I'll bet that most people aren't willing to shell out $2000+ for an Apple system with the performance of a ~$1000 x86 system when they already have an x86 system.
Exactly. I really love the tiPowerbooks. I *want* one. But that doesn't change the fact that when push comes to shove I'll most likely spend ~$1000 instead of $2799 and get 90%+ of the same capability (Mobile Athlon).
I thought the point was to finally move away from "old" 32 bit code. This 32 bit capability is there for backward compatibility until such time as individuals and companies retire their old 32 bit apps.
Ooops, I wasn't clear. The TPC-C results were 64-bit. Opteron has a pretty good edge on integer performance, 1100
I had read multiple rumors about Intel having something up their bunny-suited sleeves, but most of these rumors had Intel supporting x86-64 -- that is -- copying AMD for the first time. This announcement takes away one of the unique advantages of the Opteron/Athlon64 without following AMD's lead.
If you think running 32-bit code half as fast (1.5 GHz. Xeon vs. 2.8 GHz. Xeon) on a processor that costs four times as much takes away any advantage you're confused.
To me it looks like Opteron is around 8x more cost effective at running 32-bit code.
Further, even on head-to-head TPC-C results, the least expensive Itanic system was only half as good. The Itanic running a non-Linux OS was only 1/7 as good.
Wow you found someone with the same stupid argument as you, do you want some kind of award? A biscuit perhaps?
All you do is spout the same tired, circular arguments that show a complete lack of imagination. I'm sure Apple really wants 3% marketshare rather than 30%. After all, why would it want to make all that filthy money?!? Shareholders? Who cares...
Let's look at one of the silliest arguments in your latest polemic:
Linux running on x86 likewise does not make people flock to the platform.
1) People are flocking to Linux. It is the fastest growing operating system overall, and is taking marketshare much faster than is MacOS X, for instance.
2) Linux lacks commercial applications. MacOS X would solve this particular problem swimmingly. Apple has plenty of commercial software support.
3) Linux lacks UI polish. Guess what, this is MacOS X's strong point. Linux' user unfriendliness and rough edges are often cited as a reason its "not ready for the desktop". If I'm not mistaken, you'll agree that MacOS X is "ready for the desktop".
Therefore, your argument is what is called a "non sequitor". The conclusion doesn't follow from your premises.
We'll just have to agree to disagree. I hope Apple management has a more open mind than you do, but sadly they are probably still content being a niche player rather than an industry force. If the "Mac experience" is really better than everyone should want it for the most people possible.
This discussion has become absolutely absurd. Your entire argument is based on your personal opinions.
And yours, of course, is based on the Truth.
There's a lot of interest in PPC emulators but the proposition is not feasible! Go read up on PowerPC assembly for a little while, then take a look at some x86 assembly. It is not a simple task to emulate one on the other. Several groups have been trying for years to build a PPC emulator on the x86 architecture, it just isn't in the cards.
OK, after a brief Google search, I found SoftMac
From the site:
"All of our emulators run Mac software very quickly, typically delivering 50% to 70% of the clock speed in emulation. In other words, a 500 MHz PC running Windows 98 can emulate the equivalent of a 300 MHz Macintosh Quadra running Mac OS 8. Your results will vary depending on the exact type of PC you are using, the amount of RAM present, the version of Windows being used, video drivers, etc. For a good explanation on exactly what type of PC to use and how fast your results can be, see our Hardware Requirements and Benchmarks page."
This happens to be much more in line with the performance I would expect than your (unsubstantiated) claims would suggest. It is also a concrete example of a 100% complete PPC emulator running on x86.
You need to stop pulling things out of your ass and research them. Apple's AVERAGE margin on hardware is about 25%, read their quarterly statements for that. They make beaucoup cach off their hardware because they're the only ones that sell it and have tight control over their production process. Their high end equipment like PowerBooks have really nice margins reaching towards 30%.
Fine, I'll grant you the point regarding Apple's margins. With the new figures it will require 3-4 copies of MacOS X to equal one Powerbook.
I'm going to cherry pick the rest of you're article since we've already argued many of these points at least once.
OSX would need to support everything Windows does to be a viable alternative to Windows.
Not at all, as long as there is a logo program and an easy location to find the hardware compatibility list. The important thing is that high quality hardware is supported, not junk. And guess what, as Apple marketshare grows, more and more OEMs will support Apple.
Did you eat paint chips when you were young or do you not understand the pond concept? Apple makes very good money selling products to a niche market.
Surely you see that it does not follow that Apple wouldn't make even more money in a larger market. Especially if Apple creates additional market segments (say, the white box Mac crowd). Those who buy white boxes would likely never buy a Mac, and vice versa.
Apple's is a big fish swiming around in a little pond. They cater to the people other computer companies either miss entirely with their marketing or ignore because they desire selling to a lower common denominator.
No, in many markets (like education) Apple is head-to-head with the likes of Dell, Gateway, and Sony.
Dell is a little fish in a very big pond.
Dell is the biggest whale in the ocean.
They have to fight all the other little fish, even the fish building PCs in their garages out of white box parts, to survive.
So does Apple. If you think there aren't plenty of (for instance) students who look at iBook then decide a Compaq laptop is a better value for a variety of reasons, you're delusional.
If you dumped Apple into the big pond they would cease being a big fish and would also find they weren't equipped to survive in the big pond.
Apple could keep all of it's current branding, style and so on. The group that finds that appealing (about 3% of new computer buyers, IIRC) will continue to buy those boxes at Apple's rather obscene margins.
For the other 97%, something different is needed.
Thanks for an interesting discussion, and have a great day!
I present the fact there are currently no fast PowerPC emulators available on the x86 architecture as evidense the task is a hopeless one.
You don't think that it's just that no one cares, particularly?
I'm not going to continue back and forth on the emulation question. IMO it is possible to do decent PPC emulation on x86, given enough time and effort. 'Emulation' could even be accomplished by doing a one-time conversion from the PPC binary to x86 ahead of time - sort of a cross-compile. At least that would eliminate runtime overhead.
You're obviously misinformed about the Carbon API if you think it is portable to the x86 ISA. Carbon exists to allow developers to more easily transition their applications to OSX from ToolBox from classic MacOS. Carbon is the most used 80% or so of all the classic MacOS managers and libraries. It is written specifically to let PowerPC binaries run on both classic MacOS and OSX.
Carbon (IIRC) consists of the '32-bit clean' set of APIs that could be supported under MacOS X without causing performance problems. There is no reason this toolkit couldn't be ported to x86.
Even with the Opteron Apple would still have to sell their platform to people. They would still need to convince PHBs that their platform would be a good move for the company, they'd have to convince schools their products were worthwhile investments, they would have to still convince home users they would be happier using a Macintosh to browse the web and get their e-mail. No matter what processor Macs were powered by they would have to sell their platform. Their platform is what does or does not sell, not the processors.
The platform sells based on many criteria including performance, price/performance, availability and public perception of the company's stability. Apple suffers badly right now in several of these comparisons.
What you really don't seem to pick up about Apple is they are a big fish in a little pond. In the world of Macintoshes they are the king and reigning champion. They have no competition with other people selling Macintoshes and can thus do more with their products.
However (as the switch ad makes clear) Apple does have competition from people selling Windows boxes. If you don't think so, you're living in denial.
As soon as they enter the x86 realm they become a leeeeettle tiny fish in a great big pond. Apple would end up like VA Lin^H^H^H Software. They would be selling a non-Windows operating system on commodity hardware.
They'd be selling a very polished, Unix based OS against Windows. Windows is annoying a lot of people these days. If even 10% of Windows users switched to MacOS X, that would be a tremendous win for Apple.
That is not a business plan for success.
Not surprisingly, I disagree.;-)
I would suspect your solution to that problem is license the OS out to people, that of course would increase adoption. Apple would have to sell ten times more copies of MacOS than they currently sell Macintoshes to make up for the difference in the margins.
What do you think Apple's margin is on a $2799 Powerbook? I seriously doubt it's over 10%. One copy of MacOS X at $300 (97% margin) comes very close to making the same profit. Don't forget that Apple has to produce the OS one way or the other.
With sales numbering around a million machines a year they would need to increase that number by ten just to make as much money as they do now. In order to make the OS attractive to people they would need to support all or at least a signifigant portion of the hardware and hardware configurations that Windows does. As we know, hardware vendors are none too friendly in developing non-Windows drivers for their products.
Apple already has support for a tremendous (and IMO sufficient) PC hardware base - you know, the same hardware that's currently used with Macs. AGP cards, PCI cards and USB peripherals. Nothing needs to chang
Point 1: Any systems that Apple ships with a PPC970 in them will get "World class performance" on a par with a P4, if not handily spanking it.
All right, you've finally spurred me into looking into this chip. The performance figures from IBM, at 1.8 GHz. (fastest initial speed grade, same as Opteron) are:
937/1051 SPECINT2000/SPECFP2000
That is somewhat lower integer performance and about the same FP performance as the 1.8 GHz. Opteron (fastest speed grade currently shipping).
So yes, competitive performance...but at what price? If IBM ships this at a reasonable price point (or even lower than Opteron), great.
Point 2: IBM makes all of the G3s that Apple currently ships. You buy an iBook? You get an IBM G3 inside. You buy an older iMac? IBM G3. So it's not like Apple would be moving to a new untested company who hadn't proven themselves to be capable CPU producers.
I knew IBM had produced chips for Apple in the past, but wasn't aware they were currently. Thanks for the info.
Point 3: The PowerPC 970 was designed with the same HyperTransport support as the Opteron. The same exact system. IBM is planning on making 4-way and 8-way PPC970 boxen to sell. Apple could easily do the same, and we're talking about performance that wouldn't just "compete" but blow away anything else except possibly the Opteron. Also, keep in mind that Altivec really does turn the tables in a LOT of cases... SSE2 is nice, but it hasn't shown itself to be nearly as easy/nice to code to, nor has it shown the startling difference with regards to performance that Altivec has.
All good points, and Altivec is noteworthy. It'll be very interesting to see head-to-head benchmarks between this and Opteron.
All in all, my prediction is that a move to PPC970 is all but inevitable. Opteron would be interesting, but Apple is in the middle of a software changeover right now... there are still a few million MacOS Classic users to convert to Jaguar/Panther, you know. You tell all of your current users that their brand-new PPC hardware is actually obsolete, because new hardware will be x86-64 and all future applications will be x86-64, and you've just successfully cannibalized your own market and signed your death warrant.
If you read my original post, you'll find I advocated keeping PPC for portable applications. PPC hardware wouldn't be obsolete, it'd be used in the hottest area. Once again, Apple could easily support two processor architectures in MacOS X.
However, presuming Apple and IBM can move things along in a timely manner, the 970 does look like a very reasonable path. I was impressed to see it's power consumption at only 42 W. for the fastest part - that is about 1/2 of Opteron. There is also a 1.2 GHz. 1.1 V. part that only consumes 19 W. That is impressive.
The less impressive part is Apple continuing along as single-source niche player. Its sad that Apple takes that tack, when it could be so much more. MacOS X has every potential to take on Windows across the board. Whether Apple is willing to go beyond the "Switch" ads is the question...
All that said, if PPC 970 Macs come in at around the same price as a comparable Opteron system, my first 64-bit computer might well be a Mac...;-)
The reason I ask is there are absolutely no decent PowerPC emulators for the x86 architecture and figured since you thought it was so easy you might have one lying around. The primary reason for this is the absolute lack of GPRs on x86 and even x86-64 processors. The PowerPC ISA defines 32 32-bit GPRs, the x86 ISA defines 8, the x86-64 defines 16. In order to make up for the x86's lack of GPRs your emulator has to do a LOT of caching just to execute a single instruction. The x86 always ends up doing far more overhead work than actual execution work when emulating PowerPC code.
I'm not sure what you mean by "a LOT of caching". I'd simply implement using the eight x86 GPRs for the first eight PPC GPRs. This would likely be enough for a surprising fraction of routines. For those using more than eight registers, I'd simply use 24 more variables (r9-r32). If these variables are referenced frequently (the appropriate use for a register) they will tend to stick in L1 cache and not suffer too badly in terms of performance. If they are not referenced frequently, the use of a register wouldn't have helped the routine's performance much regardless.
[snip historical 68k emulation discussion]
Even the fastest Athlons and P4s out right now would have a hell of a time emulating so much as a 300MHz G3, not even bringing to question G4s and their vector units.
An Opteron is not going to do a whole lot better despite its performance advantage over current x86 chips.
Despite having four more general purpose registers and such low memory latency? I disagree.
I'm pretty sure the performance would be more like an ~1 GHz. G4, sans Altivec. I doubt emulating Altivec would be worthwhile (though perhaps some routines could be mapped to SSE2). My approach, though, would be to report the emulator as a G3. All Mac software supports the G3.
Wow Apple could release x86 Macs that run their current software like a 300MHz G3 (ie. like crap)
I see you've taken your 300 MHz. theory and run with it...;-)
and then use a processor no native software would run on.
Except any recompiled Cocoa or Carbon app, or any out of the box Java app. I expect software developers would have little difficulty recompiling, testing and distributing. I'm pretty sure they'd be happy with that given the potential for 10x or more growth in the Mac software market.
That means a short while after they get their third party developers moving away from Classic and Carbon development they expect them to release their software compiled, bug tested, and supported for an x86 platform.
Yes, by checking a second architecture check box.
If NeXT/Apple can't pull this off flawlessly by now, they might as well go out of business. NeXT did a great job with far fewer resources over fifteen years ago.
Their third party developers would drop them like a bad habit.
That's certainly what I'd do if Apple came out with best-of-breed hardware. Not.
In fact, if Apple actually had the world's fastest Unix workstations, I suspect they'd gain very substantial marketshare. Marketshare attracts developers, it doesn't alienate them.
With no third party developers Apple would be little more than NeXT with a cooler logo. MacOS X would die from neglect just like OS/2 and BeOS did.
If your previous prediction actually happened then this would follow...however I'm quite sure that moving to Opteron (especially if third party clones were allowed) would boost Apple's fortunes, not the opposite.
ASUS nForce Pro 3 motherboards will be available in June. This chipset doesn't support dual processors, however. All other motherboards for the Opteron in the near future are likely to be for servers only, and therefore pricy (and not ATX).
Via is also doing an Opteron workstation chipset (including AGP), and it will support dual CPUs. Sorry, I don't have a link handy.
Opteron will be a very popular workstation CPU, IMO.
Its not technical issues that are keeping Apple from releasing a port for x86.
That is a central part of my thesis, yes.;-)
If they did that, two issues would bring them down: supporting the wide array of hardware on x86
They already support a wide enough array of hardware - and guess what it is all the same as the PC hardware. AGP, PCI and USB...sound familiar? Heck, NVIDIA is even making Fireware chipsets these days...;-)
and piracy of the operating system. Right now I might be pirating a copy of Jaguar to run on my Mac, but I have to have bought a Mac in the first place, so Apple has at least gotten some money out of me. If I take a copy of OS X for x86 and install it on a Dell, Apple sees nothing.
First of all, I addressed this exact issue in my post.
Even if Apple wanted to allow white-box MacOS X boxes (with no special Apple ROM), all they need is at least as good of a licensing/authentication scheme as most of the computer games out there now. Not a big deal, really.
Except, that it was bought by Apple and essentially took it over. MacOS X is OPENSTEP with a different GUI.
I know. The point I was making was that just because you can it doesn't mean you should.
Where would Apple place Opterons on their marketing? Would they market to the high-end desktop crowd?
Their entire desktop and server lineup would switch to Opteron (blade servers, OTOH, might be a good place to offer a PPC option, for lower power consumption).
If they did, would the makers of high-end software actually create two versions of their code, one optimized for each platform (Opteron might be fast but it won't have Altivec)?
Opteron has SSE2, and plenty of software shops are already supporting that.;-) I'm sure Adobe would be quite happy to ditch Altivec, for instance.
Even assuming that development for the two environments would simply be a checkbox away ("Compile for PPC or Opteron?") Apple would basically be either killing PPC or dooming Opteron to failure.
How so? Doesn't each CPU have it's strengths? If not, why support both? It has to be one way or the other...
Software companies would probably pick one system to optimize for and ignore the other (heck, many don't even optimize for Altivec now).
Perhaps, but given decent tools it doesn't have to be that way.
And with all this risk, what exactly would the reward be? What is the prize?
World class performance, which Apple is far from today. Check the article on Adobe's site benching Photoshop on P4s vs. Macs.
Avoiding some future that may never come where IBM doesn't produce a fast enough PPC chip?
Just out of curiousity, has Apple announced it is using an IBM chip? I hadn't heard that, myself...
Not worth it. Why kill the company over a pipe-nightmare?
Why is this scenario a nightmare? Lose your prejudices (against x86 for instance) for a second, and imagine being able to get a Mac that is as fast as any desktop machine on the planet, faster than any Intel box (for real this time), and competitive on price.
All this would come at the "cost" of vastly increased Apple market/mind share. Just think if software starting coming out for MacOS X before Windows...;-)
Apple could make a very nice transition to Opteron/Athlon64. The should do a G4 emulator, allowing acceptable (if not barnburning) performance for PPC executables, just as they did to facilitate the 68k->PPC transition. The native apps would of course scream - and Apple could immediately offer 4-CPU systems, which it has never had.
It wouldn't work. The 68k->PPC transition had PPCs emulating 68k faster than 68k could run within a year!
It isn't necessary that the emulators run faster, just "nearly as fast". The native binaries would kick.
This is not possible with x86, especially with the arrival of the PPC 970.
You people keep talking like this thing is shipping now. News flash: it isn't.
Even when it does, its price/performance vs. Opteron may be pretty poor.
Do you know anything about emmulation and the difficulties involved with this or are you just running off on this one?
What difficulties do you forsee, exactly?
and Apple could immediately offer 4-CPU systems, which it has never had
IIRC they could offer that now with the G4
Then why haven't they? Traditional processors like the G4 need special chipsets to hit 4-way. Opteron doesn't.
and they can *certainly* offer it with the PowerPC 970.
If and when it ships, I suppose you mean. Further, what do you think the cost of the 970 will be versus the Opteron? My guess is that it will be quite a bit more expensive.
I also feel Apple should stick with PPC on the notebook side.
Credability is *gone*.
In your humble opinion.;-)
This would mean that they would need an Opteron Emmulator on the mac, or else this would horribly schism the market.
Nevermind, it would horribly schism the market either way--you do realize that emmulation between these is not going to be a walk in the park? Further, getting people to support fat binaries, such as what happened in the 68k switchover, or to recompile and/or *test* for two separate platforms is not going to happen in most development companies?
No, it means that software vendors should be strongly encouraged (or forced) to supply fat binaries for the two architectures. This is the same scheme that worked fine for NeXT (a much smaller company!) supporting four architectures at the same time.
If Apple chooses to take that approach, it won't solve some of the bigger problems regarding Apple hardware. For instance, Apple being a single-source supplier
You *do* realize that this is intentional on their part, right?
Intentionally stupid, perhaps. This limits their market tremendously, since many large government and private organizations won't buy single-source equipment, period.
and also limited hardware availability at times.
I generally don't notice this. I plugged in a wireless--two-button--mouse into an iBook the other day that the PC crowd had just been using for their presentation and it just worked.
I was referring to limited availability of Mac hardware either because a) Apple can't get enough of certain components or b) Apple can't manufacture enough to meet demand. White box MacOS X boxes would solve these problems nicely.:-)
Regardless, Opteron looks like a very good option.
Only if you completely don't understand the way Apple works as a business.
How do you propose anyone make a G4 emulator "scream" on a processor architecture with only 16 GPRs?
I don't care if it "screams", only that it works at some tolerable pace. Software upgrades to native binaries would be necessary for great performance.
However, with something like a 30-40% CPU power advantage over the 1.25 GHz. G4s, the Opterons should do all right.
Niche marketing can be counter-intuitive, but it's also the classic question of whether you want to be a big fish in a little pond, or a little fish in a big pond.
Apple could sell it's OS for x86 boxes at say $300 a pop. If they manage to capture 3 million installs a year (about 6% of the PC market), that would be $900 million in essentially "free money" (compared with selling hardware anyhow). CDs are quite cheap to duplicate.
Apple chose the former, exerts great influence in its chosen market, and makes a profit in probably some of the worst years ever in the industry.
Along with Dell, which has the opposite business model. Don't be so sure something in the middle wouldn't work...
which in effect nearly triples the development effort for a Mac software vendor. First, you need to build and test an Athlon version (which is not going to be compatible with the Windows version), build and test a PPC version, and then test the PPC emulation version.
You should talk to some ex-NeXT developers. Unlike some other environments, things worked very well across architectures. Further, in this situation the various busses and peripherals are identical, simplifying things further.
Thereby making Apple's already small marketshare even more fragmented, when the obvious sensible thing to do is to get a new high end PPC CPU, drop the G3, and improve G4 compiler optimizations.
Sure, if the new high-end PPC CPU is actually competitive with Opteron, both in price and performance. Also it needs to be available in large volume, though the same could be said for Opteron.
That would be plainly insane. Apple's third party software vendors tend to be smaller, and would have a very hard time hopping from platform to platform. Even some big ones have not completed the OS X transition, and you're talking about going to x86 and back?
If circumstances warrant, that is a nice option to have. As I stated, though, I doubt it would happen that way.
At any rate, I think you are vastly overestimating the complexity involved. Cocoa code is very portable.
It's very doubtful that it's about a chip that would replace the PPC since we've read many, many well-informed examinations of such a move and the technical hurdles would likely ruin Apple.
Those "well-informed examinations" were obviously hogwash.
NeXT supported several, quite disparate, computer architectures - x86, HP PA-RISC, SPARC, and 68xxx. Not only did they use different CPUs, but these systems all had different busses and peripherals! Yet, in general, NEXTSTEP/OPENSTEP ran quite well across all those platforms.
Apple could make a very nice transition to Opteron/Athlon64. The should do a G4 emulator, allowing acceptable (if not barnburning) performance for PPC executables, just as they did to facilitate the 68k->PPC transition. The native apps would of course scream - and Apple could immediately offer 4-CPU systems, which it has never had. Those systems could carry big margins.
I also feel Apple should stick with PPC on the notebook side. PPC is well suited to portable applications, and this gives a clear upgrade path for people who really want to keep their current applications. It also allows Apple to hedge it's bets by keeping current on two architectures. If PPC 980 (or whatever) turns out to be a big win over Opteron2, it's not that big of a deal to switch back. I find that scenario unlikely, however.
Note that Apple could still easily stop people from selling "white box" Opterons running MacOS X, if they choose to keep their (poor in my mind) current business model. It could simply produce Apple Opteron motherboards, incorporating a (probably encrypted) Apple ROM, required for Opteron MacOS X to boot. The DMCA takes care of the rest...:-/
If Apple chooses to take that approach, it won't solve some of the bigger problems regarding Apple hardware. For instance, Apple being a single-source supplier, and also limited hardware availability at times. Regardless, Opteron looks like a very good option.
Slashdot Mirror
Exactly. I really love the tiPowerbooks. I *want* one. But that doesn't change the fact that when push comes to shove I'll most likely spend ~$1000 instead of $2799 and get 90%+ of the same capability (Mobile Athlon).
No DVD-writer but oh well...
Ooops, I wasn't clear. The TPC-C results were 64-bit. Opteron has a pretty good edge on integer performance, 1100
I don't think so.
I had read multiple rumors about Intel having something up their bunny-suited sleeves, but most of these rumors had Intel supporting x86-64 -- that is -- copying AMD for the first time. This announcement takes away one of the unique advantages of the Opteron/Athlon64 without following AMD's lead.
If you think running 32-bit code half as fast (1.5 GHz. Xeon vs. 2.8 GHz. Xeon) on a processor that costs four times as much takes away any advantage you're confused.
To me it looks like Opteron is around 8x more cost effective at running 32-bit code.
Further, even on head-to-head TPC-C results, the least expensive Itanic system was only half as good. The Itanic running a non-Linux OS was only 1/7 as good.
Intel is in trouble.
We could root out all the criminals, misfits, homeless, and other undesirables.
We could create a new service under the auspices of the Department of Homeland Security.
We'll call it the S.S., and it can use double lightning bolts for its insignia. Wouldn't that be lovely?
"They that can give up essential liberty to obtain a little temporary safety deserve neither liberty nor safety." - Ben Franklin
Personally, I'm ready for another "bubble".
Let's hope I can keep it straight from now on. ;-)
Yah, it had nothing to do with $800+ OS licensing fees or $5000 development environments...
Sure.
Just think of how much faster you would type if you didn't insert unnecessary apostrophes into words!
IIRC, you use the apostrophe with it to indicate possession, but not for the contracted "it is".
If not, I've been doing it wrong for years...which is entirely possible. ;-)
All you do is spout the same tired, circular arguments that show a complete lack of imagination. I'm sure Apple really wants 3% marketshare rather than 30%. After all, why would it want to make all that filthy money?!? Shareholders? Who cares...
Let's look at one of the silliest arguments in your latest polemic:
Linux running on x86 likewise does not make people flock to the platform.
1) People are flocking to Linux. It is the fastest growing operating system overall, and is taking marketshare much faster than is MacOS X, for instance.
2) Linux lacks commercial applications. MacOS X would solve this particular problem swimmingly. Apple has plenty of commercial software support.
3) Linux lacks UI polish. Guess what, this is MacOS X's strong point. Linux' user unfriendliness and rough edges are often cited as a reason its "not ready for the desktop". If I'm not mistaken, you'll agree that MacOS X is "ready for the desktop".
Therefore, your argument is what is called a "non sequitor". The conclusion doesn't follow from your premises.
We'll just have to agree to disagree. I hope Apple management has a more open mind than you do, but sadly they are probably still content being a niche player rather than an industry force. If the "Mac experience" is really better than everyone should want it for the most people possible.
Think Different.
Mac OS on x86... or PowerPC 970?
Sorry I got that wrong - I'll concede the entire emulator point for the time being.
Take it easy.
And yours, of course, is based on the Truth.
There's a lot of interest in PPC emulators but the proposition is not feasible! Go read up on PowerPC assembly for a little while, then take a look at some x86 assembly. It is not a simple task to emulate one on the other. Several groups have been trying for years to build a PPC emulator on the x86 architecture, it just isn't in the cards.
OK, after a brief Google search, I found SoftMac From the site:
"All of our emulators run Mac software very quickly, typically delivering 50% to 70% of the clock speed in emulation. In other words, a 500 MHz PC running Windows 98 can emulate the equivalent of a 300 MHz Macintosh Quadra running Mac OS 8. Your results will vary depending on the exact type of PC you are using, the amount of RAM present, the version of Windows being used, video drivers, etc. For a good explanation on exactly what type of PC to use and how fast your results can be, see our Hardware Requirements and Benchmarks page."
This happens to be much more in line with the performance I would expect than your (unsubstantiated) claims would suggest. It is also a concrete example of a 100% complete PPC emulator running on x86.
You need to stop pulling things out of your ass and research them. Apple's AVERAGE margin on hardware is about 25%, read their quarterly statements for that. They make beaucoup cach off their hardware because they're the only ones that sell it and have tight control over their production process. Their high end equipment like PowerBooks have really nice margins reaching towards 30%.
Fine, I'll grant you the point regarding Apple's margins. With the new figures it will require 3-4 copies of MacOS X to equal one Powerbook.
I'm going to cherry pick the rest of you're article since we've already argued many of these points at least once.
OSX would need to support everything Windows does to be a viable alternative to Windows.
Not at all, as long as there is a logo program and an easy location to find the hardware compatibility list. The important thing is that high quality hardware is supported, not junk. And guess what, as Apple marketshare grows, more and more OEMs will support Apple.
Did you eat paint chips when you were young or do you not understand the pond concept? Apple makes very good money selling products to a niche market.
Surely you see that it does not follow that Apple wouldn't make even more money in a larger market. Especially if Apple creates additional market segments (say, the white box Mac crowd). Those who buy white boxes would likely never buy a Mac, and vice versa.
Apple's is a big fish swiming around in a little pond. They cater to the people other computer companies either miss entirely with their marketing or ignore because they desire selling to a lower common denominator.
No, in many markets (like education) Apple is head-to-head with the likes of Dell, Gateway, and Sony.
Dell is a little fish in a very big pond.
Dell is the biggest whale in the ocean.
They have to fight all the other little fish, even the fish building PCs in their garages out of white box parts, to survive.
So does Apple. If you think there aren't plenty of (for instance) students who look at iBook then decide a Compaq laptop is a better value for a variety of reasons, you're delusional.
If you dumped Apple into the big pond they would cease being a big fish and would also find they weren't equipped to survive in the big pond.
Apple could keep all of it's current branding, style and so on. The group that finds that appealing (about 3% of new computer buyers, IIRC) will continue to buy those boxes at Apple's rather obscene margins.
For the other 97%, something different is needed.
Thanks for an interesting discussion, and have a great day!
You don't think that it's just that no one cares, particularly?
I'm not going to continue back and forth on the emulation question. IMO it is possible to do decent PPC emulation on x86, given enough time and effort. 'Emulation' could even be accomplished by doing a one-time conversion from the PPC binary to x86 ahead of time - sort of a cross-compile. At least that would eliminate runtime overhead.
You're obviously misinformed about the Carbon API if you think it is portable to the x86 ISA. Carbon exists to allow developers to more easily transition their applications to OSX from ToolBox from classic MacOS. Carbon is the most used 80% or so of all the classic MacOS managers and libraries. It is written specifically to let PowerPC binaries run on both classic MacOS and OSX.
Carbon (IIRC) consists of the '32-bit clean' set of APIs that could be supported under MacOS X without causing performance problems. There is no reason this toolkit couldn't be ported to x86.
Even with the Opteron Apple would still have to sell their platform to people. They would still need to convince PHBs that their platform would be a good move for the company, they'd have to convince schools their products were worthwhile investments, they would have to still convince home users they would be happier using a Macintosh to browse the web and get their e-mail. No matter what processor Macs were powered by they would have to sell their platform. Their platform is what does or does not sell, not the processors.
The platform sells based on many criteria including performance, price/performance, availability and public perception of the company's stability. Apple suffers badly right now in several of these comparisons.
What you really don't seem to pick up about Apple is they are a big fish in a little pond. In the world of Macintoshes they are the king and reigning champion. They have no competition with other people selling Macintoshes and can thus do more with their products.
However (as the switch ad makes clear) Apple does have competition from people selling Windows boxes. If you don't think so, you're living in denial.
As soon as they enter the x86 realm they become a leeeeettle tiny fish in a great big pond. Apple would end up like VA Lin^H^H^H Software. They would be selling a non-Windows operating system on commodity hardware.
They'd be selling a very polished, Unix based OS against Windows. Windows is annoying a lot of people these days. If even 10% of Windows users switched to MacOS X, that would be a tremendous win for Apple.
That is not a business plan for success.
Not surprisingly, I disagree. ;-)
I would suspect your solution to that problem is license the OS out to people, that of course would increase adoption. Apple would have to sell ten times more copies of MacOS than they currently sell Macintoshes to make up for the difference in the margins.
What do you think Apple's margin is on a $2799 Powerbook? I seriously doubt it's over 10%. One copy of MacOS X at $300 (97% margin) comes very close to making the same profit. Don't forget that Apple has to produce the OS one way or the other.
With sales numbering around a million machines a year they would need to increase that number by ten just to make as much money as they do now. In order to make the OS attractive to people they would need to support all or at least a signifigant portion of the hardware and hardware configurations that Windows does. As we know, hardware vendors are none too friendly in developing non-Windows drivers for their products.
Apple already has support for a tremendous (and IMO sufficient) PC hardware base - you know, the same hardware that's currently used with Macs. AGP cards, PCI cards and USB peripherals. Nothing needs to chang
All right, you've finally spurred me into looking into this chip. The performance figures from IBM, at 1.8 GHz. (fastest initial speed grade, same as Opteron) are:
937/1051 SPECINT2000/SPECFP2000
That is somewhat lower integer performance and about the same FP performance as the 1.8 GHz. Opteron (fastest speed grade currently shipping).
So yes, competitive performance...but at what price? If IBM ships this at a reasonable price point (or even lower than Opteron), great.
Point 2: IBM makes all of the G3s that Apple currently ships. You buy an iBook? You get an IBM G3 inside. You buy an older iMac? IBM G3. So it's not like Apple would be moving to a new untested company who hadn't proven themselves to be capable CPU producers.
I knew IBM had produced chips for Apple in the past, but wasn't aware they were currently. Thanks for the info.
Point 3: The PowerPC 970 was designed with the same HyperTransport support as the Opteron. The same exact system. IBM is planning on making 4-way and 8-way PPC970 boxen to sell. Apple could easily do the same, and we're talking about performance that wouldn't just "compete" but blow away anything else except possibly the Opteron. Also, keep in mind that Altivec really does turn the tables in a LOT of cases... SSE2 is nice, but it hasn't shown itself to be nearly as easy/nice to code to, nor has it shown the startling difference with regards to performance that Altivec has.
All good points, and Altivec is noteworthy. It'll be very interesting to see head-to-head benchmarks between this and Opteron.
All in all, my prediction is that a move to PPC970 is all but inevitable. Opteron would be interesting, but Apple is in the middle of a software changeover right now... there are still a few million MacOS Classic users to convert to Jaguar/Panther, you know. You tell all of your current users that their brand-new PPC hardware is actually obsolete, because new hardware will be x86-64 and all future applications will be x86-64, and you've just successfully cannibalized your own market and signed your death warrant.
If you read my original post, you'll find I advocated keeping PPC for portable applications. PPC hardware wouldn't be obsolete, it'd be used in the hottest area. Once again, Apple could easily support two processor architectures in MacOS X.
However, presuming Apple and IBM can move things along in a timely manner, the 970 does look like a very reasonable path. I was impressed to see it's power consumption at only 42 W. for the fastest part - that is about 1/2 of Opteron. There is also a 1.2 GHz. 1.1 V. part that only consumes 19 W. That is impressive.
The less impressive part is Apple continuing along as single-source niche player. Its sad that Apple takes that tack, when it could be so much more. MacOS X has every potential to take on Windows across the board. Whether Apple is willing to go beyond the "Switch" ads is the question...
All that said, if PPC 970 Macs come in at around the same price as a comparable Opteron system, my first 64-bit computer might well be a Mac... ;-)
I'm not sure what you mean by "a LOT of caching". I'd simply implement using the eight x86 GPRs for the first eight PPC GPRs. This would likely be enough for a surprising fraction of routines. For those using more than eight registers, I'd simply use 24 more variables (r9-r32). If these variables are referenced frequently (the appropriate use for a register) they will tend to stick in L1 cache and not suffer too badly in terms of performance. If they are not referenced frequently, the use of a register wouldn't have helped the routine's performance much regardless.
[snip historical 68k emulation discussion]
Even the fastest Athlons and P4s out right now would have a hell of a time emulating so much as a 300MHz G3, not even bringing to question G4s and their vector units.
An Opteron is not going to do a whole lot better despite its performance advantage over current x86 chips.
Despite having four more general purpose registers and such low memory latency? I disagree.
I'm pretty sure the performance would be more like an ~1 GHz. G4, sans Altivec. I doubt emulating Altivec would be worthwhile (though perhaps some routines could be mapped to SSE2). My approach, though, would be to report the emulator as a G3. All Mac software supports the G3.
Wow Apple could release x86 Macs that run their current software like a 300MHz G3 (ie. like crap)
I see you've taken your 300 MHz. theory and run with it... ;-)
and then use a processor no native software would run on.
Except any recompiled Cocoa or Carbon app, or any out of the box Java app. I expect software developers would have little difficulty recompiling, testing and distributing. I'm pretty sure they'd be happy with that given the potential for 10x or more growth in the Mac software market.
That means a short while after they get their third party developers moving away from Classic and Carbon development they expect them to release their software compiled, bug tested, and supported for an x86 platform.
Yes, by checking a second architecture check box.
If NeXT/Apple can't pull this off flawlessly by now, they might as well go out of business. NeXT did a great job with far fewer resources over fifteen years ago.
Their third party developers would drop them like a bad habit.
That's certainly what I'd do if Apple came out with best-of-breed hardware. Not.
In fact, if Apple actually had the world's fastest Unix workstations, I suspect they'd gain very substantial marketshare. Marketshare attracts developers, it doesn't alienate them.
With no third party developers Apple would be little more than NeXT with a cooler logo. MacOS X would die from neglect just like OS/2 and BeOS did.
If your previous prediction actually happened then this would follow...however I'm quite sure that moving to Opteron (especially if third party clones were allowed) would boost Apple's fortunes, not the opposite.
As I told another poster, Think Different. ;-)
Via is also doing an Opteron workstation chipset (including AGP), and it will support dual CPUs. Sorry, I don't have a link handy.
Opteron will be a very popular workstation CPU, IMO.
That is a central part of my thesis, yes. ;-)
If they did that, two issues would bring them down: supporting the wide array of hardware on x86
They already support a wide enough array of hardware - and guess what it is all the same as the PC hardware. AGP, PCI and USB...sound familiar? Heck, NVIDIA is even making Fireware chipsets these days... ;-)
and piracy of the operating system. Right now I might be pirating a copy of Jaguar to run on my Mac, but I have to have bought a Mac in the first place, so Apple has at least gotten some money out of me. If I take a copy of OS X for x86 and install it on a Dell, Apple sees nothing.
First of all, I addressed this exact issue in my post.
Even if Apple wanted to allow white-box MacOS X boxes (with no special Apple ROM), all they need is at least as good of a licensing/authentication scheme as most of the computer games out there now. Not a big deal, really.
I know. The point I was making was that just because you can it doesn't mean you should.
Where would Apple place Opterons on their marketing? Would they market to the high-end desktop crowd?
Their entire desktop and server lineup would switch to Opteron (blade servers, OTOH, might be a good place to offer a PPC option, for lower power consumption).
If they did, would the makers of high-end software actually create two versions of their code, one optimized for each platform (Opteron might be fast but it won't have Altivec)?
Opteron has SSE2, and plenty of software shops are already supporting that. ;-) I'm sure Adobe would be quite happy to ditch Altivec, for instance.
Even assuming that development for the two environments would simply be a checkbox away ("Compile for PPC or Opteron?") Apple would basically be either killing PPC or dooming Opteron to failure.
How so? Doesn't each CPU have it's strengths? If not, why support both? It has to be one way or the other...
Software companies would probably pick one system to optimize for and ignore the other (heck, many don't even optimize for Altivec now).
Perhaps, but given decent tools it doesn't have to be that way.
And with all this risk, what exactly would the reward be? What is the prize?
World class performance, which Apple is far from today. Check the article on Adobe's site benching Photoshop on P4s vs. Macs.
Avoiding some future that may never come where IBM doesn't produce a fast enough PPC chip?
Just out of curiousity, has Apple announced it is using an IBM chip? I hadn't heard that, myself...
Not worth it. Why kill the company over a pipe-nightmare?
Why is this scenario a nightmare? Lose your prejudices (against x86 for instance) for a second, and imagine being able to get a Mac that is as fast as any desktop machine on the planet, faster than any Intel box (for real this time), and competitive on price.
All this would come at the "cost" of vastly increased Apple market/mind share. Just think if software starting coming out for MacOS X before Windows... ;-)
It wouldn't work. The 68k->PPC transition had PPCs emulating 68k faster than 68k could run within a year!
It isn't necessary that the emulators run faster, just "nearly as fast". The native binaries would kick.
This is not possible with x86, especially with the arrival of the PPC 970.
You people keep talking like this thing is shipping now. News flash: it isn't.
Even when it does, its price/performance vs. Opteron may be pretty poor.
Do you know anything about emmulation and the difficulties involved with this or are you just running off on this one?
What difficulties do you forsee, exactly?
and Apple could immediately offer 4-CPU systems, which it has never had
IIRC they could offer that now with the G4
Then why haven't they? Traditional processors like the G4 need special chipsets to hit 4-way. Opteron doesn't.
and they can *certainly* offer it with the PowerPC 970.
If and when it ships, I suppose you mean. Further, what do you think the cost of the 970 will be versus the Opteron? My guess is that it will be quite a bit more expensive.
I also feel Apple should stick with PPC on the notebook side.
Credability is *gone*.
In your humble opinion. ;-)
This would mean that they would need an Opteron Emmulator on the mac, or else this would horribly schism the market.
Nevermind, it would horribly schism the market either way--you do realize that emmulation between these is not going to be a walk in the park? Further, getting people to support fat binaries, such as what happened in the 68k switchover, or to recompile and/or *test* for two separate platforms is not going to happen in most development companies?
No, it means that software vendors should be strongly encouraged (or forced) to supply fat binaries for the two architectures. This is the same scheme that worked fine for NeXT (a much smaller company!) supporting four architectures at the same time.
If Apple chooses to take that approach, it won't solve some of the bigger problems regarding Apple hardware. For instance, Apple being a single-source supplier
You *do* realize that this is intentional on their part, right?
Intentionally stupid, perhaps. This limits their market tremendously, since many large government and private organizations won't buy single-source equipment, period.
and also limited hardware availability at times.
I generally don't notice this. I plugged in a wireless--two-button--mouse into an iBook the other day that the PC crowd had just been using for their presentation and it just worked.
I was referring to limited availability of Mac hardware either because a) Apple can't get enough of certain components or b) Apple can't manufacture enough to meet demand. White box MacOS X boxes would solve these problems nicely. :-)
Regardless, Opteron looks like a very good option.
Only if you completely don't understand the way Apple works as a business.
Think Different.
I don't care if it "screams", only that it works at some tolerable pace. Software upgrades to native binaries would be necessary for great performance.
However, with something like a 30-40% CPU power advantage over the 1.25 GHz. G4s, the Opterons should do all right.
Apple could sell it's OS for x86 boxes at say $300 a pop. If they manage to capture 3 million installs a year (about 6% of the PC market), that would be $900 million in essentially "free money" (compared with selling hardware anyhow). CDs are quite cheap to duplicate.
Apple chose the former, exerts great influence in its chosen market, and makes a profit in probably some of the worst years ever in the industry.
Along with Dell, which has the opposite business model. Don't be so sure something in the middle wouldn't work...
which in effect nearly triples the development effort for a Mac software vendor. First, you need to build and test an Athlon version (which is not going to be compatible with the Windows version), build and test a PPC version, and then test the PPC emulation version.
You should talk to some ex-NeXT developers. Unlike some other environments, things worked very well across architectures. Further, in this situation the various busses and peripherals are identical, simplifying things further.
Thereby making Apple's already small marketshare even more fragmented, when the obvious sensible thing to do is to get a new high end PPC CPU, drop the G3, and improve G4 compiler optimizations.
Sure, if the new high-end PPC CPU is actually competitive with Opteron, both in price and performance. Also it needs to be available in large volume, though the same could be said for Opteron.
That would be plainly insane. Apple's third party software vendors tend to be smaller, and would have a very hard time hopping from platform to platform. Even some big ones have not completed the OS X transition, and you're talking about going to x86 and back?
If circumstances warrant, that is a nice option to have. As I stated, though, I doubt it would happen that way.
At any rate, I think you are vastly overestimating the complexity involved. Cocoa code is very portable.
Except, that it was bought by Apple and essentially took it over. MacOS X is OPENSTEP with a different GUI.
The challenge for Apple, today, is twofold: how to increase marketshare, and how to offer competitive CPU power.
I'm quite sure Opteron systems (especially if Apple did allow white box competition) would satisfy both goals.
And yes, I mean without sacrificing margins.
Those "well-informed examinations" were obviously hogwash.
NeXT supported several, quite disparate, computer architectures - x86, HP PA-RISC, SPARC, and 68xxx. Not only did they use different CPUs, but these systems all had different busses and peripherals! Yet, in general, NEXTSTEP/OPENSTEP ran quite well across all those platforms.
Apple could make a very nice transition to Opteron/Athlon64. The should do a G4 emulator, allowing acceptable (if not barnburning) performance for PPC executables, just as they did to facilitate the 68k->PPC transition. The native apps would of course scream - and Apple could immediately offer 4-CPU systems, which it has never had. Those systems could carry big margins.
I also feel Apple should stick with PPC on the notebook side. PPC is well suited to portable applications, and this gives a clear upgrade path for people who really want to keep their current applications. It also allows Apple to hedge it's bets by keeping current on two architectures. If PPC 980 (or whatever) turns out to be a big win over Opteron2, it's not that big of a deal to switch back. I find that scenario unlikely, however.
Note that Apple could still easily stop people from selling "white box" Opterons running MacOS X, if they choose to keep their (poor in my mind) current business model. It could simply produce Apple Opteron motherboards, incorporating a (probably encrypted) Apple ROM, required for Opteron MacOS X to boot. The DMCA takes care of the rest... :-/
If Apple chooses to take that approach, it won't solve some of the bigger problems regarding Apple hardware. For instance, Apple being a single-source supplier, and also limited hardware availability at times. Regardless, Opteron looks like a very good option.
No that is not "exactly what these people are doing", as has already been explained in some detail.
The issue is broad physical/chemical/biological principles, not the exact track of life on Earth, per se.