Slashdot Mirror
No More Intel Inside, Apple Plans To Use Its Own Custom-Built Chips in Mac (bloomberg.com)
Apple is planning to use homegrown custom-built processors in its Mac line of computers, ditching Intel, the processors by which powers Apple's current line of computers, Bloomberg reported on Monday. The company could make the switch to its own chips as early as 2020, the report said. From the report: The initiative, code named Kalamata, is still in the early developmental stages, but comes as part of a larger strategy to make all of Apple's devices -- including Macs, iPhones, and iPads -- work more similarly and seamlessly together, said the people, who asked not to be identified discussing private information. The project, which executives have approved, will likely result in a multi-step transition.
The shift would be a blow to Intel, whose partnership helped revive Apple's Mac success and linked the chipmaker to one of the leading brands in electronics. Apple provides Intel with about 5 percent of its annual revenue, according to Bloomberg supply chain analysis. Intel shares dropped as much as 9.2 percent, the biggest intraday drop in more than two years, on the news.
The shift would be a blow to Intel, whose partnership helped revive Apple's Mac success and linked the chipmaker to one of the leading brands in electronics. Apple provides Intel with about 5 percent of its annual revenue, according to Bloomberg supply chain analysis. Intel shares dropped as much as 9.2 percent, the biggest intraday drop in more than two years, on the news.
Few of Apple products involve as many people as this would 2 years ahead of time. If they can ship this in two years, they've been working on the desktop processors and chipsets for a couple years already. Hell, if this ships in 2 years they would need to be involving third party software parties already. Unlike their Chinese factory workers they can't just suicide a couple of those to make an example of leaker's either :p
I think it used to be. Now it's people pretending to be those things.
Confucius say, "Find worm in apple - bad. Find half a worm - worse."
This has been in the works since the start of the LLVM project.
A few years back, Apple and the LLVM project made the announcement that code compiled for x64 with CLang was finally able to run unmodified on the ARM architecture. By compiling into an intermediate language, Apple has made it possible to write code that should run unmodified on any LLVM platform so long as all libraries are present to support it and that the code doesnâ(TM)t depend on hand written assembly or code which needs direct access to the stack for the platform ABI.
With the transition from PPC to x86, a lot of transitional APIs such as Carbon were introduced. Also, the principle of fat binaries were made common place in such that each application or framework could be compiled for two or more platforms. Consider that Apple had Yellow Box running in house on x86, PPC and Sparc.
Over the years, Apple has progressively deprecated any API which was too tightly bound to a single architecture one by one. All code not compiled with LLVM has been slowly killed off. The App Store on IOS and MacOS have set restrictions as to what system calls could be made. Most performance oriented libraries such as QuickTime have been altered, enhanced, etc... to slowly eliminate the need for hand written code. Apple has bullied developers into never writing Mac targeted compilers and instead focused them on compiling to IL or Swift/Obj-C first.
Just like Microsoft has been trying to universally move to .NET for a retargettable platform, Apple has moved to LLVM.
There is no technical reason why Mac couldnâ(TM)t run on ARM today. Iâ(TM)d imagine Apple has had Mac OS running on an iPad Pro for some time. The main difference would probably be the type of SSD they employed.
Performance wise, current Apple chips should have more than enough CPU to handle tasks at least as well as the m3 chips in the Mac Book. 4GB or RAM should be enough for most users as well. PCIe for M.2 storage should be a trivial change for Apple. And Apple has already said they are preparing their own GPU core. I would expect that GPU core to be comparable to Intelâ(TM)s from the beginning. Unlike other GPUs, OpenCL and even most of OpenGL are optional as Apple will dictate the OS graphics API. Of course they already have a strong enough following among game developers that if they cut corners, the developers will suck it up and continue.
What most people mention is a problem is that Mac has a huge dual boot audience. I would expect an agreement with MS or Amazon to happen to push cloud based virtual desktops. Many enterprises get security by using Mac because malicious Mac software doesnâ(TM)t tend to screw with virtual machines. So they deliver the enterprise desktop on a VM and let the user mess with their Mac however they want.
What I expect to really shake things up will be an announcement from Apple to support Windows for ARM as an application/subsystem. Then I expect to see Microsoft support their x86 emulator possibly with acceleration on Mac. Unlike Transmeta. Apple working with Microsoft could easily make their x86 JIT perform better than real hardware. This has to do with how branch prediction, pipelines and cache work.
I honestly donâ(TM)t see anything particularly amazing about this other than the long time it took to get here. Apple must have assessed that the lost business will be offset by the profits gained. Of course, I have been hoping to buy a new Mac Mini this year, my 2012 model is getting old. If Apple releases something âoerespectableâ for $500 or so, Iâ(TM)m in. I only need it for testing Mac builds.
I have to disagree with you there. I work for a company that does communications marketing and they're primarily on Macs. They most assuredly are not "just pretending" to be designers or artists.
I also took a tour of some of the major recording studios in Nashville last year and guess what? They still used Macs almost exclusively, even when doing so required special effort (such as finding custom rack mount kits to mount the "trash can" 2013 Mac Pro in their acoustically isolated rack enclosures).
The Apple userbase may be declining in areas it traditionally dominated, like the education sector and 3D animation work. But the creative fields, in general, are still big customers for Apple products.
I don't think it's necessarily bad if Apple parts ways with Intel and makes its own CPUs .... but as others said, the whole switch to Intel enabled a lot of possibilities with running Windows in a dual boot mode, or ensuring virtualization software worked 100%. I think that's a big negative if Apple discards it as unnecessary with the new chips.
Uhh... what is so hard about recompiling high-level code to work on a different architecture? This isn't the 1980s where most software is written in assembly.
There are still plenty of applications that at certain levels are still written in assembly. Device drivers and gaming engines come to mind. It doesn't matter how good your compiler is, nothing beats hand optimized assembly for just raw speed.
I read at +2. If your post doesn't reach that level I will not see or respond to it.
I agree though, that this is probably Apple trying to extract some sort of concession from Intel, be it pricing, input in, or influence on, the feature set or direction of development, or all of the above. The threat of a switch to ARM may seem more credible than the threat of a switch to AMD, perhaps, but either seems incredible to me.
https://www.eff.org/https-everywhere
As I said, IBM and Motorola CPUs were sinking ships. Intel is not that.
Apple does not manufacture their own chips, or anything at all actually. So they are either paying Intel, or they are paying TSMC/Samsung for manufacturing + ARM licensing. I doubt the costs are substantially different. The gain would be in control. But for all the reasons I listed, that would be a high price to pay for control.
Moreover, end users would bear the brunt of those costs, and have little or nothing to show for it at the end of the day in terms of performance improvements. When Apple jumped CPU ships in the past, it benefitted end users. I am hard pressed to think of a single benefit of an architecture swap to end users at this point, but I am all ears if anyone has any ideas.
https://www.eff.org/https-everywhere
Apple was one of the founders of ARM. An ARM license doesn't cost them very much at all.
Manufacturing chips on the scale of Apple's iPhone means the cost per chip is relatively low. The NRE is done; at that point the more you can manufacture the cheaper it is per unit. Certainly paying Intel to manufacture chips and sell them (even at the margin that Apple can command) is going to be more expensive for Apple.
As for benefits... Apple has always wanted to own the whole shebang. They get to know ahead of time what the schedule's going to be, they get to dictate the chip's abilities, and they already have the design capability in-house. I *think* it'll be cheaper for Apple, with lower thermals and higher efficiencies with potentially a better designed chip. Whether the user sees benefits from that is up for debate.
There are certainly issues with compatibility and emulation, and I don't have a good answer for that. I suspect, if Apple go ahead and do it, they will have a good-enough answer for a transition. As for recompiling etc., they'll just require an ARM64 variant of any app in the app-store for a year or so ahead of any transition in order to be listed. That'll be sufficient IMHO to get almost everyone on-board.
Physicists get Hadrons!
There are a few other issues. It's not just Bootcamp, it's also WINE. A lot of the 'Mac' games are actually Windows games with a bundled version of WINE. Note that this is WINE, not WineLib. The WINE team now actively discourages use of WineLib because you get odd issues from programs that expect COFF linkage behaviour instead of ELF, for example, and porting is a lot easier if you ship WINE's PE/COFF loader rather than relying on the host platform's ELF loader.
ARM has limited virtualization support - or usefulness for that matter
I'd disagree with the first part of this. ARM's hardware virtualisation acceleration is on a par with Intel's. I'd agree with the latter part though. The common use of virtualisation on macOS is to run Windows in a VM. Unless Qualcomm's ARM Windows platform becomes a lot more popular, I don't imagine there being much call to run ARM Windows on Macs.
Apple loses the economies of scale that Intel enjoys, eating into cost savings
That one depends a lot on how much they can share designs with the iPhone / iPad. If the Mac chips are just a higher core count and clock rate than the iPad versions, then they may get some of this back. Mac, plus iPhone, plus iPad sales add up to about 50% of the total number of PC sales, so they're only a factor of two off.
All existing MacOS apps and games, gone (without either substantial developer support for rebuilds or else subpar emulation, which is not a UX Apple is likely to support)
Note that Apple has done this before. In both the PowerPC and Intel switch, they shipped emulators that allowed you to run existing code. Modern emulators are now pretty good at adjusting call frames so that you can call from emulated code into native code. If you keep the same structure layouts in your legacy and emulated platform then you can share pointers between them. Most Mac apps spend a huge proportion of their total CPU time in Apple-provided system libraries, which is a big part of why Rosetta was so fast in the PowerPC to Intel switch: most existing code (including all of the standard UI drawing, text rendering and layout, and so on) code ran as native x86 code, so the emulator only had to be fast enough that the rest didn't become a bottleneck. OF course, it helped that the laptop Intel cores were about twice the speed of the Freescale ones that they replaced (and had more cores).
At the end of the day, it's really just trading one master (Intel) for another (ARM)
Again, not quite so clear cut. One of the big reasons for the Intel switch was their relationship with Intel versus IBM / Freescale. Apple was the sole customer for both IBM and Freescale in the relevant markets, which meant that they were paying a huge proportion of the total R&D, yet someone else was in control. When they switched to Intel, they were the single largest customer, but were only about 20% of the total.
I suspect that, given the massive growth of cloud stuff, that at least one of Google, Amazon, or Microsoft (possibly all three) is now a larger customer than Apple, which means that Apple is no longer able to demand exactly what they want. There's some evidence for this: Apple customers keep complaining about not being able to buy MBPs with 32GB of RAM, Apple says they'll ship them as soon as Intel produces a CPU that can handle 32GB of LPDDR4, Intel still isn't producing laptop chips that support LPDDR4.
Their relationship with ARM would, again, be very different. Apple is an ARM Architecture Licensee, which means that they are allowed to (and do) design their own ARM-compatible cores in house and ship them as long as they pass the conformance tests. There are also over half a dozen other ARM Architecture Licensees (you can find an abridged list of these in the ARM ARM if you look at the hardware register value that provides the vendor ID, though some companies - including Apple - request not
I am TheRaven on Soylent News