relative. Of course no one can anticipate every single use case. It's been my impression of Apple's approach is to take the average use case, ratchet it up many notches so that what you're left with is an above average experience. If they can achieve this with an AX ARM processor, more power to them and I see no reason why it wouldn't sell. I was just stating that they better not screw up what works as is. 
    I wouldn't expect them to screw it up. At least not hardware wise. The big problem would be the marketing of the product ( is it A Mac, an IOS device or something else).
    However, I have PPC 2005 Mac mini where I think the performance has never been what I think it should have been from the start, but they fixed subsequent problems with later minis. 
    This is what I don't get with respect to the rumored fanless device, I'm not getting good vibes about performance as similar Windows machines have sucked pretty bad in the blogs or forums. I actually think that Apple could ship a better performanc machine right now with an ARM chip in it instead of trying to do Intel fanless.
    On the notion of adding more cores to get the job done, there's a limit to where this approach won't work anymore. Sooner or later the design (electrical design, not industrial) you are left with is more complicated and not streamlined enough to just meet an average speedy use case.
    We haven't really hit that limit yet in desktop and laptop chips. Congestion is certianly a problem as the number of cores increases. Right now the sweet spot for most non technical users is between 4-6 cores (Intel cores). The problem is Intel has yet to ship anything with this sort of configuration for the sorts of devices we are talking about here.
    Think battery power here. There's a reason why all iPhones/iPads don't have four cores running at 3GHz. This means the processors are more efficient and don't need to rely on more cores to get the job done.  If they can get OS X to run just as speedy, they'll have pulled another cat out of the bag. 
    Remember we are moving from a tablet to a laptop here. This will provide us with more battery capacity and frankly the freedom the rev the engine (run at a higher clock rate).
    SELF EDIT: The iPad Air 2 does have three cores in the A8X. So let's go with that. They were able to increase the cores without sacrificing battery life. Great. 

    A8X is pretty amazing and it does make one wonder what the design tops out at clock rate wise.
  • Reply 62 of 150
    Since when has Apple been all about 'good enough'? Apple will stay where the performance is. ARM is quite a long way aways from that currently.
  • Reply 63 of 150
    pmzpmz Posts: 3,433member
    You people are so short sighted.

    "ARM could catch up to Intel i3 within 2 years"

    Do you think that even remotely interests Apple? That's lame. When Apple comes out the gates with their own chip for Mac, it will be something no one saw coming. Not just a repackaged ARM chip made by fucking Samsung.
  • Reply 64 of 150
    Quote:
    Originally Posted by Rogifan View Post



    What consumer benefit is there to an ARM based Mac? MBAs already get great battery life. And there are new Windows OEM machines that are thinner/lighter than the current Airs. Would an ARM MBA be cheaper than its Intel equivalent?

     

    1. Direct compatibility with iOS, imagine universal binary that can work on both OS X and iOS. Less focus on separate platforms, less code to maintain, now all platforms Apple controls are one single OS runtime that can have consistent APIs. 

    2. Deeper integration with the hardware, Apple can remove CPU/GPU features that is useless, add more power toward features they deem more important. That means they can squeeze a lot of efficiencies from CPU and GPU, which results into more performance for less power. Remember, we're not just talking about CPU but also GPU. 

    3. With Apple in control, they do not have to wait for Intel to do anything. Apple can just add it themselves and it would work for both iOS and Mac devices. 

    4. Not paying Intel hundreds of dollars for each CPU, Apple simply pay 1/3rd of that instead and earn more profits or cut the prices of their products. 

     

    Quote:
    Originally Posted by Ricardo Dawkins View Post



    and...in 2 years Skylake based Core i3s will leave this AX things in the dust!

     

    Apple has far more room to improve from where Intel has less room. Skylake isn't going to add any more than 5% of improvement, just like Broadswell and Haswell, and so on. Intel is hitting the limits much faster than Apple. 

     

    Also, don't forget Apple's A series is designed for battery in iOS devices, which is tiny compared to a laptop. Scale up their CPU and you can have a beast of a CPU/GPU consisting of 4 or even 8 cores. 

     

    Quote:
    Originally Posted by MachineShedFred View Post

     



    Everyone seems to forget that the reason why Rosetta worked in the first place is because Intel Core-series chips had so much horsepower in comparison to what Apple had been getting from IBM in the form of PowerPC 970 that they could afford to waste cycles on instruction translation.  That is completely not the case with a theoretical x64-to-ARM shift.  An ARM CPU that could take a 10-15% overhead to translate x64 to ARM64 and have the same performance simply doesn't exist, and probably won't for quite some time, if ever.

     

    Second, it would put Apple in the position of not being able to differentiate their products on the things they do best - industrial design and software design.  Intel spends billions every year on CPU designs and lithography research and fabrication process research.  Apple would definitely have to do the CPU design work, and probably have to spend loads of cash helping some other foundry play catch-up.  If they stay with Intel, they don't have to do that because Intel already is, and is spreading the cost amongst all PC OEMs.

     

    I can't for the life of me figure out why they would want to give up the hardware parity they have enjoyed for the last 9 years in order to have less performance, and far more expense.


    Have you not been paying attention to what Apple's been doing with their A* SoCs over the past several years? They've already bought a few CPU companies, custom-designed their own CPUs and they now have one of the best ARM-based CPU team on the market.  They've consistently built the fastest ARM-baseed CPU/GPU SoC for 2-3 years in a row now. 

     

    Also, ARM has support for built-in virt extensions that can speed up the translations, something that Apple didn't have with Intel. They can customize their SoC to include the said extensions (even more if they want) and get it up fast enough. 

     

    IIRC, XEN said they were able to get it within 2-4% overhead with their XEN engine on ARM with virt extensions. That was with comparable OS, so likely linux. It would be nice if someone can test Xen with Windows guests. 

     

    Quote:
    Originally Posted by Bregalad View Post



    ARM Mac - can't run Windows, but can run iOS

    x86 Mac - can run Windows, only developer tools can run iOS



    Given that iOS apps are designed for small touch screens, being able to run them on your Mac doesn't seem like a particularly important feature to me. If Apple ever decides it is they can create a consumer facing version of the iOS simulator. Intel chips have plenty of power to handle ARM emulation. The converse isn't true (yet if ever).



    Despite all the hype around mobile, positive halo effects for OS X and the poor reception for both Vista and Windows 8, the folks in Redmond continue to run roughly 90% of the world's PCs. It makes sense for Apple's PCs to maintain compatibility with the other 90% rather than embrace improved compatibility with mobile.

     

    Ever consider the possibility of universal binary code? Same backend code that can run on all platforms Apple have but OS handles the automatic layout of the interface to fit the screen. Not possible with x86 and ARM code since the data is affected by the structure of ISAs but totally possible with a single ISA, ARM. You just have to tailor the interface without messing with the rest of the code. 

     

    Microsoft is doing the same thing with Windows 10, they're calling it Universal Windows Apps. Source: http://msdn.microsoft.com/en-us/library/windows/apps/dn609832.aspx



    Apple has far more iOS apps than they have Mac apps. If they make it much easier to share code in a way that it'll be easy to build both iOS and OS X at the same time, it could help OS X get more popular. 

     

    Quote:
    Originally Posted by sirdir View Post



    @sflocal Intel is one of the most capable chip makers of the world, even if Apple could license them it wouldn't be easy to make them better and quicker.

     

    You do realize that on ARM platform, Apple is among the few most capable chip designers on the planet, right? They've consistently made one (if not the fastest) of the fastest CPU SoCs in the past few years. That's within the power constraint of smartphones and tablets. Imagine what they can do when they open it up for a laptop instead. 

     

    Quote:
    Originally Posted by steinm88299 View Post



    Other issue here is virtual machine capabilities. I run OS X everywhere but rely on a few Microsoft applications that just don't have suitable replacements on the OS X side of the house. Moving from Intel to ARM would most likely kill products like Fusion and Parallels. I don't really get this although it is just a complete rumor and could be nonsense.

     

    Not exactly, ARM CPU has support of putting in virtualization extensions to speed up the ARMv8 to x86 translation. You can find out more here: http://wiki.xenproject.org/wiki/Xen_ARM_with_Virtualization_Extensions

    Quote:
    Originally Posted by AppeX View Post



    Will Apple be fool enough to make the same mistake again? Hopefully not, because x86 is a must for compatibility with the world (Windows).

     

    Umm, what mistake? Apple have done it twice in the past and it worked out for them. 

     

    Apple can build an ARM chip with virt extensions to speed up the ARM to x86 translations. 

    Quote:
    Originally Posted by bdkennedy1 View Post

     

    Apple wrote XCode to handle the switch from PPC to Intel.  Now we have Swift. Apple didn't spend 3 years writing a new programming language for the hell of it.


     

    Swift really has nothing to do with this IMO. It's the runtime, Clang/LLVM that has the bigger impact than the language. 

     

    Keep in mind that Obj-C code is the same for both iOS and OS X, you just have to compile it to ARM/x86. 

    Quote:
    Originally Posted by mjtomlin View Post

     

     

    Yes, Apple could license the x64 ISA, if one of the companies who "own" it allow that.

     

    And I personally believe that this is the direction Apple will head. The chips they use now are bogged down with legacy logic left in to maintain backwards compatibility for the Windows platform. Apple could very well strip out all of that and produce a core at a significant discount over what they're paying Intel. And I'm sure in a few years they'll do the same to their ARM cores; strip out ARMv7 and only support ARMv8.


     

    By stripping out the legacy logic, you break the backward compatibility that all x86 OS relies on. These OS are dependent on code to work around these logic and if you change it, they will break. 


     


    What's the point of stripping out x64 ISA when you can go with the simpler and more efficient ISA, the ARMv8 and not pay Intel anything. 


     


    There's no point of Apple of licensing x86 when they already have the best experience of producing the best ARM CPUs there is. 


     


     


     

     

    Quote:
    Originally Posted by Mike Eggleston View Post

     

    I honestly don't see Apple ditching Intel to go only with the AX class of chips. They just are not powerful enough to be able to do all of the computing functions that most people need. 


     

    Right, so why didn't Apple go with Intel in the first place for iPad?

     

    A8X is fast enough to be compared to Intel CPU 5 years ago and that's at a much lower power levels. That is still a massive gap of course but increase it to 8 core, allow it to run at higher power levels, expand its extensions/APIs, and you can have a very powerful CPU/GPU combination. 

     

    Quote:
    Originally Posted by Wiggin View Post

     

     

    Except that Rosetta relied on the fact the Intel processors had a big performance advantage over PowerPC which made the translation penalty mostly unnoticeable. Similarly, PowerPC chips had a performance advantage over 68k chips which made the Classic environment feasible. And as others have already point out, the current projections for A-series performance is "less than i3" level performance. In other words, a fair deal less performance than even the slowest chip Apple puts in Macs today. Add that to the "Rosetta 2" translation to run Intel code on an A-series chips, and performance would be pretty dismal by comparison.

     

    The question remains...would it be "good enough"? For a lot of users, I think yes. Email, web surfing, etc. But it would be far below what an Intel Mac would be capable of. As others have stated, Apple wants to be a high-rung retailer. Would the sell such a low performing Mac? I think not. But they could market it as a new line of computers all together. Think Apple's incarnation of a netbook done right. But by not calling it a Mac they could avoid a lot of marking confusion and developer angst. It would be the big brother of the iPad rather than the wimpy little brother of the Mac.


     

    What projections? Can somebody show me the projections of how fast A8X is at i3's TDP levels? How about how fast i3 is at A8X's TDP? 

     

    A8X is definitely slow but it is also designed for low power levels to be put in a smartphone and thin tablets. 



    Scale A8X to 4-8 cores, expand it TDP to 20-30W and see how much faster it gets. 

     

  • Reply 65 of 150
    rogifan wrote: »
    What consumer benefit is there to an ARM based Mac?

    If you already own a lot of iOS programs, most can run on the new Laptop iDevice. You need not rebuy them; saving a lot of long green.

    MBAs already get great battery life.

    how about a lot more performance for all that time away from a charger. Much of this due to the power of Metal and/or Swift.

    And there are new Windows OEM machines that are thinner/lighter than the current Airs.

    And THAT's a problem for Apple who buys the same Intel chip. They are tied to the same release schedule as everyone else...and delayed from coming out with a better computer along with everyone else. Apple was through that with the PPC chip and solved that by going with Intel... it's time for Apple to become more independent of other people's release schedules.
    Would an ARM MBA be cheaper than its Intel equivalent?

    I'd expect the ARM to cost around a tenth of the Intel chip.
  • Reply 66 of 150
    MacProMacPro Posts: 19,718member
    mikhailt wrote: »
    1. Direct compatibility with iOS, imagine universal binary that can work on both OS X and iOS. Less focus on separate platforms, less code to maintain, now all platforms Apple controls are one single OS runtime that can have consistent APIs. 
    2. Deeper integration with the hardware, Apple can remove CPU/GPU features that is useless, add more power toward features they deem more important. That means they can squeeze a lot of efficiencies from CPU and GPU, which results into more performance for less power. Remember, we're not just talking about CPU but also GPU. 
    3. With Apple in control, they do not have to wait for Intel to do anything. Apple can just add it themselves and it would work for both iOS and Mac devices. 
    4. Not paying Intel hundreds of dollars for each CPU, Apple simply pay 1/3rd of that instead and earn more profits or cut the prices of their products. 


    Apple has far more room to improve from where Intel has less room. Skylake isn't going to add any more than 5% of improvement, just like Broadswell and Haswell, and so on. Intel is hitting the limits much faster than Apple. 

    Also, don't forget Apple's A series is designed for battery in iOS devices, which is tiny compared to a laptop. Scale up their CPU and you can have a beast of a CPU/GPU consisting of 4 or even 8 cores. 

    Have you not been paying attention to what Apple's been doing with their A* SoCs over the past several years? They've already bought a few CPU companies, custom-designed their own CPUs and they now have one of the best ARM-based CPU team on the market.  They've consistently built the fastest ARM-baseed CPU/GPU SoC for 2-3 years in a row now. 

    Also, ARM has support for built-in virt extensions that can speed up the translations, something that Apple didn't have with Intel. They can customize their SoC to include the said extensions (even more if they want) and get it up fast enough. 

    IIRC, XEN said they were able to get it within 2-4% overhead with their XEN engine on ARM with virt extensions. That was with comparable OS, so likely linux. It would be nice if someone can test Xen with Windows guests. 


    Ever consider the possibility of universal binary code? Same backend code that can run on all platforms Apple have but OS handles the automatic layout of the interface to fit the screen. Not possible with x86 and ARM code since the data is affected by the structure of ISAs but totally possible with a single ISA, ARM. You just have to tailor the interface without messing with the rest of the code. 

    Microsoft is doing the same thing with Windows 10, they're calling it Universal Windows Apps. Source: http://msdn.microsoft.com/en-us/library/windows/apps/dn609832.aspx


    Apple has far more iOS apps than they have Mac apps. If they make it much easier to share code in a way that it'll be easy to build both iOS and OS X at the same time, it could help OS X get more popular. 


    You do realize that on ARM platform, Apple is among the few most capable chip designers on the planet, right? They've consistently made one (if not the fastest) of the fastest CPU SoCs in the past few years. That's within the power constraint of smartphones and tablets. Imagine what they can do when they open it up for a laptop instead. 


    Not exactly, ARM CPU has support of putting in virtualization extensions to speed up the ARMv8 to x86 translation. You can find out more here: http://wiki.xenproject.org/wiki/Xen_ARM_with_Virtualization_Extensions

    Umm, what mistake? Apple have done it twice in the past and it worked out for them. 

    Apple can build an ARM chip with virt extensions to speed up the ARM to x86 translations. 

    Swift really has nothing to do with this IMO. It's the runtime, Clang/LLVM that has the bigger impact than the language. 

    Keep in mind that Obj-C code is the same for both iOS and OS X, you just have to compile it to ARM/x86. 



    Right, so why didn't Apple go with Intel in the first place for iPad?

    A8X is fast enough to be compared to Intel CPU 5 years ago and that's at a much lower power levels. That is still a massive gap of course but i<span style="line-height:1.4em;">ncrease it to 8 core, allow it to run at higher power levels, expand its extensions/APIs, and you can have a very powerful CPU/GPU combination. </span>



    What projections? Can somebody show me the projections of how fast A8X is at i3's TDP levels? <span style="line-height:1.4em;">How about how fast i3 is at A8X's TDP? </span>


    <span style="line-height:1.4em;">A8X is definitely slow but it is also designed for low power levels to be put in a smartphone and thin tablets. </span>


    <span style="line-height:1.4em;">Scale A8X to 4-8 cores, expand it TDP to 20-30W and see how much faster it gets. </span>


     

    Wow, I enjoyed that! Great post... my brain is exploding! (with excitement that is). :smokey:
  • Reply 67 of 150
    plovellplovell Posts: 824member
    Quote:

    Originally Posted by Macky the Macky View Post

     
    Quote:

    Originally Posted by Rogifan View Post



    What consumer benefit is there to an ARM based Mac?




    If you already own a lot of iOS programs, most can run on the new Laptop iDevice. You need not rebuy them; saving a lot of long green.

    Repeat after me: OS X is NOT iOS, OS X is NOT iOS, OS X is NOT iOS.

     

    Got it? There is no reason to expect any iOS apps to run on a Mac. Macs use OS X and that's not the same as iOS. There are similarities but they are NOT the same. Do NOT equate "ARM" and "iOS". They are orthogonal. Macs could be built using ARM but that does NOT mean that they would run iOS apps.

  • Reply 68 of 150
    plovellplovell Posts: 824member
    Quote:

    Originally Posted by mjtomlin View Post

     
    Quote:
    Originally Posted by sflocal View Post



    I have zero clue how all the x86 politics work, but couldn't Apple somehow license the x86 architecture (like it did with ARM) and essentially build its own x86-compatible chip solely for its own machines and run with it?

     

    Yes, Apple could license the x64 ISA, if one of the companies who "own" it allow that.

     

    And I personally believe that this is the direction Apple will head. The chips they use now are bogged down with legacy logic left in to maintain backwards compatibility for the Windows platform. Apple could very well strip out all of that and produce a core at a significant discount over what they're paying Intel. And I'm sure in a few years they'll do the same to their ARM cores; strip out ARMv7 and only support ARMv8.




    There is no point for Apple to strip stuff out of x86. If they want full x86 then stay with it. Maybe the reason is being able to run BootCamp, maybe not - I don't know. 

     

    One thing of which I am sure is that Apple would have no interest in doing a Franken-x86, with some of the stuff but not all. What would be the benefit? A whole bunch of stuff - not just Windows - wouldn't run and there would be endless arguments as to who was to blame. It's just not worth going there. The cost benefit isn't worth it.

     

    The situation with Ax is different. Apple has already "aged out" some of the old ones. And NONE of them have to support Windows.

  • Reply 69 of 150

    I agree that Apple is looking into making its own Laptop/Desktop chip.  Honestly they are probably looking at both an x86 compatible chip and an ARM chip.  

     

    Just like the last time this came up, I still believe that Apple needs x86 support.  While windows is on 13% of devices, it is about 90% of PCs.  PCs are where people do content generation.  While iPads are great for consumption, they are no where near as good for creation (with a few exceptions).  This means that x86 support is important to 90% of their potential market, therefore it is important to Apple.  

     

    One of the major issues with Windows RT is that it was not compatible with normal Windows.  Even Microsoft is acknowledging that.  When was the last time you saw an add for the Microsoft Surface?  I haven't seen one in months.  The Surface Pro, several times a night, but the Windows RT based Surface, I have not seen in a while.  The confusion of having two devices with similar names and appearances that are not comparable with each other will definitely kill the weaker product, and at a minimum damage the stronger product.  I don't see Apple making this same mistake.  

     

    For everyone that says "Fat Binaries", they do not remember actually going through either of the last transitions.  Your smaller companies will probably move over to Fat Binaries quickly (i.e. just do the recompile), but larger companies like Microsoft (3 years) and Adobe (2 Years) will take forever to move over to Fat Binaries (If they do at all - intuit).

     

    I personally would like to see a L1 (Laptop 1) or a D1 (Desktop 1) chip out of Apple.  If for no other reason than to get Intel moving again.  But if Apple did drop support for x86, all of those gains in the Mac marketshare will die quickly.

  • Reply 70 of 150
    plovellplovell Posts: 824member
    Quote:

    Originally Posted by MikhailT View Post

     
    Quote:
    Originally Posted by Rogifan View Post



    What consumer benefit is there to an ARM based Mac? MBAs already get great battery life. And there are new Windows OEM machines that are thinner/lighter than the current Airs. Would an ARM MBA be cheaper than its Intel equivalent?

     

    1. Direct compatibility with iOS, imagine universal binary that can work on both OS X and iOS. Less focus on separate platforms, less code to maintain, now all platforms Apple controls are one single OS runtime that can have consistent APIs. 


    Repeat after me: iOS is NOT OS X, OS X is NOT iOS, iOS is NOT OS X, OS X is NOT iOS

     

    Get it ??? There is NO way that an iOS/OS X combo app makes sense. The user interface to the file system is totally different and that's where this "compatibility" breaks down. Files in iOS are stored in the app's folder, and in OS X they're elsewhere. 

     

    And in OS X a user can run an app and open a file anywhere (within reason). Not possible in iOS. 

     

    I understand both OS X and iOS and their differences. And I want them to stay different - there are very good reasons for them to be that way.

  • Reply 71 of 150
    entropysentropys Posts: 4,152member
    pmz wrote: »
    You people are so short sighted.

    "ARM could catch up to Intel i3 within 2 years"

    Do you think that even remotely interests Apple? That's lame. When Apple comes out the gates with their own chip for Mac, it will be something no one saw coming. Not just a repackaged ARM chip made by fucking Samsung.
    exactly. Why not an 'M' series chip with X64 and ARM components, and just like its A series SOC does not have ARM legacy components, the x64 bits won't have the legacy bits that exist in Intel chips. There is a performance boost right there.

    And as it goes in the Mac, it won't need to worry as much about the constraints of size, but with Apple's experience, the extra space will be able to be readily used.

    But I agree with other posters. It has to be better than Intel offerings. Or why bother?
  • Reply 72 of 150
    xixoxixo Posts: 450member
    Quote:
    Originally Posted by bdkennedy1 View Post

     

    Imagine how much cheaper ARM Macs would be how much bigger Apple's net profit margin on ARM Macs would be, when sold at the same retail prices of today?


     

    fixed that for you

     

    A mac that runs iOS apps would have to be counted in the Gartner, IDG, etc tally of 'biggest PC manufacturer'.

     

    The death of MS Office because Ballmer thought everyone would abandon iPads for Surface shows how rapidly irrelevant Windows is becoming.

     

    Windows compatible Macs will be quite quaint in another two years. Positively zune-like, really...

  • Reply 73 of 150
    plovellplovell Posts: 824member
    Quote:

    Originally Posted by asdasd View Post


    The iPad certainly needs a keyboard for enterprise use. Text selection and copying and pasting is a mess right now.

    There is a keyboard and it works well. Apple Bluetooth keyboard is your answer. Buy it, pair it. Done

     

    But, to your point about copy/paste, what we do NOT have is a mouse or trackpad. I have tried to pair Apple's Magic Trackpad and Magic Mouse and these haven't connected - only the keyboard. I would LOVE it if I could use either of these devices with iPad (plus keyboard).

  • Reply 74 of 150
    jexusjexus Posts: 373member
    Quote:

    Originally Posted by Syrran View Post

     

    Apple, pls buy AMD for their x86 license @ a big premium over the current share price!  (But it's not like Apple to do that.)




    Sure.

     

    If you love setting money on fire this is a great idea. The Second Apple buys AMD is the second AMD loses its x86 license.

     

    Plus while the 900 series of GPU's is nice price/performance/watt wise, I hate seeing arrogant Nvidia and an Apple owned AMD wouldn't help that situation.

  • Reply 75 of 150
    plovellplovell Posts: 824member
    Quote:


    Quote:
    Originally Posted by Bregalad View Post



    ARM Mac - can't run Windows, but can run iOS

    x86 Mac - can run Windows, only developer tools can run iOS



    Given that iOS apps are designed for small touch screens, being able to run them on your Mac doesn't seem like a particularly important feature to me. If Apple ever decides it is they can create a consumer facing version of the iOS simulator. Intel chips have plenty of power to handle ARM emulation. The converse isn't true (yet if ever).

     

    Ever consider the possibility of universal binary code? Same backend code that can run on all platforms Apple have but OS handles the automatic layout of the interface to fit the screen. Not possible with x86 and ARM code since the data is affected by the structure of ISAs but totally possible with a single ISA, ARM. You just have to tailor the interface without messing with the rest of the code. 

     

    Microsoft is doing the same thing with Windows 10, they're calling it Universal Windows Apps. Source: http://msdn.microsoft.com/en-us/library/windows/apps/dn609832.aspx



    Apple has far more iOS apps than they have Mac apps. If they make it much easier to share code in a way that it'll be easy to build both iOS and OS X at the same time, it could help OS X get more popular. 


    There is a BIG difference between OS X apps and iOS apps. And it has NOTHING to do with ISAs

     

    "...OS handles the automatic layout of the interface to fit the screen. Not possible with x86 and ARM code since the data is affected by the structure of ISAs but totally possible with a single ISA, ARM."

     

    This makes zero sense. And, no, this is not what Windows is doing. 

  • Reply 76 of 150
    plovellplovell Posts: 824member
    Quote:

    Originally Posted by Jexus View Post

     
    The Second Apple buys AMD is the second AMD loses its x86 license.

     


    Not a troll-question - I honestly don't know. Does AMD have an x86 license from Intel, or did they reverse-engineer it ? My recollection is that they did the latter but I don't know for sure. Does anyone have a definitive answer ?

  • Reply 77 of 150
    MacProMacPro Posts: 19,718member
    plovell wrote: »
    Not a troll-question - I honestly don't know. Does AMD have an x86 license from Intel, or did they reverse-engineer it ? My recollection is that they did the latter but I don't know for sure. Does anyone have a definitive answer ?

    This from 2009

    http://beta.slashdot.org/story/09/03/16/1839231/intel-threatens-to-revoke-amds-x86-license
  • Reply 78 of 150
    Quote:

    Originally Posted by Wiggin View Post

     

    Except that Rosetta relied on the fact the Intel processors had a big performance advantage over PowerPC which made the translation penalty mostly unnoticeable. Similarly, PowerPC chips had a performance advantage over 68k chips which made the Classic environment feasible. And as others have already point out, the current projections for A-series performance is "less than i3" level performance. In other words, a fair deal less performance than even the slowest chip Apple puts in Macs today. Add that to the "Rosetta 2" translation to run Intel code on an A-series chips, and performance would be pretty dismal by comparison.

     

    The question remains...would it be "good enough"? For a lot of users, I think yes. Email, web surfing, etc. But it would be far below what an Intel Mac would be capable of. As others have stated, Apple wants to be a high-rung retailer. Would the sell such a low performing Mac? I think not. But they could market it as a new line of computers all together. Think Apple's incarnation of a netbook done right. But by not calling it a Mac they could avoid a lot of marking confusion and developer angst. It would be the big brother of the iPad rather than the wimpy little brother of the Mac.


    I agree that there would be a performance penalty but that would only be for non-native apps. All of Apple's apps would be native from day-one (i.e. fat-binary) and I expect that lots of third-party developers would be quick to recompile and ship fat-binary. 

     

    So many apps would be full-speed at release or very shortly thereafter. And no serious deficiency w.r.t. an Intel-based Mac.

     

    As you say, other apps would be below the comparable performance on an Intel-based system.

     

    Were I an Apple Product Manager (which I am not) then I would adopt following plan:

    1. rev Xcode for creating ARM/x86 fat binaries

    2. develop a low-end ARM-based MacBook Air [probably already in the labs]

    3. seed "major developers" with ARM-based prototypes (not necessarily MBAs)

    4. announce and ship new MBAs, have dev ship fat apps

    5. evaluate developer response and customer acceptance, and refine plans for future ARM models

     

    Note that there is no "merge iOS and OS X" in this sequence. 

  • Reply 79 of 150
    Quote:
    Originally Posted by xixo View Post

     
    A mac that runs iOS apps would have to be counted in the Gartner, IDG, etc tally of 'biggest PC manufacturer'.


    Have you seriously thought about how to run an iOS app on a Mac? Seriously considered where your files go in the file system, and all the little things that go with that?

     

    If you have then please enlighten us, in detail. Because I have and all I've seen is less-than-nice. But maybe I just didn't think hard enough.

  • Reply 80 of 150
    jexusjexus Posts: 373member
    Quote:

    Originally Posted by plovell View Post

     

    Not a troll-question - I honestly don't know. Does AMD have an x86 license from Intel, or did they reverse-engineer it ? My recollection is that they did the latter but I don't know for sure. Does anyone have a definitive answer ?




    The license is under the condition that AMD is the lone producer(outside of VIA, which is all but irrelevant). As posted below your comment, when AMD started co-oping with GF, Intel threatened to basically kill AMD by removing the license.

     

    They still to this day reserve that right if AMD either goes under or is bought out, to prevent competition from basically jacking up AMD's designs. It's why the whole "Company X can Save AMD" trend has been, frankly, dumb for 6 years now.

Sign In or Register to comment.