Mark Gurman and Ian King, Bloomberg:
Apple Inc. is designing a new chip for future Mac laptops that would take on more of the functionality currently handled by Intel Corp. processors, according to people familiar with the matter.
The chip, which went into development last year, is similar to one already used in the latest MacBook Pro to power the keyboard’s Touch Bar feature, the people said. The updated part, internally codenamed T310, would handle some of the computer’s low-power mode functionality, they said. The people asked not to be identified talking about private product development. It’s built using ARM Holdings Plc. technology and will work alongside an Intel processor.
If this interests you, take a look at Rene Ritchie’s take on the Bloomberg report. Here’s a taste:
Power efficiency is Apple’s jam. Unless and until they license x86 or swap MacBook to ARM, there’s only so much even the tight and belabored integration they do with Intel will deliver them.
Offloading low-power, low-level tasks to their own silicon, though, is absolutely something Apple could and would do regardless of the main processor architecture. Same as they could and did offload display to their own, custom timing controller when they wanted to bring 5K to the iMac and the industry just hadn’t gotten there yet.
To me, it makes sense for Apple to control as much of the silicon as it can. This is just another step down the road to an ARM Mac.
“This is just another step down the road to an ARM Mac.”
An all-ARM mac? Not going to happen. Intel owns the high end performance crown and they are not giving it up. As long as Apple makes high performance macs, they will have intel chips inside. There’s also the little problem of bootcamp – the huge gains Apple has made in mac sales have a lot to do with the way Intel macs are compatible with the universe of x86 software. If they give that up, they will lose customers who need to be able to run non-mac software at native speed.
Yes, ARM performance numbers have been getting better ridiculously quickly. But ARM is optimized for low power scenarios. Take it outside its comfort zone, and it stops being so impressive. Try to crank up an ARM chip to compete with a 3.7ghz quad core 60 watt i7, and it will start to use more power than the intel chip, and still deliver worse performance.
I miss being able to buy ARM stock.
I could totally see Apple adding optional ARM mode to Power Nap. Peer pressure would take care of the rest, just like it did with 64-bit.
You’re excluding the possibility that performance regressions may be acceptable to some.
I don’t really think that’s the case, but I can’t eliminate it either.
Part of Apple’s market might accept regressions, but another part won’t. Fragmenting the Mac OS code base to allow for two different architectures, one for power users and another for everybody else, doesn’t seem likely. Abandoning the power users doesn’t seem likely either, because they include the developers who make Mac apps and IOS apps.
I could definitely see them fracturing their market. Add a requirement that apps be recompiled to ARM for the Mac App Store and they’d be just about done. A lot of developers would recompile; in most projects, it would be relatively simple. Customer pressure would probably push the rest over, like Microsoft. If the high performance apps don’t follow, so what? It’s not for them anyway.
I don’t know how likely it is, but it’s a lesser transition than what they’ve survived before.
I thought Apple already abandoned the, “power users”?
Don’t mistake a period of missteps and flubs for abandonment.
Every single 3rd party app for an apple device has to be made on a mac. That shows no signs of changing, and as long as Apple keeps their developers inside the mac ecosystem, they will continue to make high end macs. Which will be just as useful for video/audio/photo professionals as they are for coders.
OTOH, if you define “power user” as someone who insists on being able to install their own hardware upgrades, Apple isn’t interested in making hardware for that particular segment anymore.
But what’s the benefit? Implementing power nap funtions on a milliwatt processor and leaving more demanding CPU functions for the main CPU makes sense in terms of achieving ever better battery life.
Switching away from Intel completely – I don’t see the upside. They are already one of intel’s single biggest customers, with tons of say about the shape of Intels roadmap. (Intel never would have devoted time to upgrading their integrated GPUs if not for pressure from Apple).
Maybe nothing. But what if it led to, say, 24 hour battery life for apps that don’t demand a lot on the CPU? It could absolutely be interesting.