Apple could adopt ARM for laptops, but why would it?

Apple logoThe Apple/ARM rumor du jour is that Apple will transition its entire portable Mac line to ARM-based CPUs, dropping Intel altogether. Sources speaking to Semi Accurate claim this is a "done deal," and the move should happen by 2013, when a 64-bit ARM A15 core becomes available. While a future generation of Apple's A5 processor could make some sense for something akin to the MacBook Air, the claim that Apple will ditch Intel wholesale for ARM just doesn't add up.

Semi Accurate's sources say Apple is already working on this transition. From an OS point of view, it wouldn't be that difficult—iOS and Mac OS X are both based on more or less the same code base, and iOS already runs on ARM.

"So short story, x86 is history on Apple laptops, or will be in 2-3 years," claimed Semi Accurate, based on its sources' information. "In any case, it is a done deal, Intel is out, and Apple chips are in."

Semi Accurate boosts this by saying its "moles" were right about Apple moving away from NVIDIA GPUs, keeping some laptops on Core2 Duo processors, and that Apple would be the first to adopt Thunderbolt (aka Light Peak). While that might be a good track record, those predictions were pretty safe, obvious bets. Apple has moved away from NVIDIA GPUs before, and we noted that moving to Intel's Core iX series processors (Nehalem and now Sandy Bridge) would mean ditching the NVIDIA 9400M and 320M controllers Apple had used for a few generations of Core2 Duo-based machines. We also explained why last year Apple couldn't yet upgrade its most compact laptops—the 13" MacBook Pro and MacBook Air—from Core2 Duo processors, mostly due to space and power concerns, as well as limitations in Intel's product line. And since Apple was heavily involved in the development of Light Peak, it's no surprise the company was the first to integrate the tech into its products.

Here's what's wrong with the prediction. A processor using four 64-bit A15 ARM cores running at 2.5GHz in 2013 is expected to have performance on par with a 2GHz Core2 Duo available today. Apple has already moved its MacBook Pro line to Sandy Bridge chips, and should be moving the MacBook Air to Sandy Bridge later this summer. Those chips already outperform Core2 Duo chips by a quantum leap at similar clock speeds.

In the next year or so, Intel will release an update to Sandy Bridge called Ivy Bridge. This new generation of processors will utilize Intel's new 3D transistor technology on a 22nm process, bringing either significant power savings in low voltage designs, speed improvements at higher voltages, or some combination of the two. Effectively, Intel could make a 22nm clone of Sandy Bridge processors with identical performance at close to 50 percent of the power requirements. Imagine the performance of today's MacBook Pro with something like double the battery life—there's a lot more to it than just the CPU power requirements, but you get the idea.

A major benefit in ARM's favor over x86 processors is that they currently provide mobile devices with ample performance combined with extremely long battery life. So from this perspective, a laptop running current generation low-power ARM processors would get amazing battery life in exchange for constrained performance. On iPhones and iPads, which only one run application at a time, we accept this trade off. It doesn't seem likely that users are ready to make that sacrifice when using Mac OS X (at least, not yet). Conversely, pushing ARM processors to Core2 Duo-like performance would erase most, if not all, of ARM's low-power benefits, and would suck juice from a laptop's battery about as quickly as comparable x86 processors.

With no clear performance or efficiency benefit derived from moving to ARM, it doesn't seem likely Apple will be ditching Intel wholesale for its notebooks, even two years from now. However unlikely, though, that doesn't necessarily mean that Apple won't use ARM processors for future Mac-like computers.

One factor that could lead Apple down the ARM path is that Steve Jobs has a history of preferring custom hardware. Consider the high-density 3.5" floppy disk drives that the original Macintosh used, which weren't widely adopted by DOS PCs until 1988. At Next, Jobs continued his preference for unique, custom hardware with the distinct Next Cube, which used Motorola processors like the Mac instead of the x86 processors used in PC clones. It also relied on special graphics cards which supported Display PostScript, a special version of Adobe's page description language for high-resolution printing. When Jobs returned to Apple, the company sold the universally reviled USB "puck" mouse that debuted with the original iMac in 1998 for several years before finally offering the Apple Pro Mouse. And, Jobs clung to the PowerPC platform (which Apple originally had a hand in designing) for years after Intel-based PCs had far surpassed Macs in raw performance.

Apple was also originally involved early on in the design of what became known as the ARM6 architecture, used in the Newton PDAs of the early 90s, so Apple has a long history with ARM. Apple in recent years acquired two processor design companies known for their aptitude for low-power chip designs. One is PA Semi, whose top engineers are now running the "ARM CPU architecture team" within Apple. The other is Intrinsity, known for its low-power Hummingbird ARM variants. With all this internal knowledge and skill, it is entirely likely Apple could engineer a custom ARM processor geared towards MacBook-like performance with iPad-like battery life. That capability could prove tempting to Jobs, who could then say that "Apple's notebooks have something no one else has."

The other factor which could lead to ARM-based portable Macs is the gradual melding of iOS and Mac OS X. Developers have seen Apple moving in that direction for some time, but Apple explicitly said it was doing so when it unveiled Mac OS X Lion last October. Jobs described Lion as "Mac OS X meets the iPad," noting that it would incorporate a number of iOS-like technologies including Launchpad, auto-saving files, auto-resuming applications, full-screen apps, and the Mac App Store.

One reason that makes iOS seem so fast on modest hardware are the constraints presented to the user. Only one application is active at any one time. Background processes are limited to certain power-optimized functions (like music playback or push notifications). iOS is clearly the future of Apple's operating system efforts, so if iOS slowly overtakes Mac OS X, and users become accustomed to some of these constraints, it seems entirely possible that Apple could build a MacBook Air using a higher-performance A5 descendant that works less like what we're used to today and perhaps more like the iPads of the future—with a keyboard attached. (The current MacBook Air isn't far off from this description as it is.) Such a device could satisfy the computing needs—Web browsing, e-mail, Netflix streaming, instant messaging—for a large portion of people already acclimating to tablet use.

Finally, it's also possible that Apple could realize some cost savings by using its own ARM-based designs. Apple's low end starts at $1000, so if there are enough savings going the ARM route to push those prices down to $800 or so, it's possible Apple could make significant gains in its already growing Mac sales.

With Intel's current roadmap in mind, though, it just doesn't seem wise for Apple to dump x86 for ARM anytime soon. Perhaps Apple could combine its low-power ARM know-how with Intel's 22nm process technology to result is some super amazing ARM-based chip that could outdo Intel's mobile processors on a performance-per-watt basis, but that is a big stretch. All the information available indicates that Ivy Bridge would wipe the floor with a "performance" ARM-based processor for the foreseeable future, and we have a hard time believing users would willingly downgrade from an Ivy Bridge-based laptop to an ARM-based laptop all other things being equal. There are factors that combined could push Apple in the direction of ARM, especially at the low end, but those factors rely on a lot of big ifs.

Source: Ars Technica

Tags: Apple, ARM

Add comment

Your name:
Sign in with:
Your comment:

Enter code:

E-mail (not required)
E-mail will not be disclosed to the third party

Last news

Galaxy Note10 really is built around a 6.7-inch display
You may still be able to download your content
Facebook, Messenger and Instagram are all going away
Minimize apps to a floating, always-on-top bubble
Japan Display has been providing LCDs for the iPhone XR, the only LCD model in Apple’s 2018 line-up
The 2001 operating system has reached its lowest share level
The entire TSMC 5nm design infrastructure is available now from TSMC
The smartphone uses a Snapdragon 660 processor running Android 9 Pie
The Samsung Galaxy A5 (2017) Review
The evolution of the successful smartphone, now with a waterproof body and USB Type-C
February 7, 2017 / 2
Samsung Galaxy TabPro S - a tablet with the Windows-keyboard
The first Windows-tablet with the 12-inch display Super AMOLED
June 7, 2016 /
Keyboards for iOS
Ten iOS keyboards review
July 18, 2015 /
Samsung E1200 Mobile Phone Review
A cheap phone with a good screen
March 8, 2015 / 4
Creative Sound Blaster Z sound card review
Good sound for those who are not satisfied with the onboard solution
September 25, 2014 / 2
Samsung Galaxy Gear: Smartwatch at High Price
The first smartwatch from Samsung - almost a smartphone with a small body
December 19, 2013 /

News Archive



Do you use microSD card with your phone?
or leave your own version in comments (16)