This discussion has been archived.
No new comments can be posted.
Apple to Use Intel Chips?
Related Links Top of the: day, week, month.
All the simple programs have been written.
All the simple programs have been written.
Dvorak (Score:4, Insightful)
Yes but he predicts so much crap of course he'll be right eventually.
Dvorak (Score:4, Insightful)
Nope (Score:5, Insightful)
O really? (Score:5, Insightful)
Re:Does this mean - (Score:5, Insightful)
Why move now? (Score:5, Insightful)
Intel make chips other than CPUs (Score:1, Insightful)
I can't for one minute imagine Apple replacing nice fairly cool and power efficient PPC chips for hot running 100+ watt monstrosities from Intel.
Re:Does this mean - (Score:3, Insightful)
Depends on what kind of chips (Score:1, Insightful)
Here we go again... (Score:5, Insightful)
The Mac would die the day the CPU would be the same as in a generic PC. Not from a architectural standpoint, I think they could make it happen, but marketingwise.
Re:Does this mean - (Score:3, Insightful)
If anything, they could perhaps use some non-x86 intel stuff for portables devices where the PPC sucks up too much power. Remember that Intel is more than only x86
Re:Moving toward standards? (Score:3, Insightful)
Essentially they're shifting part of the cost burden to IBM, while keeping their share of the profits intact, in an attempt to boost their sales.
Also, it could be an attempt to make sure that IBM, with its focus on the PS3, Xbox 360 and Nintendo Revolution, does not forget about Apple.
Why cheaper!? (Score:5, Insightful)
Currently all of Intel's stuff runs hotter, so Apple would have to work significantly harder at heat dissipation issues in all but their tower designs.
And what, pray tell, do you expect them to do with little-endian issues, backwards compatibility, and all those little details?
Unless Apple thinks that neither IBM or Motorola are ever going to catch up, I just can't see them justifying the huge cost of a major architecture change like this.
- Peter
Re:Intel make chips other than CPUs (Score:4, Insightful)
Re:Does this mean - (Score:5, Insightful)
Re:Here we go again... (Score:4, Insightful)
Maybe someone who doesn't want his Tech support calls forwarded to Bangalore? (Not that I don't have my complaints about Apple support, but at least I could figure out what everyone was telling me, leaving out the ambiguity of figuring out whether they really sucked or whether I just thought they sucked because I couldn't figure out what the hell they were saying.)
Re:AMD? (Score:3, Insightful)
The fact is, if Apple wants to go x86 (which I think they should), they'll consider both Intel and AMD, talk to them, see what they can get and make a strategic desicison. If Intel decides that it's worth it then they'll underbid AMD. Or maybe Apple might decide that they want a supplier that is more reliable for delivering big quantity orders given that they've themselves been bitten so often by back-ordering problems.
Re:Does this mean - (Score:2, Insightful)
Predicting the future ain't what it used to be (Score:5, Insightful)
Re:Does this mean - (Score:4, Insightful)
The second that Apple moves into the market with OS X for x86, MSFT is going to pull Office and render OS X basically useless compared to Windows. Yeah, there are open alternatives that sorta work but in the real world people want to use what they are comfortable with. Unfortunately that's Office.
MSFT knows that if they pulled Office for OS X that Apple could easily release OS X for x86 and enter a new competitor into the OS market.
Re:Here we go again... (Score:2, Insightful)
Really. I mean, everyone knows that software companies [microsoft.com] can't make any money.
Re:Here we go again... (Score:2, Insightful)
Comment removed (Score:2, Insightful)
Re:Does this mean - (Score:4, Insightful)
Re:Intel make chips other than CPUs (Score:4, Insightful)
Is that what everybody wants from Apple?
An unwieldy leviathan with an hour battery life?
Re:Does this mean - (Score:4, Insightful)
You got it backwards. There are many closed architectures with one company dictating hardware and software. It is in fact the x86 that is unique in that multiple companies provide each part of the computer in an open architecture. And though this solution has it's problems, I think it has shown itself to be vastly superior to a closed system like the Mac.
Also keep in mind that if Apple where the dominating computer provider, they could probably had squished open source efforts like Linux in the cradle by closing specs and making new hardware incompatbile. The X86 may not be pretty, but I'd prefer it over a closed architecture any day.
Apple Already Uses Intel-Intel Uses What Was Apple (Score:5, Insightful)
My guess is that this will be for a new ARM processor for the iPod - the custom chip is probably too weak for advanced features.
Intel has been wanting to move to RISC chips for some time - maybe they want to become a CELL/PowerPC production partner to catch on the wave - 100% of the gaming world will be using PowerPC or PowerPC deritives in the next year - year and a half -
Intel now owns the largest stake in ARM (bought from Apple) - this is the processor in the majority of PocketPCs, Palms, and GPS units. So - this Intel processor is most likely for a new device or even the iPod.
Also take into account that USB2.0 chipsets are currently made by Intel (and others) and that Apple uses Intel chips in the XServe line for RAID I/O.
Re:Intel make chips other than CPUs (Score:5, Insightful)
The fact that those are large fans that aren't spinning at full speed.
They keep the computer as cool as it needs to be while being much quieter than the 2-3 fan PCs with fans spinning their lil' hearts (motors?) out.
Re:Does this mean - (Score:4, Insightful)
Not to mention, the PowerPC processor is the only edge Macs have left on PC hardware. If Apple goes x86 the Mac will simply be an overpriced PC running a pretty gui on top of BSD.
Re:Does this mean - (Score:5, Insightful)
- Quark Xpress might take ages (again, remember how long OS X version took).
- Microsoft might actually not want to release office at all.
(actually maybe they could convert things on the fly and then cache the results, sort of a better emulation process... there is some mention of something along those lines on macrumors.com. It'll be a bit like running Java bytecode. They could then profile the things on the fly and optimize the most used parts of the program... JVM do all sorts of clever trickery nowdays.)
Anyway this is all purely hypothetical. Apple's not moving to x86 CPUs. As other people said, it's probably some random chip they might want from Intel.
Re:The Register says not. (Score:1, Insightful)
http://apple.slashdot.org/comments.pl?sid=63475&c
Dvorak (Score:3, Insightful)
PCMag's John C. Dvorak predicted this...
Even a stopped clock is right twice a day...
In all seriousness, though....that article is a good chuckle. He was calling for Apple to switch to Itanium for Christ's sake, and then license OS X for non-Apple hardware with a Windows compatibility layer. Bwahahaha! Come now, John, how do you dream this shit up?
Equally hairbrained is his theory of a dual-processor PowerPC/Itanium machine; he seems to have the idea that they could just duck-tape two motherboards together and have it pick and choose which processor to run what executable on...clearly, he's using drugs.
If Apple does this (which I am extremely skeptical of at this point) I expect it will be at the very lowest end....completely backwards from what Dvorak predicted. The reason is simple: IBM's Power architecture is plenty fast, and they aren't going to get a performance improvement by switching to Intel. The only benefit available from such a switch is cost.
Apple is all about spectacular announcements! (Score:2, Insightful)
And if they announce a machine based off of any Intel technology I'd be more "Why?" than "Wow!".
If I was Apple I'd be far more interested in creating a machine based on the CELL processor.
It is fast. It is cheap (at least it should be considering it is in the PS3). It is not compatible with the PC market. It is based off of POWER which will make it easy for Apple to use it.
And finally, the CELL is _sexy_.
Photoshop seems to be a very important benchmark for Apple. If they go with CELL that has one main CPU and 8 auxilliary CPU's (and with Photoshop being suitable for multiprocessor systems) the CELL would likely "kill" any Intel platform in benchmarks.
Re:Intel make chips other than CPUs (Score:5, Insightful)
Straw man, meet the overrated rumor troll (Score:3, Insightful)
Meanwhile none of your points address the obvious problems pointed out elsewhere: that Apple has denied the rumor (for the umptieth time), that Apple's a hardware shop that might not compete with Dells that could run the same OS, and so on. Breathless arguments on the level of "probably double the value of their shares if not even tripple (sic) them" are even less convincing than a John Dvorak prediction, which is pretty far down the food chain for me.
If this is true, it means Apple has decided to go head to head with MS as an OS shop and make its money that way. That's what people call a "paradigm shift," and a radical one, at a moment when every recent example shows us that Jobs is continuing to do what he does best: sell the hardware by using the OS and interface grace points as a break-even loss leader. (iTunes as loss leader for iPods, iLife suite to sell each new generation of boxes, and so on.)
Re:Does this mean - (Score:2, Insightful)
No, it wouldn't. A lot more appealing to geeks, perhaps, but not people in general. Most people don't build their own systems, but buy the cheapest crap from Dell, HP, Gateway, etc.
Re:unbelievable (Score:4, Insightful)
I don't. But it is considerably much more "on par" than the G4 ever was, and they weren't changing then, why would they now? It is almost impossible to emulate PPC on x86. I don't know if x86-64 is any better, it should be because of the added registers but it'd probably still run slow.
I'm sure apple has a drop-in ready box for running x86/Mac, but it'll essentially be the same box as today except for the CPU socket, at the same price (no, the CPU is a damn little part of the total box). How would that bring any new customers at all? Not to mention x86 OS X is so much easier to pirate than PPC OS X. Chances are if you are running OS X, you probably paid for it at least once every HW upgrade.
Kjella
Re:Does this mean - (Score:5, Insightful)
Keeping my feet on the ground here: No.
We will see Windows on PowerPC long before we ever see the full OS X on x86. There's absolutely no advantage to changing platforms at this point.
Sure, the Intel/AMD world looked very attractive when Apple was relying on Motorola and lagging way behind in CPU speeds, but current PowerPC technologies from IBM are outstanding. The G5 is a terrific chip. Multi-core PowerPC chips offer a great deal of promise in the very near future.
If Apple does move away from the G5 archetecture, it will be to go to Cell chips, not Intel-64.
Re:Does this mean - (Score:5, Insightful)
Very few people build their own computers. Most buy a box from their local computer store, or order it online from a company like Dell.
Also, no one would run OSX on a standard PC. Just like no one runs BeOS, or ran OS/2. An x86 Apple would probably be a proprietary Apple with an x86 in, and no one would care. Just like no one cares that there is a PowerPC in them today.
Re:Does this mean - (Score:1, Insightful)
Bad news for Sony, then. Looks like they will have no chips to put in their PS3 next Winter.
Re:Does this mean - (Score:1, Insightful)
Can you give an example of a non-shitty open archetecture to support your point?
Or is your belief that "open architecture is superior" simply a matter of your religious dogma?
Re:unbelievable (Score:5, Insightful)
I'm amazed at how many people still think that any performance gap (real or perceived) actually matters. The majority of your PC's performance now comes from the size of the bus, the transfer rate of your disks, and how much memory you have. No one really *needs* a 5GHz processor to run a wordprocessor, email client, MP3 player, or even something more intensive like a graphics editor, video editor, or sound studio. Even games now rely far more heavily on the GPU than they do the CPU.
Re:Apple Already Uses Intel-Intel Uses What Was Ap (Score:4, Insightful)
Apple WAS a MAJOR developmental partner in ARM for the Newton - the processor line was GREATLY enhanced during the Newton run.
So was Sharp - probably shoulda googled before that statement!
Re:Does this mean - (Score:5, Insightful)
Re:Does this mean - (Score:2, Insightful)
In this case superior means which one will win in the market, not which one is the best design-wise.
Re:Does this mean - (Score:3, Insightful)
No, perhaps not. However, in terms of marketing, Intel is way ahead of all other processors. The masses have been told to buy computer with "Intel Inside", they remember the crazy men in blue, and the guys in the bunny suits. Of course, they don't really know what "Intel Inside" means, but it's easy to remember and ask for. Consumers feel empowered by saying they want a computer with "500 megapixels memory, 60 googlebites hard memory, and Intel Inside".
Would it increase Mac sales by having an "Intel Inside" sticker on it? Maybe not, but it would have a lot more consumer brand recognition.
Re:O really? (Score:2, Insightful)
Only if you are asking people to think in a different manner.
The Apple tag line is suggesting to people that they should think about the concept of being different.
Therefore they say, "think different."
It's not correct formal grammar, but it is perfectly valid conversational English.
Re:Does this mean - (Score:5, Insightful)
PCs and Apple's have an "architecture" defining how the chips are strung together, how expansion is expected to work, how the interrupt controller works (and yes, which interrupt certain hardwired devices are on), etc. Unlike Apples, for the PC it's not one but many standards defining their function, not one of which defines how the processor should work. Worse still, it's essentially defined as "Be backwards compatible with an PC AT from 20 years ago". No single company really owns it, although many would like to. Even the evil empire has relegated itself to "putting up with cooperation" in this regard.
I find it more likely that Apple will define their own computer architecture using Intel chips. Maybe they will do their own north bridge, in fact much of the traditional PC architecture is emulated in this device, and changing it with something else would make an incompatible system. Let's not forget that much of PC legacy crap is software as well as hardware. If Apple throws all that out the window, they may as well have defined a new Intel based system. You aren't going to install windows on it, nor will you get a regular x86 build of linux to come close to working.
Re:Apple Denies (Score:4, Insightful)
Re:Fat Binaries my not solve everything (Score:3, Insightful)
Data storage is an issue but not one that is that complicated. In fact, it's not that painful to do endian swaps on x86-64 processors, for example, because there's a dedicated instruction in the ISA to do it. If the binary data files have an identifier in them (version number, etc.) then the swap can be done on the fly pretty fast and easily. I worked on a product (back in the early 90s) that had to have all I/O (network, HDD, etc) able to handle endianness issues on the fly because our product ran on both big- and little-endian machines and all were expected to work together in any combinations (server side on either type independently of client side being either type). It's not that hard if your software is written reasonably well (all particular I/O handled in libraries inside your code instead of spread out all over Hell's 40 acres).
And I agree with you about XML being a pig... it uses a lot of CPU cycles but at least it's a memory hog, too
Re:Summary of issues (Score:4, Insightful)
Why is there always the presumption that a system with an x86 CPU will be PC compatible? Someone postulates that Apple may be considering using Intel CPUs, and everyone makes the giant leap of (il)logic that Apple is considering adopting the PC platform as a whole. It is entirely possible to use the same CPU in a totally incompatible system. Look at the Original 68000 based Macs. Were they compatible with the 68000 based Amiga? It is only logical to assume that were Apple to dump IBM and adopt (say) the Pentium-M as their new CPU it would be installed on a proprietary Apple motherboard, not a $40 Abit or Tyan from Taiwan.
Re:Does this mean - (Score:3, Insightful)
I think you're wrong about this, simply because buying a Mac these days is a deliberate decision. People who just want "a computer" go to Wal-Mart or Best Buy or Office Depot and get a box with Microsoft(r)(tm)(c) Windows(r)(tm)(c) and Intel(r)(tm)(c) Inside(r)(tm)(c), because "that's what computers use, right?". (Windows no less than Intel.) Using a Mac is like installing Linux on your x86 PC, in that there's usually a fair amount of thought and research that's gone into the choice.
Re:Here we go again... (Score:5, Insightful)
You'd have to buy OS X and all the software you'd run under OS X.
C'mon, dude. The Mac mini is only $500. Apple has put out a product that seems to address your complaints about "a whole bunch of expensive hardware" as a barrier to checking OS X out, and yet you still complain about the barrier that's no longer there.
Re:unbelievable (Score:3, Insightful)
Apple ships G4 chips with low-end hardware (where price > performance) and laptops (where low heat & battery > performance). The PowerMac line has the desktop performance demons that are strong competitors to the latest Wintel offerings.
If PowerPC was truely competitive, Apple would have stopped shipping G4 chips a long time ago.
If Intel/x86 was truely competitive, they would have stopped shipping Celeron and Pentium M a long time ago.
Intel has very good marketing. That's why people think that they're always fastest, even when they're not. Low-end and Laptop PCs suffer from many of the same design aspects as low end Macs. This is an intentional characteristic, as it allows for machines to be cheaper for your average user. The high end user is going to have to pay fairly heavily for a top of the line machine.
As for laptops, Apple has recognized that these machines are not designed to be high-performance machines, but rather computers designed for doing work on the road. So they've designed them to have long battery lives and low heat disappation. Up until the introduction of the Pentium M/Centrino design, x86 laptops tended toward high performance, short battery lives, and massive heat dissapation. (Trust me, it's quite annoying when your Dell is dead after an hour and a half, and the guy with the Mac next to you decides to stop working and throw in a DVD for the next two hours or so.)
500 bucks (Score:3, Insightful)
You WILL like it, and find a use for it, even if it doesn't become your primary machine.
Disclaimer: I use a Windows laptop for work and have a beloved G5 at home.
Re:Why cheaper!? (Score:4, Insightful)
That alone seems like a good enough reason for this not to happen short of major disaster for the PowerPC platform. And with the dual cores well on the way, according to most sources, I don't see this as a major problem.
D
Re:Does this mean - (Score:3, Insightful)
It was called "one-way" because if the PPC wished too hard, for too long, it would stay a 68020 forever! So Apple started writing software that would emulate the 68020 temporarily when the PPC was at risk.
When the Mac OS was all PPC native code (8.1? 8.5?), the one-way compatibility was turned off and all the PPC chips had to grow up for ever and ever.
The End.
Intel fabbed PPC chips? (Score:4, Insightful)
And if Intel were going to produce a CPU for Apple, why is the assumption x86? Mac OS X Server on Itanium, anyone?
Mostly likely, though, is that Intel's wireless chips are on the menu. WiMax is around the corner and we all know how Apple oh-so-loves to be on the bleeding edge of technology...
Re:Low end Itanium possible - Apple software stack (Score:3, Insightful)
The code base isn't that much of an issue. At the base, it's Unix, and porting Unix-based apps from one architecture to another is relatively painless. (Endianness is an issue, but the IA-64 can handle either big- or little-endian data (instructions are always little-endian)). Of course, a PPC emulator would be required for migration, more easily done on IA-64 than x86[-64].
The Itanium had speed issues, but this has been addressed with the Itanium2. As far as floating point goes, the IA64 has always been a screamer. Virtualizing an x86 PC would be a breeze.
There are still plenty of other explanations for Apple and Intel to be talking (if indeed they are) which make more sense, explanations that have nothing to do with Mac CPUs, but the Itanium idea isn't that whacky. Going to the PPC in the first place was pretty much an inspired leap, Apple may be gearing up for another one.
PPC not an edge / x86 Mac not a PC clone (Score:4, Insightful)
Not true. Apple has two edges. (1) Complete control of hardware and operating system. (2) Mac OS X. Neither of these are PowerPC dependent.
If Apple goes x86 the Mac will simply be an overpriced PC running a pretty gui on top of BSD.
Also not true. An x86 Mac would not be yet another PC clone. Apple could keep much of its current proprietary design and ignore IBM PC compatibility. A computer's architecture is much more than it's CPU.
Re:Why cheaper!? (Score:3, Insightful)
Yellow Box (Score:2, Insightful)
Re:Does this mean - (Score:3, Insightful)
Yeah, and apart from a lot of differences, they are the same as Velocity Engine.
Comment removed (Score:5, Insightful)
Re:Does this mean - (Score:4, Insightful)
If you're going to have a different CPU, clearly you're going to have different binaries. However, I'm not sure you need to be so flippant about it. Do you know about NeXTStep for Intel ? Do you know how hard it was for most companies to recompile their binaries for it? They opened up their projects, pressed "Build" in Project Builder, and it was done. That's how hard it was. The biggest problem was for folks who wrote binary data files ( the endian issue ), but that's pretty easily worked around or avoided, really. The hurdles Apple and it's third party developers would face to provide binaries for *any* gcc-supported CPU are not as huge as many folks seem to think
Yea, if you had a huge investment in current OS X software, you'd have to buy new copies ( more likely upgrades ) if you bought a different machine. That typically wouldn't be the case, though. I'm going to be using my current Macs for years. Most new Macintosh purchases ( like most new WindowsXP purchases ) require buying some new software.
However, just because it could be done doesn't mean it will be done. I just don't think they're going to start making Intel-based Macs any time soon- I can't think of a good reason. If they're in talks, it's likely to be about one of the many other types of non-CPU chips Intel makes.
Re:Here we go again... (Score:3, Insightful)
- Digital hub [apple.com] (Synergenic Applications)
- Unix based
- No worms, no viruses
- Plenty of freeware/Linux ports/3rd party apps
The Dell is a better deal if time and convenience is of "no value" to you.
article misquoted (Score:2, Insightful)
Wall Street Journal reports that Apple will agree to use Intel chips
What the article really reports:Apple Computer Inc. has been in talks that could lead to a decision soon to use Intel Corp. chips in its Macintosh computer line, the Wall Street Journal reported on Monday
Apple hasn't agreed to anything.-c
Re:Does this mean - (Score:4, Insightful)
Then again, the Myriad code was pretty horribly written, and optimized to only compile well under Microsoft's Visual Studio environment. I was stuck on a horrid project porting the code to HPUX and Solaris using MainWin (which basically was a Win32 implementation on top of X11 / POSIX, a porting library for lazy companies that didn't want to invest time and effort in writing truly portable code or rewriting their UI code). Granted, HP's C++ compiler sucked -- it was AT&T Cfront based, and had to be told how to instantiate templates because it had dain-bramaged template support -- but even when we got this stuff working, it wasn't very performant.
Which brings me to another thought -- if Apple switches to x86 or Itanium, we might be in for similar performance surprises. Some code will obviously benefit from a native recompile, but other code might be more performant with a caching code translation mechanism.
Re:Does this mean - (Score:3, Insightful)
I figure three PowerPC processors @ 3.2Ghz should be able to emulate an Xbox without troule.
Punditry (Score:5, Insightful)
(1) Telling people what they already know or are being told by other credible sources.
(2) Being considered a credible source.
(3) Thinking of arguments that sound good suporting what everyone thinks is going to happen.
If there is a bit of recursion going on here, it's simply because the basis of credibility is so flimsy. It also means that credibility is self-reinforcing, which means the hardest thing about being credible is getting on the credibilty gravy train. Which is good, because there are limited spots avaiable.
Mr. Dvorak used a time honored method for obtaining credibility of getting in early, on the ground floor.
From a technical perspective he's a bit late on the Mac/x86 speculation though, which has been rife for nearly twenty years now. However, this is actually a highly sophisticated bit of punditry timing. Apple had been off the punditry radar screen for nearly a decade at the time. You simly cannot excercise punditry on something nobody else is thinking about -- novel ideas have no basis for sounding credibile (see above).
However, by 2004, it was apparent that Apple was no longer irrelevant, that it had not only stopped the bleeding but had built a successful business, established valuable and powerful brand identity, and had reasserted its influence as a design leader, not only in the computer field, but beyond. So people started thinking about Apple again. And, in the same way that old English roads still bear the ruts of Roman chariots, their thoughts naturally fell into the grassy ruts of the MaxOS x86 idea.
Mr. Dvorak's 2004 prediction bears the hallmarks of expert punditry. First the conclusion is public property so well broken-in that nobody is apt to mind if it takes a bit of additional abuse. Secondly , of course, is the exquisite timing that only an ear planted firmly on the ground of public opinion can execute, falling on the heels of Apple's successful iMac by a mere six years. This is probably, ifyou will permit me a bit of nelogizing, the minimal period needed for effective punditric credibilogenesis. Any shorter and you're talking about something that nobody is thinking about yet -- disaster. Any longer and all the good theories for what everyone expects to happen will have been taken, and the whole idea will have to be put back on the shelf for five or more years.
Re:Does this mean - (Score:2, Insightful)
1. If it's not the JVMs, then why are all java desktop apps of size slow? Oh sure, blame the programmer, I dare you.
2. The C/C++ argument is fallacious in its very nature. Comparing well-written java code to crap C code doesn't count (O(n) algorithms vs O(n^2) on string ops, please!).
Here's some intuition why it's fallacious: C/C++ can always express everything that a java app can, only it doesnt have the overhead of a JVM. The runtime translation will always take time during execution, while a C/C++ app had all that done at compile time. As the JVM is itself a C/C++ app, it can only add overhead to a java app in comparison to a C/C++ app.
The "Java is faster than C/C++" argument argues this:
interpretation + JVM + C < C
(speaking in overheads).
I call that false.
Re:Mod parent wrong (Score:3, Insightful)
A hooker is every so much cheaper than a Powerbook.
Plus, they don't care if you never call them again.
Additional bonus in not having to be nauseatingly pretentious.
Re:Does this mean - (Score:3, Insightful)
Which is all part of why I don't think Apple is going to abandon the PowePC. It's too invested in Altivec, for starters. It'd be more likely that Apple would release an OS X for Intel, leveraging some existing cheap PC manufacturing, for some sort of low-low-end machine. People with newer Macs ( and PowerPC-only software ) thus wouldn't buy it, and it'd be like "look at this pathetically cheap stuff you Windows folks are forced to work with, but if you want it cheap, you can at least have it nice and OS X-y"... not that they're going to do that. But they could. By actually having some cheap-ass plant in asia somewhere cranking out nearly-standard Intel PC stuff, they could probably do it cheap enough that they'd be able to keep selling the "true" PowerPC Macs as well.
They *could*, in theory, also go the 'fat binaries' route, just like NeXT did. They stopped making their own hardware and sold _just_ software for x86 machines. According to some [slashdot.org], it actually sold pretty well. If they did it today with OS X, it'd sell a hell of a lot better. And sure, maybe they'd throw in some sort of PearPC-style emulation engine ( maybe they'd "leverage" the existing open source project, what the heck ), that's not a bad idea, although it's clearly a stop-gap idea. I don't use Classic; people in practice upgrade the things they can and only use emulation where they have no other choice ( unless performance is not an issue at all ). People who really objected to getting new apps and moving to OS X are still clinging to OS 9's cold, dead body, and many of them will stay that way until their machines give up the ghost.
My point is that if Apple went to another CPU across the board ( not happening, folks! ), third-party developers would as a general rule, be able to offer cheap 'upgrades' as porting would be a snap, much like it was in the NeXTStep for Intel case. For most people, this would mean new software; emulation would be the exception, not the rule.
Again, I don't think that's the current strategy, unless they're finding that IBM just won't or can't get it together, in which case anything could happen. I think they'll give IBM another couple of years before doing anything drastic though, and this is just pre-WWDC media confusion. Not that I know anything... but IBM is getting a lot of dollars from these game console makers, which hopefully will fund more chip R&D and manufacturing infrastructure, eventually boosting their offerings for Apple. If not, Apple does have options.
On the other hand, the current G5 machines aren't exactly slow. They're pretty damn fast, actually. I think going Intel would have to be about price, and with the Mac Mini, I don't think that's any longer a very valid reason.
Re:PPC not an edge / x86 Mac not a PC clone (Score:3, Insightful)
standard pci (and AGP) bus
commodity ram
ide/sata drives and connections
All the hardware interfaces would be 100% compatible with a pc.
You are not getting low level enough. Think timers, interrupt controllers, etc. All this low-level baggage being carried around from 8088 days. Now toss in the various glue logic
In other words you are only referring to things that plug into the motherboard, I am referring to how things are implemented on the motherboard.