Slashdot Mirror
PPC 970 Confirmed for Apple?
batboy78 writes "In what perhaps is the first 'official' confirmation that IBM's PowerPC 970's will be used by Apple, BusinessWeek claims that IBM has confirmed that it's developing a new set of chips for the Mac: 'IBM says the new Apple chip will be of the 64-bit variety, which means it can process twice as much information per cycle as existing 32-bit chips.'" CT The article has been updated to make the confirmation seem... well, far less comfirming.
PPC Confirmed for Apple -> New Mac Confirmed for KoopaTroopa
Sharpies don't just sniff themselves.
Apple sales guys must hate this kind of press.
IBM says the new Apple chip will be of the 64-bit variety, which means it can process twice as much information per cycle as existing 32-bit chips.
Argh! Head... going... to... explode...
Malike Bamiyi wanted my assistance.
The AltiVec engine (which is also available in the 970 though I'm not sure if IBM can call it that or not) is like MMX/SSE/SSE2 where it can process chucks or multiple chunks of data that can be larger than 64-bit (AltiVec and SSE can handle 128-bit, not sure about SSE2).
32-bit and 64-bitness of a processor generally means how much memory it can address and the size of the registers.
Did I miss the part of the article where it said that IBM confirmed making PPC chips for Apple? I don't see a press release or any other real evidence. This is just an article about some guys speculation as to what is happening.
The G4 is a 32-bit CPU with a 128-bit vector processing unit (aka SIMD Unit) called Velocity Engine or Altivec. This kind of like (though much superior) to MMX, 3DNow!, etc. The new IBM chip is suppose to be a 64-bit chip with a 128-bit Altivec compatible unit. In the past, the Altivec unit has always suffered from Motorola's slow FSB on the G4. One bonus of the PPC 970 is that it sports a 900MHz DDR bus that can keep the SIMD unit fully fed.
Ok.. I wish people would get this through thier heads. A 64 bit chip is _NOT_ inherently faster than a 32 bit chip. It is able to address more memory space and perform greater precision calculations faster. If you are just working with lots and lots of 32 bit numbers you will see some speed improvement but not close to double. Once you are into the realm of 33 bit and higher numbers which are done with mathematical trickery on 32bit processors, you will see a huge speed increase when working with a 64 bit processor.
Also, the increased memory ceiling helps.
*note: yes, I know this is not technically correct, but I'm not explaining how 32bit and 64bit processors handle thier operations. Maybe someone can reply with that.
Karma: SELECT `karma` FROM `users` WHERE `userid`=138474;
I thought it was powers of two?
32bit = 2^32 = 4Gigs memory space
64bit = 2^64 = alot more than 8gigs
This would mean that it is far greater than twice as much information.
I could be WAY wrong since I suck at math.
Here a Sig There a Sig Everywhere a Sig Sig...
Does that mean my G3 isn't a supercomputer anymore?
From the article:
Although Apple won't talk about it, IBM is developing a new set of chips that Apple will likely use to replace theaging Motorola processors used in its G4 line.
How is this "official confirmation"?
I didn't read anywhere in the article that IBM confirmed Apple will be using PPC970.
Is this new news?
mr.
If IBM is officially releasing this information these machines should be out soon.. As apple is probably not going to sell a lot of G4s now..
For those of us who have been thinking about purchasing an Apple for a little while now, this is just one more reason to do so. I've been trying to resist the urge, but once these systems come out, I'm sure they'll be too good to resist. For someone who used to hate Apple with a passion and mock all Apple users, that's a huge step :-)
Five Dolla Moddy-Moddy?
OK, let's review. First off, this is not the regular "Byte of the Apple" columnist. Second, if I had a comment like that in my back pocket, I'd make damn sure that readers knew where I got it, who said it (if possible) and get as much detail as I could. This sounds too offhand to be authentic, and, really, the comment doesn't necessarily indicate that IBM will be building chips for the Apple. The author could simply be referring to a comment made at the Microprocessor Forum--where IBM and Moto executives deliberately avoid the A-word.
What we've got is not a smoking gun, but a shadowy silhouette of an unknown object that might be a gun and seems to be emitting some sort of vapor. If Business Week had something definite, this would be a news story and not something buried in a column.
(Pardon the troll: why does Business Week actually have a dedicated Apple columnist, anyway? They cover business: why not a column on Ford, or Charles Schwab, or Genentech? hell, it's not like it paid off for them--Apple gave the iMac story to Time.)
You must have been asleep for most of the 90s when the PPC was kicking x86 butt.
Here is what the article actually says:
"Although Apple (AAPL ) won't talk about it, IBM (IBM ) is developing a new set of chips that Apple will likely use to replace the aging Motorola processors used in its G4 line."
TO REPEAT: "...CHIPS THAT APPLE WILL LIKELY USE..."
In other words, THIS IS JUST MORE FACT-FREE SPECULATION.
It's easy to make up & spread cool- and credible-sounding stuff. Finding & checking hard facts is hard work.
The past has shown this to be untrue. Apple held the CPU speed crown with the G3s when they first came out. Motorola has been screwing Apple for dropping the clones (and cost Moto big $$$), and because there is no incentive in their embedded market for fast FSB. Mark my words! This is just the beginning. IBM has the most advance fabs in the world. And they just made a deal with AMD to share process techniques. The POWER 5 (and its PPC 980 derivitive) are a hell of a lot closer then you think. Oh, you want benchmarks? http://www.macbidouille.com/niouzcontenu.php?date= 2003-05-05#5440
Altivec or Velocity Engine was developed by Apple, IBM and Motorola together (AIM), so Velocity Engine and Altivec are the same thing. The name Altivec is owned by Motorola, but the actual 128-bit vector processing unit is owned by AIM, so IBM can use it in their processors, they just can't call it Altivec.
This article is the fluffiest piece of fluff ever to fluff the internet.
The only tidbit of info is that the article claims that IBM confirmed the chip was made for Apple. Other then that it's all fluff.
No news, you've read it all before if you know anything about it, then you already know this. 64-bits does not equals twice the computing power, PPCs do not divide up tasks in parallel better then intel chips, nor are better suited for multimedia.
Also, I doubt that this chip will even put the mac platform far enough on top to warrent more then a meh from current PC users. Intel is already ahead in bandwidth again, and unless the 970 scales into at least 2.5 ghz, intel's chips will be faster.
Not to say that it won't help the ailing macs. The G4 is much too slow by todays standards to warrent the cost. They are useful in laptops because of their low power consumption, but other then that not so great.
Also, he has no information about when or if Quark will come out. And even if it came out today, most shops wouldn't switch right away unless it was faster then the current version on the new hardware.
I was more intrigued by the "1.8 GHZ per second" claim.
1.8 Billion instructions per second per second. It's about time that somebody made an accelerating chip - way to go, IBM!
"It is our blasphemy which has made us great, and will sustain us, and which the gods secretly admire in us." - Zelazny
I'd bet money you won't see the PowerPC 970 in anything other than the PowerMac at least at first.
PowerMac = Highest Performer, iMac = Mid teir and eMac = cheapy.
PowerPC 970 isn't going to be a laptop PC unless you want to cook eggs. Can't see that nice chip being in a book just now.
(Speaking as a recent Powerbook 12" Owner too)
As a rock-in-roll Physicist once said, No matter where you go, there you are.
But come on! We all know that bandwidth scales with clock speed! And clock speed is a true and unfailing measure of a computer's performance.
You haven't been listening to your marketing department, have you? ;)
-Looking for a job as a materials chemist or multivariat
Link
benefits of 64-bit computing
increased scalability
The main benefit of 64-bit computing is increased scalability of your computer and applications. Some applications simply do not fit into a 32-bit computing model. For example, limitations on file size in a 32-bit environment may require database systems to use multiple files to represent a single file. Applications requiring large files, a large number of files, or a large number of users will benefit from 64-bit computing.
increased performance
Any application that is outgrowing a 32-bit computing environment will suffer performance hits. Applications may need large files, large memory, high precision arithmetic, and/or algorithmic accommodations for 32-bit limitations. Applications needing more code or data in memory will benefit from decreased swapping with 64-bit computing. Reduced swapping can make database inquiries as much as 100 times faster (individual performance gains may vary).
Jeez... did any one read the article? it is just repeating the rumor. It does NOT say that IBM is confiming its making the chip for macs. go back to work and clean the jism off your screen.
Some drink at the fountain of knowledge. Others just gargle.
The G4 really was a supercomputer at launch... but only by the letter of the law. The G4, capable of over 1GFlop, came in north of the Federal definition of a Supercomputer (in relation to the export of arms). So.. you couldn't ship the Macs to any 'enemy' country like Libya... or even to France... at least not right after they were released.
;-) A dual 2.5 GHz machine would be capable of up to 40GFlops (max theoretical) by Apple's calculations. ;-) hehe.
The US Govt. quickly revised the rules. I believe supercomputers are just north of 50GFlops now.... so Apple could get real close again with an SMP 970... if you go by Altivec performance again.
I'm not feeling witty so bite me
Quick everybody dump Intel and AMD stock! Their 64bit roadmaps demonstrate that they're pushing useless processors.
64 bits are coming and Apple's wise decision years ago to go to PPC mean that today it has the easiest roadmap. Itanium requires lots of rewritten software code (not just recompiled) and a lot of people think AMD's solution won't last too long. In contrast, The Power ISA has always allowed 32bit code to run on 64bit processors with little speed penalty. You *can* recompile your application code but the only program that *has* to do it is the Operating System, and even then not all of it has to be recompiled.
Apple's product roadmap seems to involve tighter and tighter coordination with IBM and their Power Series which serve many large Fortune 1000 businesses and are likely to continue to do so with 64 bit Power (and now PPC) technology.
I don't see anything in the article which cites any sources more reliable than, say, /.
As much as I am a devoted Machead, sometimes the Byte of the Apple columns lay it on a little too thick and syruppy. Objective journalism, anyone? When Windbloze columns use the same style of reporting, I get upset. However, the author is reiterating for a broader audience the same thing that we on /. are all certain will happen anyways: the PPC 970 is targetted to be shipped in Power Macs by the end of summer.
Well, all of us except maybe the diehards who are certain that this PPC 970 stuff is all a ruse, and Steve Jobs secretly wants to use the AMD X86-64 instead.
"Smart is sexy." -- D. Scully ("War of the Coprophages")
Does anybody really even care about Quark anymore? At the firm I work for no one uses Quark and no one really did. Even for brochures, newseltters, etc. Illustrator is used for everything. We have one copy that is not even currently installed (well it might actually be on all the computers) that we keep for those rare instances when we end up with a Quark file to work on, but I have not actually heard of one person who is really waitng for Quark. For anything that we would have possibly used Quark for we've switched to InDesign which is quite capable and readily available for OS X. And even those people that are waiting for it, I hardly see Quark as being the thing that helps bring Apple's profits up. -peel
As in, it'll be announced that Quark is available, but only on the new 64-bit power macs, driving the sales of both.
1.8 GHz/sec. Let's see now ... heat production is a function of frequency ... assuming the power supply is designed to keep up with a machine uptime of at least a few days (very conservative design) ... then THE WORLD IS GOING TO EXPLODE INTO A CLOUD OF GAS FROM THE HEAT!!!!
Anyone know enough physics to calculate how long it would take a 1.8 GHz/sec. chip to destroy the world?
-- Holy Heat-sinking Hellfire, Batman!!
I ordered the last OS9 booting G4 because I need a new computer now, not next week or next month. I need OS9 booting for QuarkXPress and for OS9 multitrack audio applications that I use.
If a rumour about new computers is putting you off buying you probably don't need a new computer anyway. If you make money with it who cares what's in the pipeline? If you need a new machine and it's going to make you money you buy it.
I'll worry about buying a Mac with a 970 processor when it's actually shipping and the software I use has been rewritten to take advantage of 64 bit processors.
"Clean up the air and treat the animals fair" - Captain Beefheart
The original Firewire (IEEE1394) would've been a much stronger interface platform had Apple introduced it throughout the entire product platform from its inception. But Apple took 2 years to get Firewire on all Macs from the PowerMac line down to the iMacs. That was a big mistake. Apple saved the USB standard by introducing it on all Macs when the iMac debuted. Now we have Macs that have chipsets capable of USB 2.0 (because the chips cost the same whether they are USB 1.1 or 2.0) but Apple is not advertising this or natively supporting it because of it weakening the need for Firewire (400, iLink, IEEE1394a, etc.). But if Joe Blow wants a decent scanner for a new computer purchase and doesn't want to spend $400 for a Canon Firewire based scanner, he/she/it has to settle for USB 1.1 speeds (without software driver hacks) on a new $100 USB 2.0 enabled scanner. If anything, Apple should have iPods with Firewire800 support on them to further their advantage over all the other MP3 players (yes yes, iTunes store monopoly). It would also make sense for Apple to use internal Firewire connections for the CD/DVD/Superdrives instead of relying on the ATA standard. Apple now has a great operating system, but it really needs to polish its hardware to attract more geeks with cash to switch platforms. The Apple platform holds so much promise!
"Right now, somewhere in this world, Scott Baio is plowing a woman he doesn't love," - Peter Griffin, *Family Guy*
The MacRumors article has been updated with the following:
Update: The article has been edited with the following correction/retraction:
"IBM did not confirm it was building a chip specifically for Apple, but it does say its new PowerPC
chip will work on Apple platforms"
Not exactly a "Never Mind" but the air of mystery continues.
If you're not living on the edge, you're taking up too much space.
The 'desktop' variant of the chip dissipates 19W at 1.2GHz, which is not out of the realms of possibility for a laptop (many Intel laptop chips dissipate more than this) and the 1.2V version is expected to make do with only 13W. It is entirely possible that the PowerBooks will move to this chip quickly, and the iBook will start to use G4s.
I am TheRaven on Soylent News
From the article:
"IBM did not confirm it was building a chip specifically for Apple, but it does say its new PowerPC chip will work on Apple platforms."
So IBM has confirmed that the new chip will work in Apple Machines, something they heretofore had not said.
I realize IBM is making hardware for apple and that has very little to do with their software, but could IBM be attemptting to use the Mac as an enterprise platform? All of their stuff is written for Linux, which would port easily to BSD, and apple had by far the best opportunity to take out Microsoft in the Desktop space. Could IBM be attempting to Bring Apple to the Enterprise?
I tried for 5 years to come up with a clever sig...only to realize that I am not clever.
I don't believe a word the article says as it doesn't put the requisite "beleagured" before "Apple Computer".
I'm a bit worried about the lack of 64 bit applications. Converting an application to run well on a 64 bit CPU is no small task I suspect, so Mac users might have to deal with sub-G4 performance with 32 bit software for quite a while as software developers scramble to advance.
I wonder how the Athlon64's (aka "Clawhammer") 32 bit performance will compare to the PPC970. With x86-64 extensions I'd expect it to be significantly faster, though I wouldn't be surprised if its 64 bit performance was slower.
Next, the article cites the "timing". Assuming these chips haven't been sampled yet, Apple has no chance to get these things out in time to compete with Athlon 64. Users are already doing the things he lists as high-performance tasks, and have been doing it on PowerMacs for some time (let alone Wintel PCs, though arguably it is easier to edit down your home movies onto DVDs using a mac, based on the included software.) Also, digital music is not at all a processor-intensive task; Digital recording can be if you're worried about being realtime, which I assume most people are. Realtime digital audio manipulation (though not synthesis) is generally CPU-intensive, but most people won't be doing this. Video is about a zillion times more intensive, and people are doing it NOW, but he cites "digital photography and digital music" as the reasons people need CPU? PLEASE.
As for "WATCH OUT, SUN" -- Sun is in no danger whatsoever from Apple. It's in far more danger from AMD, and in even more trouble than that since it's under fire from itanic, which is about to get another revision, right? Ultrasparc processors simply don't have the go-get'em any more, the only advantage of Sun machines is that they have the "big iron" systems and an OS to run on them. As itanic systems become more multiprocessor, Sun will be in more trouble. As Opteron/Sledgehammer systems become more multiprocessor (I believe 32 processor systems have been announced?) then Sun will be in even more trouble because of the price-performance ratio. I CAN see a day when Sun will stop making Ultrasparc-based workstations, but it won't be because of Apple.
As for a 64 bit chip processing twice as much data per cycle, you still have to do loads and stores, and Apple has traditionally had the slowest-of-class memory and system bus. I understand the new processor has a 400MHz DDR (800MHz equivalent) bus, so perhaps Apple will match it with DDR400 SDRAM, and then it will do them some good.
I guess the Quark upgrade for MacOSX could push some shops to upgrade, but can't they run Quark for MacOS9 on MacOSX just fine? Unless there are meaningful new features on the new version... Which seems unlikely.
Face it, this chip will not "breathe new life" into Apple. It will only allow it to keep fighting the "good fight" against other platforms which are going or have gone 64 bit.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
Apples machines are the most productivest.
You *can* recompile your application code but the only program that *has* to do it is the Operating System
But you will have to recompile/rewrite all of your Windows and x86 code in general.
Well that makes it definite in Apple land - a retraction's been made.
..k
The Mothership
Ok, here's my question. Why does everyone spend so much time comparing PPC to x86? Ok, so I'm a recent switcher, I purchased a 12' PB. I love it. So it only has a 867 MHz G4, its way fast enough for 90% of what I do with it. So I hear this new PPC 970 is on its way. GREAT! Anything faster then what I have now is better. Right? I have a mac, I'm not trying to run Windows on it. If OS X and the software I run on it work fine, then I'm happy. All I'm getting at is that faster processors for Apple is a good thing. Just because they are not as fast as the x86 flavor doesn't bother me.
I'm posting this on a ZX Spectrum via home-rolled TCP/IP stack. Do I win a 12" powerbook?
After the barbequed sausage incident, I think people will be wary before they cook their eggs too!
First, the issue about how IBM said that the chips would work with Apple's platform. I doubt they said that, because they won't work with Apple's "platform" in that they aren't pin-compatible with the existing PowerPC offerings. At least so I presume, since going 64 bit generally means a wider data bus and a wider address bus. I guess I could be wrong about this part. :P If you mean, the instruction set is compatible, I'm not sure I'd believe that either, but I'm willing to reserve judgement until I look at the user's manual for the new processor.
They didn't put that very well. I'm pretty sure that they wanted to say that Apple can use the 970 in a new Mac which will work with existing software. You wouldn't have that with x86 processors. Not that I believe that IBM has said anything to Businessweek, the story is lacking hard data and reeks of rumormonging to increase page-views (succesful with the help of slashdot).
Assuming these chips haven't been sampled yet, Apple has no chance to get these things out in time to compete with Athlon 64.
IBM's original roadmap was sampling in 2Q03 with production in 2H03. So they should be sampling already. IBM is known to be very conservative in its estimates, so we might see full production very soon. I've heard rumors that things are going well at IBM.
Video is about a zillion times more intensive, and people are doing it NOW, but he cites "digital photography and digital music" as the reasons people need CPU? PLEASE.
I'm not an expert on digital audio, but I do know that photoshop artist are always looking for more speed. Complex operations on 100+MB images still take too long. The same might be true for sound editing.
As for "WATCH OUT, SUN" -- Sun is in no danger whatsoever from Apple.
A 1U XServe 970 will certainly compete with Suns low end. The current XServe is already doing fairly well in that market and a fast 64 bit offering will only do better. x86-64 is a bigger threat to Sun, but a new XServe will probably be another nail in their coffin.
I understand the new processor has a 400MHz DDR (800MHz equivalent) bus, so perhaps Apple will match it with DDR400 SDRAM, and then it will do them some good.
The bus is half the speed of the CPU, the announced high-end chip (1.8 Ghz) will have a 900Mhz (equivalent) bus.
Face it, this chip will not "breathe new life" into Apple. It will only allow it to keep fighting the "good fight" against other platforms which are going or have gone 64 bit.
This chip will address Apple's main weakness, a (very) slow CPU (and bus + RAM, but those are all tied to the CPU). There are many, many people waiting for faster PowerMacs, I forsee an enormous sales surge. As for "breathing new life" into Apple, they have done so already. The enormous succes of the iPod and the iTunes Music Store is changing them into much more than 'just' a computer company.
The Drowned and the Saved - Primo Levi