Apple to ditch Intel – report Apple may dump Intel as its CPU supplier for the Mac, reports Bloomberg. The newswire quotes “people familiar with the company’s research” as saying Apple is “exploring ways” to use its own silicon in future Macs, as it has become frustrated with Intel’s inability to deliver chips that can be built into thin and light devices …
This post has been deleted by its author
Watch OS X (or XI?) drop to sub-Linux levels of marketshare as people discover they can no longer run Windows in bootcamp, or if they can, it's in an emulator and running rather slowly compared to a Core i-something.
I don't think Apple is going to drop x86/64. Not unless Microsoft is going full ReTard too.
Maybe an x64-almost-compatible-but-only-in-Apple-gear processor?
>
I don't think Apple is going to drop x86/64.
<
Why not? It would be revolutionary, beautiful, truly magical and whatever else Mr. Cook can think of.
And it would be bought: because Apple fans don't give a poo about what's inside. It's inside an Apple computer, so it has to be top quality and it will "just work".
It's like asking a Rolls Royce owner what spark plugs he prefers: The answer would, most likely, be something along the lines of "I say, I shall ask my butler to tell the driver to query the mechanic for you. And would you excuse me now, it is time to shoot an antelope."
How accurate is a Rolex? Who gives a fsck. What thread is a Pierre Cardin dress stiched together with? Couldn't care less.
Fashion ware. Veblen goods. Apple. No need to be rational.
This is 2012, not 1999. While I use both Windows 7 and OSX all day long, I can't think of a single Windows application that would be worth the bother of installing Windows (or even Parallels) on my Mac. Even Office for Mac is cleaner and faster than the equivalent on Windows 7.
I think that the most popular use for BootCamp, Parallels, VMWare, etc is probably to play games. They're still routinely released for Windows but not for the Mac. Having a quick glance at the current Amazon charts, if you exclude Windows 8 then the first thing not available for the Mac is "Honestech VHS to DVD 5.0 Deluxe" at number 24 (though, in fairness, I think not all variations of Quicken are available).
That said, per NetApplications Apple had 4% marketshare before it switched to Intel; more than six years later that's moved up to 7.2%. Linux has remained just below 1% across the entire period. There's basically no chance of Linux overtaking the Mac even if Apple were to make any sort of drastically unpopular change — there seems to be a glass ceiling Linux can't break through while the Mac has managed to endure regardless of mismanagement.
Depends upon the particular market, I guess. The high end (i.e. CAE tools >$10k) desktop in the electronics engineering world is now dominated by RHEL, with Windows 7 losing ground. This is true of most other computationally intensive engineering fields as well. Mac's share of these markets is, as it has always been, exactly zero. When it comes to the consumer desktop, I suspect that most Linux users (with the exception of a vocal evangelistic minority) don't much care who is king of the hill on the boxes at Currys.
So... you're saying that OSX isn't an acceptable alternative to Windows -- because it doesn't run proprietary Windows code? Sounds like circular reasoning to me. It's also unlikely to be true except within specific business environments -- which probably already mandate Windows for IT management reasons anyway.
I've managed engineering groups, large and small, for 30 years, and I've never encountered a situation where I *had* to support the proprietary hooks in Office. I've been obliged to use Windows in many of those situations, but there was never a good technical reason for doing so. (And if you're using Word to prepare complex documents, you're really using the wrong tool! Professional technical writers and publishers still eschew Word.)
For all the discussion so far, the only reasonable argument for a 'killer application' is for Windows games.
About that total deal breaker:
http://en.wikipedia.org/wiki/Microsoft_Office_for_Mac_2011
Seems like it supports VBA on a Mac.
Office for Mac is probably largely built built with a common C++ core as the Windows version. So if MS can't read/write files without breaking stuff between Mac and Windows versions, that would imply to me that you should not rely on any future versions of Office on Windows opening documents without breaking stuff. OfM is probably more compatible than things like Office on WinRT at the moment
You're clearly using older versions of the software - that was always my experience too, but MS seem to have really got their act together with Office '10 and '11.
After over 12 months moving data between the two environments, I've yet to see anything fail in any way.
Quite impressive if the documentation is as weak as has been mused in the past...
In this age of dynamic binary translation and API wrappers, Mac users were able to play Skyrim the day it was released thanks to Wine-X or Cider "ports". Why bother installing a bloated OS into a VM when you can have your app running seamlessly and at quasi-native speed, directly in the native env ?
The move to Intel chips was a success back in the days mostly because Motorola (and to a lesser extent, IBM) had failed to keep up in processing power. It was painfully obvious then that Macs were lacking in performance and no Photoshop tricks could hide that sinking feeling in the fans' minds. The performance boost that came with the first Macintels certainly helped the architecture transition (universal binaries, Rosetta binary translation) go smoothly from the user viewpoint.
Somehow I doubt it would go as well, moving from Core iXXXX to Ax.
It makes more sense that Apple will fuse its OS X branches, until the very same apps can run on anything they produce using the same mechanism as before (universal binaries). Expect it to go a lot more smoothly than the Win8 transition on the Microsoft side. Then they can consider ditching Intel.
"No need to be rational?"
M Gale, All through the 90's and 00's it was a few rational Apple customers among millions of personal computer users who persistently purchased machines which "just worked" over balky, clunky, virus laden, Windoze PCs.
(They're not much better these days.) So as you say, "Who cares what's in it?" Who indeed, just as long as it works. That seems pretty rational to me.
If you really have to take the joke seriously:
The hitch with Apple is that while "it just works" most of the time, it just works because there isn't anything that you don't need. And the need is defined by Apple: If we don't do it, you don't want it.
Your opinion seems to me like calling a Nr.12 Torx screwdriver a good toolkit. Good screwdriver no doubt, but a little less useful if you need a soldering iron.
If it's commercial, then it will be done for Windows (thinking of, for example, CNC controllers); chances are, if it's cool and interesting, someone might tinker about with it on Linux. On Apple OSs you eat what you're given.
Mahlzeit.
"The hitch with Apple is that while "it just works" most of the time, it just works because there isn't anything that you don't need. And the need is defined by Apple: If we don't do it, you don't want it."
On OSX? What utter, utter bollocks. OSX is just as "open" as Windows in that respect. it's a desktop on which you can install applications and applications (non-apple) exist in their thousands.
Charitably, I can only assume you're getting confused with IOS...
I assume that this is a troll, but... seeing as Dassault Systèmes (Solidworks) estimates that only a fraction of one percent of OSX machines have installed Windows (any version), I doubt if Apple is losing any sleep over it. Recent versions of Boot Camp have already dropped support for anything but Windows 7 because of a near total lack of interest.
I find it highly doubtful myself but there are some intriguing possibilities. Microsoft is in business to sell Windows licenses more than anything else. If they cut a deal with Apple to allow a special version of Windows RT for Boot Camp that allowed desktop apps under x86 emulation, this speed things up considerably by having the OS and APIs be in native code. Sort of like WINE but with an emulator.
Remember the emulator for running x86 Windows apps on the DEC Alpha under NT/2000? It was called FX!32 and had a remarkable feature unlike other emulators: it saved the translated code produced by the emulator. This meant the app's performance increased with use as more and more of it became native and optimized. (Some hints suggest Microsoft used something similar in the emulation of the original Xbox on the Xbox 360, which is why a download is needed when an old Xbox game is run for the first time on a 360.) In this day and age most popular apps could have existing translated code downloaded automatically, greatly speeding up the process.
If Apple and Microsoft collaborated on such a scheme Microsoft would of course retain the rights to use the technology on other ARM platforms, after a period of exclusivity for Apple, offering a path for Windows RT to be leveraged further against Intel the next time Microsoft needs something Intel doesn't want to give them.
I guess it's always possible that when those "people familiar with the company's research" say that Apple is "exploring ways" to use its own silicon in future Macs what's actually being proposed is the consolidation of every non-CPU function into a single chip, keeping the Intel processor and moving to a [pretty much] two-chip design? They're already doing soldered RAM and SSD, the iPad designs are triple-sandwiched CPU+GPU+RAM chips and peering at the current Macbook Pro motherboard on Google images appears to show tens of chips across the board.
They're already using the on-board GPUs but I guess that building RAM+SSD into a single unit would be a good saving? It doesn't feel like something that's likely to come onto the market from anyone else.
We can be sure ARMv7 and possibly prototype ARMv8 versions of OSX are happily running in Cupertino. I'd be surprised if much translated to product on notebook/AIO before 64-bit is viable so most likely 2-3 years out before a possible transition from x86. Other research projects using hybrid x86/ARM (e.g. GPU and iOS focussed) seem a bit more likely to be productized meanwhile although given that high-margin iPhone sales account for majority of Apple revenue and underwrites high stock valuations, seems unlikely this is a high priority for Cook and co. in short term, although worth doing even if only to pressure Intel on price and function.
Over a 5 year perspective, odds IMO must be better than evens Apple goes x86-free if things go well on proprietory silicon route but there are lots of if and buts. Intel could stumble on 14nm or 10nm node, Apple could decide to build their own FABs, impossible to predict.
Research. One thing for sure, you have to think well beyond the products you can buy in the shops today and the predictable incremental improvements underway for next year to grasp what drives this kind of change Escape being trapped in the now like journalists and most of the blogosphere. These are strategic decisions which take years to unfold, just like the Google trajectory with Android and Microsoft with Windows 8 and beyond.
That was the feeling I was getting from the article: that a move away from Intel would be something Apple would do like five years down the road IF conditions were favorable. This sounds more like back-burner stuff: stuff to consider down the road, not stuff that's on a priority track. Jumping to PowerPC and then to Intel in the past made sense since both processor lines were stalling in the face of continuing x86/x64 development. Now processor development IN GENERAL is starting to stall because of physical limitations (processors can only be so small and go so fast), and R&D is now turning towards finding other ways to improve performance. ARM has shown tremendous progress in the portable market, but as the article notes it's had trouble penetrating the performance market because arm's energy-efficiency focus makes it less suited for high-performance applications.
Is there anyone with half a brain who doesn't think the in Apple's R&D labs there's a Macbook Air with magnetic keyboard, touch screen, an ARM processor running OS X when the keyboard's attached and iOS when it isn't? Or maybe it's an iPad with attacheable keyboard?
Anyway, they've almost certainly ported OS X to ARM to see how it runs and then dropped an ARM CPU into a Mac of some sort.
This post has been deleted by its author
This post has been deleted by its author
Apple have rather successfully negotiated two architecture changes in the Mac's lifetime.
In the last one (the move to intel) many people didn't even realise they were running PPC code on intel until Rosetta was no longer installed by default.
Similarly before that many users ran 68K code quite happily for years on PPC.
I really don't think that it is the least bit surprising nor do Apple users have anything to worry about should this eventuate.
Windows user's have not a lot to worry about.
No one (as yet) has said anything about changing instruction sets - just hardware manufacturers.
I actually don't think apple would do such a thing again, mainly because in my experience with OS X, apple is caring less and less about its long term users. I bought a 2008 top of the line iMac and it's virtually useless now. Leopard and Snow Leopard ran beautifully (and still do when I experimented reinstalling them). Lion ruined Logic Studio 8 for me (which was a real kick in the teeth, a $500 kick in the teeth), and slowed the computer to a complete halt. I'm not even bothering with Mountain Lion, but to me, that says I get 4 years of support before I have to upgrade.
So if apple do, in their infinite wisdom, decide to move to a new manufacturer, or even a new instruction set, count me out.
Interesting... I had exactly the opposite experience, installing Mountain Lion on my 2007 2.8 core 2 duo macbook gave it a second life, to the point that nowadays I'm using it over my other, core i5 macbook.
But I still resent Apple for integrating such fragile, short-lived optical drives in their laptops all along.
Funny, my 2006 13" bottom-of-the-line white macbook happily runs OSX Lion and isn't slowed down at all. I also run Logic Pro on it no problem. Sounds like you're just moaning because you ain't got the latest bit of kit, want the latest bit of kit, but cannot afford the latest bit of kit. So you're moaning and threatening to "leave Mac" etc etc. Quite immature really.
Are they going to roll their own x86 though? it would be quite expensive.
Anyway, one thing is for sure it is a lot easier to run CISC code on a RISC type design than the other way around. You can assemble RISC instructions into equivalent CISC instructions. But of course, byte ordering is also important. If your emulator spends half of its time flipping byte orders around then it won't run too fast.
The PPC chip had some sort of switchable byte order to get around the above problem.
In both previous architecture shifts the new CPU family was a major boost over what the previous machines had. For instance, at the time the PowerPC 601 was first shipped (although it was not intended to be a production CPU and had been built as a proof of concept) it was the fastest microprocessor BYTE magazine had ever tested. A major jump for that era.
The PowerPC models Apple used also had the advantage of a dedicated bit of transistor real estate to do some of the conversions that would otherwise have added a LOT of overhead to emulating the Moto 68K family.
When it was decided to go to Intel the problem was that Apple alone wasn't a big enough customer for IBM to commit the resources in producing competitive desktop CPUs at a pace to match Intel. The profit margins were tiny compared to IBM mainframes but the level of capital required was greater. Apple had no interest in encouraging an open market for non-Apple PowerPC desktops, so something had to change. By the time the first Intel Macs shipped the last round of CPUs IBM produced for Apple were getting a bit dated by the standards of the PC industry. Once again, the new architecture had plenty of spare horsepower to handle the emulation problem.
Unless ARM's upcoming 64-bit product line offers unprecedented level of performance gain, at least an order of magnitude over current ARM designs, there is just no way to have a third relatively easy transition. Something has to give. Either Apple dumps its professional users and allows their desktops to age into uselessness, or they once again offer some hardware means to ease the transition.
I'd expect the former to occur as those users have become a very small portion of Apple's revenue picture. The cachet of holding that market is no longer as useful as it once was now that they've become so strong in the consumer end.
Another possibility is that Apple continues on x86 but dumps Intel. AMD is currently circling the drain but has some very valuable IP. Apple could buy the lot using the change under the cushions of the couch in Tim Cook's office. One question would be whether to retain the ATI portion of the company or spin it off into an independent company again.
A while ago when AMD was causing Intel serious pain, ISTR Intel sued AMD for various IP infringements. I don't recall the resolution. Did it fizzle or get settled out of court, once Intel competed its way beyond AMD in the server arena?
My theory is that Intel needs AMD, to avoid being treated in law as a monopoly, and to keep itself at the sharp edge. AMD is now weak, and maybe Intel is cutting it some considerable slack with respect to other possible lawsuits? Not least to make it undesirable as a takeover target?
I'm speculating. However, I really don't think Intel would like to see AMD either go bust or taken over.
Apple fanatics are so engrossed in their "religion" they just bend over and take anything from Apple. I can only imagine what would happen to Microsoft if it attempted or even entertained this idea. Microsoft is just as bad as Apple, but at least its user base is detached enough to think clearly.
Repeatedly. Windows 2008 for Itanium, Windows RT for ARM, and so on.
Those products were minority interests, or (rumour has it) underpowered crap, but that's not the point: Microsoft aren't loyal to Intel per se, they go where the market's going.
And Apple fans did take it, in 2005-6, and liked it, because it got them out of a processor dead end. I don't hope that Apple do this, because I think it would be far preferable and simpler (for users, that is) to try to develop lower-voltage x86 processors, but that's not the point. Apple was offering something extra to make up for the inconvenience: much faster processors. What if Apple now offered users iPad-style battery life on their laptops? I'm not saying they will, but that is the kind of thing that would start to get people interested in switching.
Don't forget NT 4 and Windows 2000 for almost every CPU then vying for the workstation market. DEC Alpha, MIPS, PowerPC. And the myriad processors WinCE was offered on.
There was a strong belief that Intel was going to hit a wall and you needed to be ready to have your OS sold on whatever took over the market. Even Intel tested the waters with the 80860 long before the Itanium. IBM had OS/2 3.0 Warp for the PowerPC but killed it after they decided the desktop market wasn't going to happen for non-Apple PPC machines. Perhaps if Steve Jobs didn't kill CHRP as one of his first acts upon returning to lead the company.
"Tablets do not have sensible GPUs."
Define "sensible". My Tegra 3-powered tablet seems to chug along nicely and render some quite spiffy looking games and 3D live wallpapers, thanks all the same. OpenCV is boosted quite a bit, too.
This post has been deleted by its author
Computer companies are paranoid about everything, and I'm sure Apple have considered the possibility than x86 starts to become a dead end, that Intel can't manage to reduce power consumption, and so on. Literally any such discussion in the cafe chez Apple at lunch would be sufficient to make this article 'true'. That doesn't mean this will happen, or that it would be a wise move. I'm not too sure of the benchmarks-does anyone know roughly how good emulation is in this direction? I've played with ARM emulators running on x86 and they're terrible.
Apple's offer if they did this would probably be power consumption, realistically. I can't think of anything else they could offer that would be worth it from the user end. I'm sure they could commission a custom x86 CPU with some Apple IP if they wanted one with a very consolidated design-even if Intel said no AMD would find it hard to turn down the money right now. From their end, I suppose switching to custom ARM chips might offer savings-but it leaves them dependent on their own innovation fighting against the whole PC industry, just like in the PPC days, with a risk of it all running out of steam. Staying with Intel guarantees their processor roadmap forever. And why run the risk? It's not like Apple's Mac sales need a real boost right now. Adding uncertainty when they're on the verge of stealing loads of disgruntled Windows users would be...audacious. This would also end the ability to dual-boot Windows on Macs, since Windows RT is not on sale (and I doubt Ballmer would make an exception).
TLDR: I doubt they'd do this unless ARM offered something absolutely amazing. I think this a headline planted to make Intel jump into line, not a serious threat.
"I'm sure they could commission a custom x86 CPU with some Apple IP if they wanted one with a very consolidated design-even if Intel said no AMD would find it hard to turn down the money right now."
Tricky - Apple doesn't have an x86 design license, so they couldn't do their own without spending a *lot* of money on buying one.
"From their end, I suppose switching to custom ARM chips might offer savings-but it leaves them dependent on their own innovation fighting against the whole PC industry, just like in the PPC days, with a risk of it all running out of steam."
They already have custom ARM chips - in iPhone and iPad. Ironically Apple bought PASemi which gave them a competitive PowerPC design (it would have been great in laptops), but they killed that straight away. They might ride the ARM-in-server wave that's building, but might not go in a desktop friendly direction.
"Adding uncertainty when they're on the verge of stealing loads of disgruntled Windows users would be...audacious."
Disgruntled Windows users? You can still buy Windows 7, and that's been very popular. You're right though - Windows 8 is certainly unfamiliar and disconcerting compared to the old and stuffy OS X and Windows 7.
"I think this a headline planted to make Intel jump into line, not a serious threat."
Perhaps, but I'm not sure that Intel can 'jump into line'. X86 is exceedingly difficult to make fast and low power, the instruction set is just way too crummy for that. And if Intel fixed that by changing the instruction set it then wouldn't be an x86 any more... Their latest effort has completely bombed because it's still way too power hungry. They don't need any encouragement from Apple to know that they're missing out big time.
But Intel (and AMD) are still very good if you have a mains supply and don't mind about the power consumption too much; their chips have a *lot* of compute power which makes for nice games, etc, and I can't see ARM bothering trying to compete with that any time soon.
The instruction set is hardly a problem. Intel has been dealing with converting that to something more effective on the fly since the 486. Most of the performance gains of the 486 were a direct result of that new-found freedom to do what they wanted internally. The criticism then was that this translation stage was terribly expensive compared to a native RISC chip. But Moore's Law took care of that, as Intel had known it would all along. The number of transistors needed for the translation stage became trivial in a few years.
The problem is the huge difference in performance levels between the ARM and Intel products. Low power is not a mystery if performance is not an issue. ARM chose to forego desktop level performance a long time ago in pursuit of mobile and embedded markets. (The original Archimedes PC was quite competitive with the high end PCs of that era.) It was an effective strategy that carried a cost as their market now overlaps with Intel's, just as Intel's choices did very well for them but limits their entry into where the growth is today.
"But Moore's Law took care of that, as Intel had known it would all along. The number of transistors needed for the translation stage became trivial in a few years."
Whilst the translation stage itself doesn't require that many transistors, the consequences of doing that does. To keep the thing moving fast Intel have to put in complicated pipelines, branch predictors, etc. and all of that adds more transistors. Whereas ARM's more clearly thought out instruction set allows significant economies in silicon.
It is true that ARM have wisely dwelt at the low end of the performance scale whilst Intel have impressively dominated the high performance end, but it's not that simple. Even when Intel try to do a pure mobile chip they still can't get it as low power (Intel's own admission) as competing ARMs, despite having a generally superior silicon processing capability. That's got to be the result of all those transistors adding up.
What I'd like to see is a more modern processor design on Intel's silicon. Oh wait a minute, they tried that with Itanium...
This post has been deleted by its author
What Apple could, and IMHO should do is explore much more interesting possibilities in processor design. The x86 chip is fine so far as it goes, and the ARM all well and good, and nice for low power, but neither are exactly anything more than the most boring and basic functionality. Computer archtictecture has gone backwards for decades. Right now, raw speed individual CPU is no longer the prime issue. Ever since Apple bought PSemi I have wondered if they might do something really interesting. Where interesting involves taking some advanced architecture ideas and running with them. The one that I would love to see - tagged memory. Adding tags to memory can be used to provide hardware differentiation of addresses and data. Instant pointer management, and with it a major step towards secure systems. Also add a full/empty tag, which provides for intrinsic synchronisation in memory, and with it support for fine grained concurrency. These are not new ideas - look back to the Tera MTA for one example. But you could go a very long way back to see lots of additions that can provide for secure systems, and parallel code support.
It would be a brave move, but if you look across the industry, the only company that is in a position to make a break from the ossified architectures we currently use, it is Apple. Worrying about Windows compatibility just repeats the mistakes that keep things bogged down. Linux is so conservative in its internals (no bad thing, it is just important to understand this) that it won't be able aid any such progress.
tagged memory? sounds like the paging, sandboxing and virtualization that are already being done. sometimes even in hardware. There's definitely space for a lot more interesting stuff to go on in this department, but it's going to take an exponential increase in memory density and especially throughput to make it happen.
That would definitely be a cheaper way of going independent. After all AMD has no expensive and cumbersome fab to weigh Apple down, their designs are pretty good really, and would come complete with a very competitive GPU too.
I suspect that it means that they don't want to remain x64 compatible, which begs the question, what? Presumably that means ARM, and that in itself raises certain questions.
Apple make the bulk of their cash from iPhone and iPad, not from iMac, PowerMac or the laptops. The iPhone/iPad are closed ecosystems, you have to go through the iStore for literally everything you ever want to put on them, and that earns Apple a bundle of cash too. Even the botched move to iMaps is related to ongoing income from previously sold products, and is currently a failed attempt to stop Google making money of the back of iPhones.
In contrast the iMac/etc. are open in the sense that you can install any software you like. However Apple don't make a penny from it afterwards. Every one uses Google (money going to Google), buys MS Office (money going to Microsoft), buys Photoshop (money going to Adobe), buys games (money going to EA or whoever), etc. In fact the only post sales income Apple gets through their desktop / laptop lines is iTunes sales and the occasional OS upgrade. I think that's a powerful indicator of their intent.
If this rumour / news is true I think it means that Apple want to kill of Mac OS X as we know it, and turn their non-mobile products into closed ecosystems too, and a change to the ARM architecture (or indeed any other architecture, even PowerPC) is a good excuse for doing just that.
Whilst I see where you are going with office-type apps, I can't see Apple shutting out the higher-end users of things like Adobe Photoshop or InDesign, not unless they merge OS X and iOS and effectively abandon anything above consumer and office apps for their computers.
Might happen in five years....oh, wait!
Ow, that's a scary prospect. I agree with almost everything you've said, but I'm not so sure about this statement on income after sale, actually. Apple state (yes, naive ol' me) that they basically aim to break even on the App Stores. It's certainly a modest income source compared to their super-sized hardware sales. And Apple make nearly nothing from OS upgrades now by their own choice, to keep people up to date on APIs to help developers. I think their revenue strategy here is simple: make Macs non-upgradeable black boxes and force people to regularly buy the latest model. (On the other hand, locking every Mac to App Store software would certainly make that income stream a lot bigger.) The problem is that loads of development and scientific tools can't use the App Store, so this would more or less end Macs as anything other than appliances if they care about that.
If you're right, the App Store would give them a path to upgrade. They could announce the change to happen two years in the future and require all apps filed from then on to be written and compiled for both processors. That would give them a starting ARM App Store that even included work from developers who had died out in the intervening period when ARM Macs launched.
Apart from it would start a bidding war - too many other manufacturers rely on ARM so they couldn't afford to let Apple own it. For now they all survive by having a chip designer that can be used be them all, creating a market of different vendors devices that do similar jobs.
"But since that 2005 tie-up with Intel, Apple acquired P.A. Semi and turned its technology into the Ax microprocessor range."
Apple did buy PA Semi, but it's difficult to see what benefit got from that. The first Apple ARM CPUs were definitely re-hashed Samsung designs, not something Apple designed in house.
PA Semi had a PowerPC design that was very interesting at the time (a 2 core, 2GHz, 64bit, PowerPC SoC for 13Watts - very competitive against Intel's contemporary specifications). Apple bought PA Semi for the talent, not the chip. Unfortunately the talent left, presumably they didn't like being Apple droids. Which is why Apple then bought Intrinsity, another ARM SoC designer, and only now are we beginning to see Apple designed chips.
There is no need for x86 in any product family unless the product family is commercially dependent on Windows. Don't take my word for it, look around you.
Yes there are still x86 servers from the likes of Dell (the distribution arm of Intel, as encouraged by massive, and occasionally illegal, kickbacks from Intel) and HP. HP are working on alternatives, others already have them. It's convenient for now to continue to use x86. But for how much longer?
When I recently asked elsewhere on this site, "outside the Windows world, who still uses x86", the Apple answer eventually came back.
And for now, it's still true. But, obviously, Apple don't need Windows. And, really, they therefore don't need x86.
@Francis Vaughan 05:55
Be careful what you ask for, or you may get the next Intel iAPX432.
There's a difference between NEED and AFFORD - the vast majority of Linux installs run on Intel not because they need to, but because it is (currently) about the most cost effective hardware available for the job.
There are lots of other options. But will your bean counters let you buy them?
(not saying its right, just pointing out fact)
"the vast majority of Linux installs run on Intel"
Bad starting assumption?
1) The vast majority of Linux installs run (invisibly to the IT manager) on ARM. In routers, in TVs, in NAS boxes, etc. Not to mention phones and tablets, which might be visible to some of the less dim IT managers.
2) The IT manager (especially the certified MS-dependent variety) is only buying x86 because it's the heart of the comfort zone. Not because x86 is more affordable, not because it's better for the business, but because anything else is "non standard" (according to the IT-manager-defined logic-free "standard").
The same will inevitably happen to x86 as happened to VAX and SPARC, both of which were once dominant in their fields.
x86/x64 is also in the "comfort zone" of Linux kernel developers. If you want your hardware to be supported by Linux kernel you either go x86/x64 and do very little (if any) kernel development, or you go ARM route either copying existing ARM platform which already have good support in LInux kernel (how many there are? server ones?) or you add this support yourself. Which is a bit of hassle.
It will be few more years before ARM is as well supported in Linux kernel, without vendor patches needed, as x86/x64 currently is.
"x86/x64 is also in the "comfort zone" of Linux kernel developers."
Bad call. It may be true, but it's no showstopper, and (unluckily for you) I have first hand experience of why it's not a showstopper. Lots of other people may well have the same experience too.
I've taken a kernel-integrated Linux app from realtime Suse on x86 to MontaVista Linux on ARM (on iXP422) and back to realtime SuSe on x86. The application was a custom data concentrator/timestamper (hence the RT) with a semi-custom hardware interface with a common design between ARM box and x86 box.
No meaningful code changes needed at the time that work was done. I can only hope that today's situation is no worse.
Unless you can show otherwise, I call BS.
IT managers are typically not certified in technical skills. They have people they delegate that stuff to.
Besides, the fact that an individual has done work to prove that they are competent in their area of expertise does not inherently reduce their credibility, flexibility, logic, decision making ability or anything else. To the contrary, it usually counts as a benefit.
It seems you would be surprised to learn that many who are MS certified may also be interested in, use, have certifications in and in some cases prefer technologies and solutions from other sources.
This is a believable story. I suspect that it's true only in a limited sense, but the key elements are correct.
The performance profile of Apple's A6 chip suggests that it's an Apple-designed core, rather than a standard core licensed from ARM. This has many implications.
If they are an architectural licensee of ARM, they have a big internal investment but a very modest per-chip cost. Switching to the ARM instruction set with their own processor could save Apple substantial money.
Using their own processor makes it more difficult to directly compare performance. This has served them well in the mobile phone business. They have claimed high performance without standing behind actual performance numbers that can be compared against other devices. Using their own non-x86 processor would return them to the bliss of a decade ago, where Apple faithful could say "the clock may be slower, but thanks to the instruction set it's actually faster". (Which happened right up until the switch to the actually-much-faster x86.)
They already have a design process putting their own chips into mobile devices. Having a different design cycle around x86 chips from Intel duplicates effort. (I don't actually believe this, as the same team probably can't do both. And once you have a working design process, you shouldn't break it up. But eliminating duplication sounds good to management.)
I 'upgraded' from a a Powermac G5 quad to a MacPro 3,1 and it was by no means a massive step forward in performance. In some ways, it was quite a bit slower. The PPG 970fx was an inefficient chip, but a powerful one. The major difference between the two machines was the enormous drop in power consumption.
This post has been deleted by its author
"Apple have switched architectures more than once before. It's something they seem quite comfortable doing."
Yes, they pulled that off with 68000->PowerPC->Intel, but every time the amount of compute power available increased. That eased the pain because it meant that emulators had good performance. An Intel->ARM transition wouldn't be able to do that. ARM cores are not fast, and emulation would have to run on the ARM core itself and that'd be a very slow dog indeed.
"Switching to ARM would give them a lot of potential benefits in addition to owning the silicon."
Others have already pointed out that buying AMD would give them the same control, but allow them to stick with x86.
"How many ARM processors can you fit into the same silicon/price bracket as an Intel processor?"
A lot. An ARM core has something like 48,000 transistors, whereas an x86 core contains many millions. Intel's problem is that they also need millions more transistors (cache, instruction decoding, etc) to make the x86 core fast.
"I'd be very surprised if a similarly priced array of ARMs wasn't as powerful as the Intel equivalent, and they'd probably use less power too."
It maybe as powerful in aggregate, but single thread performance would still be bad. That matters - most software is still single threaded, so all your apps would run slow. That might not be an issue for something that's not compute-heavy (a text editor). For other stuff like video decoding one of ARM's hardware accelerators would do the job, just like a mobile. However, something like Photoshop could be a real dog.
ARM or Apple might seriously pep up the ARM core to reduce the disparity in single thread grunt, and it would be more power efficient than Intel. However it sounds like a lot of work, and it be probably be cheaper to just go back to PowerPC; Freescale haven't been standing still with PowerPC, and if it comes to that Apple bought PA Semi a few years back - they had a very competitive PowerPC design at the time.
Its unlikely that they could make an ARM based chip with comparable performance to the Intel chips in use now, whilst also maintaining that super-small form factor that they are talking about for thin devices. There's a reason Intel chips are 'large' - they kinda have to be using current technologies, in order to get the processing power whilst also keeping the ability to get rid of all that heat.
No business will look at Mac OS as a suitable platform if they do this, as it proves once and for all that Apple don't care about business continuity or stability.
Switching your platform regularly will drive anyone who wants more than 5 years of support away. One thing you can say about Microsoft is that until very recently, they've provided very *long* life support for their platforms, and even when they've changed things, they still use the same processor family, so moving to their new OS isn't such a huge issue.
I would not be surprised if Apple is very focused on developing their own chips for the mac, as Tim Cook is very efficient and diligent regarding cost efficiencies while still providing a high quality technologically progressive product/service in all areas of Apple. Tim Cook is strategically steadily working to ensure all of Apple's fundamentals are solid hence there is slightly higher cost margins currently as Apple is getting their economy of scale in top shape so the company can cost effectively, while still maintain quality manufacture the millions of iphones, macs, ipads in demand by people globally. Having as much produced in house by apple will allow them to ensure high quality of standards which Apple is almost obsessive compulsive about while reducing costs and not having to be reliant on other companies which creates risk should something happen to that company ect...
Intel has managed to mitigate the weakness of the X86 instruction set by having the best fabs, and not making chips for anyone else. They even sold off their ARM based products to Marvell, to prove their faith in X86 to their sceptical customers. But if losing Apple was a done deal, and Apple don't sell bare chips, maybe Intel could make ARM, or even PowerPC SOC's for Apple.
However much you may dislike Apple's control freakery, it's what enabled them twice before to switch CPU architectures. Something both Microsoft and Intel have aspired to, but failed to gain traction with. (remember Windows NT for PowerPC? iAPX432, Xscale, Itanium?)
The nub of the matter is: what could Apple persuade Intel to do for them, given that X86 is not remotely the mainstream any more, and iGizmos must inexorably move towards zero build cost over the decades.
"The nub of the matter is: what could Apple persuade Intel to do for them, given that X86 is not remotely the mainstream any more, and iGizmos must inexorably move towards zero build cost over the decades."
x86 is still king of the roost when it comes to performance applicaitons. For people running Photoship, Premiere, or the like, that's a big deal. As for HPC, ARM doesn't rule there, either. That's more the realm of specialists and GPU makers.
It would possibly be a horrendously expensive undertaking to develop a new architecture chip that :
1. outperforms the Intel latest generation
2. delivers comparable performance at a comparable price point
3. does not infringe on AMD or Intel IP (at least not getting away with it)
4. produce it at anysignificant quantities
5. produce the relevant industrial strength compilers and cross platform the software at the time of release.
6. Alternatively, develop new software from scratch. This would truly be a can of worms, migrating to completely new hard- and software from the ground floor ?
I only have to refer to AMD who, although they make exellent products, and were even the originators of the 64 bit instruction sets as we know it, have never been able to make a sizeable dent in the Intel armour, not even when they had superior hardware (I'm conveniently ignoring the Opterons, which had a good run...for a bit). And et's not forget that even Big Blue did not have the stomach to go up against Intel at the time of the PowerPC's
I imagine that as soon as someone adds up the numbers at Fruity Towers the whole idea will be quickly relegated to 'bargaining chip' status.
But, admittedly stranger things have happened.
IBM had the stomach. What they didn't have was the customers to buy PowerPC desktop/laptop systems in the kind of volume needed to justify the capital investment to keep on par with Intel. They need far more business than Apple could supply and nobody else with the needed cash was inclined to jump in. IBM had already strangled their own effort in its crib years earlier.
Without the right numbers no amount of intestinal fortitude would make it a business worth pursuing.
It may not be so hard for Apple to smooth the transition. ARM cores are cheap to licence. Apple can devote a core, or more to code translation and emulation. Add to this the fact that OS X is Unix and that Unix was designed from the bottom up to be portable then the problem looks less difficult than before.
Have you seen an x86-on-ARM emulator or DynaRec core in action? You're talking an efficiency core trying to emulate a performance core. In the last two instances, Apple transitioned to clearly-superior hardware which smoothed the transition. Here? ARM isn't necessarily superior to Intel: just different. That handicaps emulation: just as trying to emulate a high-speed PowerPC or MIPS CPU even on today's Intel CPUs is not a walk in the park.
Once upon a time, before the second coming of Steve Jobs, Apple migrated its desktop machinery from M68k to PPC. This appears to have succeeded. There was a compatibility system for running M68k binaries on PPC; I don't know how it worked. I do recall hearing that for a CISC processor architecture, the M68k series had fewer opcodes than most.
After the second coming of Steve Jobs, migrated its desktop machinery from PPC to PPC64, and i386, and x86_64. The Intel hardware could run the PPC binaries via a compatibility layer known as Rosetta, based on JIT compilation technology, licensed (or subcontracted to, or something ..) from [looks at Wikipedia] oh yes, "QuickTransit" from Transitive Corporation. In my experience this worked well. In terms of execution speed and reliability, you'd be extremely hard-pressed to tell whether something was running natively or via Rosetta. [I myself only tossed the PPC-only EyeTV 1.x software, and bought EyeTV 3.x software, when I upgraded my desktop to 10.7, from which Rosetta had been dropped.
There were a few bits of software that wouldn't run via Rosetta, usually because they were doing spectacular things in kernel-space. I only ever encountered one..
If Apple does transition Macs to ARM-architecture processors, I shouldn't be at all surprised if something like Rosetta reappeared to support Intel-architecture binaries, and I would expect it to work.
What would disappoint me would be the non-reappearance of PPC support in this latter-day Rosetta, support for which I could find a use even now.
You have to take into account the memory model into "multi-core era", ARM has significantly weaker memory model compared to x86 (x64 is a bit stronger even). Concurrent code cannot be JITed just like that single proper memory fences have to be issued. x86 never reorder load w/ load or write w/ writes unlike ARM.
There was an awful lot of software that was ported to OSX as a result of them sharing the same architecture as PC's. I use mine to write music via Logic, when Intel Macs came out there were a lot of audio plug-ins that became available in intel-only guise. If Apple want to essentially dump the Mac in favour of desktop iOS devices then it would really be a shame, as fancy and whizzy as those devices are they're still just toys for pissing about on, sure you can check your email or browse a website or play a computer game on but anything serious you need a proper computer. Microsoft are heading down the same silly path with W8.
I am getting tired with all this 'you need to move with the times' crap. The software I use is a tool, I need those tools, I know how to use them, they deliver what I need. Having to constantly fanny around learning new interfaces, switching software to find that it doesn't do what it could before, finding existing projects no longer load and software is no longer compatible is just beyond a joke.
There has to be at least a handful of computer users left that still actually do some work on their computers, the direction the market is going in is a cause of concern.
ARM in macs?
Hmm, this'll mean that all those who eagerly awaited for the arrival of Steam on the mac will now be faced with the prospect that the CPU may not be up to scratch anymore when playing the newest games. ARM-style CPUs tend to be geared towards low power drain and efficency, not overall grunt, which puts them in a weak position for any games other than typical app store stuff.
It does look that if they move away from Intel, then buying the ailing AMD would prove to be the best route to obtain the relevant licenses and facilities, as well as the expertise in such areas without having to bumble through the pains of a cold-start. And given the AMD APU design, itm ight just work.
Still scary though, as I'd rather see AMD make a proper comeback, not get absorbed into the horrible pretentious ego-blob of Apple.
Of course, the elephant in the room is that ARM can't achieve anything remotely near the instructions-per-second of even the crappiest desktop x86 processors. And that high IPS, I'm afraid, is why the x86s need fans.
For my money, if they want thinner machines, they'd be better off advancing the state-of-the-art in peltier cooling than trying to make ARM compete with x86 on the desktop.
> ARM can't achieve anything remotely near the instructions-per-second ...
That doesn't make sense either from the arse or the genitals side. The instruction set should be pretty orthogonal to attainable "IPS" and indeed the ARM instruction set has been designed for speed and ease-of-implementation, I hear.
"The instruction set should be pretty orthogonal to attainable "IPS" and indeed the ARM instruction set has been designed for speed and ease-of-implementation, I hear."
Yep.
And if memory bandwidth turns out to be a bottleneck, be it cache or main, the more work you get done per Kbyte of instructions, the faster your app will run given the same memory subsystem.
This works in ARM's favour because they're pretty good at producing dense code (ie a given workload uses fewer instructions, and hence less memory, than the alleged competition).
This post has been deleted by its author
Unfortunately all that does is makes the heatsink even hotter as the heat is actively dragged from the CPU. Not much good for thin and light designs, because while the CPU might be running at negative-degrees celcius, the heatsink would be rapidly melting a hole in the chassis.
Now heatpipes on the other hand, they can help. Even if only to spread the radiators around the inside of the chassis to distribute and diffuse that nasty hotspot.
My first computer that I bought was a Macintosh, it was an iMac G4 and I loved it. I've stuck with Apple since because a) I like the hardware b) I generally like the software, although I'm holding out with Snow Leopard for as long as I can because anything Lion onwards seems to increasigly act like a giant iPad (stupid scrolling, full screen rows of icons for no real reason, locked down default behavior for external apps, no real save as, removal of hard drive icon on desktop to 'stop people getting confused' etc etc c) I'm kind of locked in to some of their profesional applications
Now the situation is so much different, and other manufacturers can tick most of the boxes: a) hardware from other companies can be just as good as Apple these days, and in some ways better (my girlfriend's Lenovo, for instance, has more than a hair-tearingly frustrating 2 fucking USB ports) b) Software can be just as useful, pretty and productive ad OS X - I've long thought Windows' Taskbar was far more useful than the crappy tiny arrows on Apple's pretty-but-a-bit-shitty Dock, and Finder compared to Explorer is something that I just cannot talk about. Then of course there is the vast array of mature and stable Linux distributions out today, all of them excellent OS's c) Like Os's, there are a number of alternatives to the pro apps I need and everything else has become over the last 10 or so years much more platform agnostic or cloud based, so the OS is even less of a defining factor these days
I'm afraid, Apple, that if you continue to turn your machines into oversized, locked down toys for clueless execs and middle-class, facebook browsing and Angry Birds playing families then I will shift quicker than you can say "Windows fucking 8"
"(stupid scrolling, full screen rows of icons for no real reason, locked down default behavior for external apps, no real save as, removal of hard drive icon on desktop to 'stop people getting confused' etc etc"
None of this is true. Trust me, Mountain Lion is what you want. Snow Leopard is no longer adequate when you have used ML. There's a little bit of culture shock, but things like iOS style notifications are actually excellent, and all the restrictions you cite are untrue.
A couple of years ago I predicted that this would happen, and I have seen nothing to change that opinion. The main reason I see for Apple to do this is to get full control of the hardware, like they have on their iOS devices. A secondary reason is to get iOS apps running on MacBooks. I think iOS and MacOS will merge much in the same way Windows 8 have merged the desktop and phone operating systems from MS. MS has stayed with x86 on the desktop/laptop version of Win8, but that is (IMO) mainly because many Windows applications have parts written in x86 assembler or C that assumes x86 behaviour (such as endianness and non-aligned memory transfers), which makes them harder to port to a new platform. Having learned from past experience in moving to new processor platforms, Apple have far fewer assumptions about processor in their code. And, as another poster said, they are increasingly relying on LLVM in a move that mirrors Microsoft's increasing reliance on .NET, both of which makes changing platform easier.
With the upcoming 64-bit processors, ARM should be powerful enough to compete with 64-bit x86 processors, but the licence model that allow other companies to build their own SoCs around ARM cores (and even design their own cores) is probably the main reason: With Intel, they have to use the SoCs that Intel make. With ARM, they can make a SoC that does exactly what they need and want. And make sure no one else can use this SoC to make clones.
As for Apple buying AMD, I doubt that. But I wouldn't be surprised if ARM bought AMD.
not really. It's more about Microsoft not very keen on inter-architecture machine code translation, but very keen on maintaining its advantage in the number of available applications already compiled to x86/x64.
In other words: users will stay with Windows as long as they can continue using applications they accrued over the time, some of them expensive (e.g. work-related) or large collections of cheaper ones (e.g. games). Since these are already purchased, the vendors have little incentive for rebuilding the binary for new platform. In case if Windows was to jump the platform it would upset vendors and customers by forcing one to rebuild/port and the other to purchase applications again. The effect would be Windows losing its advantage , i.e. number of available applications. You can observe that by watching how the situation with Windows RT develops.
As for Microsoft's "increasing reliance on .NET" , that has stopped with Longhorn failure. It was the last time Microsoft tried to do system programming in .NET and it was a write off. Windows 8 is move back to native , e.g. WinRT is not .NET but native code with COM-like wrappers for .NET . Surprisingly to some, that is true even on Windows RT .
... users will stay with Windows as long as they can continue using applications they accrued over the time, some of them expensive ...
Right. I have a couple of applications I use frequently that were written for 16-bit Windows, and so don't run at all on Win64. It's no problem, though, as they both run fine under Wine on 64-bit Linux.
[I don't think this can be the Steve Ballmer icon -- it seems to have too much hair]
Apple do not have sufficient experience, expertise or resource, yet, for cranking out high performance ARM rigs [e.g. 64 bit ones], even with pinched staff, so will external help.
The hardware could be fun, given lots has no support for ARM 32-bit, let-alone 64-bit, this include drivers!
There will be much upset over not just the OS, loads of application software, and I doubt GNU, Linux, or BSD has great support for ARM 32-bit and 64-bit is not probably not adequately supported yet, to provide a reference for migration!
It'll be quite painful.
How about this for an idea.
AMD and ARM get a 64bit ARM processor out the door with the new seamicro architecture.
i.e. x86 and ARM on the same board.
AMD is on its death bed, and get snapped up by apple (gets them into the enterprise market at the same time)
New iMac comes out with x86 APU which is nice and slim with decent graphics performance, and an ARM co-processor they can then slowly migrate apps over to ARM. All of a sudden 5 years down the line x86 get dropped but they now have an nice ARM+Radeon 64bit APU.
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2024
