Intel Inside For Apple?

iomud writes "Bear Stearns analyst Andrew Neff predicts that there's a better than 80 percent chance Apple will make the jump to Intel in two to four years. As the relationship with Motorola seems to be weaning the question may be what chip would you like to see in next-generation Macs and why?" It seems important to note that Bear Stearns owns shares of Intel and Dell, and has a banking relationship with Dell and HP. Oh, and even if it didn't, that I can't see any reason why anyone should care what Andrew Neff says. But that doesn't mean it can't be fun to talk about!

Comments

"Performance Boost" a result of the MHz myth?

[Theaetetus]

"Neff, for instance, predicted Apple, which uses chips from Motorola and IBM that currently top out at 1GHz, will switch to Intel, whose chips run at 2.5GHz, to get a performance boost and gain more customers. There's a better than 80 percent chance Apple will make the jump in two to four years, he said." This seems to imply that the 2.5 GHz P4 is 2.5 times as fast as the 1 GHz G4... Which is a joke. However, a lot of people (primarily the ones buying their PCs at Walmart) are great believers in the MHz Myth and will compare the two chips based just on clock speed. This indeed might make more gain in terms of customers for Apple, but at what cost? Chips that run hotter and process fewer instructions simultaneously? How about instead of advertising chips in terms of clock speeds, start marketing them in terms of calculations per second (start comparing gigaflops... in which case, last I checked, G4s were way ahead of Pentiums). -T

Re:"Performance Boost" a result of the MHz myth?

[Toraz Chryx]

No, calculations != cycles

Different processors can handle a different number of instructions per cycle.

and hence, require a different number of cycles to perform the same calculation.

Re:"Performance Boost" a result of the MHz myth?

[DavidRavenMoon]

The ultimate smackdown: Mac versus PC

Dual 1GHz G4 versus 2.2-GHz Sony Vaio RX690G Digital Studio.

"Rather than argue the point, I decided to conduct my own comparison. Apple even provided the actual Photoshop picture used, a full-color photo over 44 megabytes in size, depicting seven bike riders with colorful bikes and helmets. This is the sort of file that graphic artists have to manipulate on a daily basis.

"Apple also sent me a copy of its actual test protocol, including a Photoshop Actions file, a set of scripts that automated the various rendering functions. They also provided a high-end twin-processor desktop Power Macintosh on which to run the tests.

"The Mac was upgraded to the latest version of Mac OS X, 10.1.5. The Sony had Windows XP. I installed the standard retail versions of Adobe Photoshop 7 on both computers."

"Running the tests proved exceedingly simple because Photoshop displays the actual timing of a rendering process rounded off to tenths of a second. Per Apple's directions, I conducted each test four times to deliver the most accurate results.

"Like all Adobe applications, Photoshop is a bit slow to launch. It took 15 seconds on both computers to get ready for the main event.

"In the nine test runs, the Mac came out on top five times, besting the Sony by up to 8.1 seconds. Where the PC emerged victorious, the margin was usually less than half a second.

"In all, the Mac took a total of 35.5 seconds to complete the nine rendering steps. The PC took 50.1 seconds, making it 41% slower according to my calculator's reckoning.

...

"The upshot of all this, however, is that, when someone tells you a Windows box is always faster than the Mac, point them to this article and tell them it isn't necessarily so."

Of course the PC beat the Mac in a game of Quake ;)

Re:"Performance Boost" a result of the MHz myth?

[Golias]

The tougher fact is this: The 2.5GHz P4 is significantly cheaper than the 1GHz G4. You can buy 1GHz G4's in top-of-the-line Macs. You can buy 2.5GHz P4's at Costco.

The ratio is, literally, "bang for the buck". At some point the bang for the buck for Intel will so outstrip the PowerPC that Apple simply won't have any choice but to make the jump. Thankfully, once Apple's got everyone on board on MacOS X, the procedure isn't too evil. NeXT did it once already.

P4's are cheaper to buy, yes. However, they consume more power and run hotter, which makes the G4 a vastly superior choice for laptops (even in bang for the buck comparisons).

As for the notion that the gap will widen and Apple will be forced to switch, keep in minds that in the desktop market the x86 archetecture has always had a ! for $ edge over any Motorolla/Apple system (with the exception of the original Apple ][, in which Woz chose a Moto knock-off over Intel chips because they were cheaper). I'm fairly sure that no Mac has ever given you more flops-per-dollar than whatever the prevailing Wintel box of the day was... Not so much because the chips are so much more expensive (although the do cost a little more), but because Apple's superior operating systems have let them sell their boxen with a much higher profit margin than companies like Compaq (RIP) and Packard Bell (Ditto), who had no way of really making their computer stand out from the budget systems from your local neighborhood screwdriver shop (or the no-name vendors who get all their sales from good scores on Pricewatch.com).

So yea, Apple could (in theory) save about $50 a system (their cost) by moving everything over to Intel. But they would also end up increasing the odds that somebody could reverse-engineer their ROMs (as Compaq once did to IBM), and suddenly all those "Pricewatch Special" shitbox PC's and PC Mo-Bo kits (and I say that as a big fan of "Pricewatch Special" shitbox kits) will be able to run OS X after a simple chip-mod, and Apple would die a horrible death shortly thereafter, making version 10.5 (or whatever) the last Mac OS ever.

Nobody can make enough money to sustain a company by writing operating systems for commodity PC's sold by other vendors. Microsoft doesn't; they make the big bucks selling their Office Suite (which is MS's Real Monopoly if you ask me). Red Hat also doesn't; they sell and support an OS that they did not have to write or buy, and is being constantly dev'd by people they don't pay. Remember when we were told in the pages of "In the Beggining Was the Command Line" that Be would be the wave of the future? Be is gone. Remember when they tried to revive the Amiga OS? Remember when Gateway bought it to port to x86? Remember when the chumps they sold it to were going to release something?

Apple learned the hard way during their 1-year attempt at "clone" licensing that the only way they can develop a desktop OS and make money doing it is if they sell every single computer that runs it. By using a chip that is not a commodity part, they raise the barrier of entry to somebody that wants to copy their ROM settings and make a rival motherboard. Switching to an x86 archetecture jeopardizes that plan. Some think that this is part of the reason why Apple became interested in StrongARM technology last time their relations with Motorolla became strained. If they were to drop Motorolla, I'm guessing that they would be far more likely to contact some other chip maker (i.e., IBM, Siemens, TI, Lucent, AMD, whoever) and contract them to make another non-x86 chipset for them... maybe even one that already understands the existing G3 instructions. For that matter, buying those high-performing G3's that IBM is already making for their servers might even make more sense than moving to Intel.

Still, I can't help but think that a lot of these rumors get started by Apple turf-layers, who are hoping to light a fire under the asses of Motorolla engineers.

Not clawhammer

[Perdo]

Sledgehammer. Opteron. Whatever.

Not Itanic.

Not Pentium 4

Not C3 (heh, I just benched a C3 800. It performed about as well as a 266 PII except with the P4's weird imbalanced interger performance. the numbers looked about like a P4@500mhz)

Stick a few Opterons in an Apple and you take Apple back to the good old days where their hardware actually outperformed the x86 boxes and was still somewhat unique.

Let Apple shine again... not just on the outside, but on the inside too!

Switch and die

[jpt.d]

if ([apple switchTo intel])
[apple killSelf];

The real question is...

[BitGeek]

We all know that PowerPC chips get far more done in a given clock than x86 chips.

This was the great promise of the PowerPC, actually. By going to a superscalar Risc architecture, IBM and Motorola spent the effort to get a chip that really did more per clock.

The clock rate, however, is less of an engineering issue than a process issue. Intel has processes that increase their clock rate rather fast-- and so rather than re-engineering their processors (and paying the backwards compatibility penalty that apple paid when they switched from 68k to PPC) they have simply increased the clock rate and integrated more on chip cache, etc.

The thing is, this means that the PPC was at a very significant competitive advantage-- its really hard to beat architecture engineering, which the PPC has in spades, but pentiums lack. Design is hard. Process is easy. So, the Processes that Intel was using should have migrated to Motorola and IBM, and we should be seeing PowerPCs that run at 2GHz and leave no question as to the fact that the powerpc is much much faster.

So, the real question to my mind is-- why hasn't the process side of the house for PowerPCs kept up with intel? Certainly motorola and IBM have the know how, and they have the motivation-- competition with each other for the sizable sales to Apple, and the possibly even larger embedded and workstation markets.

I can think of two possibilities:
1) The increased complexity of a super scalar architecture on the order of the PPC makes timing more problematic and while process is there for higher speeds, the synconization of the clocks hitting all the subcomponents of hte processor at the same time is an issue. At these levels, the speed of light is a real factor when one signal goes a little further than the other, they arrive at the same place at different times due to the relative slowness it takes for the signal to go down the longer path.

2) Conflict. Motorola created Altivec and apple jumped all over it, and I don't believe IBM has a license to Altivec, giving motorola a bit of a monopoly. This combined with apple embracing altivec so much means that Motorola may not have sufficient incentive to grow the speeds. Plus, since the PowerPC has not had the widespred platform support that was expected-- NT for PPC has gone away, other Unix box makers aren't using it extensively, the market is smaller than was originally intended.

This creates quite a problem for apple. As long as they suffer from the perception- despite the reality-- that their processors are slower because people think MHz = speed-- they are going to have trouble not being seen as more expensive. Hell, even people who post here make this mistake.

So, I think Apple is planning something big. But it won't be a switch to x86, certainly as we know it.

I can imagine a couple possibilities:
1) Apple teams with AMD and brings the PPC instruction set to a future AMD processor that can handle it and the x86 instructions simultaneously. Gets AMD's process speeds, along with PPC compatibility running at native speeds (rather than emulated.) The downside is that IBM would have to agree to this, and its not clear what IBM's upside is-- unless IBM is part of the alliance and gets a competitive advantage to using this technology in its products (maybe low end power workstations)-- but still Motorola which controls altivec would have to be involved.

2) A new AIM partnership, this time its the AAIM partnership, all four companies collaborate on a new chip that will run OS X and Windows, IBM and Moto make PCs that dual boot, AMD gets Altivec and Power4 Multichip module technology, and IBM and Moto get AMD process technology, and IBM, Moto fab the chips for AMD. This gives IBM a weapon against windows, namely OSX, gives AMD the backing of two big competitors- IBM and Moto, along with a new customer, gives Moto a new jumpstart into the box making business that it gave up when Apple stopped subsidizing the clones industry.

3) The Death By Numbers Approach -- Apple goes to IBM and gets the four chip Power technology and migrates there from PowerPC, greatly increasing the volumes of these chips for IBM which is only currently using them in their servers and workstations. This drives down the costs, apple doesn't have to rewrite software (like quicktime) that was never part of the NeXT OS, and at the same time can emphatically claim the "fastest PCs in the world" title it now holds but nobody recognizes. Oh, and they sell them with 2 to 4 processor units per box.

4) Death By Numbers part 2-- apple starts shipping quad and 8 way PowerPCs running at moderate speeds, 1-2GHz using Motorola (or IBM) chips, and being competitive on price because the powerpc costs them so much less per cpu than Intel CPUs. Thus people will instinctively know that 8 1GHz CPUs are going to get a lot more done than one 3GHz intel cpu.

5) The Second Rebel Alliance-- Apple, AMD and Nvidia team up on an x86 processor that uses NVidea and AMD Hyper IO (or is it rapid io?) technology, and apple does go the x86 way..

The thing is, 5 seems least likely to me. apple has just migrated accross platforms for the second time-- the first was 68k to ppc, and the second is classic Mac to OS X. Applications have to be re-written.

Are they really going to ask their developers to re-write their apps yet again, in only a few years? I really doubt it.

So, I think there is a new processor architecture or solution coming-- I'm sure apple recognizes that the PPC has not given it the marketability it needs.

But I think that solution will be PPC compatible natively.

Re:The real question is...

[danielwright]

You're oversimplifying things a little too much when you say that if a PowerPC chip were made with the same process that Intel uses for it's new P4s, it would have the same clock rate.

Modern CPUs are all pipelined, so they divide each instruction into several pieces - say Instruction Fectch, Instruction Decode, Execute, Load/Store, Write Back for example. Then, they interleave the execution of the different stages, so while one instruction is being decode, the next is already being fetched.

At a very rough approximation (it's much more complicated than this), the clock rate has to be low enough that the largest of the pipeline stages can execute in one clock tick, so if tou divide up the execution into more, smaller stages, you can raise the clock rate higher. However, there's a lot of complex machinery to avoid "hazards" where instructions depend on each other, so they have to stall some of the instructions, and this gets more complicated and slower with a longer pipeline. (This would be a gross simplification 10 years ago, and today's CPUs are much more complicated, but it gets the main point across).

The designers of the current PowerPC implementations chose fairly short pipelines (I'm not sure of the number of stages, but I think it's around 5), while Intel uses 20 stages for the P4. That means that the P4 can run at a higher clock rate, but get less done per cycle because more of the instructions are stalled.

So, my point is, at least IBM has CPU processes at the same level as Intel's, if not better - it's due to the fundamental design of the chip that the GHz number is lower, which makes the GHz a very uninteresting measure - hence the "MHz Myth".

Also, PowerPC is an instruction set, like IA32 or IA64, it's not a chip architecture. IBM and Motorola currently make chips that implement the PowerPC instruction set (and IBM's chip, the Power4, is currently the fastest chip available, BTW).

Just to add to the list of totally unfounded predictions, here's mine:

IBM released the Power4 a few months ago, as the fastest chip on the market. They want to use it for every server platform they make (AIX boxes, mainframes and AS/400 boxes). It's designed for servers, and that shows - you need something like 1 ton of force to attach it to the motherboard, and a pretty impressive cooling system as well. This makes it unsuitable for small desktop machines like the imac, and for laptops. Also, it doesn't support Altivec. I figure, they'll work out some licensing agreement so they can make a special, slightly slower version for Apple that does support Altivec.

The merits of this: they could use basically the same CPU design and processes (which are very, very good), and now software changes.

I don't think Apple can change to Intel chips because that would require new versions of all the software. They've just asked all their customers to replace old OS9 software with OS X software. If they came back in 2 years and said everyone should replace all their software again, their customers would start to get rather irritated by it...

Re:The real question is...

[BitGeek]

I don't consider the "SPEC benchmarks" to be a very good citation-- there are a variety of benchmarks in SPEC, and they certainly don't reflect the instruction mix of modern applications.

For instance, penitums are really good at doing integer calculations but very poor at floating point, yet almost all applications that are CPU INTENSIVE use floating point. Yet Spec gives integer a much higher rating, and generally ignores floating point optimizations that are used in real world situations.

Re:What's the point?

[BitGeek]

Additionally, the size of the Mac user base has steadily eroded

I don't think you can say this. I'm aware of no information that expresses the size of the mac user base.

you often see the "%5 of the market" figure, but that is actually %5 of NEW PC SALES, (so it ignores the fact that People turn their PCs over every 18 moths, but macs are performance competitive a lot longer) oh, and these numbers also ignore most mac sales. So even saying "%5 of new sales" is a lie-- they count Dell, Ingram Micro and CompUSA. They ignore the Apple store, the Apple stores, and the hundreds or thousands of independent apple dealers around the world.

Put a better way, Apple has %5 of the Intel PC market- - because that's the market they count-- and of those people, %5 of the pcs they sell are actually apples!

The total addressable market-- that is, Macs out there in active use-- is much larger, probably %20.

Last time I had any reliable numbers, it was %30, but that was because they were the only company selling CDROM drives for computers and so you could look at the number of those sold and know how much market share apple had... so that would have been the early 90s.

I'm not saying I know what the TAM for Macs is, I'm just saying I've never seen any reliable figures, and the %5 one is clearly unreliable. ( But makes for good copy for those with "Apple is dying" stick who want to beat that dead horse.)

Re:20% of user base on OS X?

[DavidRavenMoon]

Then, how about the figures of people still running 98 or 95? Or even 3.1?

This is true. I think many people buy a PC, or a Mac, and just leave on what ever OS it came with.

These are not people like us mind you.

My brother and his wife are perfect examples.

They each had a PC, my brother a whitebox PC running Windows 3.0 (!) and his wife an old Compaq laptop running 3.1.

This was fine for them, they mostly used it for writing (they are art teachers and poets) until they wanted to get online.

The laptop was the most capable, so they went and got a PCCard modem, but lacked the drivers, and MS removed all the Win 3.1 downloads ... so they bought a 333 MHz iMac (green) and are still running Mac OS 8.6... until I get around to upgrading it to 9.2 :)

They came over one day and looked at my G4 running OS X, and had this bewildered look on their faces... like a dear in the headlghts. Ha!

Most of my PC using friends are still running Win 98, and one runs NT 4.

What creds does this guy have?

[gmhowell]

Okay, he's a staff writer for 'news.com.com'. What journalistic credit does this guy have? "Hi, I own shares of Dell and Intel. Can I write a 'story' that would pimp their stock prices?" Gimme a break. Perhaps the 50 page report has more info in it, but this is incredibly lame.

Apple has historically gone to great lengths to be compatible. First they could read PC floppies. Then fat binaries let 68k machines last for a long time after they were no longer sold. There is the compatibility layer in OSX. The idea is simply absurd.

I know next to nothing about compilers, but doesn't it stand to reason that Apple would have to redevelop most/all of their libraries, to say nothing of the compilers themselves? Particularly if they go off for some 'pseudo-x86' architecture like some are suggesting.

At that point, what will be the difference between Mac and Windows? Would companies even bother with MacOS ports, or would they just make some bit of middleware, so that the same binary could use the ABI of either system? (I'm talking way beyond my knowledge, so if it sounds like I don't know what I'm talking about, I don't.)

What would be gained by this? Go from 5% market share to 6%? Not worth the effort. Having access/drivers to PCI/AGP slots, USB, IDE, etc. makes sense. Not for the main architecture.

Hell, even Transmeta makes more sense than this sort of malarky. Get it to emulate PPC for old apps, ia64 for new stuff, or something like that. But straight Intel hardware? I think not.

Remember, even though they don't say it, the Mac is the 'computer for the rest of us'. While it's no longer the company line, don't doubt for a minute that Steve likes being a member of the elite. He likes it that cool Hollywood types use iMacs for computer scenes. He likes it that the kids of yuppie hipsters carry iPods.

Steve is not a commodity guy. Ask the owners of StarMax machines.

This article (and the one 'proving' the existence of super-duper-top-secret military aircraft) prove that in the eyes of the editors, today was a slow news day. Not slow enough to answer the question "what happens when VA is delisted" but slow, nonetheless.

Re:The future

[feldsteins]

I see Apple making Mac OS XI for x86 but only allowing it to work on special Apple motherboards.

I think that is exactly right.

Apple won't hype the switch that much. They will instead sell some sort of VMWare-like or dual-boot stuff and market the x86 Macs as being able to run Windows at full speed.

Can't see it. What I do see is that Apple will make the switch when a next-gen Intel or AMD processor comes out - and they will wait for it for two reasons. 1. Presumably one of them will find a way to make their stuff a little smaller and cooler. Apple likes things like TiBooks and fanless iMacs. Can't develop shit like that with brick-sized P4 modules can you? No. 2. Apple won't want to pull a "New Coke" on their market. Mac users are loyal to their brand and to their processors. They won't like seeing a switch to a part that has been touted as inferior for so long. This effect will be lessened when a next-gen part comes out which doesn't have quite the history of being bashed by Apple as the current one's do.

Then someone will hack Mac OS XI to work on any motherboard, or some company will reverse engineer the special Apple motherboards and make their own Mac compatible motherboards, and Apple will call out the lawyers.

Apple would never, ever make such a switch unless they were supremely sure that this couldn't happen. If the ability to sell proprietary hardware for the OS went bye-bye then so would Apple itself and they are fully aware of this. It's not just a dinosaur clinging to the old ways...it really is at the core of Apple being able to innovate the way they do. They have to control the OS and hardware of the platform to do what they do. That is the only reason why Dell or Microsoft can't be an Apple. it's not because Apple is "cooler" or even "smarter." It's because they control the entire platform.

Hell, if I worked at Apple I would want to make damned sure that those crown jewels never got lost. I'd rather run the boxes with hampsters in plastic wheels than risk that.

In the long term, anything could happen, but...

[jht]

I don't see this as likely, especially in Neff's timeframe. Here's why. The G4 processor doesn't have the legs that the P4 has right now, but Moto is known to be making at least 1.4 GHz parts right now.

Apple also has a policy of running duallys at the high end, and given XServe, we know they have a motherboard/chipset in-house that supports reasonably modern features like DDR and ATA-100. And unless all the rumor sites are wrong, there's a new PowerMac due no later than Seybold in about a month - possibly this month.

So I figure a high-end Mac with dual 1.4 GHz G4 processors, DDR PC2100 RAM, and ATA-100 support is in the cards shortly. That's going to be a reasonably competitive machine for a while, though not quite up to bleeding-edge Wintel specs. There's also likely a little bit more leg in the G4, at least enough to get up around 2 GHz.

Beyond that, Apple's got some options. They can go to quad processors pretty easily, or by next spring they have a good shot of being up on G5 processors, which are reputedly now in sampling. Should they be making the move to G5, that'll probably carry them another couple of years, so we're talking 2005 at the outside before they have to have the next stop in mind.

A lot can happen in that time. The likeliest thing is that they jump to a 64-bit contender that emerges by then - possibly AMD but who knows? Migrating to the IBM POWER processors would be another logical move because minimal work would be required and the additional volume would drive IBM's own costs down significantly. Remember, Apple sells more RISC systems in a year than Sun, SGI (though they don't control MIPS anymore), and IBM do combined - yet all those companies see it as worthwhile to continue investing in alternative architectures. If Apple decided to move their volume systems to a slightly scaled-down version of one of these workstation chips it would have a major impact on cost.

Or Motorola could get serious and start working hand-in-hand with IBM again - IBM's fab capabilities are way beyond Moto's, and IBM could probably build the same G4 as Moto at a higher clock rate with better yields. There is one key reason, though, why Apple doesn't have to worry too much about PowerPC dying - it's huge in the embedded marketplace. Versions of PowerPC are used in all sorts of devices, and I believe it's pretty popular in automotive and networking. That gets your volumes up, too.

If Apple goes to Intel chips...

[greygent]

If Apple goes to Intel chips, it doesn't necessarily mean they become PC compatible. There are many other things to an architecture...

I imagine if they did go to Intel chips they would do something similar to what SGI did with their x86-based machines, and use a custom architecture with a Pentium chip.

I'm all for Apple going to Intel chips and a custom architecture. I firmly hope that Apple doesn't EVER start making PC compatible machines, and I would wager that if they did, it would lead to their eventual death. I absolutely despise the PC architecture, and aside from OS X, was a major reason for my jump. It's just so... clunky.