Apple Switching To Intel Chips In 2006

telstar writes "According to C|Net, Apple has officially decided to drop IBM, and will use Intel processors starting in their '06 line of systems. This change was rumored last month. The announcement is expected Monday at Apple's Worldwide Developer Conference in San Francisco, at which Chief Executive Steve Jobs is giving the keynote speech." From the article: "Apple successfully navigated a switch in the 1990s from Motorola's 680x0 line of processors to the Power line jointly made by Motorola and IBM. That switch also required software to be revamped to take advantage of the new processors' performance, but emulation software permitted older programs to run on the new machines."

Hello Pear!

[eltoyoboyo (750015)]

Looks like they will want to snap up a bunch of developers from the PearPC project!

Any Evidence At All?

[GaryPatterson (852699)]

There's nothing to substantiate their story. It's all down to "CNET has learned..." and nothing else.

Is this yet another rumour? Is there anything to be read in Apple meeting with Intel above the idea that they might go PCIe instead of PCI-X?

Re:Any Evidence At All?

[by Anonymous Coward]

Unlike ASOT, I cannot post actual information without fear of losing my job. Because I'm not sure if the exact specs on what I was given is some type of loyalty test to track down leaks. Since Think-Secret doesn't have it yet.

Now, I have no evidence if we have Intel based Macs hiding anywhere. But, I do have evidence of the next PowerMac (yah, yah we just speed bumped them). But, it means at least one more generation of PowerMacs that are 970 based.

Now it could be we are switching to Intel chips and when I walk in Monday, I will learn all my work has been for naught. But, I think since I have access to a PowerMac unlike any other, I should also be allowed to know about a platform switch, but who knows.

Must be a slow news week at CNET...

[MuckSavage (658302)]

Really, this has been on the table many times. When will this rumor die? Oh, and on tuesday, Steve will announce that Disney is purchasing Apple.

It is NOT official

[vivek7006 (585218)]

From the report IBM, Intel and Apple declined to comment for this story. How the hell does that make official?

New device

[BWJones (18351)]

So while this is technically feasible, I doubt that Apple is planning a wholesale switch to Intel chips as there is too much invested in both marketing and developer relations. From a technical perspective, Darwin runs on both platforms and there have been long standing rumors of Apple maintaining dual codebases for current OS X releases, so making things run would not be a problem. Developers however, would require significant resources to recompile their code for compatibility. I suspect that the News.com story is only partially correct. Apple has for some time been using Intel chips in their Xserve, and their may very well be additional products yet to be announced. However, think about this possibility: Apple has significant resources devoted to Altivec just about everywhere in the OS, functions that are not available in any currently shipping Intel chip. But imagine this: What if rather than OS X being run on x86, Intel were to produce a PPC chip with Altivec? I do not know what the current licensing agreements are with Apple, IBM and Motorola, but if the licensing were prohibitive, perhaps Apple certainly could help with the reverse engineering of such a chip.

Even that seems like a bit of a stretch to me as I suspect the reality is more like Apple will be using Intel chips in a potential variety of new areas. Chips for networking and WIMAX for example. Or.....given the performance of Intel mobile chips relative to Motorola chips, perhaps as a warning shot across the bow of IBM, Apple will announce that Apple portable systems like Powerbooks will move to Intel chips. Even though I am quite the Apple aficionado, I have to admit that Intel is doing some pretty impressive portable CPUs. Near future plans for Intel portables include built in WiFi and dual cores. However, I realize that this would introduce more than a little difficulty for developers who have a "portable OS" and a "desktop OS" which would suck.

So....perhaps what is really going to happen is that Intel will produce a "portable" PPC chip for something new? Something like a new Newton? If I recall correctly, my Newton 130 ran an ARM chip, and I believe that Intel has the license rights to develop ARM based CPU cores..... Oh please oh please oh please.....

Transitive Technologies

[Corpus_Callosum (617295)]

I have heard rumors that Apple has been talking to Transitive Technologies about Quick Transit [transitive.com] which is a code translation system that can re-map system calls on the fly as well as do very fast optimized recompilation of native code. Think of it as a JIT for processor emulation.

If the claims about Quick Transit are true, and there is no reason to believe that they are false as evidenced by the product's success runix MIPS code on Itaniums (see here [intldeveloper.com]), then we should actually see a performance increase for PPC applications (not recompiled) running on OS X x86.

If you were Steve and your apps (as well as everyone elses) ran unmodified on intel hardware faster than it ran on your own, you would probably build some boxes based on intel as well.

There may actually be no need for developers to recompile anything. With Quick Transit built into the OS (let's assume it becomes part of OS X), it would be possible to target x86, PPC or even other architectures and yet run at essentially full speed on any deployment architecture. I know this sounds a bit wicked. It did to me as well. I am sure there will be a bit of a performance and memory hit when your applications are not native, but those hits may be completely overwhelmed by silicon horsepower.

If done properly, this could be a very good move for Apple.

This obviously means no Powerbook G5s

[dgrgich (179442)]

I'm sure that others have surmised this. There is absolutely no way that Apple will invest the money in an expensive-for-the-consumer line of computers that will be partially obsolete in less than two years; who in their right mind would buy them?

It also occurs to me - another point that I'm sure others have already thought of - that this may be why they are forced to switch to Intel. They can't get chips small enough for a Powerbook G5 line.

Overlooked points...

[Geiger581 (471105)]

1) IBM has opened up Cell, royalty-free.

2) Apple will never let MacOS run on an open platform/commodity hardware again.

3) AMD has virtually no non-x86 CPU tech.

I predict that Intel will either manufacture a Cell derivative or a big-endian, possibly non-x86 propreitary CPU and chipset.

Intel knows how to make chips, not just x86

[mactari (220786)]

Come on folks, there's a reason Via was able to enter the x86 market so easily. And there's a reason why IBM started making PPCs after Motorla. These folks know how to make computer hardware.

Would anybody be that surprised if Intel started making PPC-esque architecture chips? Don't be. Intel knows Si's at 14 as well as anyone and better than most.

Too many people have taken these rumors to mean Apple's going to release Macintosh for x86. I'm not quite ready to jump that gun just yet.

Re:Intel knows how to make chips, not just x86

[reiggin (646111)]

Mod parent up. This is what I'm thinking as well. Apple owns enough of the PPC rights to simply license Intel to produce chips for them. Afterall, Apple's only gripe with IBM (as was the gripe with Motorola) was a supply problem, not a quality problem. I think Apple is very happy with the archetexture but wants a supplier and developer that can actually handle their needs. Intel is really the only one they can trust. They have the R&D and they have the manufacturing capability. IBM is too spread out, as was Motorola. Intel only does chips. And not just x86, either. I believe that on Monday, Intel will become the new "I" in the A.I.M. Alliance.

Well spank my ass and call me Judy!

[Lisandro (799651)]

John C. Dvorak actually predicted something that happend! [slashdot.org].

I'm scared. Hold me.

Re:MacOSX on x86?

[2nd Post! (213333)]

They could always create their own motherboard, chipset, and drivers. I mean, right now Darwin doesn't run on any x86 other than the 440BX chipset. so if Apple get's it's own chipset I don't see why OS X would run on any other. Right now every release of new hardware has a corresponding point release of the OS that includes firmware and drivers for the new machine.

Re:MacOSX on x86?

[vocaro (569257)]

if Apple get's it's own chipset

ERROR: unnecessary apostrophe overflow

Re:MacOSX on x86?

[travail_jgd (80602)]

If it's true... they'd be foolish not to use only 64-bit processors (maybe dual-cores only). Then again, some site [slashdot.org] reported that Intel was adding DRM to their CPUs and chipsets.

Maybe the DRM was the clincher for Apple.

eWeek says the Intel rumor is wrong.

[Picass0 (147474)]

Dual core PowerPC G5 on the way, not Intel.

http://www.eweek.com/article2/0,1759,1823282,00.as p [eweek.com]

Analysts: Dual-Core PowerPC G5s Due for Apple

Building a G5 PowerBook could be an aesthetic challenge for Apple. The G5 chip tends to consume more power and produce more heat than the G4. Hotter, more power-hungry chips tend to require a thicker, more spacious chassis and larger, higher-capacity batteries--all of which might lead to a more portly PowerBook.

But, analysts say, versions of the 970FX technically already fit into the power envelope needed for Apple to offer a mid- to full-size laptop in the 5-7 pound range. At the moment, two of its three PowerBook G4 portables weigh in at over 5 pounds.

Aiding portability, IBM has also added a power-management feature to the PowerPC 970FX. Called PowerTune, it can cut the chip's clock speed, therefore lowering its voltage, in order to save on power.

Therefore, a 1.8GHz PowerPC 970FX would be a good choice--it would top the current G4 processor--but power management might still be an issue in some other ways.

The 1.8GHz chip "might be 35 watts or something like that. There are plenty of 35-watt [notebook] processors out there. The big problem is you want to get average power [consumption] to be a lot lower. That relies to a large degree on software management," Glaskowsky said. "If I had to pick a reason why it hasn't shown up yet ... I'd say it's [Apple power management] software."

Still, not everyone believes that the Power PC 970FX makes a great notebook chip.

"Right now, from IBM's perspective, the [PowerPC] 970 is a pretty competitive part, but they definitely lack a low-power version," said Kevin Krewell, editor-in-chief of the Microprocessor Report, in San Jose, Calif. "The question is, can you get it low enough--25 watts to 35 watts--in order to get it into something sleek enough for Apple?"

To arrive at the right mix of frequency and performance, Krewell suggests that IBM and Apple might need to consider creating a new G4-G5 hybrid instead of delivering a low-power 970.

"The best route would be to develop a new [processor] core that's somewhere between the G5 and the G4," Krewell said, "But that's a significant design undertaking ... and it's a limited-size market. A redesigned core might be attractive for future multicore processors" for desktops and servers as well, he said.

Apple could also adopt a multicore G4 derivative from Freescale Semiconductor Inc., once the chip arm of Motorola Inc., for its portables, Krewell said.

"That's still a 2006 thing ... and it's designed for the network world," he said. "It would require some modifications. But it's doable."

Representatives from Apple and IBM declined to comment for this story. A Freescale spokesman did not return a call.

Editor's Note: This story was updated to reflect the fact that an Apple representative returned a phone call to eWEEK.com but declined to comment.

Apple vs IBM

[xswl0931 (562013)]

More likely, knowing Steve Jobs, he couldn't get his way with IBM, so he threatened to go to Intel. IBM decided to call the bluff.

Re:April Fools? Right?

[bhtooefr (649901)]

Hmm... something I just thought of...

Did they outright say that Mac OS would be on x86, or just on an Intel chip? If it's on a non-x86 Intel chip, I'm thinking one of two things:

a. Intel's going to be making PPCs. Isn't PPC an open spec?
b. Apple's switching to ARM. However, could Intel get XScale to, umm, scale?

Re:April Fools? Right?

[MyDixieWrecked (548719)]

Did they outright say that Mac OS would be on x86, or just on an Intel chip? If it's on a non-x86 Intel chip

Reading this news made me physically ill. The last time I was this nauseated after reading an article was when Microsoft bought Bungie, my favourite videogame company.

After thinking about it, I realized the same thing. TFA didn't say that apple was switching to Pentium or Xeon or any other x86 processor, just intel branded chips. It's entirely conceivable that either Intell will create a new PPC chip (although how they'll crank one out in a year is beyond me), create a new chip altogether (again, in one year?!), or simply piggyback Altivec onto one of their existing designs (i dunno how good of an idea that is).

I suppose it's most likely that Intel will pop out a mutant chip that resembles something like the bastard child of their current crop of high-performance x86 processors and the current G5; a chip with extra registers, the Altivec vector unit (or multiple units), and some extra instructions (like that spiffy sqrt instruction that the G5 has).

I guess the only thing left to say is "don't knock them until you've got the details."

But I really don't think this is good news at all. I see dark clouds on the horizon.

Re:You heard it here first

[cxreg (44671)]

WINE is not an emulator! It's a translation layer, it's totally useless on a non-x86 platform.

Thanks for the insight. Did you happen to miss the entire point of this slashdot post?

Re:AMD

[FatRatBastard (7583)]

You forget one thing: Intel has a tonne of cash. My pet theory (if the rumor is true): The whole thing was started by Intel, not Apple. IBM have been having some wins with the PPC arch, and been getting good press with the PPC/Cell chips. Same goes with AMD and the x64 arch. MS has been getting a little too cosy with both IBM and AMD. So Intel hedges themselves. While they may not have the technical "mindshare" lead right now, they still do have a SHEDLOAD of cash. So throw a crapload, and I mean a crapload, of cash at Apple to grease the skids. It puts MS on notice, gives them another exclusive tier one client and is a blow to IBM's chip division (cutting off a big revenue stream)

Re:The sky is falling!

[Naikrovek (667)]

you know the world is coming to an end when the best golfer is black, the best rapper is white, apple goes to x86 and microsoft goes powerpc.

good thing i bought armageddon insurance!!

Re:The sky is falling!

[buckhead_buddy (186384)]

Actually, what would be really suprising to me is if Apple moves to Intel chips rather than AMD after the recent blatant Apple-oriented attack by Intel with the Pandora PC (Mac Mini look-alike). It's the popularity of the x86 architecture that's attractive rather than Intel itself.

So unless this direct afront to Apple was mitigated with huge discounts, I doubt Intel will get the deal.

Of course none of this will be public except the choice of chip supplier. We'll have to read the spin from Apple, Intel, and makers of the Pandora like we were reading pig entrails for signs of what's really going on.

Re:The Desperate Need For Validation In The x86 Wo

[GreatDrok (684119)]

Oh, if only those of us with x86 Intel and AMD CPUs could have the sluggish performance and high prices that one can get with a PowerPC system. I feel the jealousy welling up inside of me... :)

I didn't comment on the benchmarks story earlier as I was way too busy but it is now 4:40am and I have nothing better to do...

A lot has been said about the speed of various systems and benchmarks but at the end of the day the only real test for the performance of a computer is how well it runs your work. I have been developing some pretty compute intensive software for the last three months and I have to say that the G5 is a very quick processor. In my benchmarks a 2.3Ghz PPC was able to handily beat a 3.06Ghz Xeon EM64T chip with my code. This is only with gcc at the moment, I expect using the IBM compiler will make a significant difference just as using the DEC compiler on Alpha produced far faster code than gcc could. Opteron is also a very fast chip. So is Centrino. P4 and the Xeon based on it are also fast but clock for clock they are seriously underpowered.

Do not think that because some benchmarks showed what you want (that some cheap tatty Intel box is faster than a high end PPC970) that it is in fact the case. Write your own code and give it a whirl. Heck, my G4 Mac mini (1.42Ghz) is quicker than my Athlon XP 2200+ (1.8Ghz) running my code and it isn't even using Altivec yet.

As for Apple using Intel chips, far more likely it is something derived from the iPod part of their business than the Mac. The PPC970 is not underpowered, it is very quick, very efficient and easily a match for anything Intel has. AMD on the other hand has a very nice CPU in the Athlon64/Opteron and I would be torn to choose between the G5 or Opterons in a cluster as it would come down to performance running our apps as well as price.

Re:Or not

[edp (171151)]

This isn't a bug in the arithmetic; it is an artifact of the design. The calculator is almost certainly using the hardware's double-precision floating-point numbers for calculation. The implementation obeys the IEEE 754 standard for floating-point arithmetic. It represents a number with a sign, 11 bits for an exponent of two, and 53 bits for the significand (the "fraction part" in some sense and including an implicit one bit).

The mathematical number 9533.24 cannot be represented exactly as a double-precision number, because 9533.24 expressed in binary has a repeating string that goes on forever. It is 10010100111101.00111101011100001010001111010111000 01010001111... When you round it after 53 bits, you have 10010100111101.00111101011100001010001111010111000 0101, or 81889908046875/8589934592 or about 9533.2399999999997817.

Similarly, 215.10 is 11010111.00011001100110011001100110011001100110011 00110011001... Rounded to 53 digits, that is 11010111.00011001100110011001100110011001100110011 0011 or 7568158436307763/35184372088832 or about 215.09999999999999432.

The difference is exactly 327852904935829005/35184372088832 or 10010001100110.00100011110101110000101000111101011 1000001101 or about 9318.1399999999997874. However, you cannot represent the difference in double-precision, because it requires too many bits. The result of a subtraction instruction is rounded, and you get 640337704952791/68719476736 or 10010001100110.00100011110101110000101000111101011 1 or about 9318.1399999999994179.

(Caveat: I produced the above numbers with some quick Maple commands. They could be off a bit, but the concepts are correct.)

It might be nice if calculators intended for the general public used decimal arithmetic internally. (But it still would not be able to exactly calculate 1/3 * 3. There will always be limits to mathematical correctness.) But that is an issue of application design; it has nothing to do with correct floating-point results, as mentioned in the post you responded to. The floating-point arithmetic here is correct.