PowerPC Goes 64 bit

prostoalex writes "ExtremeTech runs a story about IBM planning to introduce a new 64-bit PowerPC architecture for desktops in October at the Microprocessor Forum. The conference agenda tells us that "this processor is an 8-way superscalar design that fully supports Symmetric MultiProcessing. The processor is further enhanced by a vector processing unit implementing over 160 specialized vector instructions and implements a system interface capable of up to 6.4GB/s"." There's also a News.com story.

Comments

Altivec?

[spookysuicide]

Is that "160 specialized vector instructions" the infamous motorola designed altivec? Is this the next processor apple will use? Does this mean all that intel talk was well.... just talk?
&nbsp
anyone know?

Re:Altivec?

[znu]

It's impossible to be sure, of course, but it's probably AltiVec. The phrase in the article is "over 160 specialized vector instructions". AltiVec has 162.

Re:Altivec?

[binaryDigit]

the infamous motorola designed altivec?

Infamous? It's shipping in all the G4's, so Apple is already using AltiVec. And what Intel talk are you referring to?

Re:Altivec?

[Jobe_br]

If IBM wanted to have any hope at all of wooing Apple, they'd have to support AltiVec as is. There's now way that Apple would recode their OS for a different set of vector instructions and THEN try to convince Adobe, Mayasoft, etc. to rewrite their apps as well. Not likely.

So, yes, its very likely that the specialized vector instructions are exactly the AltiVec instructions. There is *supposedly* an alliance between Motorola and IBM on the PowerPC platform ...

Re:Altivec?

[vought]

IBm has already built G4 chips with Altivec on the mask. I've seen 'em and used 'em - but only in prototypes of 2 year vintage.

Point is, IBM is well-versed in building high performance PowerPC-style chips (invented the core architecture, after all) and has the werewithal to continue as a strong supplier for Apple. Motorola is a badly-run has-been in many respects, and the morale in Austin and their other fabs has been low for many years.

I wouldn't be surprised to see Apple swap the Mach 3 Kernel in Jaguar for something a little more 64-bit savvy down the line.

Re:Altivec?

[hilker]

Infamous? It's shipping in all the G4's, so Apple is already using AltiVec.

Dusty: "What does that mean? Infamous?"
Ned: "Ah, Dusty! Infamous is when you're more than famous! This guy El Guapo is not just famous, he's IN-famous!"

Re:Altivec?

[civilizedINTENSITY]

Can you say "reverse engineering"?

"Moreover, the new PowerPC will have a vector-processing unit with more than 160 specialized vector instructions, the Microprocessor Forum site said. This processing unit, which is similar to Motorola's AltiVec technology, will allow the chip to break up large amounts of data and process them in parallel form. It will be used when the chip is handling graphics or processing signals."

I knew you could ;-)

Re:Altivec?

[Jobe_br]

Indeed. I think a good deal of Apple's 64-bit savviness may depend upon GCC3. When I stumbled on old news concerning Motorola's G5 (85xx) I tried to see if any GCC compatibility existed yet, but I couldn't find anything that pointed in that direction. I thought if GCC3 could target 85xx, there would be a decent possibility that Jag + new G5s in full 64-bit mode might not be too distant.

Who knows ... Apple is so tight about releasing hardware related news and Motorola doesn't seem to really have their act together (as you indicated).

Re:Altivec?

[hyperizer]

He's probably referring to a prediction by Bear Stearns analyst Andrew Neff (who owns Intel stock, BTW). According to the article, "There's a better than 80 percent chance Apple will make the jump [to Intel] in two to four years, he said." Shortly after Neff's report was released, AnchorDesk Executive Editor David Coursey made a similar prediction, predicting the change would take place in less than 18 months. No word on how much Intel stock he owns ;-)

Of course Apple makes virtually all its money from hardware sales, so I can't imagine why they'd want to make such a move. Not to mention, direct competition with Microsoft is never a good idea...

Re:Altivec?

[Elwood P Dowd]

All that Intel talk was just talk.
All this IBM talk is just talk too.

Nobody with insider information is talking right now. That means that nobody knows a damn thing. Everyone is simply surmising about what could possibly happen. And they could all be full of crap.

Re:Altivec?

[beerits]

Is Rich Garces really THAT famous?

I was thinking the same thing. I'm glad there is at least one other Sox fan on slashdot.

eWeek Story

[hatter3bdev]

There is also an eWeek story.

Re:eWeek Story

[civilizedINTENSITY]

From eWeek link:

"What I find is interesting is the fact that IBM can talk about it. If there was committed Mac design, you know (Apple CEO) Steve Jobs would have his hands around IBM's neck not to talk about this chip," said Kevin Krewell, a senior analyst at In-Stat/MDR. "The fact that IBM is talking about it indicates to me that it's not a mainstream Apple product at this time."

Apple switching to intel?

[pstreck]

If these are as good as they sound, all those speculations and rumors of apple switchin to intel are going to be thrown out the back door.

Re:Apple switching to intel?

[bsharitt]

I hope so, I don't think Apple would survive that close to the Wintel world.

Re:Apple switching to intel?

[altarity]

Au contrair... This might be what allows Apple to release a x86 OSX. You have to remember that Apple sells itself as a Premium brand. If they had a chip that trounced anything available in the Intel world, they're HW sales would be safe, no matter a x86 OSX. In fact, apple could use a less HW-integrated OSX, as a hook to get the PC masses started with Apple, so they might consider an apple pc for their next computer.

Re:Apple switching to intel?

[hendridm]

I think Intel would be more happy to work with Apple and their unique desires that Motorola is. Apple seems like a side job on Motorola's plate, whereas Intel has been looking to become less dependent on Windows PCs. Plus, Intel doesn't seem to care where it sells its CPUs to as long as they sell.

Re:Apple switching to intel?

[pstreck]

I don't think it would happen mainly because Jobbs is a control FREAK. He needs absolute 100% control over everything in the computer, there hardware sells what not be safe because of the clones, it would happen no matter what kind of proprietary things apple put into there own hardware.. If someone makes it someone will break it.

Re:Apple switching to intel?

[certron]

If you ask me, all the 'Apple switching to Intel' stories have been pretty much just silly hype. What I think is more interesting, but only slightly less fanciful, is Apple switching to AMD Hammer processors.

I don't follow this whole thing as much as some people, but Apple is part of the HyperTransport consortium (as is NVidia, and AMD), and so there is some speculation that Apple might go with a hammer/nforce combo (with HyperTransport), if they were to make any huge jump to another architechture.

The last jump was from the Motorola 680x0 platform to the current Apple/IBM/Motorola PowerPC platform, and that was a while ago. The problem with this new IBM chip is that it isn't terribly close to being done yet. I guess we'll have to wait and see how it turns out.

Here's a link I dug up: http://www.theinquirer.net/?article=4814

Re:Apple switching to intel?

[Kranium]

Well, I for one don't want a less HW-integrated OS X. What a nightmare. Besides, I think if Apple went to Intel, it would be on an apple board, not an off-the-shelf or Intel board.

Re:Apple switching to intel?

[altarity]

What I meant was that only Macs would have the new Power-4 processor, and that apple sell OSX to run on non-apple Intel PC's as a commerical alternative to Windows. Less control, but it sure would piss off Bill...

Re:Apple switching to intel?

[jandrese]

On the other hand, Jobs might be a control freak because he saw what other people did to Apple when he left. Remember when Gil Amelio left Apple saying "but Jobs won't push the 100Mhz bus technology through fast enough..." That was when I realized just how much the old CEO didn't understand Apple or its customers.

In a lot of ways Apple's story is very similar to SGI. SGI got a new CEO (and old PC guy at that) that immediatly began to waste tons of money building PCs. For some reason CEOs of PC companies get this myopia that prevents them from seeing the future. This leads to conclusions like: Well, PCs are big now, maybe we can do PCs. I heard that Dell, Microsoft, and Intel made a killing in the PC market, I wonder if I can get a chunk of that pie...

Re:Apple switching to intel?

[dbrutus]

Somehow I doubt that IBM is going to withhold their processor from other customers. Apple doesn't have the kind of money to get exclusivity. Others buy PPC today. I expect that to continue.

Re:Apple switching to intel?

[homer_ca]

Silly hype and a way of holding Motorola's feet to the fire to not fall behind in the CPU race. I think Motorola would just as soon ditch the desktop CPU market for the embedded market. It's expensive keeping with AMD and Intel on speed especially when your userbase is so much smaller than x86.

Re:Apple switching to intel?

[Golias]

It's expensive keeping with AMD and Intel on speed especially when your userbase is so much smaller than x86.

Maybe if they got their shit together and made comparably fast chips, the user base they are selling to would not remain so small. Right now the speed gap of Motorola's chips is probably costing Apple more customers than any other negative factor, including the price gap (which is not as wide).

Re:Apple switching to intel?

[Oculus Habent]

But the control Apple has over functionality would cause headaches for Apple, HW vendors, and users alike.

Apple would spend time agonizing over the conflicts and driver issues that the PC world just accepts as the price of business because they would ruin everything Apple is. There's a reason everything they make is smooth white plastic. Because it looks good - like there won't be any hassle.

Vendors would have to do one of three things.

• Develop drivers for Win/x86, Mac/PPC, Mac/x86 (and Linux/x86 + whatever else they feel like)
• All get together and produce unified drivers for their products (yeah, right)
• Give up on a low-income portion of the market (Mac/x86)

While it's possible, and in some ways mutually beneficial, to produce a single driver for all CD-RWs, it would be huge, and it would make innovation difficult. Vendors would probably go to war with Apple over disabling of buggy devices (Apple HW generally works or doesn't - have you noticed?) and they don't want to spend time appeasing Apple SW engineers. They're much more likely to say "Apple can build some friggin drivers for MacOS X86."

Apple also isn't in a position to piss off Microsoft. Part of the appeal of MacOS X is that Office now integrates seamlessly across Windows and Mac (accepting Access *grumble*). They need Microsoft's continued support if they wish to grow.

Anyhow, I'm not sure Microsoft isn't slowly pushing themselves away from Windows. Sure, it's easy to build everything to work all in-house, but with more emphasis being placed on server-based applications, Microsoft probably alreadly sees the day when it's not the OS that you're running on the desktop, but the applications you run on your server. They are making a big push to be a key player in server-side application development - .Net has the promise of a dozen languages all working seamlessly together, and there's already a section in Barnes & Noble for .Net programming.

Apple wants people to see simplicity when they use Macintosh, and yet feel the power of the function. You can import, edit, and export an entire movie without ever having a dialog box open in iMovie (accepting upon launch to create a new movie), but you can do so much. I don't see Apple going x86 (at least not beige box) for some time because they can't have that there yet.

Re:Apple switching to intel?

[be-fan]

Apple people are such morons. A few years ago, Compaq got lambasted for making proprietory motherboards. They promptly stopped that practice. Yet, Apple people *like* their proprietory crap. You should be asking for higher quality, less troublesome open hardware, not pretending that proprietory hardware is okay at any cost.

Re:Apple switching to intel?

[Phroggy]

If these are as good as they sound, all those speculations and rumors of apple switchin to intel are going to be thrown out the back door.

Nope, won't happen. We've been trying to get them thrown out the back door for YEARS, and they keep coming back.

Re:Apple switching to intel?

[MoneyT]

Less troublesome open hardware? You can't be serious? How is it less troublesome to have to tell your computer to stop trying to use a piece of hardware that isn't there anymore? I had a PC that despite being custom built, and taken to shop still wouldn't stop tellign me that I had new hardware everytime I started up. And yes, all the onboard hardware was turned off so the cards could work. I have never ever had as much trouble getting hardware to work as I have with "open" computers. Generic devices suck. As long as I can get replacements when I need them, give me proprietary any day.

Re:Apple switching to intel?

[MoneyT]

Pardon me for being rude, but are you stupid?

We already know that for the majority of consumers, espesialy PC users, price is a major factor in determining the computer they buy. The next factor is bennefit / dollar spent. Taking these to factors into account. If OS X was availible for the x86 computers. Even a crippled or slower version. Would you buy a mac as your next computer? What would make you more likely to buy it than if you just walked into the Apple store, saw how damn cool the new iMacs are and bought one then and there?

Re:Apple switching to intel?

[toby]

No - it's not one or the other. The Intel/AMD switch remains highly likely IMHO; Apple needs to reduce low-end h/w costs to effectively compete, while keeping performance. I believe Apple is contemplating segmentation of its product range into low-end consumer on Intel/AMD, and high-end 64-bit for the multimedia production markets (they have to go 64-bit sooner or later, but POWER is way too fancy for the [ie]Mac market).

While Darwin (and OS X no doubt) already run on Intel (it was designed to be portable like NEXTSTEP, which runs on PPC, Intel, SPARC, PA-RISC and M68K at least), Apple will not support generic hardware IMHO. It will be limited to drivers for Apple's own Intel-based hardware lines so you won't be able to buy retail OS X for your random PC (unlike Linux and that other O/S).

Essentially, applications would merely need to be recompiled; NetBSD, Debian et al have proven that architecture can be transparent.

Re:Apple switching to intel?

[GauteL]

You are sadly both rude and ignorant (I don't like the word stupid).

Price and benefit/dollar is important to CONSUMERS. There are other markets in the world than consumers, and they mostly have WAY better margins.
If Apple sold OSX with PCs, and had Macs with OSX that were much more powerful, the professionals would buy it because increased productivity is worth the cost. Increased productivity is worth almost any reasonably priced hardware, because the salary of the professionals is almost always a way bigger expense than hardware.

Apple on X86 - Dead now?

[Anonymous Coward]

Hmmm. Perhaps all the doom and gloom about PPC's future is smoke after all.

Look like Apple on X86 isn't even a remote possiblity now.

Is that bad? :)

Re:Apple on X86 - Dead now?

[msgmonkey]

Hmm, PCI slots, SDRAM, IDE hard disk, ATI graphics cards.. other than the CPU/OS what else inside a Mac does n't come the PC world? When you buy a Mac you buy it for the OS and more recently the ergonics.. this has been the case for a couple of years now.

Re:Apple on X86 - Dead now?

[stux]

The firmware :)

http://www.openfirmware.org/

POWER ISA == PowerPC ISA?

[DominiqueChanet]

I used to be under the impression that the POWER processors from IBM used the same instruction set as the PowerPC processors. Is this correct? In that case, transforming the POWER4 into a PowerPC shouldn't be much of a hassle: more something of downscaling and cutting the really big-iron features.

I really hope Apple jumps on this bandwagon: it may be their only viable alternative for the future, regardless of all the mindless speculations about a transition to x86.

Re:POWER ISA == PowerPC ISA?

[Russ Steffen]

POWER and PowerPC are mostly the same, but not quite. There are something like 10 to 15 instructions that either have different semantics or are present in one arch but not the other. IIRC all of those instructions are fairly esoteric supervisor mode instructions, so they'd likely only affect the OS and not user-space programs.

Re:POWER ISA == PowerPC ISA?

[Space Coyote]

I believe the current PowerPC instruction set is a subset of the POWER's, with the exception of AltiVec, which sounds like IBM has cloned with their claim of 160+ vector processing instructions. Also, the claim is that 32-bit PPC code should be binary compatible with this 64-bit chip. Sounds like a processor tailor-made for Apple to me, but there's not enough detail yet, and Apple is being very tight-lipped on its future processor plans.

Re:POWER ISA == PowerPC ISA?

[eallison]

As stated elsewhere in this thread, theres's a great discussion of this over at ars, in this thread, this thread, and this article.

In regards to your question, someone in one of the above threads posted a quote from John McCalpin at IBM that neatly answers your question:

"Please note that the old distinction between "POWER" and "PowerPC" is no longer operative. IBM's POWER3, RS64, POWER4,and subsequent processors all implement the 64-bit PowerPC architecture (of which the 32-bit PowerPC architecture is a subset). The RS64 and POWER4 (and following) processors also support the 64-bit PowerPC AS architecture, which includes some additional stuff to make the processor work in iSeries (formerly AS/400) systems."

Re:POWER ISA == PowerPC ISA?

[red_dragon]

If I remember what I've read before correctly, POWER is little-endian. When Apple/IBM/Motorola started working on the PowerPC, one of their goals was to run AIX and MacOS (though not simultaneously). And, as we know, 680x0 processors were big-endian. So, the PowerPC was given an endianness switch, and the firmware was tasked with flipping it into the required position during boot.

There's more detail about the PowerPC's heritage (including its relation to Motorola's 88000 processor) in this Wikipedia page.

Re:POWER ISA == PowerPC ISA?

[AxelTorvalds]

POWER is a superset of PowerPC. There 12 instructions in POWER that aren't in PowerPC. PowerPC now also has Altivec

Re:POWER ISA == PowerPC ISA?

[clem.dickey]

Correct in concept, wrong on some details. RS/6000 and Mac were both big-endian.

POWER chips were big-endian only. POWER had a few instructions with a big endian bias, i.e. the used computed values as big-endian indices into registers.

PowerPC removed the biased instructions (and made other changes too) resulting in an "unbiased" architecture.

I don't know what caused PowerPC to become endian-agnostic. Maybe it was a desire for elegance. But it was not a desire to accomodate both MacOS and AIX 3 heritage; they were both big-endian.

- Clem (POWER/AIX user since about 1992)

Re:POWER ISA == PowerPC ISA?

[Nutello]

I don't know what caused PowerPC to become endian-agnostic.

Windows NT for PowerPC? AFAIK it ran in little-endian mode.

Re:POWER ISA == PowerPC ISA?

[clem.dickey]

> Windows NT for PowerPC? AFAIK it ran in little-endian mode.

Of course! How could I forget? That and OS/2 for PowerPC.

actually the 1.2GHz ARM is more intresting

[johnjones]

the fact that PowerPC high end is comeing down to the low end well who whould have that coming .....

the intresting part will be a 1.2GHz ARM part from Samsung useing the Alpha technology
(they say its ARM10 but I think thats wrong and its just ARMv5 complient but that sounds bad in marketing speak so thedy said it was like an ARM10(I think I am not sure) )

regards

John Jones

Re:actually the 1.2GHz ARM is more intresting

[psamuels]

(they say its ARM10 but I think thats wrong and its just ARMv5 complient but that sounds bad in marketing speak so thedy said it was like an ARM10(I think I am not sure) )

Kind of like RAID5 versus RAID10? I.e. what is called RAID10 would for most of us fall under the definition of RAID5?

Re:actually the 1.2GHz ARM is more intresting

[doorbot.com]

I.e. what is called RAID10 would for most of us fall under the definition of RAID5?

RAID5 and RAID10 (or, RAID1+0) are two entirely different RAID implementations.

Please read this link regarding the "Skinny on RAID"

Re:actually the 1.2GHz ARM is more intresting

[suicidal]

I thought that RAID 10 was RAID 1 over RAID 0.
Mirrored Stripe Sets without Parity. MANY more drives than RAID5 for the same effect. Am I incorrect?

Re:actually the 1.2GHz ARM is more intresting

[stux]

Well, I hope its nothing like intel's 900mhz ARMv5 part...

Performance isn't really very stunning...

A G4/500 is about... 4-8 times faster

Of course, this is because of AltiVec... but then again, isn't that the whole point?

ars forum

[pohl]

There are a few pages of good discussion here.

What about the Motorola 8500?

[Jobe_br]

Motorola's 85xx processor, aka G5, is 64-bit, if this article is to be believed.

Is this IBM just coming out with their own 64-bit PPC core? I thought Apple, Motorola and IBM were in an alliance? Seems to me that its quite a competitive alliance, eh?

Re:What about the Motorola 8500?

[znu]

Motorola doesn't seem to care about anything but the embedded market lately, and there are persistent rumors lately that Motorola's desktop G5 efforts are totally dead. Of course, nobody seems to really know anything solid.

Re:What about the Motorola 8500?

[frankie]

I thought Apple, Motorola and IBM were in an alliance?

Officially yes, but each partner has a different agenda. Apple wants desktops, IBM wants servers, Motorola wants embedded.

MacSlash had some very good points about this in their article: IBM's chip has "160+ vector instructions"; Motorola's Altivec has 162. IBM's chip has 6.4GB/s bandwidth; Apple is a founding member of HyperTransport, which is 6.4GB/s.

Hopefully the dots will connect and Apple will get out of the Motorola doldrums.

Re:What about the Motorola 8500?

[psamuels]

Is this IBM just coming out with their own 64-bit PPC core?

IBM has been making 64-bit POWER3 chips for years - nothing new on that front. I guess the news is that they're now adding AltiVec or something very like it - AltiVec (unlike 64-bit mode) is not specified in the original early-90s PowerPC spec, Motorola invented it later.

Re:What about the Motorola 8500?

[cbuskirk]

They are an alliance, but a very loose one. About two years ago the PowerPC line split in two. IBM continued on with the G3 processor line, while Motorola moved on to the G4 with Altivec. IBM decided that Altivec was unncessisary for their product lines and stuck with the G3 arcitecture. Apple then announced the G4 and demand was far far higher than expected. Apple was then able to convince IBM to start producing G4s. This didn't make Motorola happy because they had a monopoly on Apple again. This relationship got even more strained, as IBM's G4s were much faster, than Motorola's, but due to contracts IBM could only sell Apple Processors on par or below Motorola's speeds. This is I suspect why the new top of the line apples are about $500 less than the top of the line a 6 months ago, because IBM had a huge back log of processors it could not sell to Apple for a long time.

holy sh*t

[jormurgandr]

Where do I sign up? Am I the only one that can imagine the fun you could have with this? How about an SMP Mac os X running on this beaut? Damn, that would look good (OSX is way too slow now, maybe it just needs a couple of procs for "eye-candy"...)

Re:holy sh*t

[PythonOrRuby]

Mac OS X already takes advantage of multiple processors. Think Xserve and the dual processor PowerMacs.

Re:holy sh*t

[Shanep]

(OSX is way too slow now, maybe it just needs a couple of procs for "eye-candy"...)

I'm getting sick of hearing people say OSX is slow. I run OSX on an old 300MHz G3 iBook with 128MB ram. I find it more than usable.

OSX 10.1.5 gave hardware accelerated support for my ATI video which made it suddenly much quicker visually. 10.1.5 is much quicker than the 10.1.3 I have on CD.

OSX keeps getting quicker and plenty of RAM helps too, which is why I'll be upgrading this old machine to 320MB soon. Jaguar should be even quicker again.

Now having said all this, I imagine running Jaguar with RAM maxed out on any high end G3 or G4 should be very nice.

Coming from a Lintel/Wintel background, I am loving the combination of excellent stability and extreme intuitive usability.

I wonder...

[MissMyNewton]

...if this is one of the 64-bit procs that some recent web article had an MS exec making noises about? Something to the effect of supporting *several* 64-bit procs, which means Itanium of course, and probably AMD, but who'd be left (Alpha being dead).

Interesting thought to say the least.

(Anyone else recall that article or have a link to it?)

Re:I wonder...

[user32.ExitWindowsEx]

Do recall that Microsoft has had Windows for PowerPC since NT 3.51. They 'officially' ditched it with NT 4.
I personally think they never stopped updating it; they just never released the binaries. (Yes, I know that's implying there might be Windows XP for G4-based Macs, but MSFT is capable of anything.)

By the way, that article (as far as I know) originated on www.winsupersite.com.

Re:I wonder...

[MissMyNewton]

Supersite - that was it!

http://www.winsupersite.com/reviews/winnetserver_r c1.asp

"The next Windows Server version--code-named Longhorn--will include support for Intel's 64-bit Itanium family, of course, but it will also support 2-4 other 64-bit platforms, including AMD's Opteron, said Brian Valentine. "We will only support high volume 64-bit platforms," he said, alluding to problems Microsoft had supporting alternative architectures such as the MIPs and PowerPC on NT 4. "We will support them fully with key enterprise applications. There may be a slight lag time after the x86-64 release [of these applications], but we will support [the new platforms]." Valentine wouldn't elaborate on which 64-bit platforms Microsoft was currently evaluating."

PowerPC has been 64 bit for 6 YEARS!

[neurojab]

PowerPC has been available in 64 bit since the introduction of the A10 in 1996.

Here's some proof.

The new multi-code die is very interesting though...

Re:PowerPC has been 64 bit for 6 YEARS!

[Duck_Taffy]

Well, I thought that they just used it to process two 32-bit calculations in the same cycle. Actually running it as 64-bit is different - more addressable memory, etc. Besides that, are there actually any 64-bit PPC operating systems or compilers?

Re:PowerPC has been 64 bit for 6 YEARS!

[jbolden]

RS/6000 run on Power chips http://www-1.ibm.com/servers/eserver/pseries/hardw are/workstations/.

Re:PowerPC has been 64 bit for 6 YEARS!

[neurojab]

did you read the article I linked to? Obviously not. :) There was a fully 64 bit OS with full 64 bit addressability, and full compiler support, all on the PowerPC in 1996.

Re:PowerPC has been 64 bit for 6 YEARS!

[Duck_Taffy]

Unfortunately not. My DNS at work doesn't work so well, and at the moment, it's giving me the following message:

No such host www-1.ibm.com

Re:PowerPC has been 64 bit for 6 YEARS!

[Inthewire]

Here's a quick pair of tips for you - if you can't reacha site due to bad DNS, try hitting www.anonymizer.com and using their free proxy. It's imperfect but it may do the trick.
Another option is to use visualroute.visualware.com to get the IP, then going to that instead of the URL.

Re:PowerPC has been 64 bit for 6 YEARS!

[sl3xd]

AS/400s dont use apples regular PowerPC chips moron.
They use PowerPC/400 chips with proprietary cores and instructions.

This is like saying that the Pentium4 is a cpu with proprietary cores and instructions. The P4 has SSE2 instructions, where earlier Pentiums (and any AMD CPU) do not have them. Until the Palomino core (AthlonXP & MP), AMD had no support for Intel's SSE instructions (which Intel introduced with the P3). On the other hand, the Athlon is also a proprietary core, with its own proprietary instructions (3DNow!), that are not available on any Pentium.

PowerPC is like saying x86 or SPARC - a family of compatible processors, with a set of identical instructions.

The difference between the PowerPC/400 and the PowerPC "G4" that Apples uses is that the G4 (not the PPC/400) has the proprietary instructions & core (Altivec is a Motorola-proprietary tech).

Re:PowerPC has been 64 bit for 6 YEARS!

[Nutello]

OS/400 has always used 128bit pointers (since they started working on the AS/400's past incarnation, the System/38, in the late 70's). Only 64bits are actually used for addressing, though.

Finally

[Hott of the World]

So IBM decides to get back into the PowerPC chip market, now that they have a more powerful chip and Apples using motorola to make theirs. Hopefully it will mean a great deal to get big blue back on the ball!

The PowerPC 620 lives!

[perlow]

Back in 1993-1994 when IBM was still working on the OS/2 for PowerPC and WorkPlace OS, and Taligent and "Pink" were still on the drawing board, IBM was planning to release the PowerPC 620 Series, a 64-bit version of the PowerPC 604. They intended to use it to run a 64-bit version of OS/2 that ran on the Mach kernel.

The design was scrapped because back then the manufacturing process was way too expensive to be cost effective in mass producing the chip. And we all know what happened to PowerPC OS/2.

http://www.byte.com/art/9411/sec8/art5.htm

Re:The PowerPC 620 lives!

[AxelTorvalds]

I actually saw one of the early cuts of the PowerPC OS/2 on top of Mach/IBM microkernel...

The sadest thing about it all to me isn't the fact that it never really happened so much as the wonderful lesson to learn that only a handful of people really get to have.

PM was designed with shared memory in mind, Mach doesn't really support shared memory. Next thing you know you have a PM port that runs slower than snails. There was a team of people assigned to that problem and they never came up with a suitable solution other than rewrite. OS/2 died officially in the minds of IBM's strategists at that point, back in the early 1990's. It was both political as well as technical and that's when things got bitter; some people thought that they weren't trying hard enough to port it, the OS/2 fanatics. On the other side a tremendous amount of OS/2 was written in IA32 assembly...

It was a text book design lesson with a healthy dose of business politics. Look at how Linus Torvalds runs Linux, it's all vanilla, nothing terribly exotic in the mix and it runs on just about every platform that shows up. It's not as quick out of the gate on some of them but it quickly get's tuned that way, using standard and non-exotic features of the hardware. RS/6000 has reverse pagetable support if you want it, but Linux doesn't use it, why? because it's the only hardware that does it practically. It's all different hardware but it all follows the same standards at the end of the day. When your code relies on the bare metal like that it will die, even when you're big blue, unless the bare metal is bare metal everywhere.

Whats wrong with power4?

[nr]

Why not use the proven high-performance IBM power4 design instead. Why design something brand new that will have "less" performance that the already existing 64bit single/dual core power4 design. I dont see the point, looks like a big waste of money and resources.

Re:Whats wrong with power4?

[psyconaut]

Because the existing Power4 design is an expensive chip to fabricate! Those dual core versions are mucho heavy on the transitor count.

This is designed to be a "lite" Power4 platform for low-end servers and desktops.

Actually, if truth be told, it's probably being fairly and squarely pitched at Apple as their new CPU ;-)

-psyco

Re:Whats wrong with power4?

[Gilmoure]

One of the reasons Apple has stuck with Motorola's PPC chips vs. IBM PowerX chips is the AltiVec units on the PPC chips. This new chip, while based on the Power4 chip is geared towards desktop use and not server use. Think of a passenger car vs a semi-truck. They both do basicly the same thing but are more optimized for certain uses. The desktop chip needs to be quickly responsive to a wide variety but small concurrent number of processes or threads while the server chip needs to handle large numbers of threads or requests to do pretty much the same thing (file access, database access, ect.).

IBM's just bringing down a high horsepower diesel and gearing it for passenger use. They're also throwing in AltiVec type of processes which Apple really likes/needs. One more reason why going to X86 chips would be difficult; no AltiVec.

Re:Whats wrong with power4?

[nr]

Yes I understand the point, but there are a single core "light" version that are used in IBMs low-end UNIX server line and workstation line. Ofcouse it wont be compatible with the PowerPC architecture used by Apple and others.

Re:Whats wrong with power4?

[foonf]

Why not use the proven high-performance IBM power4 design instead. Why design something brand new that will have "less" performance that the already existing 64bit single/dual core power4 design.

From the register article:

It needs to remain competitive with entry-level workstations against the likes of Sun and HP's Alpha, where the size and heat dissipation of the mighty POWER4 have kept it out of systems below $12,000. IBM's desktop workstations still run POWER3

IBM would need to design this chip even if Apple didn't exist, simply because the current Power4 cannot be produced cheaply enough for a $10,000 workstation, much less a $800 macintosh.

Re:Whats wrong with power4?

[stux]

Apparently the single core lite versions are just multi-core versions where the other cores failed testing...

of course I have no idea if this is true or not :)

Have you seen the size of those Power4 MCMs?

I can't really imagine an iMac with one ;)

Re:Whats wrong with power4?

[psyconaut]

Yeah, size would be an issue (*giggle*)....plus the existing Power4 core doesn't really meet the needs of a desktop machine, as previously stated.

Can you imagine an Apple TiBook running on a Power4? ;-) 4 minutes battery life and the size of a life raft.

-psyco

About bloody time

[Drakon]

I requested this at IBM's PPC booth at linux world in JANUARY
what took them so long ;-)

Re:About bloody time

[JollyFinn]

Well I said it 2 years ago. And with couple of reasons why they should go for it. Including, leverage of software developement.
IF they make a powerPC compatible linux box that is cheap enough of linux users. Their shoftware support will be improved and they protect their selfs agains embedded x86 processors. As Intel compatibles are spreading in their market share for larger and smaller systems where the powerPC architecture has its current market share.It could definitely get nice foot hold in universities/ students /linux users, and that would improve the STABILITY of linux software in powerPC.

Consider how many of slashdotters wouldn't get PowerPC Linux box if they could get higher performance than x86 systems with similar price?

Jouni
-John 2:3 And when they wanted WINE, the mother of Jesus saith unto him, They have no WINE.

Re:just curious...

[furiousgeorge]

>>a PowerPC is a mac that can run some x86
>>applications and hardware right?

wrong.

Gunning for 2GHz ...

[Jobe_br]

Though it's unclear what clock speed the new PowerPC will offer, IBM has been gunning for 2GHz.

Interesting ... you'd think they'd set their sights a bit higher. This "MHz Myth" thing, while true in some respects, isn't going to sell more computers. And if you're not selling computers, you're not making money. Plain and simple :)

I'm an avid Mac fan, love 'em - use 'em - own 'em. But, I know that a 2.54GHz Pentium 4 will likely be quite a bit faster than even a dual-1GHz G4, much as I hate to admit. A dual Xeon will likely be even faster (with its increased cache size and a few other enhancements).

Now, the G5 (at 1.6GHz), in the works by Motorola, supposedly has SPECfp and SPECint scores to rival even the Itanium 2, which itself (supposedly) has scores that double any Intel predecessor. As usual, it seems that hope is in the wings ... but when will we get our hands on it?!?

Re:Gunning for 2GHz ...

[Simba]

Interesting ... you'd think they'd set their sights a bit higher. This "MHz Myth" thing, while true in some respects, isn't going to sell more computers.

Why bother? The Pentium4 is at the end of its life cycle, and Intel will be moving to the Itanium fairly soon... which will come out in the 800mhz range.

I'm sure Apple will enjoy the irony.

Re:Gunning for 2GHz ...

[msgmonkey]

P4 at the end of it's cycle? The Pentium Pro started up at 150MHz and the core was tweaked and added to and is still used in the Pentium III-S running at 1.2GHz.. to say the P4 is at the end of if's cycle is either stupid or naive (you choose). I'm no fan of the P4 but I can easily see it reaching atleast 8GHz.

Re:Gunning for 2GHz ...

[stux]

I've written some highly optimized code for MMX/MMXExtended and altivec.

A 500Mhz G4 is about 30% faster than a 1.3Ghz Athlon when running these image filtering functions...

And the Athlon is using DDR, while the G4 has only a 100mhz bus... and the functions place a huge demand on both the integer units and the memory interface.

Basically my point is...

I'm not convinced that a 2.5Ghz P4 is faster than a DualG4... when running highly optimized vector code.

And that's of course the reason people need 2.5Ghz PCs :)

(don't tell me you need that much power for a typing letters ;))

BUT, I haven't written SSE2 versions yet, and SSE2 does seem to be fairly competitive with AltiVec (not as good, but competitive, AltiVec makes MMX 'feel' like a cheap toy)

Re:just curious...

[Jeffrey Baker]

PowerPC is a line of CPUs with similar instruction sets and architectures. It is developed by IBM and Motorola, and formerly by Apple. It is related to IBM's Power line. It has nothing to do, and is incompatible with, x86 CPUs. The PowerPC 60x, 750, and 74xx models are and were used in Apple computers.

Price Issue? Pay attention...

[Ironix]

IBM also mentions that this processor will initially be made available to high end workstations and entry level servers.

I would worry about the cost of the chip, as it may be prohibitive.

I think that if Apple were to use this chip, it probably wouldn't be for about 6 months to a year after it's debut, that is to allow prices to become reasonable.

Re:Price Issue? Pay attention...

[Jobe_br]

The G4 towers qualify as high end workstations. Especially the dual-1GHz systems. Also, the Xserve fits squarely into the entry level servers category. So, as others have noted, it certainly appears that IBM is pitching this straight at Apple. Who knows when we'll actually get anything, though. Back a few months, I heard rumours that Apple had already seeded G5 systems to certain testers, but ... nothing has panned out since then.

Re:Price Issue? Pay attention...

[Maserati]

They certainly do. I'm supporting video editing machines and the Photoshop jockeys who do have to apply filters to billboard-sized files. They don't get super happy when you get them up a gig of RAM, because their machine can take another 512MB. These people would get all hot and bothered over the prospect of 64-bit SMP systems. Mine (god bless 'em) would want to use one as the rendering engine for our production Splash to chew on their 150MB Postscript files.

The sooner Apple starts on the mobos for these the happier I'll be. Besides, nobody ever got fired for buying IBM :-)

No, Apple should continue to heed Intel

[Ars-Fartsica]

Sorry, but market forces are now as powerful as performance metrics. Apple no longer benefits from not being x86...cost being the biggest issue, and most of the time now they can't even claim a performance gain.

Intel won the CPU war on desktop PCs. Look to servers, handhelds, game consoles, etc. for the the next CPU battle worth fighting.

Re:No, Apple should continue to heed Intel

[yeoua]

"Intel won the CPU war on desktop PCs."

Really? I can't help but notice that AMD has been able to fight back a bit and claim some land in this war. Maybe they aren't winning by a huge margin yet, but they are fighting, and doing well.

Until everyone in the consumer sector owns an intel (which almost was several years back in the pc market...) and continues to buy only intel, intel hasn't won yet.

Re:No, Apple should continue to heed Intel

[CynicTheHedgehog]

And yet Apple produces desktops and servers that are as fast as the user needs them to be. That is, the user interface is responsive while still aesthetically pleasing; gamers don't suffer paging or poor frame rates when playing games; and programmers are not lacking in development tools and do not lament the speed of their compilers. And they do this all without a fan on their processor.

As an owner of a 700MHz G3 iBook, I can say that I never once have thought, "damn, I wish this thing was faster." Apple may not be for the hardcore overclocking benchmark junkie, but they're just fine for the rest of us who just want to get some work (or play!) done.

Personally, I'll sacrifice performance I'll never realize in return for a beautiful, intuitive, and responsive interface housed in a quiet, attractive package.

Re:No, Apple should continue to heed Intel

[gr]

Hrm.

Did this somehow slip past your notice as an Apple product?

In addition, I've a hard time believing the time (and, by way of paychecks, money) spent porting would be worth the (probably moderate) savings in chip costs. Granted, since Darwin's written based on a portable OS (NeXTStep, itself based on 4.2 BSD), porting it to another processor architecture wouldn't be any big feat (espeically considering this already happened at Apple to get from mac68k to macppc), but I'm not so sure it'd be saving Apple any money to do so.

Re:No, Apple should continue to heed Intel

[Dixie_Flatline]

What are you talking about? Apple's money is mostly made on hardware sales. I don't know what it is with you people that think Apple should move to Intel, but it's a bad idea. Take note of this next sentence:

Apple relies on being on a seperate platform from Microsoft to survive.

If Apple ever moved to Intel, they would be crushed. Steve Jobs said a long time ago that the desktop war had been won by Microsoft, and he's right. Switching to Intel would be suicide.

The Mac isn't about being the fastest machine on the block, it's about being the best designed, easiest to use, most useful machine on the block.

Re:No, Apple should continue to heed Intel

[GreenKiwi]

Personally, I'll sacrifice performance I'll never realize in return for a beautiful, intuitive, and responsive interface housed in a quiet, attractive package.

Wouldn't we all... especially if she'll do the dishes too...

Re:No, Apple should continue to heed Intel

[Elwood P Dowd]

That's funny, I have the 600 mHz ibook and I say that all the time.

Your L2 cache may have saved you this time, but PC laptops have been Fast Enough for a year or two. Sure, *now* Apple's hardware is all fast enough, but it's not like that's been a continuing design decision.

Re:No, Apple should continue to heed Intel

[SoupIsGood Food]

The battle for the 32bit desktop processor has been won, you mean. It's been a long, bloody battle, and for a time in the mid-'90s, when Apple was on the ropes, the victory looked complete. Intel and AMD have finally emerged victorious, laying claim to the most powerful 32bit processors on the planet.

But, to be frank, Itanium sucks... even Linus thinks so. Nobody wants to use it, Dell, SGI, even HP is still developing PA-RISC silicon, and is incredibly hesitant to commit to the "next generation" IA-64 chip it designed partly in-house. Yamhill is a nice idea, but Intel has no plans to go that route yet, and what's more, denies it's even considering them.

AMD's 64bit offering are, as yet, vapor... and unlikely to pack the punch of the Power4, nevermind a dual-core Power4 with Alti-Vec.

Meanwhile, PowerPC's been 64bit since '96.

Indeed, the PC will continue to kick Apple's butt in 32bit systems, except in notebook applications, which is the only place Apple will keep using 32bit PowerPC processors. D'oh.

So, yes, x86 is irrelevant and outclassed by PowerPC, Itanium is a floundering wreck, leaving Hammer to look very lonely and small up there all buy itself, shoulder to shoulder with UltraSPARCs, R2400s and Power4s. Economy of scale? What scale? When it comes to 64bit hardware, RISC/Unix =is= the scale.

Game on!

SoupIsGood Food

Re:No, Apple should continue to heed Intel

[mir@ge]

I own a 500Mhz G3 iBook with 640MB. I run linux on it. It is my favorite "input device", but on several occasions I have though "damn, I wish this thing was faster". It is not that it is not fast enough to do your everyday tasks. I can email, edit files, and surf the web just fine. My complies run at what you would expect of a 500Mhz machine. I may be spolied but I now consider that slow. It becomes quite appearant when I am compiling multiple files. I've given up on OS X. It crawls when I play any games. That is really the reason I use a Mac OS at all.

This chip looks to be ideal for servers and workstations. I don't care. The day they put one of these chips in a laptop is the day I buy a new laptop.

Re:No, Apple should continue to heed Intel

[Sebastopol]

And yet, Apple has 4% market share. If Apple is a corporation, than it has a duty to expand this share and make bigger profits for shareholders. Otherwise they are just philanthropists and not capitalists. Judging by Jobs' smarmy marketing tricks over the past 5-7 years, they're trying to be a big playa and failing because of ideological inertia.

If Apple is smart, they will try to dominate the handheld market b/c they are the champs at logical interfaces. Or rather, I wish they would, becuase that is where the most cpus will eventually go, and i really don't want all gadgets to suck as bad as Windows.

Re:No, Apple should continue to heed Intel

[norkakn]

I disagree, but only slightly: mac is about being the fastest machine, but in terms of productivity instead of raw power.

sure, your athlon might have a higher clockspeed, but I can do the work in less time because of the easier to use, more useful machine (-:

Re:No, Apple should continue to heed Intel

[Dixie_Flatline]

I totally agree, but I figured that was implied. :)

Re:No, Apple should continue to heed Intel

[Macka]

I popped into PC World and tried a 500Mhz iBook some months ago. I wasn't impressed with the speed and walked away. A couple of weeks back I did the same with a new 700Mhz iBook. The difference was amazing. I'm now waiting, cheque book in hand, for the new iBook to ship with 10.2. I need some of the features that 10.2 will provide. Can't wait!

Re:No, Apple should continue to heed Intel

[geekee]

A friend of mine at AMD claims they have working K8 (64 bit Athlon) parts in the lab.

Re:No, Apple should continue to heed Intel

[MoneyT]

Slashdot needs and "Amen" modifier

Re:No, Apple should continue to heed Intel

[MoneyT]

Intel won the Mhtz war, but the CPU war is still on. AMD is working on their own 64 bit chip, and Apple is doing what Apple does best, being different. Sooner or later Mhtz as a measurment of performance will not matter. Intel has saturated the market with power. They release faster and faster speeds, making things seem out of date long before they really are. But joe schmoe isn't about to lay down another $500 for the next speed bump that will be outdated 6 months from now. The Mhtz war was won, and ruined by intel. Now we need new ways of selling processors and computers. Don't believe me? Then look at Apple touting the Mhtz myth (and briefly the gigflops), look at AMD going to model numbers instead of clock speeds. Look at Intel, trying to push those prosessors they release a while back, the ones that clocked in at 800 and 833 Mhtz.

Re:No, Apple should continue to heed Intel

[puppetluva]

I hate to be the one to burst the RISC/UNIX bubble (since I'm a fan, but).

64 bit doesn't mean faster. A dual processor 2GHz Xeon machine with a nice wide mobo beats the pants off any 4-processor, 64 -bit Sun sparc machine (name your Sun model, it gets crushed). I know, I take care of them day in and day out. I dream in full-color Xeon-Linux every night after work now. Put it to test in your labs too. . . you'll see what I'm talking about. Hyperthread the Intel chips and Sun starts the bus even earlier. For a 32-bit chipset to whip a 64-bit chipset handily shows an incredible set of optimizations on Intel's part. . . and impending demise on Sun's (a tear rolled down my cheek as I typed that).

Intel's has crushed TI/Sun at the Processor/hardware game - Motorola/IBM is the only real microprocessor variation left out there that you should give a damn about.

Re:No, Apple should continue to heed Intel

[gabebear]

Apple hasn't/isn't going to release their GUI code. Darwin is free/OpenSource and doesn't include a GUI (you can get Xfree86 running). OSX isn't free at all. Darwin is basically just the kernel(BSD) of OSX with the GNU tools thrown in.

Re:No, Apple should continue to heed Intel

[Art Tatum]

Yes, but Alpha floating point performance was still ahead of Intel last time I checked. If you want to do lots of realtime number-crunching, that could come in handy.

Re:No, Apple should continue to heed Intel

[GreenKiwi]

Ahh, nipples. The most intuitive interface known to man.

Connected to one of the most confusing devices EVER!!!

2GHz

[big_oaf]

From the article:
Though it's unclear what clock speed the new PowerPC will offer, IBM has been gunning for 2GHz.

Sweet! Finally Apple will have processing brawn and marketing brawn.

Re:2GHz

[big_oaf]

D'oh! Redundant. 3 minutes too late. Maybe I should start typing a little faster, yah think?

Re:Two Words

[Anonymous Coward]

PS, the specs quoted are not for the new processor, but for the existing, very expensive Power4. The CPU will be a scaled back version.

Why go from 32 to 64? Why not jump to 128?

[Sembiance]

Why do all these chip manufacturers go from 32 to 64?
Why not make a brand new chip at 128?!
It would propel that company to the top easily.

Re:Why go from 32 to 64? Why not jump to 128?

[Sembiance]

I understand if the technology to create 128bit processors do not exsist.
I understand if there is some sort of whacky law preventing it from being made.
I understand if going to 128bit will make no difference because of hardware bottlenecks or software incompatibilities.

But if your saying that us humans just simply can't conceive and design a 128bit processor...
I don't understand.

Re:Why go from 32 to 64? Why not jump to 128?

[digitallis]

Because We aren't even using the 64 bit processors that we do have. SPARC stations have 64 bit processors, but nobody has written Solaris for 64 bits. Half the bitspace goes unused. It's rather a shame, but at the moment, few applications even need the space.
MS Whistler (Microsoft's 64-bit OS)is still banging around in development and has been for several years. The Itanium's are found few and far between. 64-bit isn't widely used yet because the applications just aren't demanding it yet. Developing a 128-bit proc would be an extreme waste of processor die space. With the current software, 3/4 of the bitspace would lie dormant.

Re:Why go from 32 to 64? Why not jump to 128?

[BlackGriffen]

More liek 99% of the population will never need a full 128 bit integer support. The biggest reason for moving to 64 bit is to increase the amount of memory the system can address. Moving up in size actually has disadvantages, though. Every time you're moving data around, you're pushing twice the amount of bits, whether you need them or not.

BlackGriffen

Re:Why go from 32 to 64? Why not jump to 128?

[maxwells_deamon]

A 128 bit chip would likely be slower for many/most applications. Because the amount of memory fetched and used would be larger, the real time thruput can be slower.

As a way of over simplifying the problem think of the following example:

I give you two calculators you can do math with. One has an 8 digit display, one has a sixteen digit display.

OK, now one extra rule, you must enter ALL the digits for every number you put in. Including leading zeros.

You will vary rarely need to use the 16 digit machine and you will quickly hate it.

Re:Why go from 32 to 64? Why not jump to 128?

[questionlp]

Er.. I though Solaris (SPARC edition) was 64-bit ever since Solaris 7? Sure, maybe not all of the userland and other applications have been ported yet, but even Solaris 9 has the option to install either the 64-bit version or the 32-bit version.

A lot of the applications need the space, databases, 3D modelling, data processing outside of databases, GIS, etc. The 4GB addressing barrier of 32-bit (sans PAE and virtual addressing of up to ~ 16-64GB) is rather limiting. Check out some of the conversations brewing at Ace's Hardware and you'll see some of the discussions. x86 PAE sucks because the performance of shifting the window is much slower than regular memory operations (but still much faster than swapping out to an already busy I/O subsystem -> hard drives).

Re:Why go from 32 to 64? Why not jump to 128?

[dbrutus]

I've seen theoretical arguments for this. As bandwidth in the computer widens a lot of problems that currently are done with an eye towards efficiency can be solved using simple, inelegant brute force techniques. The problem really is that there aren't enough savings to justify the massive extra expense of retooling everything else. After all you wouldn't shoehorn that 128 bit processor into a dinky memory system that would result in a mostly idle processor, now would you? It's all the other components that need to be updated before it becomes practical to take the next step.

Re:Why go from 32 to 64? Why not jump to 128?

[axxackall]

I can predict that after the crisis the Moor's law (when vendors will fail to double the CPU speed every 18 months) the market will be ready for Moor's law revised in one of the following editions: "CPU bits doubles every N months" or "average computer RAM doubles every N months".

It doesn't matter what doubles every N months, but the consumer must upgrade its system - otherwise we will have a new recession.

Re:Why go from 32 to 64? Why not jump to 128?

[psamuels]

But if your saying that us humans just simply can't conceive and design a 128bit processor...

They can, they can. There are plenty of good reasons not to:

• Memory bandwidth. This is probably the biggie. If you have 128 bits for every memory address, that's 128 bits for every pointer in your C program, 128 bits for every instruction that loads from an absolute memory location (ok so such an instruction probably doesn't exist, but that doesn't make the problem go away). Memory bandwidth already cannot keep up with CPU speeds - that's why we have such huge caches nowadays, and caches are expensive.
• Real estate. Moore's Law was originally formulated in relation to transistor size / density. The more transistors you can cram into a given amount of silicon, the faster and cheaper you get. Likewise, the fewer transistors you need, the better. Expanding all your registers, all your speculative registers, all your ALUs, all your address xlation units, all your caching logic, all your pipelines, to accommodate 128-bit words is far from free.
• Disk storage. A 64-bit memory or disk address is on the order of 16,000,000,000,000,000,000 bytes of addressibility. (And that's assuming you can't multiply by about 4 more orders of magnitude to address blocks rather than bytes.) That will be vast overkill for years to come, which is why the new ATA standard (IDE disks) specifies a 48-bit rather than 64-bit block number. (The original 28-bit ATA lasted for what, 15-20 years?)

In short, provide even one application domain where having 128 bits of addressable memory, or a convenient 128-bit word size, would come even close to offsetting the inherent architectural costs compared to a 32- or 64-bit design. I can't think of one.

NO, IPv6 isn't a valid answer! (: Word size hasn't been a significant obstacle for current implementations.

Re:Why go from 32 to 64? Why not jump to 128?

[msgmonkey]

Moores law has nothing to do with CPU speed doubling. Moores law is about the CPU transistor count doubling, thats not the same thing.

Re:Why go from 32 to 64? Why not jump to 128?

[axxackall]

My logic was simple: if something doubles in CPU now and it will stop doubling later, then it may put CPU (computer) industry into a danger. So, the vendors will create the hype again, now around another CPU parameter. Or even not CPU - just another parameter in the computer system. They will do everything to convience consumers to upgrade their systems (and to pay money).

After 10 years my typical desktop is crazily upgraded. Has it improved my work? I do the same: I edit documents, write programs, run databases.

The change in look-n-feel (TTY-->GUI) made my work more comfortable, but it did not improve my knowledge (abstract thinking?).

And Java just got my CPU and RAM without any positive outcome! Lisp, the child of 1960, still looks more innovative than all that Java hype.

If amount of transistors per chip will stop doubling every 18 months - they will start doubling something else, something they can explain to moms and pops. They can't explain why Lisp machines would improve our world. Bits, transistors - that's simple, it's about speed. It doesn't matter we don't need such speed. Generally - speed is good. So, let's do upgrade!

Ugh PowerPC OS/2

[glrotate]

The project that was going to save all of us in 93, and then 94, and then .....

If only.

PowerPC 64, POWER4 and PowerPC discussion here

[class_A]

Head over to Ars where there's a good discussion running about this new processor, its intended market and the differences and similarities it has with existing the POWER and PowerPC ISA's including 32 bit code execution, AltiVec/SIMD implementation and such like :-)

"Reduced" Instruction Set Computer???

[Anonymous Coward]

I find it amusing that the old i486 machine had
235 instructions. The "RISC" PowerPC originally
had 225 instructions. It now has 160 more
instructions. Compare this to 69 for Sparc
and 94 for MIP-Rx series of RISC processors.
Perhaps we need a new definition for "Reduced"
as it applies to the PowerPC. On the upside, at
least you can't say the PowerPC designers are
stuck on dogma =)

Re:"Reduced" Instruction Set Computer???

[Kranium]

I think in general RISC nowadays doesn't refer to the number of instructions, but is instead used for a category of chips that a) have a fixed instruction word size (NOT x86) and b) have a load-store architecture (meaning you can't add 2 words in memory; have thousands of addressing modes, etc.)

Re:"Reduced" Instruction Set Computer???

[civilizedINTENSITY]

RISC
PowerPC architecture is an example of a RISC (Reduced Instruction Set Computing) architecture. As a result:

• All PowerPCs (including 64-bit implementations) use fixed-length 32-bit instructions.
• The PowerPC processing model is to retrieve data from memory, manipulate it in registers, then store it back to memory. There are very few instructions (other than loads and stores) that manipulate memory directly.

Technically, a developer can use any GPR for anything. For example, there is no "stack pointer register"; a programmer could use any register for that purpose. In practice, it is useful to define a set of conventions so that binary objects can interoperate with different compilers and pre-written assembly code.

Re:"Reduced" Instruction Set Computer???

[yggdrazil]

RISC is a design philosophy. Not a hard instruction count or limit.

Furthermore, design philosophies has evolved a bit since the purist days. Speed is more useful than a philosophically correct processor, after all.

In many ways, this is similar to microkernels and monolithic kernels. Microkernels can be larger than some monolithic kernels, but it's the philosophy of how you organize the thing that's important, not the number of bytes/instructions.

Re:"Reduced" Instruction Set Computer???

[Bungie]

I am not 100% sure, but I think the extra 160 extra instructions are for Altivec, not the general PPC instruction set.

Re:"Reduced" Instruction Set Computer???

[axxackall]

Don't be dogmatic yourself. Try to be more creative. For example, try apply the Moor's law to "Reduced Instruction Sets". What would you get? "Reduced Instruction Set doubles every 18 months". I think we are far way from it. Yet.

Re:"Reduced" Instruction Set Computer???

[John Whitley]

In practice, it is useful to define a set of conventions so that binary objects can interoperate with different compilers and pre-written assembly code.

As a point of general information: These conventions are referred to as a platform's ABI, or Application Binary Interface. The ABI sets the necessary register use (e.g. stack/frame pointer policy), parameter passing (in registers/on stack), and function calling conventions for a given hardware platform. This is typically C/C++ centric. FWIW, compilers which don't depend on C/C++ link level compatibility need only obey the ABI when calling external code.

Re:"Reduced" Instruction Set Computer???

[pianophile]

>Moor's law

No, That's Moop's Law

:-)

160 hrm..

[autopr0n]

The processor is further enhanced by a vector processing unit implementing over 160 specialized vector instructions and...

Yet Mac zealots will still be going on and on about how PPC is better because "Its RISC!". Never mind that the 486 only had 142 instructions total or anything like that.

Re:160 hrm..

[Anonymous Coward]

RISC philosophy says nothing about the number of instructions in an ISA, only the type. the goal is to include only simple instructions that execute in ~1 cycle, and that are of general frequent use. There is no restriction on how many instructions in an ISA, only the kind of instructions. See: hennissey/patterson texts...

Re:160 hrm..

[pi radians]

You must be a blissful fellow (read: ignorant)....

RISC vs CISC is a concept of design, there is no set amount of instructions for either. Go back to computer science 101.

Re:160 hrm..

[crawling_chaos]

He'd do better in a Comp. Architecture class, or reading some of Hannibal's stuff over at arstechnica. He's got a knack for explaining modern processors. Of course, neither the PPC or x86 architectures are really purely RISC or CISC anymore, either.

Re:160 hrm..

[msgmonkey]

So buy that defintion all Intel processors since the Pentium Pro are RISC processors. RISC does n't mean anything in todays processors, the Instruction decode section of the latest SPARC looks awfully complicated to me.

Re:160 hrm..

[stux]

The difference is that each of the 142 instructions had multiple modes, multiple formats, multiple argument lists and where compeltely different from each other

RISC means reduced complexity, not reduced instructions, all the instructions can roughly be divided into

load/store
processing
branching

that's more or less it, and they're all the same in each category, they just do different things

so you have loads, they all load from memory to a specified register, there are different instructions for loading a 8 bits, 16bits, 32 bits etc, and some different ones to handle signextension etc.

meanwhile the processing instructions are basically all of the form

C = A + B

where A, B and C are any registers, B could be a number instead of a register. The + of course can be one of many operations, and thats the difference between teh instruction

All the instructions might update the condition registers, or might be word, byte, or halfword variants... but there aren't very many base instructions but, if you combine the base instructions with the 5 combinations of instruction for every instruction, then you get a fairly large number.

But because the ISA is so elegant its very easy to learn. And its very easy for the CPU to process it.

In relation, to a CISC architecture (which is a retroactive name), any RISC design is a model of simplicity.

Re:just curious...

[foniksonik]

Nope, A PowerPC is what every Mac has currently. G3 / G4 are PowerPC CPUs.

PowerPC and x86 are completely different CPU architectures.

Apple going 64 bit will have almost no impact on developers or the OS other than to improve upon it. The only thing that will have to happen is that Apple, et al will have to recompile all of their binaries using a 64 bit compiler. That's it. If Apple or IBM already has the compiler for 64 bit PPC or at least a working version then it (64-bit Mac) is practically here already.

Re:uhm hello?

[MisterSquid]

The question is did *YOU* read the article?

To quote:

IBM Microelectronics will present a new 64-bit PowerPC architecture for desktops in October at the Microprocessor Forum.

and a little later

"Based on the award winning Power4 design, this processor is an 8-way superscalar design that fully supports Symmetric MultiProcessing," the description says.

This chip is PowerPC all the way.

PPC? It was 64-bit since inception.

[romanval]

The original specs for POWER/PowerPC CPU's were 64/32 bit anyways. This was set in stone over 10 years ago.

The great thing is that PPC-64 is that it's natively code compatible with PPC-32. No ISA 'extentions' (like x86-64), or instruction convertion (like Itanium), just a simple processor mode switch.

Apple would be a fool not to jump on this CPU for their high-end workstations or low cost servers.

Re:PPC? It was 64-bit since inception.

[Russ Steffen]

Funny you should say that. When I read the X86-64 documention, I was struck by how similar it was to the way PPC scaled from 32 to 64 bits. Now, I still think PPC is the better architecture, but your pat dismissal of X86-64 is off target IMHO.

No

[autopr0n]

PowerPC has nothing whatsoever to do with the x86 instruction set. It's just a brand name for a CPU architecture, like "Pentium", "Athlon", or "Alpha". In fact, it isn't even mac spesific.

Will this be before or after the G5s?

[AugstWest]

They're been delayed so long now I'm starting to wonder if they're hanging out with Duke Nukem, or even Prey fer chrissakes.

Re:Will this be before or after the G5s?

[tux-sucks]

All the G5's are locked up securely in the Team Fortress. ;)

Re:Will this be before or after the G5s?

[Openadvocate]

Damn, you beat me to it, Let me see, Team Fortress 2. oh, yeah, that was 2 jobs at dot-com-fakes ago. :)

Sad to see how the time between each news post got higher and higher.

Re:uhm hello?

[foniksonik]

hmmm did YOU read the article?

" IBM's presentation, for example, says the company's 64-bit PowerPC processor will be designed for desktops and entery level servers. "

Does that NOT say PowerPC? Does it NOT say Desktop?

The chip is based on Power4 manufacturing and tech that's all.. it is a PowerPC.

Discussion on comp.arch...

[Anonymous Coward]

There's a fair amount of discussion in comp.arch on this chip. Guesses are that it's adopting the Motorola e500 vector instructions, ones that work on general-purpose registers. Considering that the Power4 has a very, very, very good floating-point unit that works with the memory units to get vector-like performance, I doubt if they need FP vector ops...

it says more than 160 and Altivec=162

[johnjones]

it says more than 160 and altivec has 162

regards

John Jones

Re:it says more than 160 and Altivec=162

[xenocytekron]

its not altivec but an altivec-variant, altivec is owned by motorola and the reason apple wasn't using IBM chips in the first place is because they didn't have Altivec because Motorola charged too much for licenses.

Re:it says more than 160 and Altivec=162

[dbrutus]

My bet is that it's either it's reverse engineered or it's licensed, not that it's a variant. Apple isn't likely to want a variant different enough that Motorola's lawyers could claim infringement.

Who'd a thunk it, we've arrived at a day when IBM is the reverse engineering firm!

Re:it says more than 160 and Altivec=162

[Elwood P Dowd]

NOBODY HAS SAID THAT APPLE WILL USE THIS CHIP. Everybody *suspects* that they *might* use it. But everyone is blowing smoke and guessing until we actually hear news from inside Cupertino.

IBM will use this processor in their machines. We have no evidence whatsoever that this chip was designed to be compatible with Apple software. It might be.

Re:it says more than 160 and Altivec=162

[dbrutus]

Duh! Apple never talks about unreleased hardware this far in advance. It's a slam dunk that the sales force that is going to be tasked to sell this will be looking at Apple as a large client for the chip and that they will be pressuring the engineering team on making their SIMD system Altivec.

I suspect that the engineers aren't going to resist that too much.

really?

[bill_mcgonigle]

Apple no longer benefits from not being x86...cost being the biggest issue

C'mon, you can't be privy to internal Apple component pricing and not share it with us... You are sure they pay more than Intel would charge, even though they buy processors in lots of a few hundred thousand or so, right?

and most of the time now they can't even claim a performance gain.

And the 8-way superscalar 64-bit G4 still won't help, right?

Re:Wait a minute

[Jobe_br]

I believe the 128 bit vector engine relates to the size of the data it can operate on, ie the size of the registers used for vector operations. The instructions, however, aren't 128 bit. I might be confused on this issue, though.

Either way, the entire chip surrounding the Altivec engine is 32-bit, so this would be an improvement on that.

Mutant Power4?

[Duck_Taffy]

This sounds like a beautiful processor, and I'm guessing it's why they contracted a plant in upstate New York to manufacture the .1-micron chips. I'm thinking that this is the mutant brain-child of the Power4 and the G4. Kind of like a miniaturized Power4 with a vector-processing unit, running at 64-bits and possibly with 32-bit PPC binary compatibility built-in. It would be nice if they could apply double the SMP capability to 32-bit code.

Hopefully they'll write a really efficient compiler for it. This could be the chip to launch Mac OS X into the enterprise market.

Re:just curious...

[Kranium]

Well, I think it's a little more complicated than that. What about other hardware in the system that uses 32-bits of address space? What about all the driver software that assumes physical addresses are 32-bits wide? Maybe not super difficult, and helped by the fact the IOKit is an object oriented framework, but still harder than flipping a switch.

Misleading title

[danielwright]

The article title is a bit misleading - this isn't a new, more powerful chip, it's a new, less-powerful chip designed for consumer markets. The PowerPC has been 64-bit for a while now, but the chips have been aimed at high-end machines (especially the Power4). It seems that this is a low-end Power4 that's more suitable for desktops.

Re:Misleading title

[dbrutus]

Is that sort of like the Macintosh being a less powerful version of the Xerox Snap system? How many snaps have you seen? I've only seen one (Voice of America used the system, maybe they still do). There are certain price points where you get quantum jumps in acceptance. Microsoft is starting to hit a nasty one for them with low end PCs no longer being able to afford the MS tax, IBM is trying for a Power4 sweet spot to sell their chips in volume.

IBM should have one-upped everybody

[sjonke]

Ours goes up to 65-bits

Re:IBM should have one-upped everybody

[Nutello]

If this chip is going to be used in iSeries systems, then it's actually going to be a 65-bit CPU for real, at least when run in tags-active ("OS/400") mode. Careful what you joke about!

Re:IBM should have one-upped everybody

[Inthewire]

Strange use of the word obscure. I've never seen the movie and I knew what the parent was referring to. It's part of the culture. It's the air that we breathe. It's mother's milk.

Might this have something to do with Nintendo

[Fehson]

If I recall correctly, when Nintendo had IBM create the processor for the gamecube, IBM retained the rights to fiddle the their specialized PPC chip, then resell it. I'm wondering if the vector instructions are spillover from the Gamecube chip (I know it does a lot of fast vector math).

Embedded Processors

[death00]

This will (in about 5 years) make a huge difference to the embedded systems market, especially for military applications. Defense systems are perpetually chawing at the bit for more processing power in embedded display systems. This could finally help. I'm SOOO sick of looking at 600/700/7000 series systems with no power! "Power" PC my butt!

Re:just curious...

[Etcetera]

Actually, Apple File Exchange came with System 6 and would let you transfer a file off of an MS-DOS floppy. PITA to use, but it was Apple Software.

Just wondering...

[__aahlyu4518]

Will Linus soon be praying that AMD and Intel switch to these babies?

PowerPC 64bit

[dlawson]

Power 4 architecture has an I/O architecture that is WAY too expensive for workstation/low end server use. The PowerPC 64bit, however, would be quite a CPU. To see if Apple is interested, look to see if BSD runs on Power Architectures ...

It's already there, been there for some time, and IBM told me that Apple had Darwin and some GUI running. Apple just needs the market to see that it weould be worth the investment in a new mobo/system design.

Re:PowerPC 64bit

[dbrutus]

They could always put it in a black cube. How much industrial design is needed for that?

For the uninitiated, IBM favors black, blocky systems and the NEXT computer company put out a model that was a black cube many years ago.

Re:PowerPC 64bit

[Art Tatum]

If they would can the overwrought MOSX GUI and bring back the NeXT GUI, I'd buy one. :-)

Oooo

[Loki_1929]

This should be interesting to check benchmarks with. Now we'll be able to look at Itanium vs. Hammer vs. PPC-64. That might be a bit interesting..

PS. Check out my friend's band on this site. They're called Hat Trick of Misery.

Darwin is 64-bit clean!

[BawbBitchen]

Darwin is, IIRC, 64-bit clean. As a newly converted Mac-Head I am looking forward to Apple moving to these chips. I will buy a new system and put it next to my Dual-G4 and my NeXTCube.

FYI:

Oh, I submitted this story with 3 links yesterday in the afternoon but it was REJECTED. I never will understand how they pick what goes up.

Re:Darwin is 64-bit clean!

[daveman_1]

If I'm not mistaken, they probably rejected your submission faster than you could click 'submit', followed by 'submit story'. I have literally had stories rejected that fast after spending the better part of a half hour composing them. I will never submit another story because of this. They didn't even take the time to read it. Don't waste your time. And don't waste your time reading about Taco's omelette either. It'll make you puke.

Re:Darwin is 64-bit clean!

[BawbBitchen]

nope. it sat in the que for the whole night. about 8 hours.

cool... or rather, HOT

[lingqi]

Based on the award winning Power4 design, ...

Power4 has *huge* cooling requirements, despite being copper-interconnect and all that. (it also has something like 5800 pins, btw, drawing somewhere in the range of 100A worth of current, IIRC) -- I wonder how much cooling needs to be for the 64-bit power PC if they are based on the Power4 design?

Re:cool... or rather, HOT

[perfects]

100 amps... can that be right? Even at 3 volts that would be 300 watts. Just for the CPU?

Re:cool... or rather, HOT

[be-fan]

The friggin thing is quad core with 128MB of cache per chip and like 680 million transistors. At 1.5 volts (the more likely voltage for a chip of its die size) that's 150 watts, which is entirely reasonable given that some athlons are north of 50 watts.

Re:cool... or rather, HOT

[SlugLord]

wow! I'm guessing you don't recall correctly... the average house has 100 amp service. Large houses (that use large air conditioners) often get 200 amp service. There is no way that a cpu uses 100 amps. That's just unrealistic... Hey, while you're at it, go find a 1 farad capacitor....

Re:cool... or rather, HOT

[JollyFinn]

Hey you forgot few things.

a) ITS DUAL CORE die with 4 dies in package.
b) 100A*1.8V=180W
c) 0.18u
d) LOW VOLUME= [NOT handlayout.]

So if they mean per die its 90W per core and its pretty close to alpha. And if we take away the extra multiprocessor logic, like those highspeed package interconnections you probably end around 70W and ITS NOT HAND OPTIMIZED VERSION.
Consider that AMD/INTEL puts lots of resources in hand optimization of their processors, while IBM didn't because time to market considerations/ portability / costs of doing it.

ITs similar of using assembler in software developement in systems that are atleast Million lines of C. With no peaces that are used most of the time. And with the speed of system as slow as its slowest function of the package.

BUT if they make handoptimized execution core they could use the same core block as high-end systems and low end systems, but that requires more sales to make that cost-effective.
Of course with high level code version you need to do some optimisations but its not as costly as with doing execution units and scheduling logic with hand layout.

Re:cool... or rather, HOT

[daveman_1]

Hey, while you're at it, go find a 1 farad capacitor....

You can find one of these at your local car audio dealer, err rather your local 'bass shop'.

Re:just curious...

[Gainax]

There is x86 emulation software available for PPC systems. This, I imagine would still be the same. (google: Connectix Virutal PC)

As for hardware, recent Apple machines have PCI slots, so any PCI compliant hardware will work in a Mac, provided there is a driver. For some cards, such as video cards, you will need a card with a Mac-enabled BIOS ROM. Other than that, it is the exact same hardware.

This is also true for Alphas, StrongARM desktops, UltraSPARC etc.

Yeah, but every once in a while...

[sweetooth]

I say to myself. "Self, I wish this damn iBook wasn't burning a whole through my pant leg."

I do have to say that the iBooks are VERY nice though. Good performance at a great price. My wife loves hers, the only complaint either of us have with it is that it does heat up under the hard drive, and a small fan couldn't possibly hurt to push the air around and out the large vents on the left side where most of the heat builds up.

Re:Yeah, but every once in a while...

[guacamole]

Go into the Energy Saver and set an early idle
time out for your hard drive. It is better to let it spin down as a soon as possible. This saves the energy and the laptop is not hot any more.

Re:Yeah, but every once in a while...

[Golias]

I've never noticed the heat being excessive, but if you have then put a hotpad on your knee first. It's cheaper than a fan, quieter than a fan, and doesn't draw power away from the battery. If you are not running off the battery, you are probably using it in your home or office, in which case why don't you just put it on a desk or table, where it will be easier to type anyway?

I plan on buying a new iBook soon, and there's no way I would want a fan in there.

Re:Yeah, but every once in a while...

[Matts]

Strangely the iBook actually does have a fan. But to conserve power it's usually off. If you do some serious heavy lifting with it, like compiling stuff or rendering 3d scenes, you'll hear it come on.

Of course then you miss how quiet it was ;-)

Re:Yeah, but every once in a while...

[numpins]

iBook burning a hole through your pant leg? try a TiBook. Yow!

I love my super-quiet, sometimes-hot iBook.

Re:Yeah, but every once in a while...

[qengho]

it does heat up under the hard drive

I just bought a Traveler CoolPad and I'm really happy. The left side of the iBook stays much cooler, and the slight tilt is nice.

Re:Yeah, but every once in a while...

[sweetooth]

It's actually already on the lowest settings, and really I guess I was just trying to be funny more than anything ;) The extra heat from the front left corner does occasionally get excessive, but nothing to worry about the majority of the time....

Re:Yeah, but every once in a while...

[sweetooth]

Interesting, even doing 3d or compiling I've never heard a fan come on, and I was under the impression it didn't have one, oh well. ;)

Re:Yeah, but every once in a while...

[sweetooth]

Yeah, it would help if I used the proper spelling of hole wouldn't it ;) Oh well, if I actually checked my spelling/grammar more carefully I wouldn't fit in around here ;)

The heat in the iBook isn't all that bad in comparison to some of the other laptops I've used, my VAIO PCG-505TR actually get's a good bit warmer and that's a whopping 300mhz pentium MMX. Of course I plan on replacing it shortly with a Ti Book and a cooling pad so that I don't set my pants on fire ;)

Free Markets Require Competition to Exist

[FreeUser]

Sorry, but market forces are now as powerful as performance metrics. Apple no longer benefits from not being x86...cost being the biggest issue, and most of the time now they can't even claim a performance gain.

Intel won the CPU war on desktop PCs. Look to servers, handhelds, game consoles, etc. for the the next CPU battle worth fighting.

Until we have a monoculture in all our products, and have eliminated every trace of competition or choice, everywhere?

You waive your hands at the "invisible hand" of the free market as an argument for competitors to not even try competing for a portion of the marketplace, in effect advocating the replacement of a market with competitors with an intel monopoly.

I suspect you do not even see the contradiction in your argument, so let me spell it out for you. Monopolies are antithetical to a functional Free Market. Without competition the entire basis for capitalism functioning in any worthwhile capacity at all is removed and no free market exists. In short, without competition capitalism dies, and the free market "authority" you are alluding to becomes meaningless.

It astonishes me how people can argue "the market says" with one breath and "everyone should cave and give company X a monopoly" with the next. Indeed, one is forced to wonder if much of the current economic chaos isn't a result of an entire graduating class, perhaps an entire generation, not understanding even a little of economics in any context other than the inflated (and as it turns out largely fradulant) boom of the 1990s.

I won't even get into the fact that free markets are but one force, one tool, necessary for a functioning society or culture, another point often ignored in our western myopia, but that is a discussion for another thread.

Re:Free Markets Require Competition to Exist

[Elwood P Dowd]

Man, I hate it when trolls like you have a good point. Of course you're correct about morons talking about monopolies as free market perfection. But:

What, you're going to blame this fiasco on one age group being myopic? What generation have you picked as the culprit? I assume you don't mean your generation. How come the other more intelligent generations didn't have the foresight to not go along with the myopia and invest sanely? If they had done that, there's no way the myopia could have caused this turmoil.

You're going to have to lay the blame a little more evenly than that. There were/are a whole lot of shills in every age group. Jesus.

Re:Free Markets Require Competition to Exist

[Tablizer]

Until we have a monoculture in all our products, and have eliminated every trace of competition or choice, everywhere?...You waive your hands at the "invisible hand" of the free market as an argument for competitors to not even try competing for a portion of the marketplace, in effect advocating the replacement of a market with competitors with an intel monopoly.

It is an issue of de-facto open standards (the X86 instruction set), and *not* the manufacturer.

Intel has *not* monopolized CPU sales quite yet.

Besides, non-X86 chip makers are competing with Intel whether they go with X86 or a completely different instruction set. If non-x86 chips cannot keep up, then customers or OEM's are gonna pick x86 chips anyhow.

If they cannot keep up with x86 instruction chips, then they probably cannot keep up with their own instruction set also.

Nobody is gonna want it.

Re:Free Markets Require Competition to Exist

[Elwood P Dowd]

Right. That's the point. I'm not quoting myself. Sorry about my homepage.

Right on!

[Slur]

Let's hear it for the 486 - woohoo!

Re:just curious...

[JimBobJoe]

You're not getting particular great answers to this question. :-)

The PowerPC is a completely different chip architecture (search for explanation of RISC vs. CISC if you want more detail) in comparison to the Intel x86 architecture. There is a lot of complex discussion on this, but theoretically speaking the Power PC architecture is more advanced and efficient at the same processor speed.

At any rate, the Mac OS is optimized for this processor type. I guess it could be rewritten to run on x86, if Apple wanted to do that.

With the help of an emulator, Win32 programs can be executed in the Mac OS environment. (Virtual PC is the one that I can think of off the top of my head.) It's a testament to the architecture of the Power PC that the performance of Windows in an emulated environment is pretty good. (Not a computer science person, but my understanding is that Virtual PC makes Windows thinks that it's on an x86 computer...and it's an elegant hack.)

I think other posts here are discussing how Apple can/will migrate Mac OS X to the 64 bit processor, and whether or not 32 bit programs need to be recomplied/redesigned for the new processor, or if they can run directly on it in some sorta emulation mode.

Re:Two Words

[dbrutus]

Actually, the PPC has usually run much cooler than the equivalent Intel and AMD chips. It's what lets Apple get away with some of the case design decisions they make. It also is going to be a plus for them as they get more into the server market. Lower monthly cooling bills is a significant recurring savings.

Re:just curious...

[PythonOrRuby]

Whatever 64-bit PPC CPU Apple ends up with, be it from IBM, Motorola, or a new partner like AMD or nVidia, will almost certainly have to natively run 32-bit code.

Wonder long before the linux port?

[Perl-Pusher]

Great! Another chip for a linux port.
Oh and "Imagine a beaowulf of ....... "
I just could'nt resist!

Re:just curious...

[FrankNFurter]

PowerPC has nothing to do with x86. It's an acronym in fact, standing for 'Performance Optimised With Enhanced RISC Performance Chip' (where did they come up with those acronym monsters in the 90's?).

Let's see these in OpenPPC based systems :)

[JoeGee]

I think it deserves mention that OpenPPC.org is an IBM-supported initiative to bring OpenPPC-based machines to us commoners.

Re:just curious...

[hyperizer]

Although used in Macs, the PowerPC chip probably shouldn't be called "Mac technology."

Most chips using this architecture are used for embedded applications.

Re:Motorola folks going to Intel more like.

[dbrutus]

Yeah, because everybody knows that IBM doesn't have the money to retaliate.
[giggle]
The market caps on these companies are about the same. If you're going to play 'steal the employee' it's always wise to play that game with a much smaller company.

Re:just curious...

[greed]

You pick the words to go with the cool name.

Enfoce In-Order Execution of Input/Output anyone?

You know someone wanted to be able to have an instruction called "eieio".

0ddc 0ffe ebad f00d

Re:Obligatory...

[dbrutus]

No, no, these would be Appleseed clusters. Though, I do imagine that eventually you might be able to create an Appleseed of Beowulf clusters...

B-)

Re:uhm hello?

[aanantha]

It's the same thing now. The POWER3 is a PowerPC 630. They're not using the old POWER instruction set anymore.

Re:just curious...

[nosphalot]

Not necessarily.

When Apple transitioned from 68k to PPC there was a lot of code that was still 68k and it was transparently emulated. While it's likely that the new 64 bit PPC will have some support for 32 bit instructions, it's not a requirement, just a convenience.

Re:just curious...

[Maserati]

A Mac can read pretty much any media created on a PC. And it's a safe bet that there's an application that can read the files, like oh let's say MS Office or any of the vast selection of OS 9, OS X and Unix freeware.

Basically, this creates a 64-bit option for Apple. Very important for a Unix vendor. All you'll lose is the smaller address space :-) If Motorolla really is focusing on the embedded market then letting IBM start producing AltiVec (or something much like it) is less of a shock than when they were looking at the desktop market. Likewise, IBM now sees Apple expanding both their desktop market and their new server line, and an AltiVec optimized GCC 3. Apple, looking onwards and upwards sees Motorolla losing interest, and a line of IBM chips that scale from their fast, cool G3s through the Power line for medium-to-big iron.

Put those three viewpoints together and it looks like Jobs has found that Motorolla alternative he has been talking about.

iBooks are Slow

[nemesisj]

I had a 500mhz iBook running 10.1, and while the OS was pure heaven, the speed of the iBook was pure hell. I constantly said "damn, I wish this was faster" until I finally gave up when I noticed it'd take me twice as long to browse the web as on a PC. What a drag. I sold it and am looking forward to the day when I can get a decently fast iBook. Maybe the 700mhz model is a lot faster, but I'd be surprised.

Re:iBooks are Slow

[guacamole]

The 500MHz iBooks very much slower. The problem is that they still used 66MHz system bus and memory. 600MHz iBooks use 100MHz system bus and memory and the 700 iBooks have double the L2 cache as the 600MHz iBooks.

Re:iBooks are Slow

[namespan]

I sold it and am looking forward to the day when I can get a decently fast iBook. Maybe the 700mhz model is a lot faster, but I'd be surprised.

The 700mhz have a larger cache and faster bus if I recall correctly.

On the other hand, I am posting this from a Powerbook G3 running at 333 Mhz, and I'm comfortable with the speed of normal applications. My secret? RAM, my friend, boatloads of RAM. Actually, 320 MB really isn't considered a boatload any more, but it's enough that the OS and most apps speed remarkably.

Of course, when I'm encoding mp3s or doing other signal processing stuff like photoshop, or recompiling PHP, I do sometimes wish for some more speed.

POWER != POWER2 != PowerPC ISA, but close

[psamuels]

POWER and PowerPC are mostly the same, but not quite.

Correct. gcc and AIX xlc compilers by default output the common subset - the moral equivalent of -march=486 or so.

IIRC all of those instructions are fairly esoteric supervisor mode instructions, so they'd likely only affect the OS and not user-space programs.

Mostly extensions, a few dropped or changed facilities. It's worth noting that the PowerPC is much closer to its immediate ancestor the POWER2. Here are some highlights of POWER -> 32-bit PowerPC, taken from The PowerPC Architecture (IBM, 1994):

• a few instructions, formerly privileged, are now general-use
• two instructions, formerly general-use, are now privileged
• 34 instructions (only 3 of which were privileged) have been dropped
• 35 instructions have been added - a few privileged ops, quite a bit of floating point, a few new facilities
• many "don't care" conditions have been tightened up to e.g. "reserved, must be 0"
• a few facilities changed around - memory management for one, RTC for another (PowerPC uses a new "time base" instead of an RTC - the time base has an implementation-defined tick and sounds more like the Pentium TSC), etc.

The main changes listed for POWER2 -> 32-bit PowerPC seem to be dropping several opcodes for floating point loads/stores, and some semantics of FP <-> int conversions.

Solaris is 64-bit OS since version 7

[guacamole]

enough said.

Bad News for Mac owners

[Jungle guy]

If IBM is talking openly about a Power PC processor, they probably don't have a deal with Apple. That's the opinion of an analist included int this article. So nexx-generation Macs may ship with Motorolla processors.

Re:just curious...

[Maserati]

That's just the same as the first PowerPC Macs. The OS had to emulate the 68K instruction set. They managed it pretty well in software. The 32-bit to 64-bit transition will probbaly be even easier since the 64-bit chips will probably handle the 32-bit emulation and porting apps won't be a major hassle, certainly less than the OS 9 to OS X switch. And only those who need it will port, others will rely on 32-bit mode.

Incidentally, Connectix (who make VirtualPC) at one time had a faster 68k emulator on the market. They're Real Wizards at Connectix. VirtualPC doesn't emulate Windows, it emulates an x86 PC at the hardware level. Then you install a standard OEM copy of whichever version of Windows you got. Then you install drivers for the emulated PC hardware. You can also load it up with a basic DOS image, reformat the virtual drive and install Linux or a free BSD. Neat stuff.

Re:just curious...

[Bungie]

Apple has switched architectures before. Remember that old Macs were origionally Motorola 68k CPU's, and when Apple switched to PPC, they needed to be able to use their existing software base. Their solution was to include an on board 68k emulation chip that translated the old 68k instructions to PPC. This worked so well that they didn't even bother to remove most of the 68K code from their OS (rumour has it that it is still not all gone even in OS9).

I suspect that the new chip would either support some kind of backwards compatability with PPC32 code, or they will include another emulation chip.

Re:just curious...

[Octorian]

Actually, they shouldn't have to recompile anything, unless they want their apps to use 64-bit addressing. (but they will have to modify the OS kernel)

Real 64-bit chips which are new versions of older 32-bit lines are fully backwards compatable.

Case in point, you don't need to recompile 32-bit SPARC applications to run them natively on a 64-bit UltraSPARC.

Re:just curious...

[Golias]

He's not getting particular[sic] good answers because it was not a particular good question.

This was obviously a case of somebody who has been conditioned by the M$ marketing empire to believe that "PC" is a registered trademark of Intel or Microsoft or somebody, and it somehow stands for "Windows Computer."

When he saw that Apple had something called "PowerPC", he immediately assumed that it must have something to do with Wintel compatability, and in his mind tied it to various rumors of various cross-platform projects he overheard while walking past the cubicles in his office.

That, or he knows perfectly well what PowerPC chips are, and he's just trolling.

Strange comarison

[axxackall]

Please, compare dual G4 with dual P4. Or single G4 with single P4. Otherwise you compare nothing.

So what do we do with it?

[thatguywhoiam]

Someone refresh my memory - I seem to recall (not being a hardcore cpu guy myself, but just an enthusiast) that 64 bit calculations were useless to the vast majority of computing tasks. That is, 32-bit precision was all anyone needs, for most things.

Could someone with a clue maybe give us some examples of why a 64 bit PowerPC is a Good Thing?

Re:So what do we do with it?

[adb]

For one thing, you can directly address all the bytes on a hard disk partition, so you can map them all into virtual memory. (This is how the Hurd filesystem code works, which is why it doesn't cope with >1GB filesystems on 32-bit machines, which is all it runs on right now...)

Power3 and Power4 ARE PowerPC chips

[Valdrax]

Welcome to the modern world. POWER as an architecture is dead and no longer implemented. What chips you know are POWER are in fact 64-bit PowerPC implementations. The Power3 chip was also known as the PowerPC 630 and has been used in RS/6000 workstations since 1996. You can find out more about it here, straight from the horse's mouth.

PowerPC was designed from the POWER architecture to replace it, and has been designed from the beginning to support 32-bit and 64-bit versions. The architecture is actually designed from the beginning to be a 64-bit architecture, and the common desktop implementations are only the 32-bit subset of the original design.

Here's some additional background info:

• Wikipedia -- a little out of date, but good on history.
• Power PC Architecture: A High-Performance Architecture With a History

Re:uhm hello?

[psamuels]

Does that NOT say PowerPC? Does it NOT say Desktop?

Guys, guys! Enough! It's just a label. If it's backward-compatible with the PowerPC spec, it's a PowerPC. You're starting to sound like me:

Me: What kind of CPU is in there?
Other: 450 MHz.
Me: Yeah but what chip?
Other: A Pentium.
Me: Where did you find a Pentium running at 450 MHz?

*sigh*

Compatibility with 32-bit?

[inkswamp]

First off, I know almost nothing about the technical aspects of processors, so if this sounds like a clueless question, my apologies. However, I am aware that programs compiled for 32-bit processors won't work on a 64-bit processor. If that's the case, what happens if Apple should jump to this chip? Does that mean we Mac users have yet another OS 9-to-X-type wait while developers drag their feet updating their apps or is there some way that a 64-bit processor can also handle 32-bit apps? As far as I can see, that's the only problem with Apple going to this chip. I'm not sure how eager Apple will be to annoy users who are finally seeing the light at the end of the OS X tunnel.

Re:Compatibility with 32-bit?

[bbbl67]

Actually, the source of incompatibility is not from whether the processor is 32-bit or 64-bit. The incompatibility comes from whether the processor's instruction set has been carried over or not. Any 64-bit processor should be able to maintain compatibility with a 32-bit processor, provided it implements the 32-bit instruction set. So the idea behind a 64-bit PowerPC would be to carry over the 32-bit instruction set intact. If it is carried over, then there's no problem, as far as 32-bit programs are concerned they will think they are still working on a 32-bit processor.

Re:Compatibility with 32-bit?

[inkswamp]

Actually, the source of incompatibility is not from whether the processor is 32-bit or 64-bit. The incompatibility comes from whether the processor's instruction set has been carried over or not.

Then my follow-up question would be, on a design level at least, is carrying over a 32-bit instruction set into the 64-bit processor feasible and/or trivial enough task?

If it is carried over, then there's no problem, as far as 32-bit programs are concerned they will think they are still working on a 32-bit processor.

That being the case, I hope like hell Apple has been doing some serious talk with IBM about doing exactly that. I love Macs, but fercrissake, they are fighting a losing battle with this MHz Myth stuff.

I recall that earlier this year Steve Jobs was asked in some magazine or interview what Apple is doing about closing the speed gap between Macs and Wintel machines and the article said Jobs was almost smug about his response, saying that Apple had some big surprises up its sleeve. I certainly hope that was in reference to this.

Re:Compatibility with 32-bit?

[bbbl67]

Then my follow-up question would be, on a design level at least, is carrying over a 32-bit instruction set into the 64-bit processor feasible and/or trivial enough task?

The usual answer to that is "it depends." If the 32-bit ISA were sufficiently thought out in advance for future expandability, then it shouldn't be a problem, obviously. The most common example of an ISA regeneration was the x86 instruction set architecture.

For example, the x86 ISA has not just a 16-bit and a 32-bit mode, it also has a compatibility mode known as Real mode, and a more modern mode called Protected mode. So x86 has Real mode, 16-bit Protected mode, and 32-bit Protected mode. Each mode represents a generational change in the x86 ISA. Real mode represents the mode that the first ever x86 processors operated in, the 8086 and 8088. The 16-bit Protected mode represents the 286 processor, and 32-bit Protected mode represents the 386 onwards.

When they designed the 16-bit Protected mode, existing 16-bit Real mode programs couldn't run in that mode. So the 286 processor usually operated in Real mode to maintain compatibility with programs designed for 8086's. So there wasn't a really good solution put in place to run 16-bit Real mode and Protected mode applications together with the 286. So that was a poorly designed generational upgrade as far as the previous generation was concerned. But they did plan for the future and left lots of growing room for a possible 32-bit protected mode in the next generation; which made it a good generational upgrade in that sense.

When the 386 came out with the 32-bit Protected Mode, they had come up with ingenious solutions to preserve compatibility with all modes simultaneously: Real, 16- and 32-bit Protected modes! They could run programs designed for all three modes simultaneously, which made the 386 processor one of the landmark processors of the x86 ISA -- not simply because it extended the architecture out to 32-bits.

However, it did look like 32-bits was the end of the road for x86, because I really didn't think they could continue to extend x86 out to 64-bits the way it was currently setup. Intel agreed with me, and came up with Itanium processor with its IA64 or EPIC ISA, which is not compatible at all with its previous generation IA32 or x86 architecture. AMD disagreed with me, and came up with an ingenious way to extend x86 out to 64-bit, i.e. the x86-64 ISA. x86 is a series of ingenious hacks that just keep the life of the ISA going. The way AMD has implemented their x86-64, they've probably left a lot of growing room for future improvements beyond 64-bits.

So based on this similar history, and whether PPC's architecture is sufficiently flexible enough to accomodate 64-bit, IBM may have an easy job or a hard job.

That being the case, I hope like hell Apple has been doing some serious talk with IBM about doing exactly that. I love Macs, but fercrissake, they are fighting a losing battle with this MHz Myth stuff.

I don't think Apple is fighting a losing battle against a Mhz myth, they are simply fighting losing battle against the weight of more available software and hardware choices. Let's face it, this Mhz mania in the x86 world is just a recent mania, resulting from the competition between the two main x86 CPU makers, Intel and AMD. Prior to this everybody used to laugh at how pathetic x86 architecture was at scaling up in Mhz compared to other ISA's including PPC. But that didn't stop people from buying x86 PC's in the past either.

Re:Compatibility with 32-bit?

[inkswamp]

Thanks for explaining this. I appreciate it.

In use?

[EdMcMan]

Does anyone still actually use PPC anymore, besides Apple? I havn't seen many IBM machines at all with them, even the big ones. Why is IBM going through the trouble?

Re:In use?

[stux]

Ahem...

The big ones (IBM's) use PowerPC chips...

They just call them POWER3 and POWER4 ;)

IBM doesn't make big ones which don't use PowerPC's as far as I know.... all the ones which use Intel's chips aren't.... big :)

Re:In use?

[JollyFinn]

Actually they use in their mainframes some other ISA but thats totally different than even server market. Ridiculous stability ensurances, and software thats history goes far beyoud powerpc.

Jouni

Already licensed

[Valdrax]

IBM has alread licensed Altivec from Motorola as far back as 1998-2000, allegedly to help with the design of the PowerPC variant used in the Gamecube. The PowerPC 405 embedded processor in the Gamecube contains 38 additional instructions for vector FP math (vs. the 162 in Altivec). A glance at this PDF file from the web makes me pretty sure that these aren't just lifted from Altivec. Instead of Altivec's 128-bit 4 32-bit FP vectors, Gecko adds instructions for fitting 2 32-bit FP numbers in a single 64-bit FPU register and working with them. It also adds some odd but interesting MMU features.

Anyway, I know it's been licensed because back in 2000 there was a lot of conspiracy theories that Motorola was preventing IBM from selling faster clocked PPC chips to Apple than they could produce via an obscure clause in that license. Both parties denied it, of course. I don't really believe that was the case. I think it was just bitter rumor-mongering by Mac users who were rightfully angry at Motorola for pissing away the performance (and MHz) advantage that PowerPC had on x86 chips back in the 603/604e and Pentium/PPro days.

Oh, admittedly, the MHz advantage went away as Intel/AMD extended their pipelines for that explicit purpose earning theirselves increased performance penalties for mispredicted branches and requiring increased CPI for many instructions, but I still miss the days when PPCs were faster per clock AND had higher clock rates. Now the clock rate advantage is so extreme that the PowerPCs' better performance per cycle doesn't catch up for the most commonly executed code. Once again, though, I digress.

Re:Already licensed

[Nutello]

IBM has alread licensed Altivec from Motorola as far back as 1998-2000, allegedly to help with the design of the PowerPC variant used in the Gamecube. The PowerPC 405 embedded processor in the Gamecube contains 38 additional instructions for vector FP math (vs. the 162 in Altivec).

IBM doesn't need an Altivec license for the Gekko extensions. As you point out, Gekko can treat a single 64bit FPU register as a pair of single-precision numbers. Altivec, instead, uses an additional set of 128bit registers. Gekko's paired-single extensions target one particular application, 3D graphics, and are pretty much like the MIPS3D extensions that SGI created some ten years ago. Altivec is much broader and is more like MIPS' MDMX (MaDMaX) extensions on steroids. Pretty much everything is done differently; even the programming model for condition codes is not the same.

Research first

[denjin]

IBM already licensed the technology. There isn't any reverse engineering involved here. However, I think they'll call it VMX as opposed to just altivec.

apples to lemons

[Bobartig]

You've got the wrong kind of "proprietary" in mind. Compaq used proprietary boards so that you couldn't upgrade with standard parts, were locked into their upgrade path. For a standard user, this did not offer any additional functionality.

Apple uses proprietary boards so they can offer features like autoswitching networking (just plug in an ordinary ethernet cable between two macs, and the two computers show up on each others local network), target disk mode (use a scsi or firewire cable between two macs, and one computer becomes a HDD on the second computer), instant dynamic network configuration (change your IP/ or configure multiple network devices with just a few clicks, no restarts), dynamically driving multiple monitors with multiple cards (I can plug in two graphics cards, and two monitors, then tell the mac which monitor to drive with which card, while its on.), and USB/Firewire plug and play ease that's still years ahead of windows (oh look, it's the windows hardware manager, again...). On the portables, multimonitor/external monitor support is so slick, it's enough to make a Wintel laptop user cry.

There are plenty of things you _can't_ do as a result of proprietary HW, such as move as quickly with the industry as new HW comes out (lets see how long it takes apple to get AGP 8x...*roll*), but the main differences in functionality between MacOS9 and Win9X/ME/XP is the hardware tweaks that you don't realize by using "open" HW. In the Wintel world, the peripherals people don't work with the OS people, who don't live on the same continent as the BIOS ppl, etc. etc.

Mac admins live for these tweaks, since it means hours less frustration and "pointless clicking" to set up an office of computers, or get them networking just so, using external devices, while adapting the systems to individual work flow and idiosyncrasies.

Re:apples to lemons

[BitGeek]

It was in 1985 and 1988, when Apple first introduced them. What only 5 years before Windows support? 7? 10?

Not to mention the 3.5 inch floppy drive, the laserprinter, both co-developed by apple, not having a floppy drive (Which is funny, especially since so many people don't get it. You realize just how stupid it is to have a rackmounted server with a dinky 3.5 inch floppy drive on it?)

etc etc. etc. Yeah, Apple's been copied and these things aren't as special anymore... but the copies always seem to be lower fidelity anyway.

Re:apples to lemons

[Kranium]

I was under the impression that multi monitor support on wintel required the use of a dual-head card.. can someone tell me if thats true?

Re:apples to lemons

[be-fan]

Apple uses proprietary boards so they can offer features like autoswitching networking (just plug in an ordinary ethernet cable between two macs, and the two computers show up on each others local network)
>>>>>
On PC's, it's $10 for a cross-over cable. Big deal.

target disk mode (use a scsi or firewire cable between two macs, and one computer becomes a HDD on the second computer)
>>>>>>>
In WinXP, you have firewire networking built in as well. Essentially the same thing, but you still have to deal with security (which is a good thing).

, instant dynamic network configuration (change your IP/ or configure multiple network devices with just a few clicks, no restarts),
>>>>>>
And this is different from Win2k+/Linux how?

dynamically driving multiple monitors with multiple cards (I can plug in two graphics cards, and two monitors, then tell the mac which monitor to drive with which card, while its on.)
>>>>>>>>
Been able to do this since Windows 98 (maybe SE).

and USB/Firewire plug and play ease that's still years ahead of windows (oh look, it's the windows hardware manager, again...). On the portables, multimonitor/external monitor support is so slick, it's enough to make a Wintel laptop user cry.
>>>>>>>
Specifically how?

Modding the story

[swagr]

Synopsis: "Someone in the hardware industry has created a faster CPU".

Moderation: -1 Redundant.

PowerPC has been 64bit for years!

[lscotte]

We've been running them for maybe 5 years or so - RS64, RS64II, RS64III, etc.

AltiVec == VMX

[stux]

I've been running into a new acronymn the last few weeks

VMX.

Its a PowerPC vector instruction ISA...

Anywho, the most interesting run in was in an IBM publication where they referred to AltiVec/VMX as the vector instructions on a Motorola 74XX 'G4' CPU

Anywho, point is, the only people in the entire world I've heard referring to AltiVec as VMX are IBMers :)

But IBMers like to use alternative words to the rest of the computer industry ;)

Anywho, my prediction is these chips feature a VMX unit ;)

It is a very IBM sounding acronym, and matches up with other vector ISA names... MMX, SSE, SSE2, VIS, MDMX etc

Re:just curious...

[bhawbaker]

there was no on board 68k emulation chip.. it was all ppc software emulating 68k ops

Re:SuperH uber alles.

[Nutello]

The Dreamcast doesn't use the SH3, it's the Japanese Zaurus PDAs and a few WindowsCE PDAs that use it. The SH3 would be utterly useless for the Dreamcast, because it lacks a FPU. Instead, Sega used the SH4, whose FPU kicks ass.

By the way, SuperH (a separate company started by STMicro and Hitachi) introduced a few months ago the SH5, which introduces a new 64bit architecture (both for registers AND addressing).

Re:Two Words

[Toraz Chryx]

OTOH, an IBM 750FX @ 800Mhz uses less than 5w and performs _better_ than a Motorola 7455 per clock (unless the Altivec hardware on the G4 comes into play)

IT's already 64 bit but here is the difference:

[gelfling]

Based on the award winning Power4 design, this processor is an 8-way superscalar design that
fully supports Symmetric MultiProcessing," the description says. "The processor is further
enhanced by a vector processing unit implementing over 160 specialized vector instructions and
implements a system interface capable of up to 6.4GB/s.

It's the 8-way ss + new vector instruction set that's new. The 8-way would drive the overall bandwidth requirement.

Clearly this is no longer a RISC design because the original PPC instruction set had what, 174 instructions? So add 160 more and you have 334.

Re:Some are happy with a 600 MHz P3 too...

[Toraz Chryx]

actually, a 700Mhz Sahara should be able to smack a 600Mhz Coppermine P3 around quite handily.. not only is it based on the original 4-stage G3/G4 pipeline (which is higher IPC than Motorola's current 7-stage G4's) but it also has a half meg of L2 cache on the die with a 256Bit link to the processor core.

Apple on x86 != OS X on a Dell

[PaxTech]

Apple relies on being on a seperate platform from Microsoft to survive.
If Apple ever moved to Intel, they would be crushed.

You imply that moving to x86 (Intel) would mean Apple no longer maintains a separate platform from Microsoft, but this isn't necessarily so. Just because Apple currently uses one processor architecture in their machines doesn't mean they can't switch to another while maintaining their separation from the PC world with proprietary ROMs and the like.

The idea of Apple moving to x86 doesn't mean they would release a boxed OS X that runs on a standard Dell box. More likely they'd just come out with new Macs that are functionally identical to the current machines, but with an Intel or AMD chip inside instead. That way they maintain their focus as a hardware company first, while gaining the ability to run Windows apps natively and the economies of scale that result from using CPUs that are practically commodity items.

The Mac isn't about being the fastest machine on the block, it's about being the best designed, easiest to use, most useful machine on the block.

And if a Mac had a blazing fast x86 chip inside it'd STILL be the best designed, easiest to use, and most useful machine on the block. It'd just be fast as shit as well. Not that I'm not happy with the speed of my Mac, but if the speed gap gets any wider Apple would be crazy not to consider switching.

Re:Apple on x86 != OS X on a Dell

[sl3xd]

More likely they'd just come out with new Macs that are functionally identical to the current machines, but with an Intel or AMD chip inside instead

By functionally identical, I assume you mean that the user doesn't see the difference?

And, of course, it's pretty obvious that Apple may use an AMD or Intel chip-- but it won't be x86. More like Itanium2/3 or a modified Opteron (that is not x86 compatible).

But there's one thing that many fail to see: Unlike x86, with an Apple, you can't just pop out the CPU and replace it with a faster one. The cases aren't exactly 'standard' either. If they switched to an Intel or AMD chip, the Apple motherboards likely wouldn't allow for CPU upgrades at all.

And, of course, for the overclocking crowd (whose only desire seems to be to run OS X on their cheapo hardware): Forget about overclocking anything from Apple if they go Intel/AMD. Apple values stability far more than speed-- they won't push any of their hardware past its design, nor will they allow it to happen. Locking the clock speed to the motherboard/cpu is how Apple can ensure that shady dealers won't try to sell an overclocked (and unstable) Apple, while claiming that it's not overclocked. The whole 'unlocking Athlons' is a moot point: x86 motherboards are capable of multiple clock speeds; primarily so it can handle CPU's of multiple speeds (and many are designed to allow overclocking of the CPU). But in an Apple design- expect to see the motherboard and CPU speeds permanently locked (Easy to do, espescially if the clock generator is part of the chipset, and requires 100's of surface-mount de&re soldering to replace; a task that is nearly certain to ruin the motherboard)

yet to see it

[johnjones]

intel said the Xscale would do 900MHz but all the test chips and produvtion has been 400MHz

so really unless you have benchmarked it (A chip which I havnt seen) you can say that

compare a 400MHz G3 against a 400MHz Xscale and then we can talk

in terms of apps like telephonery and video then the ARM wins because of the DSP extensions in terms of floating point add a VPU and then the ARM is not to shabby

regards

John Jones

Re:yet to see it

[stux]

I have benchmarked it.

The ARM DSP extensions aren't very applicable to video. For audio they are pretty nifty though.

Re:Wait a minute

[stux]

WTH are you talking about?

Apple uses 64bit FPU operations on the 64bit FPU...

BUT the altivec unit is only capable of 32bit FP operation (of course it does 4 of them at a time)

so you are saying

[autopr0n]

That all 160 of these vector instructions take that format? I do find that a bit hard to belive.

Also, load store instructions don't take that form.

Re:so you are saying

[stux]

I didn't say the load/store instructions took that form. The data processing instructions take that form.

BTW, almost all the altivec data processing instructions DO take that form. An interesting example of an instruction in non-normal form is the permute instruction which is :

d = vec_perm(a,b,c); where a,b are source registers, c is the permute register and d is the destination. Very powerful instruction

You misunderstood

[FreeUser]

What, you're going to blame this fiasco on one age group being myopic

Absolutely not. The wrongdoers and politicians span several generations.

My point was how commonplace the rhetoric of "free market says, so everyone should just cave and do" has become. This is a relatively new development, one that flies in the face of economic theory, free markets, free societies, and a functional society, and one that would have been laughed into submission a few short years ago.

These days one rarely hears a rebuttal, so I begin to wonder why that is and speculate that there is perhaps a group of people who do not grasp capitalism, perhaps because the only form of it they've been exposed to is the corporate perversion of it we've had throughout the late 80s, 90's, and early naughties.

Nothing more was implied or intended than that.

Oh, and if any one generation were to take a big chunck of the blame for the philosophical myopia and malaise that has engulfed so much of the American psyche over the last twenty years, I would most certainly rank my generation at the top of that list, though, as you rightly point out, the blame is a little more widely spread than that.

Re:just curious...

[MoneyT]

I don't know the technical details, but from my own experience:

VPC doesn't just make windows think it's on a PC, it actualy emulates the x86 environment, right down to the hardware. This means you could install any x86 based OS to your mac. It uses (dynamic?) disk images to serve as the harddrive, and runs the machine in it's own window. As near as I've been able to tell, the only thing VPC can't do well is video games. Oh well, that's why I bought a PS2

(correction) Re:Free Markets Require Compet....

[Tablizer]

Correction:

This: "Intel has *not* monopolized CPU sales quite yet."

Should read: "Intel has *not* monopolized x86 CPU sales quite yet."

Actually I should also toss the "quite yet". I cannot predict the future after all.

RISC != fewer instructions (despite acronym)

[dutky]

How many times do we need to go through this crap? Despite the reputed meaning of the acronym, RISC doesn't have anything to do with the number of instructions!

gelfling wrote

Clearly this is no longer a RISC design because the original PPC instruction set had what, 174 instructions? So add 160 more and you have 334.

and, earlier, autopr0n wrote

Yet Mac zealots will still be going on and on about how PPC is better because "Its RISC!". Never mind that the 486 only had 142 instructions total or anything like that.

RISC is about reduced complexity and designing architectures for best use by optimizing compilers.

If anyone actually wants to learn something (rather than simply spouting ignorant marketing propaganda) you can check out John Mashey's periodic RISC vs. CISC article from the comp.arch newsgroup.

The essence of the RISC philosophy can be summed up in this quote from Hennessey & Patterson: "Make the common case fast and rare case correct." The question is, however, how do we know what is the common case? The answer from H&P is to look at the occurrance of various instructions in actual programs. Since most programs are generated by compilers, this amounts to looking at what is used most commonly by compiler code generation engines.

Once you have made an inventory of instruction usage, what you find is that lots of time and instructions are spent moving data between registers and memory because you don't have enough registers, and over 80% of the addressing is done with only a couple of addressing modes. In other words, compilers are simply no good at making use of most complicated instructions common in most pre-RISC architectures (including the 80x86).

When you design an architecture that caters to the kind of usage a compiler likes, you come up with an architecture that has lots of registers and performs all arithmetic operations on values in the registers, only accessing memory with simple load and store instructions supporting a few simple addressing modes (absolute address, register direct, and, possibly, register direct with immediate index). Along the way, in order to make various CPU bookkeepping tasks as simple as possible, you will use a fixed length instruction word with only a few instruction formats, and ensure than any single instruction can only cause one fault condition (memory access fault, instruction operand fault, etc.)

This general description is a pretty good match for almost all, so-called, RISC architectures: MIPS, M88000, ROMP, POWER, PowerPC, PA-RISC, Alpha, AMD29000, Sparc, ARM, Clipper, etc. The fact that all of these architectures share so many common features says something profound about the descriptive power of the term 'RISC' which cannot, easily, be said of the converse term, 'CISC'.

Just to head off the other popular mis-conception concerning RISC vs. CISC: RISC has nothing to do with the implementation features of a given processor, only with the programmer visible architectural features (number of registers, instructions, instruction encoding, etc.). Hence, no matter what name Intel or AMD use to describe the current dynamic micro-coding scheme used to salvage another generation of bloated, power guzzling, 8-bit microcontroller follow-ons, the 80x86 will never be considered a RISC processor.

Re:RISC != fewer instructions (despite acronym)

[daveman_1]

And RISC will never make it onto the PC desktop. But I would still love to own an Alpha. ;-)

Re:RISC != fewer instructions (despite acronym)

[dutky]

daveman_1 wrote

And RISC will never make it onto the PC desktop.

What, precisely, do you mean by "never"?

There have been personal computer systems in use for at least 10 years that are based on RISC processors, not to mention a large number of game platforms and hand-held computers. In the desktop world, the fifth largest personal computer manufacturer has been selling only RISC based systems for the past 7 years.

I don't think that word means what you think it means.

Re:just curious...

[ZigMonty]

my understanding is that Virtual PC makes Windows thinks that it's on an x86 computer...and it's an elegant hack.)

It actually emulates the hardware of a PC so Linux x86, *BSD, etc will also run fine. One of the reasons that VirtualPC is surprisingly not shitty is that the PPC has a few little tricks to help. For example when emulating x86 code, VirtualPC throws the PPC into little endian mode (it's natively big endian). This saves lots of byte swapping instructions. The PPC was designed to be a great emulator.