Is Windows for ARM a Dead End?

  • Share
  • Read Later

Over at Cult of Mac, John Brownlee has an in-depth explanation of why it seems unlikely that Apple intends to ditch the Intel chips inside Macs for ARM-based ones akin to the processors it uses in the iPhone and iPad. His reasoning is long and technical–though he does a nice job of explaining it clearly–and it boils down to the fact that Macs need more computing horsepower than current ARM processors can provide. By the time ARM chips get faster, he says, Intel ones will have become more power-efficient–and Intel should have the overall lead when it comes to zippy performance and respectable battery life.

Brownlee quotes my friend David Kanter of Real World Technologies, who knows more about the insides of computers than I ever will:

The fact is that there is no ARM processor today, nor any that will be coming in the next five years, that are suitable for Appleā€™s existing models of laptops and desktops…On a deep and profound level, there is no technical advantage right now for Apple to switch to ARM across its laptops and desktops.

The story leaves me thinking that my instinctive take on things–that ARM-based Macs are a real possibility–isn’t well grounded in technical reality, at least if you define “Mac” as “A desktop or laptop computer running the current version of OS X and existing OS X applications.”

And it also left me wondering: If ARM-based Macs don’t make sense, what does that say about the ARM-based Windows computers that will ship once Windows 8 is available?

Anyone who’s ever used a tablet based on an existing Intel CPU knows why Microsoft is building a version of Windows for ARM. Intel tablets are too chunky, run for too little time on a charge, and are often burdened by noisy fans. By bringing Windows to ARM, Microsoft is giving PC makers a shot at building Windows tablets that don’t feel like ungainly antiques compared to the iPad.

But if Brownlee and David are right that Intel will make mobile processors that are superior to ARM-based ones from companies such as Qualcomm and Nvidia within a few years, Windows for ARM could turn out to be a stopgap. If an Intel-based Windows computer was just as thin, elegant, and power-efficient as an ARM one, you’d probably prefer it, because it will run all existing Windows applications. (ARM-based Windows machines won’t run old-style Windows programs.)

Of course, Microsoft is so very far behind in the tablet business that it can’t afford to wait a few years to see if new, improved Intel chips erase ARM’s advantages. So it’s hard to argue that it’s making a grave strategic mistake by developing a version of Windows for ARM processors. By 2015, it should be clear whether Wintel represents computing’s past or its future–remind me to reassess the situation then, will you?

(MORE: Why the BlackBerry Is All Thumbs)