Slashdot Mirror
IBM Officially Unveils Dual-core PowerPC Chips
PM4RK5 writes "Today at the Power Everywhere Forum in Japan, IBM officially unveiled its rumored dual-core PowerPC line of chips, the 970MP. Code-named Antares, these chips have been rumored to be under development since 2004. It is believed that Apple has been working with prototypes and is likely to use them in forthcoming updates to the PowerMac G5 line. The press release is in Japanese; as of this writing, IBM has not released an English version. Some of the slides from the presentation given by IBM are available.
The processors pack some impressive specs, ranging from 1.4 to 2.5 GHz and including 1MB L2 cache per core; the chips also include the ability to power down the extra core when it is not needed. Alongside the 970MP, IBM also announced its low-power 970FX chips, ranging from 1.2 to 1.6 GHz, with power consumption ranging from 13 to 16 Watts, respectively."
Why would Apple want to waste any more time with PowerPC? I thought Intel had the most appealing "roadmap".
IBMs own server products and embedded processors. IBM's blue gene used the core from earlier PowerPC series.
the world has plenty of PPC chip uses besides filling Macs, from network appliances to video games to Unix & Linux servers and mainframes and supercomputers. Still, Apple chips are almost 1% of IBM's $99 billion revenue, that's a big chunk of money.
Still and all, Apple has been harping on about the superiority of PowerPC for so long that I'm even more surprised to see them switch when IBM has these things, which look like the answers to a couple of Apple's problems, coming up.
I'd be interested in seeing what Steve Jobs saw on Intel's roadmap for the next few years that convinced him...
Whoever corrects a mocker invites insult;
whoever rebukes a wicked man incurs abuse.
--Proverbs 9:7
Why use a 13-16 Watt PowerPC chip when you can use a 27-watt Pentium M?
"Scientists don't change their minds, they just die." -- Max Planck
Apple (Steve-boy) already mentioned that there were moreproc. updates coming, and even said there were some good updates coming down the pipeline. His big concern was not just "now" but the future road map.
We'll see. IBM promised Steve 3 GHz in one year and didn't deliver. They've announced these chips, but give no indication as to when they'll be shipping in quantity. Could be the same as before.
Also, we don't know how compelling the roadmap looks in the future. Apple will get to use these chips in the short term and then switch to Intel by the time these chips have completed their "lives." Steve may be getting what he wants now, but he knows as well as you and I that it is not necessarily an indication of things to come.
Per Square Mile, a blog about density
From the notes:
The dual 64-bit core PowerPC970MP(TM) (970MP) is the next evolutionary step in the PowerPC 970 family of microprocessors. The higher frequency grade versions of the 970MP consume higher amounts of power than earlier IBM microprocessors do, and that can cause temperature issues. Each 970MP processor core contains a thermal diode used to monitor its operating temperature. The thermal diode must be monitored to ensure that the maximum operating temperature of the 970MP is not exceeded.
The press release is in Japanese; as of this writing, IBM has not released an English version.
Assembly is bad enough. I can't imagine assembly in Kanji.
Weaselmancer
rediculous.
Speaking of Roadmaps... Why not would Apple not switch to AMD? AMD's chips run with less power consumption and way less number of transistors. When comparing the Dual core chips from AMD and Intel, AMD wins on power consumption. But I thought Jobs said Intel had the best Performance per watt? ADA4800DAA6CD (AMD Dual core 64-bit): 110W Intel® Pentium® Processor Extreme Edition: 130W These are the latest and greatest from Intel and AMD right?
From the roadmaps and rumor mill, even the Pentium EE 130 W(clocked at what, 3.8ghz?) and the AMD Athlon 110 W and too high power and not good enough on performance.
It appears Intel plans on dropping the P4 line and going to enhancing the Pentium M edition. It is expected that Apple will be going with the Pentium Ms (which apparently have dual core slated in their lineup) instead of with the Pentium EE.
In summary, Apple won't touch the Pentium EE due to high power consumption. However, they do like the Pentium M with has much better performance per watt/clock cycle and much lower power consumption.
From that I would guess that either AMD could not give Apple the same deal as Intel could. Either that or Apple expects Intel to have much better performance than AMD by that time. Also, as far as I know the Pentium Ms are much better than AMDs mobiles in power and performance.
Fly me to the moon Let me sing among those stars Let me see what spring is like On jupiter and mars
Best performance per watt != Lowest power usage of highest-performing part.
The Pentium M family is much lower power than the Pentium 4, and has reasonably good performance. I don't think AMD really has a chip that competes with the Pentium M, even though AMD's chips are generally less power-hungry than a Pentium 4.
Yes, most individual programs don't fully take advantage of multiple processors. However, if you have multiple applications open at a given time and each is actively doing something, that's when you're glad you have processor #2 available.
Foreground app has the first processor, some busy app in the background (file copy, MP3 encoding, DeCSS, photoshop filter, etc) gets the second. You're much happier because your system isn't taking a few seconds to respond to each mouse click.
If these had been around a year ago we could be talking about Apple innovation etc, but the fact is the x86 market is ahead and Motorola/IBM have their eyes on high end servers and the embedded market.
:)).
But still, the power use of these chips is very impressive. Always liked Motorola but AMD64 is where I'm at now (it's close in name to CBM64 too
Now that would make a good shirt for a lass. Check out my dual processors!
And that, my liege, is how we know the Earth to be bannana-shaped.
Why is IBM unvailing it now? There are no known potential customers for this chip.
Well, IBM is a customer as will be Apple. The PowerMacs aren't planned to dump PPC for another 18 months, so you should see dual-core PowerMacs for some time here.
This announcement also helps illustrate why Apple jumped - 2.5GHz at the high-end means that Apple remains topped out on performance, and the low-power chips are okay, but really aren't low-power enough, nor fast enough to give Apple a significant gain on laptops.
The 3GHz promise is completely irrelevant to the Intel switch. In the last two years, IBM has gone from 2.0 to 2.7GHz, which a proportionally larger increase than Intel going from 3.0 to 3.8. Everybody ran into the same problems at 90nm; it's not a case of IBM dropping the ball. The real motivation is laptop chips, where the Pentium-M trounces the G4 today, and Yonah will easily beat a 970FX at 1.6GHz.
How to solve most of our problems: 1.Lots of nuclear plants. 2.Cure aging.
Alongside the 970MP, IBM also announced its low-power 970FX chips, ranging from 1.2 to 1.6 GHz, with power consumption ranging from 13 to 16 Watts, respectively.
This sounds exactly like what Apple needed for a G5 powerbook. Did Steve just get a little too impatient? Had he waited another month maybe he would have found the answer for a G5 powerbook? Did Apple threaten IBM that they would go to Intel if something didn't change soon? (and now IBM has delivered, but perhaps a bit too late)
I don't understand how some people are saying "OMG Apple switched at the wrong time oh noes!@#!!"
Does everything HONESTLY think Apple didn't know the exact release date of the 970MP BEFORE they announced their switch?
Apple knew when and where this was going to be released, and they know when and where Intel will release their next series. They switched because they wanted to, this isn't a surprise to them.
IBM has since released an English press release, available here.
This should be significantly more informative than the earlier available Japanese documents.
AMD has approximately 20% of the PC Processor market.
Apple has 3% of the PC Market.
3% of the PC market is 15% of AMD's market.
AMD's market is normally capped not by distribution but rather by production. If AMD won the Apple contract, they would EITHER need to increase their production by 15% (not historically AMD's strong suit), or increase prices to the PC market...
If AMD picks up the Apple contract and CANNOT increase production...
Then AMD has to reduce their PC market-share by 15% of their production, which means increasing prices.
Either way, Apple would be a HUGE account for AMD, and would require a substantial portion of AMD's manufacturing resources.
Alex
You're 100% right.
:)
One of the things we do at the company I work for is tell people the G4 is better
than the G5. The G4 is wonderfully more generic in performance - random memory
access is a good one to benchmark. The G5 is very good at streaming huge
contiguous blocks, but the high RAM access latencies and cache latency/line width
problems kill random access or impact code such as array lookups (best Vector
Permute trick on the planet, also hampered by a weak Permute unit).
But that's not to say the G5 doesn't have merits; it just has some VERY specific
applications that it's very good at. Perhaps too specific for Apple. Companies
like Mercury (www.mc.com) would probably have gone for the G5 if they hadn't
found an even more specific processor for their needs (Cell, in this case).
With lower power chips the G5 could actually start to replace the G4 in places
where performance in high memory and streaming data are paramount.
For laptops, desktops, and places where we don't need 16GB of memory, the G4 is
going to rock for years to come though. I actually wonder why there couldn't be
a special "pseudo-64bit" version of Linux for the G4, which used the 36-bit
addressing modes to implement high memory support. Maybe it's because IBM practically own ppc64 Linux and don't want to overshadow their own chips?
-- Neko
How are they "topped out for performance"?
There's nothing here significantly stronger that what we've had for the last several months. Sure, dual core vs. dual G5 has benefits, but without a clock boost or anything else, it's not much more than packaging.
I would say IBM's offerings are competitive. Steve Jobs and his "wah I wanted a 3GHz chip!" is all bullshit when you look at it; he wanted to compete with the Intel marketing machine, and still hasn't noticed that AMD Opteron chips top out at 2.6GHz - and have done for some time. The G5 is competitive in that it matches or outperforms the AMD Opteron (that frontside bus helps).
Yah, and Apple can have pretty much the same performance with Intel chips. It's not the top end that drove the decision, it's in part the laptop chips. 1.6GHz G5 is good, but the Pentium M looks like the place to be for a while.
Ultimately, I suspect its Intel DRM that drove the decision. If the media giants want DRM, they're going to go with Intels, and anyone else is going to have a uphill fight. Better to be in the game from the start there.
Their dual cores top out at 2.2GHz and also probably will for some time. Apple still have the potential to create a 2.4GHz PowerMac and an XServe with up to 4 processors which competes with AMD's most expensive and little used 400 and 800 processor lines.
Apple has always been able to do 4-way with the G5. Dual dual-core isn't *that* much easier than 4-way. If the market was there for 4-way we'd have it.
I don't see why it "illustrates" anything except that Steve Jobs is a nut job who lied himself through a developer conference. It's a damn shame Apple has gone so low and a damn shame the developers are so loyal that they keep so quiet.
How did he lie? Everybody knew about the MP before the conference. The transition lasts until 2007. The decision surely wasn't made based on any product that will ship between now and then. In fact, the MP is likely the main reason why the PowerMacs will be last to move - the performance is there with PPC in the near term. Will IBM make a 980, though, or is this the end of the line?
There is a lot of dissent in private quarters. All that PowerPC hype Apple pushed down our throats - some of it actually real as it turned out - has left 1000s of developers with a lot of AltiVec code and not a lot of choice. They are mighty
pissed about rewriting their apps again, especially to bridge the gap between now and the 10 years in the future that Steve's Intel Roadmap says they will have better integer performance.
Oh, come on. There aren't 1000s of Altivec apps. There are thousands of apps using Apple's SIMD libraries (which are already ported to SSE3) and using other OS X libraries, but there are *maybe* hundreds of apps using Altivec directly. Apple isn't worried about them being pissed. Developers will chase the money like everyone else and Apple isn't a bad ride right now. They'll suck it up, diddle their code and start selling product again.
The biggest dissent seems to be inside IBM. Not long after the 970 came out IBM merged their semiconductor and server groups. The semiconductor group that was quietly making small profits (due to low pricing to Apple) on 970s was publicly costing the server group big profits by taking a bunch of HPC contracts that could have gone to IBM 970 or POWER systems (IBM execs would of course claim that every Apple HPC sale was a lost IBM server sale since it was the CPU that carried the day).
Once those groups merged, Apple's sweet deals went away and Apple was expected to pay their way. The contract came up, Apple didn't want to pay the enormous development costs of a CPU line, so they saw their opportunity to further commoditize the product line and struck a deal with Intel. In the end, consumers and most developers really won't have a problem, and it *might* (who really knows) portend good things for Apple.
AMD operates their own CPU fab in Dresden, Germany. AFAIK IBM has no direct role in the fabrication of K8-based processors.
AMD and IBM do work together on developing fabrication technology. But AMD is not fabless nor totally dependent on IBM for manufacturing.
g5 is to g4 as p4 was to p3 better overall IPC, less picky about memory latency, less power, basically a great thing to quad core if you're looking for perf/watt
I refuse to believe that the 28- and 31-stage Pentium 4 pipelines are a better thing than the 10-stage pipeline in the Pentium III, particularly when we're talking about IPC. Do you remember the fuss made about P4 being slower at the same clock speed than the PIII? That's proof it has worse IPC rate.
Neither the P4 or the G5 are lower-power than their predecessors and they fail to provide better performance/watt, in any configuration. This is why the P3 architecture has been adopted into the Pentium M line for low power use and the G4 processors remain the chips used at the core of Apple's iBooks and PowerBooks.
The great thing to do with the Pentium 4 architecture would be to put in on good Strained Silicon and SoI processes to push it above the 4.0GHz clockrate at which it is believed to be a very strong chip.
The differences between the G4 and G5 chips are what happens when you move from a desktop computer chip to a cut-down Big Iron chip (IBM's POWER4, IIRC). The G5's are inherently 64-bit capable in a way that the first three generations (Willamette, Northwood and Prescott) of the Pentium 4 are not, although there exist Prescott-based Pentium 4 processors with Intel's EM64T implementation.
BTW: http://arstechnica.com/ is your friend. Hannibal has done a good job of talking through the history of the Pentium chip family (1 & 2) and the PowerPC family (1 & 2, part 3 hasn't yet arrived) up to the G4's. There's discussion of the IBM POWER5 architecture too, and some commentary on pipelines in processor design (1 & 2). I learned a lot from these, and value their information. But I'm going to stop telling Granny to suck eggs now.