“Could Apple be working on next-generation Mac hardware that would be powered by an in-house designed processor based on CPU blueprints from British fabless semiconductor maker ARM Holdings plc?” Christian Zibreg reports for iDownloadBlog. “That’s exactly the conclusion one could reach by looking closely at code strings in the macOS Sierra kernel, discovered by Dutch outlet TechTastic.nl.”
“It’s very peculiar that Apple would add support for ARM technology to macOS Sierra,” Zibreg reports. “As you know, all Macs manufactured since 2005 run Intel chips. The Apple appears to be implementing support for ARM chips in the Mac operating system could mean that first ARM-based Macs might appear this year.”
“The macOS Sierra kernel indicates support for the ARM Hurricane family,” Zibreg reports. “Now, ARM’s existing blueprints make no mention of the Hurricane CPU so this is most likely Apple’s internal code-name for a custom ARM-based CPU architecture… An ARM-based Mac notebook would theoretically have a much longer battery life than any existing MacBook with an Intel chip. With its own custom-designed Mac processor Apple would no longer be dependent on Intel’s slowing roadmap. More importantly, it would be able to refresh Macs once per year because any future A-series processors for computers would likely be on the same annual release cycle as the iPhone and iPad chips.”
Read more in the full article here.
MacDailyNews Take: Certainly Apple has OS X running on A-series processors in their labs.
As we wrote back in January 2015:
There is no reason why Apple could not offer both A-series-powered Macs and Intel-based Macs. The two are not mutually exclusive…
iOS devices and OS X Macs inevitably are going to grow closer over time, not just in hardware, but in software, too:
Think code convergence (more so than today) with UI modifications per device. A unified underlying codebase for Intel, Apple A-series, and, in Apple’s labs, likely other chips, too (just in case). This would allow for a single App Store for Mac, iPhone, and iPad users that features a mix of apps: Some that are touch-only, some that are Mac-only, and some that are universal (can run on both traditional notebooks and desktops as well as on multi-touch computers like iPhone, iPad, iPod touch, and – pretty please, Apple – Apple TV). Don’t be surprised to see Apple A-series-powered Macs, either. — MacDailyNews Take, January 9, 2014
The iPhone’s new A10 Fusion chip should worry Intel – September 16, 2016
Apple’s MacBook Pro not likely to sport Intel Kaby Lake processors this year – August 16, 2016
Mac sales to grow in enterprise with new Apple A-series-powered Mac – October 14, 2015
Apple is a semiconductor powerhouse; expect the first ARM-based Macs to appear in 2016 – March 31, 2015
Apple A-series-powered Macs are not only feasible, they may be inevitable – January 15, 2015
Why Apple dumping Intel processors would be disastrous – January 14, 2015
KGI: Apple is designing its own processors for Mac – January 14, 2015
Apple A9-powered MacBook Air? – December 16, 2014
Why Apple will switch to ARM-based Apple A-series-powered Macs – August 27, 2014
Intel-powered Macs: The end is nigh – August 4, 2014
Intel’s Broadwell chips further delayed; not shipping for most Macs until early-mid 2015 – July 9, 2014
Apple will inevitably drop Intel for their own A-series processors in the Mac – June 26, 2014
How long before Apple dumps Intel from MacBook Air? – June 26, 2013
You think MacBooks and Airs are thin now, wait until they run the A-series processors. Smaller processors, much small batteries, no headphone jack make for a machine as thin as a knife.
Mac Pros will cease to be relevant if they put A-series chips in it.
Yeah. Plus the advantage for some to run Windows will evaporate. So will Apple really support both chip architectures for Macs in the years to come? Do we feel lucky punk? Well, DO WE?
Aah, the punk reference will probably be lost on most of the commenters. One of my faves.
Would have been a very different scene if he had started the “talking to an empty chair” thing a few decades earlier.
I gots ta know.
APPLE is aware of the problem.
Just cuz Apple is aware of the problem, doesn’t mean they care enough to address it.
What’s stopping Apple from slapping both CPU’s in a MacBook Pro and giving it the tools to run either MacOS or iOS? It would be just like Apple to do something radical like this.
Don’t think that is gonna happen in the foreseeable future.
They are irrelevant now. Losing capability to run the right software — sorry, that’s windoze ware for the vast majority of businesses– would relegate the Mac to consumer use only.
Why would anyone that needs to run Windows software opt for a Mac instead of one of the many, and in some cases cheaper, Windows alternatives?
That’s why I said the Mac Pro is irrelevant. Does it even make Apple any money? Price of a Mac across the board is out of whack with performance.
Could this be my nano-blade, Mac Pro super cluster?!!
I/3 the size of the old Mac Pro, drop down side with slots to hold gobs of low power nano-blades creating one beast of a super computer.
Hmmm, could be.
I don’t know what that means. BUT I WANT ONE!
Abandoning the option of running/virtualization Windows would be a big mistake.
That wouldn’t be an issue if there is a 2-3x performance delta with a new A series chip. If it is that much faster, virtualization, LLVM, & emulation would be exactly the same as running on native hardware. Plus if they find a way to integrate amd Polaris and/nividia Gpu’s into the design you could easily have a windows system that runs virtually as an llvm with native Directx graphics under boot camp or parallels. This is very possible for apple to do especially with less thermal constraints in a larger form factor. Given the performance of the A10 fusion @ 3000+ single core, a desktop variant with 6000+ single core is jt out of the realm of possibility. And since PA semi had a risc ppc variant that was 2x faster than the core 2 duo 8 years ago when apple bought them…. it is doable.
Keep dreaming. A-series chips aren’t even in the ballpark with the best Intel chips. And Apple is so screwed up right now, they aren’t even getting the full performance out of Intel chips.
I’ve been watched that video, and that is the 2014 retina 5k iMac, not the current one. The current machine uses a 6700k i7 and it benchmarks at 16-17000 just like any PC with that chip. I use one every day as a matter of fact and it’s performance is not an issue. Graphics are, and they should put in a more powerful GPU, but not on the CPU department.
Also, yes, A series mobile chips are not yet as fast as the current skylake line up… but they are as fast as the ivy bridge, sandy bridge, and some haswell generation chips. And there is no reason they couldn’t have a desktop variant that is at the performance level of skylake or twice as fast when they’re getting that level of performance out of a phone chip.
PA Semi did in fact have a ppc RISC variant that was twice, look it up, twice as fast (2x) as the core 2 duo line up in 2008. There is no reason why they couldn’t have been developing that architecture for the last 8 years concurrently with their industry leading mobile chips. Apple dual core designs destroy every other company’s quad and octo core processors in mobile in every metric. If they put their mind to it they could smoke intel since x86 is hitting the wall again just like it was in the early 2000’s. Intel is getting 2-4% performance improvement every generation while apple is still getting 30%+ every generation of A series chip. Those deltas are going to intersect soon and they will pass them whether you like it or not.
Also, as much as I like Linus for his entertainment value, he doesn’t understand how macOS works nor does he understand that when an iMac thermal throttles it doesn’t hurt performance under macOS because of the way it handles resources. Under windows and games it can be an issue, but if you run windows virtually with parallels it’s not a problem either. It’s also telling that he never did a follow up to that video with the new model.
And if you like him, then watch his videos praising the iPhone performance. He still doesn’t understand that thermal throttling doesn’t matter in macOS or iOS, but A series chips don’t do that anyway. You can bang on intel all you want but ultimately their x86 chips are going to be supplanted if performance is sufficient to be able to run emulators at near native speed similar to how Rosetta worked in tiger-snow leopard.
This would be the logical future for a MacBook Air indeed the only future that makes any sense for that brand if it is to remain. It would be a great competitor to Chromebooks and ultra books while texting the water for the acceptance more generally of Mac on Arm while not intrinsically threatening Intel on it in the foreseeable future as the markets would be quite different at this point. It would also allow a true laptop/tablet combo in whatever form Apple might want to take that concept, if it has any wish to do so.
For the purpose of continuity, the first A- processor macs will still have an intel processor. the next step after that is to release an xcode that creates a universal or fat binary. After many years, when very few of the apps in the app store are not universal, apple will drop intel, or even go to AMD. I am predicting that Apple will buy AMD prior to that point. in other words. X86 will be marginalized. Apple will have sufficient control of X86 as well as Arm
Apple has gone through this before, and not just once. They did the transition from Motorola 68k to PPC; then from System 9 to OS X (not a hardware migration, I know, but the move was significant), then PPC to Intel, 32bit to 64bit.
I think this is definitely happening. It has been over ten years that Apple has been on Intel. The percentage of Mac users who run Windows has been rather low even in the beginning, and has been dwindling ever since. Today, it is practically zero. The move from PPC to Intel was forced by IBM’s reluctance to push development of PPC forward beyond G5 chips. Apple needed Intel’s predictable roadmap, and Intel needed apple for the prestige it brought, against AMD. Today, Intel’s roadmap isn’t as clear anymore, and Apple has in-house chip design facility and can plan on their own.
If Steve were still alive, we would have likely already had A-based Macs by now. Without him, it might take another year or two, but they are on their way, for sure.
And we know how it went before, and how it will go this time: a year or two of blue-box emulation (like Classic for System 9 in OS X, or Rosetta, for PPC apps on Intel hardware), and then an optional emulation for a little while longer, for the last of the holdouts. With the total number of Macs out there, as well as the relative market share today considerably greater than twelve years ago (for the previous migration), there is no doubt that the main software players (Adobe, Microsoft, etc) will reluctantly re-code their stuff to run on A-chip Macs.
Unifying code base across Apple hardware will make for much smoother development of solutions for all the platforms (iOS, AppleTV, Mac). The few people who run Windows apps on their Macs will have to hold onto their old Macs while looking for alternative solutions for the future.
Very well articulated, and I believe correct.
Bingo and finally someone who gets it. My gut says there is less interest in apps being written today that need to be installed locally. SaaS is the future for numerous reasons. SaaS locks in an ongoing revenue stream and AI will need to be imbedded and drive many industries and solutions. AI ain’t gonna run locally and Internet speed and latency is improving to the point where I don’t care if something runs locally much anymore.
Only question I have is, will Apple finally bring out the Red box to run Win apps.
That would be most un-Apple thing they could possibly do.
Intel is slowing Apple down, like IBM and Motorola did. Move on Apple.
Stop fooling yourselves. No A-chip is closing the gap compared to Core i7 and Xeon processors. One is designed for efficiency, the other for performance. When you want superior performance, you buy Intel, in a large desktop model. Of you rack it into the lab or studio. Thousands of companies need power, not portability.
But let’s just forget about the chip for a second — hasn’t anyone looked at the software out there? The iOS store is 90% games and time wasters. The Mac store is a ghost town with very few pro level apps ready for business or scalable for enterprise. How many Windows Apps are there? How many of them are technically superior with no Mac equivalent? That’s the issue Cook continues to ignore.
As Apple continues to make the Mac more of a walled garden like iOS, completely dependent on iCloud and a 24/7 internet connection to do anything, and then forge ahead with incompatibility to Wintel x86 applications, then Apple would kiss its remaining professional customers goodbye.
It’s harder and harder to justify the Mac in the workplace as it is, rumors like this only scare away businesses further. A move to all A-chips will show that Cook doesn’t give a damn about productivity. Apple is chasing consumer fashion.
Enjoy the emoji and bubble messages, kids.
so, the train being assembled, with IBM, Cisco, SAP, Deloitte and of course Apple Inc. is not going to make serious inroads into the Enterprise space?; certainly with Mobile computing and in the future with Macs that will blow the antiquated Windows based nonsense away … if you don’t think this will happen, it already is!!
IBM, Cisco, SAP, and Deloitte obviously have influence. But face it, most of these companies are not market leaders anymore. So while SAP might be growing, IBM software revenue is half of what Microsoft is and pretty stagnant.
For specifics, Apps Run the World does a great job analyzing software by market and by type.
You may be surprised how few software companies offer any Mac apps at all. I have been saying for a long time that Apple needs to work with these companies to get native Mac software made, but Cook has obviously not bothered to invest in the Mac. He only cares about iOS app sales.
I think that this might change for enterprise applications given the support of IBM to swift at the server level running on Linux.
The biggest issue I have with the mac right now is the desktop hardware. I have a hard time recommending an iMac, mini, or mac pro to anyone right now when something comparable (and in my opinion better) in speed, upgradability, connectivity, and performance could be built for a fraction of the price.
I still recommend a Mac to people… as I don’t want to be their 24/7 support guy. 🙂
Just wondering if it would be possible for the mac to have both processors with the ability to run in low power mode on the A chip and then in full power mode with an intel chip.
I’m also wondering if this would allow some ios apps to make it to the desktop.
An ipad pro that would allow me to use mouse/trackpad/ports and filesystem like a current desktop (to get work done) and the abilities and portability of an ipad would be very appealing to me and would allow me to use an ipad for more than just an expensive toy or gadget or only for specific tasks that are limited to the ios ecosystem.
That would be worse than an MS Surface!
Simplicity is elegance. Any device that requires a bloated bipolar operating system to handle lightweight touchscreen apps as well as heavy duty processor intensive desktop programs is going to be a highly compromised unit. I don’t want that. Apple claimed it doesn’t want convergence either. My fear is that Cook is actively attempting to sunset the Mac and just go 100% iOS. When that day comes, Apple loses me as a customer. iOS isn’t but a shadow of the power of a Mac.
Hey Pro’s… you know who you are. Start jumping ship now. Apple has been making it fairly obvious that they have outgrown the Pro market. The computers they make now may have Pro in the name, but that’s mainly to separate them from the lesser non-Pro machines. The computer they call Mac Pro is not made is a huge plant in China that can churn out millions of them a day, it is made in a relatively small factory that easily keeps up with the fairly weak “demand” that exists.
I just helped someone buy a late model MacBook Pro… refurbished. Thousands of people like her are buying Macs every day, buying their software from the Mac App Store, buying music from iTunes, syncing to their iPhone. And, if Apple were to replace the Intel processor with something else… as long as THESE folks needs are met, Apple will continue to sell to this group.
If you NEED to run Windows on a non-Windows native machine, I believe your days are numbered. Not very soon, but I’d be looking into which PC maker you’d like to buy from in the future.
If the A10 chip could work simultaneously (parallel) with the intel chip , that would speed up the system considerably. The A10 chip could handle all system processes and leave the intel chip available for X86 processes only … If this would be possibel , it could mean less power consumption and faster top speed execution
“Could Apple be working on next-generation Mac hardware that would be powered by an in-house designed processor based on CPU blueprints from British fabless semiconductor maker ARM Holdings plc?
The macOS kernel, aka XNU, is entirely capable of running on ARM chips and it DOES run on ARM chips. Thus iOS. Therefore, no big deal that dangling bits of RISC code are in the kernel.
The challenge: What to do with all that code in macOS and ALL of its applications, drivers… that are dependent upon Intel CISC processors. You figure out how that’s possible. Don’t bother arguing with me about it as I’m done attempting to explain it to those who don’t understand. Thank you.
But I will point out what to start understanding:
I’LL bookmark this and, if Apple does it, I’LL reply with how they dealt with that challenge. 🙂
If ARM RISC chips provided a significant advantage over Intel CISC chips, if Intel and AMD seriously hit a wall with CISC technology, I could see Apple being motivated. But there are so many barriers to consider. I’ll toss in yet another:
-> Either licensing Intel’s CISC based code OR spending years creating it at Apple from scratch.
Here’s an article from 2009 that gives an idea of what’s at stake with this particular problem as well as the motivation to get rid of proprietary Intel/AMD code:
the x86 instruction proprietary extensions: a waste of time, money and energy
Agner goes in great detail why the incompatible SSE-x.x additions and other ISA extensions were and are a pretty bad idea, but let me summarize it in a few quotes:
• “The total number of x86 instructions is well above one thousand” (!!)
• “CPU dispatching … makes the code bigger, and it is so costly in terms of development time and maintenance costs that it is almost never done in a way that adequately optimizes for all brands of CPUs.”
• “the decoding of instructions can be a serious bottleneck, and it becomes worse the more complicated the instruction codes are”
• The costs of supporting obsolete instructions is not negligible. You need large execution units to support a large number of instructions. This means more silicon space, longer data paths, more power consumption, and slower execution.
RISC gets rid of all the legacy and proprietary Intel/AMD CISC code baggage. But what will replace it all? It would be a massive effort.
“MacDailyNews Take: Certainly Apple has OS X running on A-series processors in their labs.”
Of course they have. It is called iOS. You idiots.
I don’t expect there to be any revolutionary advances in the new Macs, other than progress in Jony Ive’s battle against the third dimension. It seems like Apple can only chase the latest butterfly. They don’t make their products work together so much as they take their obsession of the day and make all the other products work with it. macOS is multitasking, but Apple doesn’t seem to be.