PowerPC 970 at 90nm and the Power5

[MacRumors]

A Japanese news blurb (http://pcweb.mycom.co.jp/news/2003/11/12/10.html) reports that IBM will be presenting two papers at the 2004 ISSCC (http://www.isscc.org/isscc/):

"Design and Implementation of the POWER5 Microprocessor"
"PowerPC 970 in 130nm and 90nm Technologies"

Current shipping PowerPC 970s utilize a 130nm process, though it was reported in September (http://www.macrumors.com/pages/2003/09/20030929111948.shtml) that IBM was already sampling 90nm chips. A 90nm chip would theoretically bring higher clockspeeds and lower heat production as compared to the corresponding 130nm chip.

Meanwhile, Microprocessor Watch (http://www.mdronline.com/) is providing subscribers with more details about the Power5 from IBM's presentation at the Microprocessor Forum. MacWorld.co.uk (http://www.macworld.co.uk/news/top_news_item.cfm?NewsID=7268) notes that the Power5 will ship in 2004, with a Power5+ in 2005 and the Power6 in 2006. Notes from the same presentation were previously detailed in this report (http://www.macrumors.com/pages/2003/10/20031014182826.shtml).

Meanwhile, a new AppleInsider report claims that 90nm chips will bring Apple above 2.0GHz while the PowerPC 980 (Power5 based) chip will bring Apple to 3GHz. If true this could confirm a previous report which claimed the same... that the 970 would top out at 2.6-2.8GHz, while the 980 would bring Apple to the 3GHz mark.

And a Page 2 report hints at specifically designed low-power mobile PowerPCs.

[sethypoo]

90NM.....cooler running.....I hate to bring this up but could we be seeing a G5 PowerBook a little sooner? I think so.....

:) :rolleyes: :D

[arn]

Originally posted by sethypoo
90NM.....cooler running.....I hate to bring this up but could we be seeing a G5 PowerBook a little sooner? I think so.....


Um, I'm sure Jobs et all were aware of this logical step when he said it was going to take some time.

In other words, this is a natural progression... not a surprise advancement.

arn

[mactastic]

This should mean we are still on track for 3Ghz G5s by Q3 of 2004 right? And hopefully 2.4 - 2.6 Ghz updates in January?

And is the 90 nm process going to be the one that makes it into the PB? If so then hopefully we will see those before we see the 3Ghz PowerMacs.

[dieselg4]

OK, now to incite seom speculation . . . andy tech types care to guess how much heat a 90 nm G5 would produce, maybe at 1.6 GHz? And how might that realate to the heat a 1.33 GHz G4 produces? Granted I haven't see one up close for very long, but the heat sink for the G5 looksa like it almost ans tall as the case is wide. . .

[Rincewind42]

Originally posted by dieselg4
Granted I haven't see one up close for very long, but the heat sink for the G5 looksa like it almost ans tall as the case is wide. . .

It is nearly as tall as the case is wide. But that's just so that there is a large area for air to flow over, which means that the heat can dissipate faster, the fans can run slower, etc. Don't be fooled by the size of the heat sinks - the G5 doesn't put off that much heat :)

[dongmin]

Originally posted by mactastic
This should mean we are still on track for 3Ghz G5s by Q3 of 2004 right? And hopefully 2.4 - 2.6 Ghz updates in January?

And is the 90 nm process going to be the one that makes it into the PB? If so then hopefully we will see those before we see the 3Ghz PowerMacs. I take this to mean that Apple will have shipping 90nm products by then. My guess is for revised Power Macs, with an outside chance for iMacs. And yes, we should be on track for a 3 ghz G5 in Q3 2004. It might come even sooner than that. Supposedly, they had 3.2 ghz chips sampling way back last September.

Quoting an earlier rumor (http://www.macrumors.com/pages/2003/09/20030929111636.shtml) the 90nm G5 dissipates 34 W at 2.0 ghz. So a 1.6 ghz G5 should come in around 27 W, probably too high for a PowerBook but doable for a revised iMac. I'm sure the redesign of the iMac is specifically to accomodate the hotter running G5s.

[iGav]

woah, this feels kind of weird, after years of Moto, knowing that we've got regular substantial performance increases in the pipelines for the next few years atleast and probably way beyond...

feels good.... feels very good!! ;)

[AmigoMac]

Someway, it means PB's coming, but how soon? I have a PB 12" and think a lot about selling it and get a 15", but would be a deal with this news? or will it take more than 1 year before the nice G5 gets into the PB? ohh no, it's pretty confusing ...:( :)

[dieselg4]

Originally posted by AmigoMac
Someway, it means PB's coming, but how soon? I have a PB 12" and think a lot about selling it and get a 15", but would be a deal with this news? or will it take more than 1 year before the nice G5 gets into the PB? ohh no, it's pretty confusing ...:( :)
Unless you really want a bigger screen, I'd keep the 12" for awhile. If you jsut got it, you take a loss on eBay to sell it. The 12" is a fine machine (I bought one myself) and its highly portable. Why spend another grand or so for a computer that isn't a whoel lot faster (unless you'd really like a bigger screen)

[agreenster]

Its GREAT to see serious progress happening in the Apple world.

For TOO long it was Motorola running the show (or should I say 'ruining' the show) and slowing down the release of new Apple hardware. Now that IBM is in the picture, it seems like they (Apple + IBM) will be keeping up with Intel when it comes to chip upgrading roadmaps and times.

Can I get an amen?

:D

[Samir 3.0]

I hope that theese cooler processors could allow Apple to put less fan inside the case to free some space for another HD.

I'm thinking about a SATA RAID with new WD Raptor.

[hayesk]

Originally posted by dieselg4
OK, now to incite seom speculation . . . andy tech types care to guess how much heat a 90 nm G5 would produce, maybe at 1.6 GHz? And how might that realate to the heat a 1.33 GHz G4 produces? Granted I haven't see one up close for very long, but the heat sink for the G5 looksa like it almost ans tall as the case is wide. . .

The G5 by itself is irrelevant. You also have to consider the support chips that go along with it. There may be an issue with the power consumption and heat dissipation of those too.

[mrsebastian]

i can't wait for g5 17"pb!! though i think it will probably be later than sooner, it's just a matter of time.

[dho]

Originally posted by hayesk
The G5 by itself is irrelevant. You also have to consider the support chips that go along with it. There may be an issue with the power consumption and heat dissipation of those too.
I would hardly say it is irrelevant. Yes, other chips and systems play a role in heat disipation, but not nearly as much as the procesor itself.

Also dieselg4 was refering to chips running at lower speeds then currently used. From what I understand, the high performance and heat generating chips scale down with the procesor anyway.

[dho]

Originally posted by dongmin
I take this to mean that Apple will have shipping 90nm products by then. My guess is for revised Power Macs, with an outside chance for iMacs. And yes, we should be on track for a 3 ghz G5 in Q3 2004. It might come even sooner than that. Supposedly, they had 3.2 ghz chips sampling way back last September.

Quoting an earlier rumor (http://www.macrumors.com/pages/2003/09/20030929111636.shtml) the 90nm G5 dissipates 34 W at 2.0 ghz. So a 1.6 ghz G5 should come in around 27 W, probably too high for a PowerBook but doable for a revised iMac. I'm sure the redesign of the iMac is specifically to accomodate the hotter running G5s.

I dont believe the relationship between clockspeed and disipation is linear.

The 1.6 should have a much lower disipation. :)

[Remus]

AMEN

[sethypoo]

Wow, 3Ghz by Q3 of 2004? Geez, Apple + IBM=Speedy Gonzales.

It's so nice to see Apple having a good partnership with a company that cares about its image. :)

[sethypoo]

Originally posted by arn
Um, I'm sure Jobs et all were aware of this logical step when he said it was going to take some time.

In other words, this is a natural progression... not a surprise advancement.

arn

Just thinking out loud.

Geez. (my new word.).:D

[Rocketman]

Originally posted by agreenster
Its GREAT to see serious progress happening in the Apple world.

For TOO long it was Motorola running the show (or should I say 'ruining' the show) and slowing down the release of new Apple hardware. Now that IBM is in the picture, it seems like they (Apple + IBM) will be keeping up with Intel when it comes to chip upgrading roadmaps and times.

Can I get an amen?

:D

Send IBM a thank you card! I bet that has never happpened to them before from OEM's customers!

Rocketman

http://www.v-serv.com/-upload/avatar2.jpg

[ksz]

sethypoo:
Wow, 3Ghz by Q3 of 2004? Geez, Apple + IBM=Speedy Gonzales.
If the following is true, the 3GHz PowerMac will be based on the PPC 980 which is much more than a speed-bumped increment.

http://www.macrumors.com/pages/2003/07/20030706031041.shtml

Excerpt:

"Improvements in the PPC 980 include Hyperthreading, eLiza error correction, and more massive parallelism. IBM's implementation of hyperthreading provides a 30% gain over Intel's. eLiza technology will reduce the bottlenecks when the branch prediction unit fails. Altivec will split into 3 pipelines (vs 2 in the 970), 4 Integer and 4 Floating point units. 980 will have to be built on a 90nm processor due to heat dissipation requirements.

Steve's comment of 3GHz in 1 year will not be accomplished with the G5 (970) - which will top out at 2.6-2.8GHz. The PPC 980 will start at speeds of 2.6-3GHz and top out around 4.5-5GHz. The G5 will make its way into PowerBook lines in Jan/Feb, Xserve's later this year, and iMacs in approximately one year."

According to AppleInsider, current 980 samples are showing "huge performance gains over the G5":

http://www.appleinsider.com/news/

[BenRoethig]

I think this article also implies the 980 will keep the G5 name. I'm not surprised though. If true, I'm very happy with the direction IBM is taking the PPC.

[macMaestro]

Steve said that the G5 would reach 3 Ghz by next June. If the PPC 970 cannot reach 3 Ghz, I take it to mean that whatever chip does reach 3 Ghz would still be called a G5. If that rumor that ksz submitted is true, then I would assume that we would keep the name G5 through the 990. We might get the G6 name for the 9900. Then again, Apple's marketing might want to do the opposite and go through a new G name for each new chip.

Man though, 45nm in four years. That's pretty darn small (and leads to a pretty darn fast chip!)

[gwuMACaddict]

nice to see that IBM and apple are working together and taking this serioiusly. had moto not sucked so bad for so long, i feel like apples market share would have been a lot higher today. it will be interesting to see if there is any shift now that IBM is on board with chips

[ksz]

Originally posted by macMaestro
If the PPC 970 cannot reach 3 Ghz, I take it to mean that whatever chip does reach 3 Ghz would still be called a G5.
I would tend to agree, however Apple might introduce a suitable marketing buzzword to differentiate the "new G5" from the old G5. For example, when Intel added (or more properly, enabled) Hyper Threading on the P4, they still called it a P4 but displayed the words Hyper Threading prominently on packaging, advertising, press releases, etc. Intel wanted to make it clear that this chip was something special, but not special enough to warrant a new base name.

[billyboy]

Originally posted by gwuMACaddict
nice to see that IBM and apple are working together and taking this serioiusly. had moto not sucked so bad for so long, i feel like apples market share would have been a lot higher today. it will be interesting to see if there is any shift now that IBM is on board with chips

I bet the Apple marketing department are happier to make a huge IBM related bang rather than the more difficult job they have had of making something exciting out of a few loud Moto knocks on the door.

[sethypoo]

What would constitute a G6? A 90 or 45NM chip called the Power PC 990?

[szark]

Originally posted by ksz
I would tend to agree, however Apple might introduce a suitable marketing buzzword to differentiate the "new G5" from the old G5.

And we all know what that would be...

G5 Extreme !!!

:eek:


Seriously, though, this is extremely good news if it's true. I just can't decide whether I'll be buying a 980 tower or a G5 PB next year...

[ddbean]

[QUOTE]Originally posted by szark
And we all know what that would be...

[b]G5 Extreme !!!

:eek:

I like G5X as a name.

[ddbean]

ddbean
macrumors member
Hey I'm a member now. How'd that happen? (And no I didn't read anything when I signed up for these forums)

[Head Wound]

Originally posted by szark
And we all know what that would be...

G5 Extreme !!!



I vote for G5 XP!

[ksz]

Originally posted by szark
And we all know what that would be...

G5 Extreme !!!
Not a bad choice of names. Then again, Intel's latest P4 series with 2MB Level 3 cache (vs standard 512K of Level 2 cache) is called:

Pentium 4 Extreme Edition

http://www.intel.com/products/desktop/processors/pentium4HTXE/index.htm?iid=ipp_desk+proc_p4htxe&

[Tim Flynn]

Originally posted by dho
I dont believe the relationship between clockspeed and disipation is linear.

The 1.6 should have a much lower disipation. :)

The relationship is roughly linear (disregarding leakage).
BUT, at lower speeds you can reduce the voltage, and that's a square law thing, and get your best power reduction.
But the laws of physics tend to get in the way :(

[Tim Flynn]

Originally posted by ksz
Pentium 4 Extreme Edition

I like what most people call it :

Pentium 4 Extremely Expensive :D

[dongmin]

Originally posted by Head Wound
I vote for G5 XP!

980 --> G5x 'extreme'
990 --> G5xp 'extreme plus'

[ITR 81]

All I can say it all looks good over at the Apple camp. I'm going 3GHz when it comes out and G5 PB whenever they come out next yr. I'm sure Apple will be releasing the G4 17 incher with the 1.42GHz processor.

[Photorun]

Yes to whomever posted further upthread, they are correct, the 980 isn't just a step up, it's almost a whole new ballgame of chip that will reap gains quite potentially as large as G4 (7xxx) to G5 (970). There's different on-process chip abilties with different piping. In other words a G5 (970) 2.0 GHz chip would be quite a bit slower computation for computation than a G6 (980) 2.0 GHz. Again, MHz IS in fact partly a myth, it's how the chips and their corresponding architecture handle the info and with IBM's chip advances detailed in white papers, Apple's future is very bright, potentially much MUCH brighter than those stuck with their crummy WIntel boxes.

[fahlman]

Originally posted by macMaestro
Steve said that the G5 would reach 3 Ghz by next June. If the PPC 970 cannot reach 3 Ghz, I take it to mean that whatever chip does reach 3 Ghz would still be called a G5. If that rumor that ksz submitted is true, then I would assume that we would keep the name G5 through the 990. We might get the G6 name for the 9900. Then again, Apple's marketing might want to do the opposite and go through a new G name for each new chip.

Man though, 45nm in four years. That's pretty darn small (and leads to a pretty darn fast chip!)

Steve never said, to the to the best of my knowledge, that the G5 would reach 3GHz withing one year. He promised that Macintoshes would be operating at 3GHz in one year, never stating which processor it would be.

[dongmin]

Originally posted by fahlman
Steve never said, to the to the best of my knowledge, that the G5 would reach 3GHz withing one year. He promised that Macintoshes would be operating at 3GHz in one year, never stating which processor it would be.
what else? the G4? hahahahahahaha



(i know i know you're thinking of a 'G6')

[manitoubalck]

Originally posted by hayesk
The G5 by itself is irrelevant. You also have to consider the support chips that go along with it. There may be an issue with the power consumption and heat dissipation of those too.

Good point, The North Bridge on the Dual G5's has one hell of a job, feedng data to both the procs, 8GBmax memory, the south Bridge, and the AGP. just to name a few, maybe an active cooling solution on that might prove useful.

[manitoubalck]

Originally posted by ksz
Not a bad choice of names. Then again, Intel's latest P4 series with 2MB Level 3 cache (vs standard 512K of Level 2 cache) is called:

Pentium 4 Extreme Edition

It's alos called a Xenon, and a cheap ploy to just and I mean only just keep the edge on the Athlon 64 FX Which is clocked 1GHz lower.

[ksz]

Originally posted by fahlman
Steve never said, to the to the best of my knowledge, that the G5 would reach 3GHz withing one year. He promised that Macintoshes would be operating at 3GHz in one year, never stating which processor it would be.
You may be right. I think Steve made the 3GHz remark for several reasons (caution: this is speculation on my part):

1. The PPC 970 on a 130nm process was not what he really wanted, but he needed something to pit against the Intel juggernaut and establish credibility for Apple's high-end hardware.

2. He would have preferred to introduce the first G5s based on a 90nm process. I don't know how much power the 130nm 2GHz G5 consumes, but the 130nm 2.5 GHz model is thought to consume 96 watts (www.appleinsider.com/news). IBM's 300mm fab at the time was not ready and was in fact having yield problems with 130nm. It takes time to introduce and stabilize a new process technology.

3. The current crop of G5s seem (to me) to be a stop-gap release. Hence, Apple will probably (none of us really know) keep the G5 name as it introduces the 3 GHz models in order to show confidence and longevity in the "G5" strategy. Similarly, Intel has remained at "Pentium 4" for a handful of years and has continued to make incremental improvements to its architecture. Remember when Intel first introduced the P4? Most people thought they were obsoleting the Pentium III too quickly, and large corporations running mission critical software balked at the idea of having to re-qualify their systems with the new processor.

While Apple is not nearly as affected by concerns over software compatibility with next-gen CPUs, my guess is that they will likely keep the G5 name, for a couple of years, to represent their high end.

Again, this is all speculation.

[manitoubalck]

You make a good point ksz, since the PPC970 is a member of the Power4 proc's from IBM and hence their 4th gen of proc's, but is known to the mac community, and the public as the G5 to show a progression.

How long has the K7 Athlon been around still using the Socket A. This has to be one of the longest standing computing standards.

[AidenShaw]

Originally posted by manitoubalck
It's alos called a Xenon

Not really, on two points.

First, I assume that you meant "Xeon" - the name for the workstation and server SMP Pentium 4 chips.

The other error is that the Xeon chips come in a 603 or 604 pin package with a max bus speed of 533 MHz. Pentium 4 desktop chips come in a 478 pin package at up to 800 MHz.

The Pentium 4 Extreme is a variant of the Xeon MP chip internally, but it is definitely a 478 pin desktop Pentium 4 with an 800 MHz bus. It will not plug into a Xeon motherboard, and it is not called a Xeon.

[manitoubalck]

Sorry about the spelling errors.

You might want to check out www.tomshardware.com, www.anandtech.com and some other internet review sites before you say what you said about the P4EE not being a rebadged Xeon.

"Thanks to its ideal configuration and use of the best components, the P4 3.2 in the Extreme Edition (actually a Xeon labeled 'P4')" from the review on tomshardware.
http://www6.tomshardware.com/cpu/20030923/athlon_64-53.html

[weezer160]

We've never experienced leaps like this with Moto!!:D

[madmark]

Skimming:

http://www.isscc.org/isscc/2004/ap/ISSCC2004_AdvanceProgram.pdf

PowerTune sounds like it was MADE for the Powerbook...

3.7 PowerPC 970 in 130nm and 90nm Technologies 4:45 PM

A 64b PowerPC microprocessor is introduced in 130nm and redesigned in
90nm SOI technology. PowerPC 970 implements a SIMD instruction set
with 512kB L2 cache. It runs at 2.0GHz with a 1.0GHz bus in 130nm. The
90nm design features PowerTune for rapid frequency and power scaling
and electronic fuses.

[AidenShaw]

Originally posted by manitoubalck
some other internet review sites before you say what you said about the P4EE not being a rebadged Xeon

It is not a "rebadged" Xeon, it is a "repackaged" Xeon.

A rebadged Xeon would be in a 603/604 pin package, with a sticker that says "Pentium 4" pasted over the "Xeon" label. ;)

The Extreme is in a 478 pin package, with a different bus speed from any Xeon chip or motherboard or Xeon chipset.

So, it may be based on a Xeon, but is not "named" Xeon.

By the way, your Tom's link calls the Extreme a Prestonia, when it is obviously a Gallatin. (see http://www6.tomshardware.com/cpu/20030923/images/cpu_history_big.gif)

[ksz]

Originally posted by manitoubalck
...since the PPC970 is a member of the Power4 proc's from IBM and hence their 4th gen of proc's, but is known to the mac community, and the public as the G5...
That's my feeling as well...the G5 will be synonymous with the Power 5 and the G6 with the Power 6. In this sense, the existing PPC 970 is a stop-gap measure.

[frankzeg]

If they want to make a real splash with these awesome new chips they need to somehow encourage teh development of applications for the Mac that right now live on unix boxes. If these chips are what they say then professional tools like Studiotools, Pro-E, Ideas, Flow3D, Sinda/Fluint, Fluent which are incredibly compute intensive would be a great way to get Macs back in the engineering workplace. Believe me there is NO love lost on these Unix or windows boxes given the headaches with interoperability, support, viruses etc. But right now there is not much choice.

[Telomar]

Originally posted by frankzeg
If they want to make a real splash with these awesome new chips they need to somehow encourage teh development of applications for the Mac that right now live on unix boxes. If these chips are what they say then professional tools like Fluent which are incredibly compute intensive would be a great way to get Macs back in the engineering workplace. I can tell you one of the competitors to Fluent is considering it.

[stingerman]

Originally posted by frankzeg
If they want to make a real splash with these awesome new chips they need to somehow encourage teh development of applications for the Mac that right now live on unix boxes. If these chips are what they say then professional tools like Studiotools, Pro-E, Ideas, Flow3D, Sinda/Fluint, Fluent which are incredibly compute intensive would be a great way to get Macs back in the engineering workplace. Believe me there is NO love lost on these Unix or windows boxes given the headaches with interoperability, support, viruses etc. But right now there is not much choice.

Send them a request on the Apple site. You make some good points.

[stingerman]

IMO, Apple will not hesitate to jump to G6 to make some marketing noise. Going to a PowerMac G6 by Fall of 2004 to incorporate the 980 would be the right thing to do; it would be great for marketing and accurate. IBM is stating that the Power5 is 4X faster than a Power4 though the frequency increases less than 25% and it stays at 130NM process. If we get 2X on a 980 that would be huge and worth the name change.

Such a move would permanently erase the past reputation and reflect Apple's leading position. It would also encourage G4 PowerMac users to upgrade, as now they are two generations behind! Apple's biggest problem has been getting 1st generation G4 owners to upgrade. They made the damn things too well and the upgrades didn't give enough bang for the buck. Now G5's are helping and the G6 will clinch Apple's crown.

[ksz]

Originally posted by BenRoethig
I think this article also implies the 980 will keep the G5 name. I'm not surprised though. If true, I'm very happy with the direction IBM is taking the PPC.
This sums up the sentiment of many posters in this thread. IBM is not only pushing forward with advances in chip design and fabrication, but also paying due attention to compiler technology. Without a compiler that can properly exploit the features of the hardware, a lot of the promised gain is lost.

Optimizing compilers are an important part of the solution and should not be overlooked. If comments in the following thread are true (URL below), then IBM's XL C/C++ compiler, currently in Beta, is delivering 200-300% performance gains on EXISTING processors. Even a 3 GHz POWER-5 will not be 200-300% faster than today's 2 GHz PPC 970! It will take a LOT of extra gigahertz, cache size, front-side bus speed, memory speed, etc. to return those kinds of performance gains.

http://forums.macrumors.com/showthread.php?s=&threadid=47110&perpage=25&pagenumber=4

[Analog Kid]

Originally posted by Tim Flynn
The relationship is roughly linear (disregarding leakage).
BUT, at lower speeds you can reduce the voltage, and that's a square law thing, and get your best power reduction.
But the laws of physics tend to get in the way :(

To give the same answer with more words...

Yes, the relationship to clock frequency is pretty much linear with everything else held constant:

P=(.5*f*C*V^2)+Pq

(sorry, someone asked for a techie answer...)

P=power
f=clock frequency
C=capacitance, both transistor gate capacitance and routing parasitics. More transistors means higher C. Smaller process or better dielectric means lower C for transistors but typically higher C for routing.
V=operating voltage, smaller process typically allows lower voltage operation. Lower clock speeds allow lower voltage operation.
Pq=static power (clock stopped). This is mostly leakage, and goes up appreciably at very small processes. At 90nm, up to half the power can be static power.

So, if you're doing everything you can to cut power you'd reduce both the clock and the voltage for a non-linear power reduction, bearing in mind that voltage can only be reduced slightly.

As an example of the other factors, Apple Insider quotes: "According to preliminary tests, a 2.5GHz Power PC 970 G5 processor based on the 130nm process consumes 96 watts, while 2.5GHz G5 built around the 90nm process pulls a more manageable 62 watts."

Due only to the process shrink (presumably) the power will likely have seen a reduction in C and V, with an increase in Pq giving a net 30% total reduction at the same clock speed.

Trying to answer the original question is complicated by the fact that folks here can't agree on the power of the current G5... :)

[Analog Kid]

Originally posted by ksz
(caution: this is speculation on my part):
1. The PPC 970 on a 130nm process was not what he really wanted, but he needed something to pit against the Intel juggernaut and establish credibility for Apple's high-end hardware.

2. He would have preferred to introduce the first G5s based on a 90nm process. I don't know how much power the 130nm 2GHz G5 consumes, but the 130nm 2.5 GHz model is thought to consume 96 watts

Not sure why anyone would be disappointed with a .13µm process... It's the best anyone has for a processor right now and was smaller than the G4s at that time.

Anyone know when Prescott is due to hit the shelves? Would an early '04 release make the 90nm 970 the first shipping 90nm processor?

[Analog Kid]

Originally posted by stingerman
Send them a request on the Apple site. You make some good points.

Where would we send these requests, exactly? I can never find an appropriate email address...

I'd love to see some of the ASIC development EDA tools move to OS X....

[Gorbag]

Just wondering how any of this news could be considered Negative? For the first time in ages, there seems to be nothing but good news coming from the Apple/IBM axis, certainly

Who does this? Can they not read properly or something?

Yeesh!

[ksz]

Originally posted by Analog Kid
Not sure why anyone would be disappointed with a .13µm process... It's the best anyone has for a processor right now and was smaller than the G4s at that time.
Of course he is not concerned about the process technology itself, but the operating specifications of the chip he is buying. The PPC970 built from a 130nm process consumes a lot of power. This has led to a large case that is itself designed to be an efficient "exhaust" system. Despite the size of the chassis, there is very little room inside for expansion. You are limited to 2 hard drive bays, one optical bay, and 3 PCI/PCI-X slots. Now contemplate a laptop version of the PPC970...

So while the process technology itself is not the issue, my guess (and again this is speculation) is that Steve is not someone who tolerates design "imperfections". Chips that might require liquid cooling or other extreme designs to maintain safe temperatures are not ideal for the mass market.

The challenge of the semiconductor industry is to keep finding ways to increase performance while keeping power consumption in check. Transition to a copper process was a significant step forward (I believe IBM pioneered copper dual damascene) while today the search for low-k and high-k dielectrics is raging. Low-k dielectrics will allow oxide or metal-insulating layers to be made thinner and reduce the height of vias (which in turn reduces the signal path). High-k dielectrics will allow fabrication of thicker gate junctions without compromising switching properties, while reducing leakage and wasted energy by a significant margin (100 to 1 for example).

Last week Intel announced a breakthrough in their search for the holy grail of high-k dielectrics. Of course they did not divulge any details. This type of breakthrough is essential, particularly for the 90- and 45-nm technology nodes.

Briefly, then, my guess is that Steve was enamored over the performance of the PPC 970, but disappointed in the fact that it was not being produced with more favorable operating specifications. A perfectionist like Steve might have wanted more creative freedom over the design of the case, fewer fans, and [maybe] more internal room for expansion.

[Tim Flynn]

Originally posted by Analog Kid
I'd love to see some of the ASIC development EDA tools move to OS X....

DITTO

Other EDA tools as well (schematic, PCB)

[ksz]

Last week Intel announced a breakthrough in their search for the holy grail of high-k dielectrics. Of course they did not divulge any details. This type of breakthrough is essential, particularly for the 90- and 45-nm technology nodes.
Press release:

http://www.intel.com/pressroom/archive/releases/20031105tech.htm

[Analog Kid]

Originally posted by ksz
Of course he is not concerned about the process technology itself, but the operating specifications of the chip he is buying. The PPC970 built from a 130nm process consumes a lot of power. This has led to a large case that is itself designed to be an efficient "exhaust" system. Despite the size of the chassis, there is very little room inside for expansion. You are limited to 2 hard drive bays, one optical bay, and 3 PCI/PCI-X slots. Now contemplate a laptop version of the PPC970...

Ok, that makes more sense... Personally, though, I think they lovingly and eagerly made all those compromises when they saw the IBM roadmap.

[stingerman]

The decisions Apple made were not about accommodating the G5, if they wanted more space for more components, they would have simply used a fan directly on the processor to minimize the heat sink size and create room for more bays.

The current design allows Apple to quickly assemble and build G5's with minimal labor. At the same time it creates a beautiful wire free interior.

[Sun Baked]

Apple also needs the UniNorth3 and KeyLargo2 chips scaled down.

The support chips are cranking out quite a bit of heat now.

Sort of interesting to see heat pipes on the back of the PowerMac G5 logic board.

[ksz]

Originally posted by stingerman
The decisions Apple made were not about accommodating the G5
Which decisions were not about accommodating the G5? I don't mean this sarcastically, but it does appear that the case and airflow designs are heavily influenced by the heat dissipation of the G5 and related chipsets.

Rumors are that the case for the PPC 980-based PowerMac will be redesigned (after all, this is a rumors website). One can only speculate about the changes, but Apple will try to make the best use of space. Filling the chassis with fans and heatsinks is not a good use of space for the customer -- it is a necessary use of space for the base electronics.

The current design allows Apple to quickly assemble and build G5's with minimal labor. At the same time it creates a beautiful wire free interior.
Even the G4 case accommodates easy upgrades. One side flips out and upgrades are more or less a snap.

The wire free interior of the G5 is designed to minimize restrictions to airflow. Apple would not spend money unnecessarily to beautify the interior.

[iansklar]

Hi,

I just bought a gh 2gh. Does it run so hot that it will shorten the life of the computer/processor compared to a cooler chip at the 90nm process?
I haven't turned on the computer at all yet.

Thanks,

Ian

[ksz]

Originally posted by iansklar
I just bought a gh 2gh. Does it run so hot that it will shorten the life of the computer/processor compared to a cooler chip at the 90nm process?

No, as long as the processor remains within its safe temperature window you should not be concerned about this. You raise another issue though: solid state devices will break down eventually with use, but much much before that happens your computer will have already have been melted down and recycled or, less wishfully, found its way into a landfill.

But if temperatures exceed safe margins and assuming the heat-protection circuit fails to shutdown the motherboard, you can expect this (before and after pictures):

http://www6.tomshardware.com/cpu/20010917/heatvideo-01.html

[novice]

$ 1k to read the article from Microprocessor Watch??? I cant afford that. Does anyone have a copy of that article? I wanna read