IBM Processor Yields

[MacRumors]

eeTimes reports (http://www.eetuk.com/bus/news/showArticle.jhtml?articleID=20300708) that while IBM is running at full capacity at its 200 and 300 nm fabs, it continues to wrestle with chip yields.

Even so, IBM claims that it is close to resolving these yield issues which Apple has pointed to as a reason for shipping delays for the Xserve G5.

IBM's chip yields "are not quite where we would like them to be," said John Kelly III, senior vice president and group executive of IBM's Systems and Technology Group. "Lately, our defect densities have improved quite rapidly. We expect to do a better job to meet the demand of our customers," he said during a conference call on Wednesday (May 12).

[denm316]

hopefully this can help Apple more into the enterprise market with G5's

[ingenious]

hopefully this helps G5 updates... PM, iMac, and PB :rolleyes: :D :cool:

[fussball]

These supply problems scare me, I worry that we will see moto. all over again :(

[xtekdiver]

But will they yield a Dual 3GHz announcement at the Developers conference?

[PowerMacMan]

Maybe they're trying to reach the promised 3Ghz...

[dizastor]

Maybe they're trying to reach the promised 3Ghz...

That is accurate, however they currently have only been able to produce 3 chips running at 1ghz... apple is in the process of welding these 3 together to make a prototype 3ghz G5 for WWDC.

[Mr. Anderson]

That is accurate, however they currently have only been able to produce 3 chips running at 1ghz... apple is in the process of welding these 3 together to make a prototype 3ghz G5 for WWDC.

so a dual 3 GHz machine would actually have 6 cpu's :p

I just hope I'm not disappointed in June - waiting a whole year for an upgrade seems a bit much....I hope its worth the weight.

D

[themadchemist]

at least they recognize the problem...hopefully they can fix it.

[PowerMacMan]

That is accurate, however they currently have only been able to produce 3 chips running at 1ghz... apple is in the process of welding these 3 together to make a prototype 3ghz G5 for WWDC.

Just a prototype, or will it be an actual product by WWDC? (Will you be able to buy it)
;)

[iriejedi]

About the 200nm and 300nm fab stuff - arn't we all concrened with 130nm and 90 nm fabs?

Irie

[Daveman Deluxe]

"200mm" and "300mm" refer to the diameter of the wafer that the chips are produced on. "130 nm" and "90 nm" refer to the process size.

[gekko513]

So we get a new rumor every time a news site does an article even if the article is based on the same information source as a previous rumor
:confused:

[wordmunger]

According to the chart, IBM has lowered the delta in terms of defect rates over the last year and is close to its target yields in the plant.

If this is true, this is *very* good news--that's more impressive than just "we're improving."

[Frohickey]

These supply problems scare me, I worry that we will see moto. all over again :(

I need to remind everyone, that even though making processor chips out of silicon is NOT rocket science, it is still a pretty difficult process to do. ;)

[Phatpat]

Is there anything Apple can do to prevent things like this slamming them to a halt?

I'm curious.

[saabmp3]

Is there anything Apple can do to prevent things like this slamming them to a halt?

I'm curious.


Well,....


Basically, no.

BEN

[dopefiend]

Is there anything Apple can do to prevent things like this slamming them to a halt?

I'm curious.


Yup, switch to x86!

[szark]

Yup, switch to x86!

Yeah, Intel hasn't had ANY problems with their 90nm process... :rolleyes:


Sounds like IBM is getting a handle on the problems, and we'll see some PowerMac updates soon! (hopefully!)

[Quixcube]

Is there anything Apple can do to prevent things like this slamming them to a halt?

I'm curious.


No. Unless they want well established and stable chips (read slower.) Cutting-edge hurts.

[dopefiend]

Yeah, Intel hasn't had ANY problems with their 90nm process... :rolleyes:

Never mentioned Intel.... :rolleyes: ( <---- ha :p )

[Remus]

I think we will see 3 Ghtz by September of this year. I do not think that they will announce them at WWDC. :)

But we shall see...

[shamino]

Never mentioned Intel.... :rolleyes: ( <---- ha :p )
Actually, this isn't as crazy as it seems.

IIRC, AMD's K7 (Athlon) and K8 (Athrlon-64) architectures are actually a proprietary RISC architecture with an x86 emulation layer over the top. It may well be possible for them to make these with a PPC emulation layer instead.

I have no idea, however, how well these would compete against a real PPC. I would be really surprised if they can match a G5, but they might be able to match a G4's performance.

Of course, designing any such a CPU would be expensive and time-consuming, and it would be hard to make the business case for AMD to even consider such a project.

I believe TransMeta's Crusoe chip is similar - and its CPU emulation is loaded as software, so you don't need to spin new hardware. But it has never been known for high performance. Crusoe's big claim to fame is low power consumption. But it's another possibility, at least for low-end laptops.

[iriejedi]

Is there anything Apple can do to prevent things like this slamming them to a halt?

I'm curious.


Pray!

:p

Does Intel HAVE a 90nm chip - guess I missed that rumor! Sigh now only my wife will know I'm perfect - cause you now certainly know my flaw - missed an intel rumor

[Kelson]

Umm....about the emulation over a RISC core, so does Intel....

Also, I don't think there is sufficient financial motivation for alot of companies to go start building PPC chips, even if it is just putting an emulation layer over their current core.

- Kelson


Actually, this isn't as crazy as it seems.

IIRC, AMD's K7 (Athlon) and K8 (Athrlon-64) architectures are actually a proprietary RISC architecture with an x86 emulation layer over the top. It may well be possible for them to make these with a PPC emulation layer instead.

I have no idea, however, how well these would compete against a real PPC. I would be really surprised if they can match a G5, but they might be able to match a G4's performance.

Of course, designing any such a CPU would be expensive and time-consuming, and it would be hard to make the business case for AMD to even consider such a project.

I believe TransMeta's Crusoe chip is similar - and its CPU emulation is loaded as software, so you don't need to spin new hardware. But it has never been known for high performance. Crusoe's big claim to fame is low power consumption. But it's another possibility, at least for low-end laptops.

[szark]

Never mentioned Intel.... :rolleyes: ( <---- ha :p )

So, you mean they should switch to AMD64 (x86-64) then... :p

Of course, AMD is relying on IBM's Fishkill engineers to help them develop their 65nm process, so we'd just end up back in the same place! :)

[Mord]

That is accurate, however they currently have only been able to produce 3 chips running at 1ghz... apple is in the process of welding these 3 together to make a prototype 3ghz G5 for WWDC.

Wha?

you make no sense you cannot weld cpu's together to acheive higher clockrates otherwise the g5 would be advertised at 4GHz not dual 2GHz somehow i get the fealing you are making this up

[mdriftmeyer]

This is the same sort of s*** storm Motorola started rolling out when it talked out its ass about meeting commitments with technologies it had yet to perfect to satisfactory levels.

The main reason AMD is making headway on Intel is it doesn't claim delivery before it can support such claims.

This is also the reason historically Apple always gets s*** press from Wall Street-another product line that looks great but scarcely available.

IBM has zero excuses worth justifying this delay.

[stoid]

IBM has zero excuses worth justifying this delay.

Other than the laws of physics. The reports I've read state that the heat the chips produce is melting the CPU before the heat energy even escapes the molecular level. Not an easy problem to counteract if you ask me.

[rosalindavenue]

Somebody who knows more about this should answer-- is there something about the PPC architecture that makes it inherently more difficult to fabricate than the x86? I mean if IBM can't do it (disregarding motorola), who can? This is really disapointing...

[Frohickey]

Somebody who knows more about this should answer-- is there something about the PPC architecture that makes it inherently more difficult to fabricate than the x86? I mean if IBM can't do it (disregarding motorola), who can? This is really disapointing...

No. There is nothing inherent about the PPC architecture that makes it more difficult to fabricate than the x86. But, here is the big caveat.

With IBM or Motorola, there is the PPC architecture, and the specific chips themselves. The market for these chips is not as large as the x86 market, and so, there is limited resources with which to design and produce the chips.

With the x86 market, Intel can afford to put multiple engineering teams to the design and manufacture of the parts, and can afford to have a few of the engineering teams fail. The sheer number of resources they can put is quite large. You just have to look at the fact that there are at least two different products, a desktop x86, and a laptop x86. There is no such bifurcation of design in the PPC architecture, at least for the leading edge processors for personal computers. (Server Power4 and Power5 chips are a totally different beast altogether.)

[dho]

Actually, this isn't as crazy as it seems.

IIRC, AMD's K7 (Athlon) and K8 (Athrlon-64) architectures are actually a proprietary RISC architecture with an x86 emulation layer over the top. It may well be possible for them to make these with a PPC emulation layer instead.

I have no idea, however, how well these would compete against a real PPC. I would be really surprised if they can match a G5, but they might be able to match a G4's performance.

Of course, designing any such a CPU would be expensive and time-consuming, and it would be hard to make the business case for AMD to even consider such a project.

I believe TransMeta's Crusoe chip is similar - and its CPU emulation is loaded as software, so you don't need to spin new hardware. But it has never been known for high performance. Crusoe's big claim to fame is low power consumption. But it's another possibility, at least for low-end laptops.


Im afraid it MAY not be that simple. Not only do PowerPC's have different general archetectures, they have opposite endians. PowerPC is big endian and X86 is little endian. When I say i X86 i include those AMD chips with the emulation layer. In order for them to properly emulate they would need to have the same endian.

From my understanding the best you could do with one of those amd chips would be to make an ALMOST pcc with a different endian. We would end up in the same place with annother VirtualPC type app.

If I am mistaken please ocorrect me, this is just how I have come to understand the differences in chip types.

[ingenious]

Wha?

you make no sense you cannot weld cpu's together to acheive higher clockrates otherwise the g5 would be advertised at 4GHz not dual 2GHz somehow i get the fealing you are making this up

duh he was kidding :P

[stoid]

Im afraid it MAY not be that simple. Not only do PowerPC's have different general archetectures, they have opposite endians. PowerPC is big endian and X86 is little endian. When I say i X86 i include those AMD chips with the emulation layer. In order for them to properly emulate they would need to have the same endian.

From my understanding the best you could do with one of those amd chips would be to make an ALMOST pcc with a different endian. We would end up in the same place with annother VirtualPC type app.

If I am mistaken please ocorrect me, this is just how I have come to understand the differences in chip types.

Can you explain the little/big endian difference in laymen's terms?

[JFreak]

The market for these (PPC) chips is not as large as the x86 market, and so, there is limited resources with which to design and produce the chips. With the x86 market, Intel can afford to put multiple engineering teams to the design and manufacture of the parts, and can afford to have a few of the engineering teams fail.

this is not so simple.

intel has to have many teams to KEEP their market share, whereas ibm has to have many teams to GAIN the market share they have set as their target for long term. ibm would not have even begun the G5 fabbing if they would have been happy with 3% market share in the beginning, so it is very clear that they have started a beginning of a revolution here. they try to make itself the king of the jungle again, that's for sure, and for that reason they must have AT LEAST as strong r&d department as the competition has.

ibm has the powerX series which i believe dissipates even more heat than intel's chips, so it's not a matter of power consumption. ibm just tends to tolerate errors worse than intel, so what i'm saying is that the two are not even comparable in yield percentages - intel has a BIG error tolerance and sells most of the chips in the wafer, but ibm wants to do things right. it has a strong reputation (regarding manufacturing quality) which it cannot afford to lose. for ibm it's better to sell one chip out of the wafer keeping its fame, rather than selling ten and losing it. ibm makes money in the long term.

go ibm! please make intel cry.

[ddtlm]

Modern x86 chips have purpose-built RISC cores, not general purpose ones. They are designed from the ground up to hide behind x86 and would not likely apapt well to hiding behind PPC.

stoid:

Endianness is sorta like reading left-to-right or right-to-left.

[ddtlm]

JFreak:

ibm would not have even begun the G5 fabbing if they would have been happy with 3% market share in the beginning, so it is very clear that they have started a beginning of a revolution here
I'm not gona get into a lengthy arguement about what amounts to religion, but just so someone stands up to it, I have to that this idea of yours is just a fantasy. All the 970 is doing is spreading out IBM's R&D cost so that they can keep making ever-more-advanced Power series chips to compete with Intel's money-sponge Itanium. IBM is never going to get a large market share, and they are not putting a whole heck of a lot of R&D into desktop chips. Desktop chips are just "free" money for them.

ibm just tends to tolerate errors worse than intel, so what i'm saying is that the two are not even comparable in yield percentages - intel has a BIG error tolerance and sells most of the chips in the wafer, but ibm wants to do things right
Intel is not churning out chips with errors in them, if they were then the computers based on them wouldn't be stable. I'm sure you've heard of Linux and BSD running on x86, thats some dang stable stuff.

[JFreak]

Intel is not churning out chips with errors in them, if they were then the computers based on them wouldn't be stable. I'm sure you've heard of Linux and BSD running on x86, thats some dang stable stuff.

sure they do, not one cpu is 100% error free - not even the big iron server hardware. it's all about specification, you know, and intel seems to drive its threshold lower than the others - hell, you can overclock amd some 30% to have it still stable (keeping the error occurency rate low enough), but try to overclock intels, they just are sold already on the limit.

and ibm is famous for having higher thresholds than other manufacturers.

[nmk]

I'm not gona get into a lengthy arguement about what amounts to religion, but just so someone stands up to it, I have to that this idea of yours is just a fantasy. All the 970 is doing is spreading out IBM's R&D cost so that they can keep making ever-more-advanced Power series chips to compete with Intel's money-sponge Itanium. IBM is never going to get a large market share, and they are not putting a whole heck of a lot of R&D into desktop chips. Desktop chips are just "free" money for them.

I believe that IBM will be supplying Microsoft, Sony, and Nintendo chips for their next gen game consoles. At least in the case of MS, they managed to drive Intel out of contention. This is a pretty big market. So no, I don't think that IBM is looking at desktop processors primarily as extra money. Their marketing for the PPC 970 (and its future iterations) would indicate that it's a market they're going after quite seriously. Or do you believe that the entire game cosole market is irrelevant.

[Bigheadache]

I believe that IBM will be supplying Microsoft, Sony, and Nintendo chips for their next gen game consoles. At least in the case of MS, they managed to drive Intel out of contention. This is a pretty big market. So no, I don't think that IBM is looking at desktop processors primarily as extra money. Their marketing for the PPC 970 (and its future iterations) would indicate that it's a market they're going after quite seriously. Or do you believe that the entire game cosole market is irrelevant.

Have you seen how much consoles cost?? The console market is extremely price sensitive for componentry. There wouldn't be much margin, compared to selling in the big iron part of the market. At the end of the day, getting into consoles and selling G5s is about amortising the cost of developing the POWER series which is the main game for IBM.

[sun-ice]

Wha?

you make no sense you cannot weld cpu's together to acheive higher clockrates otherwise the g5 would be advertised at 4GHz not dual 2GHz somehow i get the fealing you are making this up


what is the base of dualcore ?
I think i was to "put 2 CPU" with a common front bus ... :confused:

And rumors about the XBox II deal with triple core PPC CPU at 3.5GHz (so 3 cpu at 1.166GHz) ? :confused:

I don't know is someone knows ? :)

[nmk]

Have you seen how much consoles cost?? The console market is extremely price sensitive for componentry. There wouldn't be much margin, compared to selling in the big iron part of the market. At the end of the day, getting into consoles and selling G5s is about amortising the cost of developing the POWER series which is the main game for IBM.

Granted, the console market is very cost sensitive. I hope you realize that consoles are sold at a loss by the major manufacturers. They make their money of game licenses. Therefore they are certainly paying IBM more than a fraction of the $250 that they will sell the console on the market for. Also, IBMs penetration into this market required a fair bit of marketing. It just goes to show that they are serious about finding customers for the product.

Since neither you nor I are involved in the strategic planning at IBM, I don't think it is wize to make assuptions about their developemnt of the G5. Their actions would indicate that it is a product they are taking seriously.

[johnnowak]

Wha?

you make no sense you cannot weld cpu's together to acheive higher clockrates otherwise the g5 would be advertised at 4GHz not dual 2GHz somehow i get the fealing you are making this up

I get the *fealing he was joking.

[rosalindavenue]

Have you seen how much consoles cost?? The console market is extremely price sensitive for componentry. There wouldn't be much margin, compared to selling in the big iron part of the market. At the end of the day, getting into consoles and selling G5s is about amortising the cost of developing the POWER series which is the main game for IBM.

I would have to believe that the manufacturers (Sony MS Nintendo) are the ones who take the hits on the components, not the component manufacturers themselves. IBM, as the processor manufacturer, is not going to make money from the software/games ; other than large volume, they have no incentives to decrease their margins. If they weren't making money selling processors to the console manufacturers, they wouldn't bother making them. The losses (if any) won't be taken by the component manufacturers.

[Bigheadache]

I would have to believe that the manufacturers (Sony MS Nintendo) are the ones who take the hits on the components, not the component manufacturers themselves. IBM, as the processor manufacturer, is not going to make money from the software/games ; other than large volume, they have no incentives to decrease their margins. If they weren't making money selling processors to the console manufacturers, they wouldn't bother making them. The losses (if any) won't be taken by the component manufacturers.

The console makers do take a hit, but that doesn't mean they don't squeeze their suppliers that extra bit. Refer Microsoft vs Nvidia 2002-2003 Xbox contract dispute.

[Chryx]

sure they do, not one cpu is 100% error free - not even the big iron server hardware. it's all about specification, you know, and intel seems to drive its threshold lower than the others - hell, you can overclock amd some 30% to have it still stable (keeping the error occurency rate low enough), but try to overclock intels, they just are sold already on the limit.

Where the hell are you getting that ?

Intel chips overclock very well. (the current Prescott P4 aside, and that's got design issues)

Historically, at least over the last two years or so, Intel chips have overclocked a LOT better than AMDs....

I'm no fan of the architectural direction Intel have taken of late, but what you're saying directly contradicts the reality of the situation :)

[Telomar]

the cost of developing the POWER series which is the main game for IBM.The main game for IBM are service contracts. That's why they are pretty platform independent. Doesn't mean they aren't interested in succeeding in other areas and having PPC grow though.

[gop007]

The issues regarding yields is what is of concern to Apple. Sure they can make all the 1.8 and 2.0 chips, but right now the PowerMacs are not selling that well. Apple is will proabably place many of those chips into the iMacs, but they need much faster chips for the PoweMacs. If history is a guide, the next upgrade will see 1.8 and 2.0 chips into consumer models, and a very limited supply of 3.0 chips or lower for the PoweMacs. Sure they will announce the 3.0 sometime this summer, but once again they will fail to ship them in adequate supplies until early fall.

[ssamani]

Can you explain the little/big endian difference in laymen's terms?

There was a brief explanation as reading left to right or vice versa.

Specifically, under ASCII, characters are stored as an 8 bit number. Therefore in a 32 bit system you can store 4 ASCII characters in each memory value (2 in 16 and 8 in 64). I can't remember which way is which but one out of Intel / Motorola with the x86 and the 68xxx chose to store "Nice" as "Nice" and the other as "eciN". The reason for choosing the latter method is that it makes some string handling easier for a CPU. Emulators have to handle this difference when running on different architectures.

The reference for why this is called big endian and little endian is from Swift's Gulliver's Travels. The Lilliputions went to war over which end of a boiled egg should be cracked first - big end or little end. The choice for byte storage for 16+ bit CPU's, like many things in the technical world, generated a fierce argument thought not quite as bad as the Mac vs PC wars of the late 20th and early 21st centuries.

[trippen_raven]

I've heard before, actually it was a interview I read sometime ago last year that Intel has tried pretty hard to crack into Apple boxes. So it's really up to Apple where they want to go. If powermac shipments really drop, heaven forbid, but if they do, because of the lack of performance chips like the G5. They have alternitive options and it seems Intel is one of them. I've even heard that Intel CEO and Jobs are good friends.

I just hate seeing good software and OS X being wasted, because the lack of powerful processors. IBM has a lot on the line here, thier customers, reputation, and lastly investment(notice $ is last,,,,,,,,,customers should come first------------hear that ADOBE). So I'm confident big blue will pull through and rise to the occasion as they are doing so well. :)

[gekko513]

Specifically, under ASCII, characters are stored as an 8 bit number. Therefore in a 32 bit system you can store 4 ASCII characters in each memory value (2 in 16 and 8 in 64). I can't remember which way is which but one out of Intel / Motorola with the x86 and the 68xxx chose to store "Nice" as "Nice" and the other as "eciN". The reason for choosing the latter method is that it makes some string handling easier for a CPU. Emulators have to handle this difference when running on different architectures.
Well this is a nice explanation but not really accurate. When computer systems went beyond 8 bit, they all still kept backwards compatibility to 8 bit computation and storage. Memory is therefore still adressed with a number that points to 8 bits.

"Nice" is always stored as
Address - Value
0x0000 - N
0x0001 - i
0x0002 - c
0x0003 - e
But actually the direction of storage of strings are decided by the software and not by the processor.

The difference between little and big endian is the way 16, 32 or more bit values are stored. A 32 bit value is stored as four 8 bit values. In big-endian system, the numbers are stored with the most significant 8 bits at the lowest adress. Little-endian is the other way around. So the number 520 (256x2 + 8) is stored like this
Address - Big-endian - Little-endian
0x0000 - 0 - 8
0x0001 - 0 - 2
0x0002 - 2 - 0
0x0003 - 8 - 0

Intel processors are little-endian. And this (http://www.webopedia.com/TERM/b/big_endian.html) article claims that the PowerPC system is bi-endian and can understand both.

[shamino]

The main reason AMD is making headway on Intel is it doesn't claim delivery before it can support such claims.
So, to you, it doesn't matter that their chips have equal power at half the price?

[shamino]

Im afraid it MAY not be that simple. Not only do PowerPC's have different general archetectures, they have opposite endians. PowerPC is big endian and X86 is little endian. When I say i X86 i include those AMD chips with the emulation layer. In order for them to properly emulate they would need to have the same endian.
This is actually one of the easiest problems to get around. You just tweak your load/store instructions to swap byte-orders when moving data between registers and memory, and leave just about everything else alone.

The byte-order (and bit-order, for that matter) inside the CPU doesn't have to have any relationship to the representation in main memory.

Also note that the PPC architecture (and most PPC chips) can work either way. The 970 (G5) is a notable exception (the lack of this feature is probably the reason that Virtual PC 6 isn't compatible with it.)

A much more difficult problem is emulating features that don't have analogues on the other architecture. Not knowing much about PPC or modern x87 assembly language, I can't name any specific features, but I would guess that the biggies would be the vector-math units (AltiVec on PPC, SSE on x86).

Also, the instruction pre-fetch/branch-predict/pipeline model would have to be emulated exactly. While making it different wouldn't break applications, it would hurt performance - code optimized for one model would not be optimized for the other.

[shamino]

Can you explain the little/big endian difference in laymen's terms?
Real simple. Memory is (normally) addressed in terms of bytes (8-bit integers, capable of representing numbers between 0 and 255.)

Most data, however, is too big for this. Integers in applications are most commonly 16 and 32 bits wide (2 and 4 bytes), with 64-bit (8-byte) becoming more common. Floating point numbers are typically 4- and 8-bytes wide.

When stored in memory, these numbers are typically stored in a contiguous range of bytes. But they can be stored in different orders. The most common two orders are big- and little-endian.

Big-endian is when you store the most-significant byte (the one storigng the highest-place digits) in the lowest memory address, with the least-significant byte (the one storing the lowest-place digits) in the highest memory address, and any other bytes ordered in descending order of significance.

Little-endian is when you store the least-significant byte in the lowest memory address, with the most-significant byte in the highest memory address, and any other bytes ordered in ascending order of significance.

There have been other schemes used in the past, but these two are the only ones you're likely to find in use, unless you have a collection of classic mainframes to play with.

Intel chips generally use a little-endian scheme. Other chips (from Motorola, IBM, SUN, etc.) typically use big-endian. Which is better is a matter of religious argument these days. The big deal is that data meant for one has the be converted (by swapping the byte-order of all multi-byte numbers) before it can be used on a processor that uses the other.

Normally, this is only an issue when reading data files from a disc or packets from a network. If you're emulating a processor with the opposite order, this is obviously something that the emulator must deal with as well.

[Dippo]

Historically, at least over the last two years or so, Intel chips have overclocked a LOT better than AMDs....

Before anyone actually thinks that what you say is true, you might want to provide something that supports your "theory".

AMDs overclock vastly better than Intels due to the ability to change both FSB and multiplier. My processor currently overclocks about 35%.

Anyways, what does that have to do with IBM's yield problems??

I think that IBM is just having the same problems that all of the chip makers are having. Getting the 90nm process just right is proving to be quite difficult. I hate to see the problems they are going to have with 65nm!

[shamino]

... ibm would not have even begun the G5 fabbing if they would have been happy with 3% market share in the beginning, ...
I assume you're aware of the fact that IBM chips are used in more than just Macintoshes.

PPC chips (and the POWER series they are based on) are used in a wide variety of IBM equipment, from mainframes, to server clusters, to workstations. Theyre also used in embedded devices (like routers and line-cards for telco equipment) from a wide variety of vendors. And then, of course, IBM makes more chips than just the PPC/POWER series of processors.

Intel's chips are also used in a wide variety of products besides PCs. And they also make other kinds of chips (remember the i860/960? How about the ARM/StrongARM?)

You can't take Mac-vs-PC market share numbers and jump to the conclusion that those numbers are the same as PPC-vs-x86 processor market share numbers.

[zelman]

I need to remind everyone, that even though making processor chips out of silicon is NOT rocket science, it is still a pretty difficult process to do. ;)

wasn't the space program around prior to silicon-based processors?

[HiRez]

"200mm" and "300mm" refer to the diameter of the wafer that the chips are produced on. "130 nm" and "90 nm" refer to the process size.Except that the article says "nm". Confused me too.

[mdriftmeyer]

Whose chips specifically and how does AMD being able to meet their claims compare to IBM being unable to meet their claims?

We're not discussing chip performance on platforms. We're discussing a political issue to market technology that either they projected would be ready and now is biting them in the ass by not being ready, or IBM's own manufacturing branch projected too soon they could ramp up to meet the roadmap both Apple and IBM committed to publically.

Leaving conspiracy theories to the paranoid the option that IBM is now playing favorites I'll not even touch.

IBM is large enough and old enough that to make such claims to companies including Apple is just plain unwise.

So, to you, it doesn't matter that their chips have equal power at half the price?

[Henriok]

I assume you're aware of the fact that IBM chips are used in more than just Macintoshes.The PowerPC-processor that by far have sold the most through the years must be the Gekko which powers the Nintendo GameCube. In the same time span, Nintendo have sold more GameCubres than Apple have made Macintoshes, and the GC uses only one type of PPC and Apple have used several models from different manufacturers.

In the future IBM will be making Cell processors for Sony, Xbox 2-processors for Micrsoft and GameCube 2 -processors for Nintento. Apple will be quite a small contractor when compared to all of the others. And, one can hope that IBM themselves stop procrastinating and starts a serious PPC/Linux assault on the Wintel market.

[cb911]

okay, that really had me confused. i thought, what the heck do i want to know about 200-300nm problems for? i thought that IBM was working on 90nm?

well, the article does say 200-300mm, but here at Mac Rumors it's reported as 200-300nm, that's quite a big descrepency in size. ;)

well, i don't really want to hear about the problems, i just want results!! :D

[oingoboingo]

Actually, this isn't as crazy as it seems.

IIRC, AMD's K7 (Athlon) and K8 (Athrlon-64) architectures are actually a proprietary RISC architecture with an x86 emulation layer over the top. It may well be possible for them to make these with a PPC emulation layer instead.


It would probably be easier just to re-compile the software to run on the existing x86 ISA, rather than try and design a whole new chip with a PPC emulation layer on top of the Athlon core. Remember NEXTSTEP was running on x86, and only ported to PPC after Apple acquired NeXT. The first releases of Rhapsody also ran on both x86 and PPC.

I'm not saying Apple is going to do that, but I just think a software port would be easier than a hardware/CPU redesign...remember Linux runs on just about every major hardware architecture ever developed (x86, PPC, SPARC, Alpha, MIPS, PA-RISC, m68k and S/390 to name a few), Sun maintains concurrent versions of Solaris on SPARC and x86, IBM has AIX for POWER and IA64, and even Microsoft used to sell and support Windows NT 4 on x86, Alpha, MIPS and PPC, and until recently, Microsoft's Windows CE/Pocket PC OS ran on CPUs from both ARM and Hitachi.

If you take a look around the industry, single-platform operating systems are actually the exception, rather than the rule.

[JFreak]

I'm not saying Apple is going to do that, but I just think a software port would be easier than a hardware/CPU redesign.

easier for who?

apple is know in making things easy for the end user, and because of that, apple will not - unless forced to - release osx for some other cpu platform [than the ppc] because that would either force all mac software developers release different versions of the software or another possibility is that other cpu osx systems simply become second class mac citizens [due to lack of software support from many companies].

THAT, my friend, is the reason for the possibility of hardware ppc emulation. it is easier for the end user.

[oingoboingo]

easier for who?

apple is know in making things easy for the end user, and because of that, apple will not - unless forced to - release osx for some other cpu platform [than the ppc] because that would either force all mac software developers release different versions of the software or another possibility is that other cpu osx systems simply become second class mac citizens [due to lack of software support from many companies].

THAT, my friend, is the reason for the possibility of hardware ppc emulation. it is easier for the end user.

Again, let me start by saying that I don't think Apple will move OS X to x86. But hypothetically, weren't NEXTSTEP and Rhapsody capable of working with 'fat binaries', in the same way that earlier versions of Classic Mac OS supported fat binaries, with both Motorola 68000 and PowerPC code in the same package? There wouldn't need to be separate distributions for different architectures...just one CD or DVD which contains executables compatible with both. As for developers, if Apple was going a hybrid PPC/x86 route, they'd probably make cross-platform libraries available to developers, and producing an x86 version of existing PPC code would be down to a recompile.

So I still think it would be easier for Apple (and ultimately the end users, who would be oblivious to which binary type they were running) to go down a software route, rather than trying to develop a proprietary, one-off hardware implementation of a hybrid PPC/x86 chip. As for developers, well, they can go **** themselves. Witness the Classic/Copland/Rhapsody/NEXTSTEP debacle.

I promised myself I wasn't going to post in the news/rumours related forums any more, because these hypothetical arguments about the pros and cons of a hypothetical G5 iMac/G5 PowerBook/G5 iPod/Mac OS X on x86/Mac OS X on pocket calculator are all such a pointless waste of time. I'll see if I can restrain myself next time :) Enjoy the show.

[dontmatter]

Other than the laws of physics. The reports I've read state that the heat the chips produce is melting the CPU before the heat energy even escapes the molecular level. Not an easy problem to counteract if you ask me.

OK....then how do AMD and intel do it?

[Telomar]

OK....then how do AMD and intel do it?Neither of them have. Intel has completely changed their roadmap to get around the difficulties and AMD shifted their introduction of 90 nm parts by 12 months. Nobody has brought the 90 nm processes online without serious difficulties.

[dieselg4]

Just a prototype, or will it be an actual product by WWDC? (Will you be able to buy it)
;)
I think he was being facetious

[dernhelm]

Im afraid it MAY not be that simple. Not only do PowerPC's have different general archetectures, they have opposite endians.

From my understanding the best you could do with one of those amd chips would be to make an ALMOST pcc with a different endian. We would end up in the same place with annother VirtualPC type app.

If I am mistaken please ocorrect me, this is just how I have come to understand the differences in chip types.

MIPS architectures (since the R2000) can switch endianness at boot time. It really isn't that difficult of a problem to deal with. But endianness is only one small hurdle when talking about one processor emulating other architectures, I'm guessing it would be cheaper and easier to build a single box with two different CPUs in it - one from IBM and one from AMD/Intel. Seems like Apple did this a while ago...