Apple's shift to ARM Mac at WWDC will define a decade of computing

13

Comments

  • Reply 41 of 76
    canukstormcanukstorm Posts: 2,606member
    elijahg said:
    nubus said:
    2)  As the article points out, Apple has successfully implemented a program to design their own chips and SOCs -- and that that is both very difficult and very expensive.   But, once begun it must be continued -- even though it will continue to be both very difficult and very expensive.   The danger lies in the possibility of Apple following other U.S. companies and focusing on stockholder well being over product well being.  If this program is stripped of funding (even a reduction) in order to provide better returns to stockholders, it could take down the whole company -- turn it into another RCA.
    Apple will hit more problems by doing this. Intel stalled due to engineering problems. Microsoft did Vista - and not due to lack of funding. It can happen to anyone - Apple failed on keyboards for 5 years, and on the Mac Pro for 10. Can't blame Microsoft for any of that. This won't make MS, or Apple the next RCA or Xerox, but is it worth taking the risk? If Apple truly cared about the Mac CPU then they would do more updates to their products - the CPU is such a non-issue at this point.
    You make several very good points. The iMacs were essentially abandoned between 2015 and 2019, (the iMac had a spec bump in 2017, and the 2019 one still has no T2 chip) and apart from minor attempts to fix the Macbook keyboards, they saw little love between 2016 and 2020. And of course the Mac Pro went 6 years before an update. So with the lack of attention toward Macs, why all of a sudden is there a CPU switch, when the current CPUs are fast enough for 99% of tasks? I wager a big reason is so Apple can increase their profit margins more on Macs, by using the already developed and paid for tech in the A-series chips in Macs, rather than giving Intel $800 per high-end CPU.

    And yes, when Apple hits the same physics wall as Intel, what happens then? Obviously ARM is a much more computationally efficient architecture than x86 so all things being equal, ARM will beat raw x86, but Apple will have to keep pouring billions into their chip R&D to keep ahead of Intel. Right now they can say they're fastest, but if they lose that crown they'll be wasting billions to catch up when they could have just stuck with Intel.
    The supposed benefits of Apple designing its own custom processor for the Mac isn't only about raw processing power.  A lot of it has to do with adding features to the SoC, that Apple won't be able to accomplish by staying with Intel, and that macOS apps will eventually be able to take advantage of.  Things like:  integrating AI / ML (Neural Engine), security (Secure Enclave), and cellular.  These are the features we know for now.  Who knows what other type of co-processors that Apple can eventually integrate onto the SoC.
    commentzillaGeorgeBMactechconcwatto_cobrarazorpit
  • Reply 42 of 76
    jharnerjharner Posts: 4member
    Apple has already made it difficult for data scientists by not providing Nvidea drivers supporting cuda. The real problem is not virtualization for Windows. Rather it is virtualization for Docker and and to a lesser extent for VirtualBox. Docker containers herald the wave of the future for STEM, including data science and statistics. It also will be critical for reproducible research. Now the Mac is dominant in STEM---go to any related conference to see what attendees are using. Two factors may change this---ARM Macs and Windows Subsystem for Linux. STEM increasingly is running on Linux-based open-source software using multiple software ecosystems that must work together---R and PostgreSQL, R or Python with Spark and Hadoop, etc. These integrated environments are best containerized and reproducibility of research and collaboration of developers and scientists along with bash and git will make Docker and related infrastructure essential. Currently, the Mac excels in this area, but an ARM Mac may not support Docker, Singularity, Kubernetes, etc., even if it does continue to support open-source UNIX software. But now Windows runs containerized Linux. What faculty and researchers use will filter down to students. We are not talking about a 2% loss---it will be much larger for STEM related disciplines in academia and industry. In principal, Apple could support Docker and related technologies, but will they? They could support cuda, but they don't. Even if computing moves to the cloud, what technologies are behind this? Docker, Kubernetes, open-source software, etc. Everyone will need to develop, test and deploy their code from their local machine. This cannot be done using iPadOS and if cannot be done on macOS, the the Mac is done in STEM.
    sphericelijahgcroprrazorpit
  • Reply 43 of 76
    canukstormcanukstorm Posts: 2,606member
    jharner said:
    Apple has already made it difficult for data scientists by not providing Nvidea drivers supporting cuda. The real problem is not virtualization for Windows. Rather it is virtualization for Docker and and to a lesser extent for VirtualBox. Docker containers herald the wave of the future for STEM, including data science and statistics. It also will be critical for reproducible research. Now the Mac is dominant in STEM---go to any related conference to see what attendees are using. Two factors may change this---ARM Macs and Windows Subsystem for Linux. STEM increasingly is running on Linux-based open-source software using multiple software ecosystems that must work together---R and PostgreSQL, R or Python with Spark and Hadoop, etc. These integrated environments are best containerized and reproducibility of research and collaboration of developers and scientists along with bash and git will make Docker and related infrastructure essential. Currently, the Mac excels in this area, but an ARM Mac may not support Docker, Singularity, Kubernetes, etc., even if it does continue to support open-source UNIX software. But now Windows runs containerized Linux. What faculty and researchers use will filter down to students. We are not talking about a 2% loss---it will be much larger for STEM related disciplines in academia and industry. In principal, Apple could support Docker and related technologies, but will they? They could support cuda, but they don't. Even if computing moves to the cloud, what technologies are behind this? Docker, Kubernetes, open-source software, etc. Everyone will need to develop, test and deploy their code from their local machine. This cannot be done using iPadOS and if cannot be done on macOS, the the Mac is done in STEM.
    I feel your frustration but I think it's best to wait a week and see what we're told.
    docno42watto_cobrarazorpitfastasleep
  • Reply 44 of 76
    glhglh Posts: 13member
    It seems to me that there's a good and bad side to going to ARM. The good part is that Apple gets to control the CPU, developing it according to its needs, rather than having to craft its Mac hardware around a CPU developed by someone else without Apple in mind. ARM should enable Apple to market less expensive machines that have better battery life and probably lots of other nice features not available on intel PC's. The bad part is that Apple is cutting itself off from lots of standard software developed by non-Mac people that may never be ported over. See the post above from jharner. It will be extremely interesting to see how this turns out. Myself, I would love to have an ARM MacBook (without butterfly keys), but I don't even know what Docker, cuda etc. are. For people like me, the ARM computers will probably be fantastic. For people like jharner, not so much.
    elijahgwatto_cobra
  • Reply 45 of 76
    thttht Posts: 4,714member
    glh said:
    It seems to me that there's a good and bad side to going to ARM. The good part is that Apple gets to control the CPU, developing it according to its needs, rather than having to craft its Mac hardware around a CPU developed by someone else without Apple in mind. ARM should enable Apple to market less expensive machines that have better battery life and probably lots of other nice features not available on intel PC's. The bad part is that Apple is cutting itself off from lots of standard software developed by non-Mac people that may never be ported over. See the post above from jharner. It will be extremely interesting to see how this turns out. Myself, I would love to have an ARM MacBook (without butterfly keys), but I don't even know what Docker, cuda etc. are. For people like me, the ARM computers will probably be fantastic. For people like jharner, not so much.
    jharner is fearing that Apple's ARM Macs won't have VM support, or won't expose the Unix underpinnings in the ARM version. I think it will. Being on Intel is irrelevant to the Unix software being referred to as "standard software". As long as macOS/ARM is POSIX or Unix compliant, the situation is the same no matter whether macOS is on ARM or Intel. Software still needs to be compiled, and it will be up to the Docker meta platform vendor to provide it. The rest of the tools will be compiled to ARM. If they compile on macOS/Intel today, they'll compile on macOS/ARM when it is available.

    The ARM version of macOS will be identical to the Intel version.


    docno42techconcwatto_cobrafastasleep
  • Reply 46 of 76
    normmnormm Posts: 653member
    elijahg said:
    normm said:
    swineone said:
    In closing, I wager a part of the announcement is going to be an x86 emulation layer with never-seen-before performance. I guess we'll see soon enough.
    There's no reason they couldn't include some hardware support for x86 emulation on their ARM chips.  After all, they make the chips.

    There is: x86 is copyrighted by Intel and Apple would need a license to emulate it in hardware, and possibly software too. Good luck getting an x86 emulation license from Intel to assist Apple ditching Intel's lucrative CPUs.
    x86 is protected by patents, not copyright (unless you exactly copy something).  Most of the instruction set is more than 20 years old, so that shouldn't be an issue.  If there's a legal impediment to implementing newer instructions in software, that could be a show stopper.  Assuming no impediment, it would be better to provide a little hardware assistance, rather than a complete x86 implementation.  Perhaps hardware translation of common x86 instructions into sequences of equivalent ARM instructions? Some tables for hardware recognition of API calls?  Whatever the slowest parts of the virtualization software are, add some hardware to speed them up.  ARM already has virtualization extensions, just as Intel does, for handling high-level issues such as shared memory management.
    edited June 2020 watto_cobra
  • Reply 47 of 76
    Re-engine, Not Re-imagine
    http://bslabs.net/2020/06/12/reengine-not-reimagine/

    This sums it up...

    "Above all: these will be Macs. Macs exist to run Mac software, and Apple’s top priority is to make it as easy as possible to recompile existing Mac apps to run natively on ARM."

    "
    When Apple decided to switch in 2005, they saw Intel’s (then-confidential) roadmap and knew that no one else would be able to match it.

    Today, I believe that Apple is looking at their own internal ARM SoC roadmap and thinking the same thing.

    My last prediction: we’ll be blown away by what Apple’s silicon team comes up with."

    tmaydocno42watto_cobrafastasleep
  • Reply 48 of 76
    glh said:
    The bad part is that Apple is cutting itself off from lots of standard software developed by non-Mac people that may never be ported over.
    That's exactly the point. That's what's holding the Mac and the entire platform back. With x86 compatibility many developers simply won't bother to bring native software to the Mac. With the iPhone and iPad dominating the offices of corporate executives and the creative crowd, a move to ARM will force many choose to go native on the platform, which will expand the available software that now only on x86. Apple is the most valuable company in the world and while it doesn't dominant marketshare, it dominants profit and mindshare. Whatever Apple can offer with ARM it must be so compelling that they are willing to take the risk. I don't think Apple's ARM is going to match INTEL or AMD, I think it's going to leap past them and Apple has the resources to do it.

    x86 was bridge back to custom RISC chips as Apple developed ARM chips over the last decade. No one has matched the success and profits that the iPhone and iPad (computers) have.
    docno42watto_cobrafastasleep
  • Reply 49 of 76
    Rayz2016Rayz2016 Posts: 6,957member
    jharner said:
    Apple has already made it difficult for data scientists by not providing Nvidea drivers supporting cuda. The real problem is not virtualization for Windows. Rather it is virtualization for Docker and and to a lesser extent for VirtualBox. Docker containers herald the wave of the future for STEM, including data science and statistics. It also will be critical for reproducible research. Now the Mac is dominant in STEM---go to any related conference to see what attendees are using. Two factors may change this---ARM Macs and Windows Subsystem for Linux. STEM increasingly is running on Linux-based open-source software using multiple software ecosystems that must work together---R and PostgreSQL, R or Python with Spark and Hadoop, etc. These integrated environments are best containerized and reproducibility of research and collaboration of developers and scientists along with bash and git will make Docker and related infrastructure essential. Currently, the Mac excels in this area, but an ARM Mac may not support Docker, Singularity, Kubernetes, etc., even if it does continue to support open-source UNIX software. But now Windows runs containerized Linux. What faculty and researchers use will filter down to students. We are not talking about a 2% loss---it will be much larger for STEM related disciplines in academia and industry. In principal, Apple could support Docker and related technologies, but will they? They could support cuda, but they don't. Even if computing moves to the cloud, what technologies are behind this? Docker, Kubernetes, open-source software, etc. Everyone will need to develop, test and deploy their code from their local machine. This cannot be done using iPadOS and if cannot be done on macOS, the the Mac is done in STEM.

    The first thing that needs to be remembered is that all this came from a Bloomberg report: the same people behind the "Chinese spy chips are everywhere! EVERYWHERE!" story. So before we all panic and start posting the same message to every story, it's best to wait until next week and see what happens (as Canuckstorm has already said).

    Now, let's assume that this is true.

    Apple has never shied away from making decisions that they know will lose them users if they believe they will it will expand the user base in the long run. Every time this happens there is several months of crying into the forum well, followed by adapting to the situation, or leaving the platform. Shame that this has to happen, but so far, Apple's decisions have kept the MacOS user base growing, even though folk keep claiming that the end is nigh. Having said that, a lot of the panic/wishful thinking posts around here don't seem to make a lot of sense.

    but an ARM Mac may not support Docker, Singularity, Kubernetes, etc., even if it does continue to support open-source UNIX software.
    It 'may' or 'may not' do a lot of things, posting multiple posts panicking about it before anything has been announced doesn't accomplish anything, aside from make it look like only one person actually needs it.

    It's the the vendor's job to make sure their stuff runs on Apple's kit. The switch, if it happens, won't happen today, so they'll have to time to work with Apple to iron out any problems. The UNIX underpinnings of MacOS will remain, so I don't see why stuff like Docker and Kubernetes should be much of a problem. Apple has been beefing up its cloud expertise for the past year, covering areas such as containerisation and java virtual machine support, so I don't really see them making life hard for container software. Linux is already on ARM and so is Docker, so I'm not sure why you're panicking just yet.

    A few other unrelated bits:

    Why not AMD? The whole point of this switch exercise is to give Apple control of the hardware. They can then optimise the chipset for MacOS which will allow them to do more mac-specific stuff at the hardware level. This is not just about Intel hitting roadblocks because this has been on the cards since the Intel switch. They're not going to switch to AMD because that's just moving to the same set of disadvantages: lack of control, lack of optimisations. Speed has never been the only consideration here.

    What about virtual machines? No reason why they won't be supported, but without the X86 then Parallels and VMWare are going to have to work very much harder, which brings us to:

    Apple will add special instructions/special translation layers to make x86 run at native speeds. I don't think this is going to happen, no. If there's one thing we know about Apple it's that they like to hack away the cruft as fast as possible. I'd be very surprised if they started adding it back into their shiny new chipset.  

    Apple is very mindful of the OS/2 principles:

    1. Don't give developers an excuse to stop writing natively for your platform. (OS\2's near native support for Windows)
    2. Don't add code old code that folk then start to rely on and so you can't remove it later on when it starts to hamper the platform (read up on the OS/2 Single Input Queue)
    3. Don't add code that a disgruntled or cash-strapped vendor can use to beat you down or milk you dry with later on. (OS\2's near native support for Windows)

    I think the last one is the main reason why this is not going to happen. Apple is tied to Qualcomm for a couple of years under unfavourable terms until they can come up with their own comms stack. If they're going to add support for x86 then I doubt it's going into the chip. They might come up with a co-processor box that cables in so that any future problems don't impact the architecture strategy. 

    But the best thing to do is just wait and see. Bloomberg isn't very good at tech journalism, so meditate for one more week … and then you can panic.
    edited June 2020 docno42watto_cobrafastasleepp-dog
  • Reply 50 of 76
    tmaytmay Posts: 5,824member
    Rayz2016 said:
    jharner said:
    Apple has already made it difficult for data scientists by not providing Nvidea drivers supporting cuda. The real problem is not virtualization for Windows. Rather it is virtualization for Docker and and to a lesser extent for VirtualBox. Docker containers herald the wave of the future for STEM, including data science and statistics. It also will be critical for reproducible research. Now the Mac is dominant in STEM---go to any related conference to see what attendees are using. Two factors may change this---ARM Macs and Windows Subsystem for Linux. STEM increasingly is running on Linux-based open-source software using multiple software ecosystems that must work together---R and PostgreSQL, R or Python with Spark and Hadoop, etc. These integrated environments are best containerized and reproducibility of research and collaboration of developers and scientists along with bash and git will make Docker and related infrastructure essential. Currently, the Mac excels in this area, but an ARM Mac may not support Docker, Singularity, Kubernetes, etc., even if it does continue to support open-source UNIX software. But now Windows runs containerized Linux. What faculty and researchers use will filter down to students. We are not talking about a 2% loss---it will be much larger for STEM related disciplines in academia and industry. In principal, Apple could support Docker and related technologies, but will they? They could support cuda, but they don't. Even if computing moves to the cloud, what technologies are behind this? Docker, Kubernetes, open-source software, etc. Everyone will need to develop, test and deploy their code from their local machine. This cannot be done using iPadOS and if cannot be done on macOS, the the Mac is done in STEM.

    The first thing that needs to be remembered is that all this came from a Bloomberg report: the same people behind the "Chinese spy chips are everywhere! EVERYWHERE!" story. So before we all panic and start posting the same message to every story, it's best to wait until next week and see what happens (as Canuckstorm has already said).

    Now, let's assume that this is true.

    Apple has never shied away from making decisions that they know will lose them users if they believe they will it will expand the user base in the long run. Every time this happens there is several months of crying into the forum well, followed by adapting to the situation, or leaving the platform. Shame that this has to happen, but so far, Apple's decisions have kept the MacOS user base growing, even though folk keep claiming that the end is nigh. Having said that, a lot of the panic/wishful thinking posts around here don't seem to make a lot of sense.

    but an ARM Mac may not support Docker, Singularity, Kubernetes, etc., even if it does continue to support open-source UNIX software.
    It 'may' or 'may not' do a lot of things, posting multiple posts panicking about it before anything has been announced doesn't accomplish anything, aside from make it look like only one person actually needs it.

    It's the the vendor's job to make sure their stuff runs on Apple's kit. The switch, if it happens, won't happen today, so they'll have to time to work with Apple to iron out any problems. The UNIX underpinnings of MacOS will remain, so I don't see why stuff like Docker and Kubernetes should be much of a problem. Apple has been beefing up its cloud expertise for the past year, covering areas such as containerisation and java virtual machine support, so I don't really see them making life hard for container software. Linux is already on ARM and so is Docker, so I'm not sure why you're panicking just yet.

    A few other unrelated bits:

    Why not AMD? The whole point of this switch exercise is to give Apple control of the hardware. They can then optimise the chipset for MacOS which will allow them to do more mac-specific stuff at the hardware level. This is not just about Intel hitting roadblocks because this has been on the cards since the Intel switch. They're not going to switch to AMD because that's just moving to the same set of disadvantages: lack of control, lack of optimisations. Speed has never been the only consideration here.

    What about virtual machines? No reason why they won't be supported, but without the X86 then Parallels and VMWare are going to have to work very much harder, which brings us to:

    Apple will add special instructions/special translation layers to make x86 run at native speeds. I don't think this is going to happen, no. If there's one thing we know about Apple it's that they like to hack away the cruft as fast as possible. I'd be very surprised if they started adding it back into their shiny new chipset.  

    Apple is very mindful of the OS/2 principles:

    1. Don't give developers an excuse to stop writing natively for your platform. (OS\2's near native support for Windows)
    2. Don't add code old code that folk then start to rely on and so you can't remove it later on when it starts to hamper the platform (read up on the OS/2 Single Input Queue)
    3. Don't add code that a disgruntled or cash-strapped vendor can use to beat you down or milk you dry with later on. (OS\2's near native support for Windows)

    I think the last one is the main reason why this is not going to happen. Apple is tied to Qualcomm for a couple of years under unfavourable terms until they can come up with their own comms stack. If they're going to add support for x86 then I doubt it's going into the chip. They might come up with a co-processor box that cables in so that any future problems don't impact the architecture strategy. 

    But the best thing to do is just wait and see. Bloomberg isn't very good at tech journalism, so meditate for one more week … and then you can panic.
    John Boyd's OODA Loop is appropriate;

    "As one of Boyd's colleagues, Harry Hillaker, put it in "John Boyd, USAF Retired, Father of the F16":

    "The key is to obscure your intentions and make them unpredictable to your opponent while you simultaneously clarify his intentions. That is, operate at a faster tempo to generate rapidly changing conditions that inhibit your opponent from adapting or reacting to those changes and that suppress or destroy his awareness. Thus, a hodgepodge of confusion and disorder occur to cause him to over- or under-react to conditions or activities that appear to be uncertain, ambiguous, or incomprehensible."

    ARM has given Apple an advantage over its competitors, and extending ARM into the PC space will for Apple, extend that advantage to the Mac.

    I doubt that Apple will eliminate Intel anytime soon, albeit they could replace Intel with AMD and gain an immediate performance boost, but for people not needing x86, why wouldn't Apple want to leverage its ARM expertise and TMSC's superior fab nodes?


    https://www.extremetech.com/computing/311529-a-competitive-apple-arm-core-could-finally-break-x86s-long-computing-monopoly

    "Process Nodes or Processor Architecture?

    The question of whether CPU architecture X is better than x86 has been a popular one for decades, where X is understood to mean SPARC/MIPS/Itanium/PA RISC/POWER/ARM and every other architecture under the sun. Whatever conclusions academics might reach, x86 has certainly owned the market, vanquishing every competitive architecture from the PC industry. An Apple-based ARM SoC, however, is a threat to x86 in a way that Windows on ARM isn’t.

    The inevitable performance impact of emulation ensures that no ARM Windows PC is going to match the capabilities of an x86 system — not until applications are natively available for both chips, with equal levels of GPU support and low-level optimization. ARM’s Cortex CPUs, while capable performers, aren’t as powerful in single-threaded code as Apple chips — and given that we’re also talking about moving from mobile phone power envelopes to laptop and desktop power envelopes, Apple has very good reason to want the highest level of single-threaded performance it can get.

    If AMD hadn’t launched Ryzen in 2017, we might frame the coming match-up as an evaluation of the question: “Does Intel build the best CPUs?” Given that AMD’s Ryzen is arguably the better CPU than Intel’s current Core family, however, I’d widen the scope of the query: “What matters more — processor architecture, or process node and engineering?”

    The argument that x86 is at some kind of fundamental disadvantage compared with ARM relies on the idea that low-level features of the ARM ISA convey a substantial advantage over x86, or the fact that x86 CPUs translate native x86 code to internal micro-ops for execution. According to Intel and AMD, the power penalty for performing this kind of decode in hardware is tiny. Studies on the power efficiency of various ISA’s backed up this argument some years ago, claiming that above the microcontroller level, CPU design decisions like cache size, transistor usage, and other aspects of the physical design had a much heavier impact on power consumption than the ISA itself did."

    Apple has the ability to optimize ARM for MacOS, which it is not able to do with x86.
    edited June 2020 docno42watto_cobra
  • Reply 51 of 76
    GeorgeBMacGeorgeBMac Posts: 11,421member
    elijahg said:
    nubus said:
    2)  As the article points out, Apple has successfully implemented a program to design their own chips and SOCs -- and that that is both very difficult and very expensive.   But, once begun it must be continued -- even though it will continue to be both very difficult and very expensive.   The danger lies in the possibility of Apple following other U.S. companies and focusing on stockholder well being over product well being.  If this program is stripped of funding (even a reduction) in order to provide better returns to stockholders, it could take down the whole company -- turn it into another RCA.
    Apple will hit more problems by doing this. Intel stalled due to engineering problems. Microsoft did Vista - and not due to lack of funding. It can happen to anyone - Apple failed on keyboards for 5 years, and on the Mac Pro for 10. Can't blame Microsoft for any of that. This won't make MS, or Apple the next RCA or Xerox, but is it worth taking the risk? If Apple truly cared about the Mac CPU then they would do more updates to their products - the CPU is such a non-issue at this point.
    You make several very good points. The iMacs were essentially abandoned between 2015 and 2019, (the iMac had a spec bump in 2017, and the 2019 one still has no T2 chip) and apart from minor attempts to fix the Macbook keyboards, they saw little love between 2016 and 2020. And of course the Mac Pro went 6 years before an update. So with the lack of attention toward Macs, why all of a sudden is there a CPU switch, when the current CPUs are fast enough for 99% of tasks? I wager a big reason is so Apple can increase their profit margins more on Macs, by using the already developed and paid for tech in the A-series chips in Macs, rather than giving Intel $800 per high-end CPU.

    And yes, when Apple hits the same physics wall as Intel, what happens then? Obviously ARM is a much more computationally efficient architecture than x86 so all things being equal, ARM will beat raw x86, but Apple will have to keep pouring billions into their chip R&D to keep ahead of Intel. Right now they can say they're fastest, but if they lose that crown they'll be wasting billions to catch up when they could have just stuck with Intel.
    The supposed benefits of Apple designing its own custom processor for the Mac isn't only about raw processing power.  A lot of it has to do with adding features to the SoC, that Apple won't be able to accomplish by staying with Intel, and that macOS apps will eventually be able to take advantage of.  Things like:  integrating AI / ML (Neural Engine), security (Secure Enclave), and cellular.  These are the features we know for now.  Who knows what other type of co-processors that Apple can eventually integrate onto the SoC.

    Good point!
    But that will complicate things even further -- especially comparisons that will increasingly be biased against Apple products.   That is, even today, pretty much all comparisons between Macs and other products are done strictly on hardware --which is ridiculous because 1)  Apple is using mostly off-the-shelf hardware anybody can use and, 2)  it ignores Apple's OS, other software as well as their extensive ecosystem -- which is the real thing(s) that set them apart (not the hardware).  

    Now, if you are right (and I think you are), those subjective differences will become even more extensive and profound.
    But, Macs will still be compared to the others based solely on hardware comparisons and the real differences that set them apart will be ignored.
    docno42canukstormwatto_cobra
  • Reply 52 of 76
    mcdavemcdave Posts: 1,919member
    elijahg said:
    nubus said:
    2)  As the article points out, Apple has successfully implemented a program to design their own chips and SOCs -- and that that is both very difficult and very expensive.   But, once begun it must be continued -- even though it will continue to be both very difficult and very expensive.   The danger lies in the possibility of Apple following other U.S. companies and focusing on stockholder well being over product well being.  If this program is stripped of funding (even a reduction) in order to provide better returns to stockholders, it could take down the whole company -- turn it into another RCA.
    Apple will hit more problems by doing this. Intel stalled due to engineering problems. Microsoft did Vista - and not due to lack of funding. It can happen to anyone - Apple failed on keyboards for 5 years, and on the Mac Pro for 10. Can't blame Microsoft for any of that. This won't make MS, or Apple the next RCA or Xerox, but is it worth taking the risk? If Apple truly cared about the Mac CPU then they would do more updates to their products - the CPU is such a non-issue at this point.
    You make several very good points. The iMacs were essentially abandoned between 2015 and 2019, (the iMac had a spec bump in 2017, and the 2019 one still has no T2 chip) and apart from minor attempts to fix the Macbook keyboards, they saw little love between 2016 and 2020. And of course the Mac Pro went 6 years before an update. So with the lack of attention toward Macs, why all of a sudden is there a CPU switch, when the current CPUs are fast enough for 99% of tasks? I wager a big reason is so Apple can increase their profit margins more on Macs, by using the already developed and paid for tech in the A-series chips in Macs, rather than giving Intel $800 per high-end CPU.

    And yes, when Apple hits the same physics wall as Intel, what happens then? Obviously ARM is a much more computationally efficient architecture than x86 so all things being equal, ARM will beat raw x86, but Apple will have to keep pouring billions into their chip R&D to keep ahead of Intel. Right now they can say they're fastest, but if they lose that crown they'll be wasting billions to catch up when they could have just stuck with Intel.
    The supposed benefits of Apple designing its own custom processor for the Mac isn't only about raw processing power.  A lot of it has to do with adding features to the SoC, that Apple won't be able to accomplish by staying with Intel, and that macOS apps will eventually be able to take advantage of.  Things like:  integrating AI / ML (Neural Engine), security (Secure Enclave), and cellular.  These are the features we know for now.  Who knows what other type of co-processors that Apple can eventually integrate onto the SoC.

    Good point!
    But that will complicate things even further -- especially comparisons that will increasingly be biased against Apple products.   That is, even today, pretty much all comparisons between Macs and other products are done strictly on hardware --which is ridiculous because 1)  Apple is using mostly off-the-shelf hardware anybody can use and, 2)  it ignores Apple's OS, other software as well as their extensive ecosystem -- which is the real thing(s) that set them apart (not the hardware).  

    Now, if you are right (and I think you are), those subjective differences will become even more extensive and profound.
    But, Macs will still be compared to the others based solely on hardware comparisons and the real differences that set them apart will be ignored.
    Indeed, benchmarks draw our attention to common parts of a system/platform whilst drawing our attention away from other, often more significant, components.
    docno42GeorgeBMac
  • Reply 53 of 76
    mcdavemcdave Posts: 1,919member
    elijahg said:
    Another point no one seems to have factored is that Intel has tons of extensions to x86 which are essentially never compared in benchmarks against ARM. SSE1/2/3, AVX, MMX, Quicksync etc. Lots of cross-platform software uses these extensions to speed things up, and the code can be directly ported from the huge market that is Windows to the smaller Mac market. Software that makes use of those extensions is much much faster than that which uses general x86 instructions because they come with much less legacy cruft. If Apple switches, cross platform devs aren't going to waste time optimising their software to double the speed on the tiny Mac market, Mac users will just get an inferior experience, again.
    The article does cover custom silicon engines.  Apple has answers for every one you mentioned & what about those that Apple’s SoCs cover which Intel doesn’t? Where are Intel’s CPU AI extensions? 
    docno42watto_cobra
  • Reply 54 of 76
    docno42docno42 Posts: 3,733member
    I so want an ARM MacBook Air - Apple shut up and take my money!

    Also I dunno why everyone seems to continually assume this will be an all or nothing transition.  I don't see Apple eager to get into the higher end CPU business any time soon - unless they have already cracked that nut.  But I find that highly unlikely.  I expect there to be ARM and Intel Mac's coexisting peacefully and utterly transparently to the vast majority of Mac users for some time to  come. 
  • Reply 55 of 76
    docno42docno42 Posts: 3,733member
    elijahg said:
    There is: x86 is copyrighted by Intel and Apple would need a license to emulate it in hardware, and possibly software too. Good luck getting an x86 emulation license from Intel to assist Apple ditching Intel's lucrative CPUs.
    Or they could just get it from AMD.  The x64 instructions came from AMD and Intel adopted them. 

    Or even more reasonably, they just continue to ship the higher end, especially desktop Mac's, with Intel CPUs.  Apple has the software tooling and decades experience servicing multiple CPU architectures concurrently so there is zero need for them to make a binary choice.  Everyone is assuming it's going to be a binary choice but that seems to be a very unfounded assumption to me. 
  • Reply 56 of 76
    docno42docno42 Posts: 3,733member
    elijahg said:
    Another point no one seems to have factored is that Intel has tons of extensions to x86 which are essentially never compared in benchmarks against ARM. SSE1/2/3, AVX, MMX, Quicksync etc. Lots of cross-platform software uses these extensions to speed things up, and the code can be directly ported from the huge market that is Windows to the smaller Mac market. Software that makes use of those extensions is much much faster than that which uses general x86 instructions because they come with much less legacy cruft. If Apple switches, cross platform devs aren't going to waste time optimising their software to double the speed on the tiny Mac market, Mac users will just get an inferior experience, again.
    I dunno - the Apple ARM chips have dedicated ML cores - I could see writers of some of that software being excited to access such power on a desktop/laptop.  And often that functionality is in a library - port the library once and programs that rely on it can more easily be adapted to use it.  It all depends on what Apple bakes into the chips they put in these future Mac's.  It could turn out to be another significant differentiator. 
    tmaywatto_cobra
  • Reply 57 of 76
    docno42docno42 Posts: 3,733member
    Rayz2016 said:
    Apple is very mindful of the OS/2 principles:

    Yup.  I dunno why people are reacting like this is something Apple is being forced to do - Apple won't be making this change (if they do) from a position of weakness, that's for sure!
    GeorgeBMacmattinozwatto_cobra
  • Reply 58 of 76
    What about the pro market with their investment in x86 software running on their $30,000 Mac Pros?  
    GeorgeBMacelijahg
  • Reply 59 of 76
    techconctechconc Posts: 245member
    elijahg said:
    Another point no one seems to have factored is that Intel has tons of extensions to x86 which are essentially never compared in benchmarks against ARM. SSE1/2/3, AVX, MMX, Quicksync etc. Lots of cross-platform software uses these extensions to speed things up, and the code can be directly ported from the huge market that is Windows to the smaller Mac market. Software that makes use of those extensions is much much faster than that which uses general x86 instructions because they come with much less legacy cruft. If Apple switches, cross platform devs aren't going to waste time optimising their software to double the speed on the tiny Mac market, Mac users will just get an inferior experience, again.
    For starters, you should understand that ARM has the same kind of SIMD extensions (called NEON).  I don't think you understand how they are accessed though.  Apple has an accelerate framework that leverages these functions natively.  Developers on Apple platforms aren't writing for Intel or ARM instructions specifically.  If they have an application that can leverage this sort of thing, they are using Apple's Accelerate framework and they are getting this huge performance improvement.  Apple abstracts the CPU specific details, so applications can simply be recompiled and they will also be tuned to leverage the SIMD instructions of ARM processors. 
    Rayz2016tmaycornchipcommentzillawatto_cobrafastasleep
  • Reply 60 of 76
    techconctechconc Posts: 245member
    braytonak said:
    While a new ARM-based MacBook is logical, I would think it would also reinforce the expectation that %desktopOS%-on-ARM = slow. Apple’s confidence in ARM would be clearer if they put it in a MacBook Air, which we already know is a capable machine. 

    Either way, I would replace my 2015 and 2017 MacBooks with an ARM-based model if they ditched the butterfly keyboard in them. If this comes to fruition this year I will find it a very fascinating time, indeed. 
    I really don't understand why there is this perception that ARM is on desktop would be slow.  What leads you to think that?  The single core performance of Apple's A13 chip is within 6% of the performance of Intel's fastest i9 core.  That's with a low wattage mobile chip running on a phone as compared to a much higher wattage desktop based chip from Intel.  The A14 will likely exceed what Intel can do at single core performance and they'll do it on a phone.  On the desktop, it's just a matter of Apple providing a chip with more cores.   Also, as it stands now, the 2 year old A12x based iPad pro is more powerful than a brand new Core i5 based MacBook Air.  Provided we have native applications, performance will not be an issue.

    Also, Apple has already moved away from the butterfly keyboard in all of their models, so that concern is completely a non-issue.
    tmaycornchipthtGeorgeBMacfastasleepwatto_cobra
Sign In or Register to comment.