PowerPC 970 Running at 2.5 GHz

kuwan writes "IBM has just released a press release that indicates they have the new PowerPC 970 running at 1.8 to 2.5 GHz making it 'the fastest PowerPC so far.' IBM's original estimates were to have the chip running at 1.4 to 1.8 GHz at introduction, so this is very good news for those of us hoping Apple will use this as their next-generation chip."

Let's see some FAB speed scores

[MarkRH]

Who cares how fast IBM has this running in the lab--let's see how fast those fab lines are running before we get too excited.

Re:Let's see some FAB speed scores

[warrior]

I think everyone else may have misinterpreted this post. The question is not "how fast are the chips that have been fabbed", but how successful have they been with fabrication? They may have one really fast part while the rest of the lot has serious issues. If they're getting low yield from their manufacturing the chips will be very expensive. There are always a few really fast chips at the extreme end of the distribution, but that's not what speed they'll be selling at. Getting those extra MHz is up to the overclockers if possible.

Re:Let's see some FAB speed scores

[writertype]

Absolutely. As a journalist, it's much easier to attract readers by being deliberately vague. Not only are you never wrong, but readers spend all their energy trying to figure out what you MIGHT have said rather than picking apart what you actually did say.

Nostradamus should have won a Pulitzer.

Re:Let's see some FAB speed scores

[dbrutus]

In the case of speculating on yields, the relevant number would be the low end of the range. Originally, the low end was 1.4Ghz, practically the same speed as current G4s but the new number is 1.8Ghz, thus it's likely that there will be 1.8Ghz machines in cheap plenty with 2.5Ghz being more expensive and rarer.

What's the current offering for 64bit computing from Intel running as of today? The Intel website has 2 speeds available for the Itanium 2 chip, 900Mhz and 1Ghz. That's Intel's fastest 64bit solution.

Intel's got a *lot* of catching up to do if IBM starts shipping in quantity soon.

Re:Let's see some FAB speed scores

[AresTheImpaler]

here is some info i found.. might help:
SPECint2000
- 937 @ 1.8 GHz
SPECfp2000
- 1051 @ 1.8 GHz
Dhrystone MIPS
- 5220 @ 1.8 GHz
- 2.9 DMIPS / MHz
Additional Performance
- Peak scalar GFLOPS = 7.2
- Peak SIMD GFLOPS = 14.4
- RC5 : 18M keys/sec
Unfortunately at the very bottom it says that some of this are estimates.. here is the link where I got the info: http://www-3.ibm.com/chips/techlib/techlib.nsf/tec hdocs/A1387A29AC1C2AE087256C5200611780

Re:Let's see some FAB speed scores

[Clockwurk]

Because we're all too lazy to copy/paste [ibm.com]

Estimated Scores of 2.5GHz Chip

[Galahad2]

Assuming the same bus speed (which is impossible, so take these numbers to be within, say, one hundred points of reality) and linear performance progression, the 2.5GHz chip should have:

SPECint2000 =
937 / 1.8 = 520.5 points/GHz * 2.5
Estimated Score ~= 1300
Average P4@3.0GHz score ~= 1080 (the 970 = 20% faster)

SPECfp2000 =
1051 / 1.8 = 583.9 points/GHz * 2.5
Estimated Score ~= 1460
Average P4@3.0GHz score ~= 1100 (the 970 = 33% faster)

RC5 =
18 / 1.8 = 10 * 2.5
Estimated Score ~= 25M keys/sec
Average P4@3.0GHz score ~= 4.3M keys/sec (the 970 = 581% faster)

Take these numbers with a grain of salt, but they're somewhat interesting. I like the RC5 score, especially. ;)

Re:Let's see some FAB speed scores (specs here)

[writertype]

Well, hauling out the report [extremetech.com] from Microprocessor Forum it looks like:

The core, as defined, contains 64 Kbytes of instruction cache, 32 Kbytes of data cache, and 512 Kbytes of 8-way set associative level 2 cache. Unlike the Power4, the core does not apparently contain an onboard cache controller to enable the use of off-chip L3 cache.

The front-side bus electrically runs at 450-MHz, double-clocked to an effective rate of 900-MHz, generating a peak bandwidth of 7.2 Gbytes or 6.4 Gbytes/s of useable bandwidth after transaction overhead is taken into account, Sandon said. Five instructions can be issued and acted upon at any one time, while a total of 200 instructions can be "in flight" at any time, taking into account instructions that are stored in queues.

Performance-wise, IBM believes the chip can record a benchmark of 932 on SPECint 2000 and a score of 1051 on SPECfp2000, both at 1.8-GHz. Peak SIMD GFLOPs should be about 14.4, Sandon said. Using Dhrystone MIPS, the chip should output a score of 5,220. or 2.9 DMIPS/MHz/. IBM expects the chip should test 18 million RC5 keys per second.

Re:Let's see some FAB speed scores (specs here)

[nosferatu-man]

For comparison's sake, the P4 Xeon @ 1.8ghz pulls 703/717 (int/fp) on SPEC CPU2000.

Assuming a linear scaling in SPEC performance, we can look forward to a 2.5ghz 970 scoring about 1294/1460, which is pretty respectable. Not a world beater (especially for 2H03), but a far cry from the abominable performance of the current G4.

'jfb

Re:Let's see some FAB speed scores (specs here)

[nosferatu-man]

Fair enough. Right now, the fastest processor in the world is the Pentium 4 3.06ghz: 1130/1103 (int/fp). For pure floating-point horses, it's the Itanic 2 743/1427 (int/fp).

So a 2.5ghz 970 would be close in performance to both of today's fastest shipping processors. It's likely that the P4 and Itanic will be 15-20% faster in six months, so IBM will still be lagging in the performance hunt. However, it's striking how much closer to the peak performers this chip will move IBM -- and, by extension, Apple.

'jfb

Re:Let's see some FAB speed scores (specs here)

[FatherOfONe]

Wow guy take it easy!

He has a valid point. It would be fair to compair it to the best chips out now. I don't care what AMD + rating it has or what MHZ Intel has it running, just the best chips out. It would also be good to see how the best sparc chip, Xeon, (whatever SGI uses), etc compared.

I realize that this is just ONE benchmark and a lot goes in to a system, but it would still be interesting to see.

Re:Let's see some FAB speed scores (specs here)

[Dr_Cornholio]

Hear hear. Why are new chip speeds ALWAYS compared to P(insert number here) speeds? Fair enough they are the PC industry standard, but why not do a comparison to some of the higher end chips? Then we could see where our new processors fit into the bigger picture of things and find new markets for them, rather than focusing on the Desktop market every single time. Case study: Transmeta. Good chips for laptops coz of heat issues, but just couldn't cut it on the desktop. (Not trying to be flamebait, but it's a damn good example)

Reality check

[Rui del-Negro]

At the same clock speed, and for short sequences of instructions, a Z80 can beat a P4. The problem is... they don't make them at the same clock speed.

It's irrelevant how many times per second the chips clock says "tic-tac", what matters is how fast real chips can get real jobs done. For real-world purposes, you can compare the best (ie, the fastest chips) or the most valuable (ie, the ones with the best speed/price ratio).

So you see, Mr. Anonymous Coward, comparing the performance "per clock cycle" is irrelevant. It's like comparing the performance "per instruction length", or "per transistor count". It might be interesting from a theoretical point of view, but if a chip that does a lot of work per cycle cannot do more than a couple of cycles per second, it's still a terribly slow chip. The P4 was designed to do less work per cycle, but work at higher frequencies. The Athlon, on the other hand, does more work per cycle but cannot reach such high frequencies. In the end, they're more or less matched. So, in that situation, which one do you buy? Perhaps you buy the one with better "performance per clock cycle". I buy the one that's cheaper (funnily enough, in this case they would be the same).

I thought Macs were competitive with PCs. Or are you saying that anyone who buys a Mac is totally clueless? It all depends on the market you're talking about. When this chip is finally released, PC processors will be twice as fast than they are now, and will probably cost half what they cost now. Anyone buying a Mac for raw number-crunching is an idiot, just as anyone using Windows for a firewall or a quad Xeon for an office machine is an idiot. It doesn't matter is something is faster or slower, as long as it's fast enough.

To use a car metaphor (that most people seem to understand), not everyone needs or wants to drive a Lamborghini. It's expensive, it's hard to park, it's hard to drive, it's cramped and it drinks like a fish. Most people are better off with a "normal" car, that's fast enough and powerful enough for them, is easy to drive, and has room for the kids and the dog.

Having said that, if you spot someone selling a metallic-gray Lamborghini Diablo Roadster (convertible) for less than 15K, let me know, will you?

RMN
~~~

Re:Reality check

[EelBait]

Anyone buying a Mac for raw number-crunching is an idiot, just as anyone using Windows for a firewall or a quad Xeon for an office machine is an idiot.

Don't tell that to all the folks in the scientific and bio fields doing number crunching on G4s.

Ignorance is no excuse.

[pastafazou]

That's a wonderful list you have there. It's full of machines that cost hundreds of thousands and even millions of dollars. Does Apple produce a high end server like that? No. So the fact that Apple isn't on that list means nothing. You might also want to take a closer look at the list. See number twelve, held by IBM? That's a Power3 cluster. The Power3 is IBM's version of the G3. Look a little further down now. See number 19, IBM's ACSI Blue-Pacific? It's using the 604e processor. That's the processor Apple DISCONTINUED 6 YEARS AGO when they released the G3!!!!! Now if you want to learn just a little bit about powerful Apple processors, try EP2 Cluster [ist.utl.pt] or Bio-IT News [bio-itworld.com]. Maybe in the future a bit of knowledge before you open your mouth might be prudent.

Re:Let's see some FAB speed scores (specs here)

[dbrutus]

Since this chip hasn't seen the light of day, comparing on the best available basis is just foolish, wouldn't you say?

Since this is a 64 bit chip though, wouldn't the proper comparison be with the 64 bit Itanium series?

Re:Let's see some FAB speed scores

[Monokeros]

OK, Everyone who wants to understand which processor is fastest should really take a course on processors. Here's the (condensed) deal with the MHz myth:

All other things being equal, faster clock frequency = faster processor. The trick is in the magic words "all other things being equal". If I have a 1 GHz G4 and overclock it to 1.8GHz it will be faster. That's because the processor is using the exact same process but all the steps in the process suddenly take less time.

The problem is that no two processor designs are the same. RISC vs CISC isn't even the only consideration. There are cache sizes/locations, number of pipeline stages, number of pipelines, processor component layout, all kinds of crap. And thats just IN the processor. Motherboard designs don't even enter into my discussion.

PPC and x86 are very different, as well you know if you are a nerd (if you aren't then what are you doing here anyway?). But even processors that run the same instruction set are different enough that clock frequency doesn't necessarily dictate relative processing speed. This is why if you went to tom's hardware when the P4's first came out and looked at the benchmarks, initial P4's were rated as slower than P3's which were running at a SLOWER clock frequency. And I don't think I have to tell you about AMD vs. Intel processors at equal clock speeds.

The point is that clock frequency is a number that represents something that is actually going on inside your processor. It doesn't always accurately represent speeds relative to other processors, but its a pretty good heuristic when used wisely. If you're comparing the speed of different P4's you wouldn't be in error if you said "I want a 2.6GHz P4 because its faster than a 2.2GHz P4". However, you probably would be in error if you said "I want a 2.6GHz P4 because its faster than a 2.5GHz Power5".

Re:Let's see some FAB speed scores

[UnknownSoldier]

Once upon a time, Monokeros doth spoketh
> Here's the (condensed) deal with the MHz myth:

[ long explaination snipped... ]

I like my description better ...;-0

MHz is like RPM. Pretend you have 2 engines pulling a heavy load. One is at a high RPM, but with a few cylinders (Pentium 4), and the other at low RPM, but lots of cylinders (Athlon XP). Both can pull the load effectively the same, but watch out when the one with more cylinders gets its RPM up.

It's not completely accurate, but then again, its an anology to illustrate the point.

Cheers

So Sad...

[pardasaniman]

That is pretty pathetic considering my cordless phone goes faster!! --Mickey Mouse Microsoft Geek

US wireless phones better

[GunFodder]

We run GSM at 1900Mhz! Take that eurotrash!

?!?!?!1

[Spazntwich]

I wonder how they managed to up the clock so dramatically? Is it just SOI and other techniques, or did they lengthen the pipeline significantly.

If it's just a pipeline lengthening scheme, well, meh, but if they kept the same execution pipeline and are now at 2.5ghz operating range, they're going to kick some ass.

Easy

[sydlexic]

I wonder how they managed to up the clock so dramatically?

Xeon + hobby paint.

Re:Easy

[Tumbleweed]

Xeon + hobby paint.

No way, man, VTEC stickers! :)

Re:?!?!?!1

[addaon]

This is the same 970 as before. No lengthened pipeline, although the 970 has a relatively long pipeline to begin with. And they probably hit 2.5ghz by selective testing... I haven't seen suggestions they can manufacture these chips in quantity yet. Keep in mind that Intel demos ~5GHz chips every few months or so. Even so, it's promising that the design seems to scale up that far without issues and without needing a process change.

No

[Galahad2]

The 2.5GHz number isn't the same as Intel talking about 5GHz P4s. IBM means that they're going to sell 2.5GHz Blade servers. The reason that Intel talks about their insane GHz processors is to impress consumers into buying Intel. People in the market for mid-range Blade servers couldn't care less about what IBM can do in one in a million chips, and they would likely be annoyed if IBM misrepresented it in that way. If IBM can't manufacture the chips in quantity (I'm not aware if they're manufacturing any 970's in mass yet), they will be able to shortly, certanly before the release of the chip.

Re:?!?!?!1

[binaryDigit]

Funny that you ask. The fact is that it doesn't matter. Remember the so called "mhz myth" well it definitely exists from a marketing standpoint. IBM could have cranked up the clock rate and achieved 0% performance increase and it wouldn't matter to most people. They just say "oh, Apple has a 2.5ghz processor, that's better than 1.8ghz, oooh, aaaah". This is the same battle that AMD fights. They are spending big bucks trying to remind people that just because that P4 is running at 3ghz, it doesn't mean that it is THAT much faster than a 2.2ghz Athlon.

Re:?!?!?!1

[dbrutus]

I can't understand why so many insist on comparing Intel's 32 bit solutions to this chip which is a 64 bit solution. Intel ships a 64 bit solution too and I think that's the proper comparison.

Then again the max shipping speed on the Itanium 2 (Intel's fastest 64 bit chip) is 1Ghz.

I think the days of selling computers based on Mhz just drew to a close.

From the Specs...

[aSiTiC]

From reading the specs it says:

9 Fetch, Decode Stages
5-13 OoO Execute Stages
2-3 Dispatch, Commit

So at total of 16-25 pipelined stages. I also notice that the longest(25) is for the Alti-Vec engine. This is very comparable to Pentium 4 which has 26 pipelined stages, although Pentium 4 does not have a vector engine.

x86 does have vector support

[AHumbleOpinion]

...although Pentium 4 does not have a vector engine.

http://www.intel.com/home/desktop/pentium4/faq.h tm ?iid=ipp_dlc_procp4p+prod_faq&#micro5

Q: What is Streaming SIMD Extensions 2?

A: Streaming SIMD Extensions 2 extends Intel® MMX(TM) Media-enhanced technology and the Streaming SIMD Extensions. Single Instruction Multiple Data (SIMD) allows a single instruction, such as addition or subtraction, to operate on more than one data set concurrently. The 144 new cache and memory management instructions enhance performance to accelerate the most-demanding Internet and computing applications. SIMD double-precision floating point accelerates demanding content creation, 3D rendering, financial calculations and scientific applications. In addition, 64-bit MMX technology (SIMD integer) instructions have been enhanced and extended to 128-bits, accelerating video, speech, encryption, imaging and photo processing.

Re:x86 does have vector support

[Dominic_Mazzoni]

Yeah you're right I didn't account for MMX and SSE.

However there is little comparison.

Alti-Vec
# 32 separate Registers
# 128 bits per register
# No interference with FP registers
# no context or mode switching
# max throughput: 8 Flops / cycle

MMX/SSE
# 8 MMX registers shared with the FPU, 8 for SSE
# 64 bits per mmx register, 128 bits per xmm register
# MMX stalls the FP registers
# context switching required for MMX
# max throughput: 2 Flops / cycle

When you are playing a 3D game do you really want your FPU stalled for vector calculations?


To be fair, you could program your 3D game to do all FPU calculations in SSE. gcc has an option to do this automatically now. And SSE2 is one step ahead of AltiVec in one regard - it supports a few double-precision operations.

But aside from those two nitpicks, I agree completely. I've hand-optimized code for both Pentium/SSE and G4/AltiVec and there's no comparison: SSE provides a small performance boost for a lot of work, while AltiVec provides a large performance boost for a little bit of work. AltiVec has very fancy shift, rotate, and shuffle instructions that are completely lacking in SSE. These are useful for more than just RC5 - they're totally necessary to vectorize many more complicated algorithms without the overhead of putting the data in the right place eating up any potential speed gains.

That's why the 970 in a Mac will easily beat the P4 in a number of tests: Apple has optimized hundreds of system calls to use AltiVec already, so many programs get the speed gain automatically.

From what i understand...

[martissimo]

They shrunk the size of the gates on the transistors, basically trading reliability for performance. Considering that one of the main selling points of Apples is their longevity and ability to hold value due to it, I can't help but wondering if this is the right move.

Apparently, in order to increase the reliability of the Power4 for the high-end server market, IBM used much thicker gate oxides on the chip's transistors. The trade-off for this decreased failure rate and improved reliability was that the Power4's transistors have slower switching speeds, so even with process shrinks it's harder to push the design to higher clock speeds. Since the 970 is made for the desktop market, there's no need for such measures and therefore the new chip's clock speed will scale much higher than the Power4's. In sum, the 970 is made to be faster, cheaper, and significantly less reliable than the Power4. (Of course, when I say "significantly less reliable than the Power4," you have to understand that this puts the 970's product life and failure rate on par with other mainstream CPUs, since the Power4's increased gate oxide thickness makes it significantly more reliable than most mainstream CPUs.)

ArsTechnica overview [arstechnica.com]

It's a given that Apple enthusiasts will be happy as can be once they fire up a brand new powerfull box, the question is how they will feel when they find out it has the lifespan of a typical Intel or AMD CPU.

Re:From what i understand...

[Shuh]

They shrunk the size of the gates on the transistors, basically trading reliability for performance. Considering that one of the main selling points of Apples is their longevity and ability to hold value due to it, I can't help but wondering if this is the right move.

As reliable as Apples are, they are still pretty much consumer and light server iron with consumer-grade reliability. All they are doing to the 970 is scaling back from industrial server-farm $30,000 workstation reliability to normal consumer-reliability... right where Apple has always been.

Re:From what i understand...

[Theaetetus]

They shrunk the size of the gates on the transistors, basically trading reliability for performance. Considering that one of the main selling points of Apples is their longevity and ability to hold value due to it, I can't help but wondering if this is the right move.

Agree and disagree - reliability on my Mac is a wonderful thing, and I love showing my uptime reports to my PC friends.
However, I do occasionally turn it off - and I'm actually pretty good about turning it off regularly, like every 5-6 days.

This is a far cry from a server environment - we have several servers at work that we reboot once every 3 months or so, as a precautionary measure, figuring they could probably go twice that without a reboot, but we can't have an unscheduled downtime (we're a 24/7 radio group). While I believe, under OS X, that my Mac might be able to make that length of time (hell, probably could easily), I'd never try. No need.

So, if they can crank the speed and reduce continuous uptime to 3 months or so at a stretch, I really wouldn't mind terribly, and I don't think many desktop users would even notice... and don't forget this is a 'desktop' CPU rather than a server CPU.

-T

Re:?!?!?!1

[commodoresloat]

I wonder how they managed to up the clock so dramatically?

Easy. They updated to OS X 10.2.4

Oh, I thought you asked "I wonder how they managed to fuck up the clock so dramatically? "

Motherboards ready for 2.5MHz?

[occam]

I just hope Apple has their motherboards ready for 2.5GHz. The original spec of 1.8GHz with 6+GB bus was a little heady compared to Apple's current technology (no thanks to Motorola). I'm hoping they know how to build motherboards with the best of them to take advantage of IBM's new 970 chip. Pushing the envelope from 1.8GHz to 2.5GHz just makes the whole motherboard engineering issue more challenging. Let's hope Apple hardware design it up to the task (and then some).

Re:Motherboards ready for 2.5MHz?

[addaon]

What's more interesting is that the frontside bus of the 970 was designed to scale with processor speed. So the 1.8GHz was supposed to have a 900MHz (well, presumably 225MHz quad-pumped) FSB, using a multiplier of 2. The 2.5GHz, then, has two options... either drop down a notch to use a multiplier of 3 (getting an 833MHz FSB, which is manageable)... or go full-hog and hit a 1.25GHz FSB. While I suspect that for the 2.5GHz chip the answer is, unfortunately, the former, the question is a bit hazier in the case of a 2GHz part... 1GHz is manageable but impressive, whereaz 666MHz simply isn't enough. Of course, they can allow non-simple multipliers and solve the issue, but I do recall that they were planning on supporting only integral multipliers.

Re:Motherboards ready for 2.5MHz?

[mduell]

Except multipliers are based off the true FSB and not the effective bandwidth FSB (only bandwidth changes with DDR and QDR, latency remains the same). So a 1.8Ghz part on 450 DDR FSB would be a 4x multiplier, and on 225 QDR FSB it would be 8x. Still better than Intels 20+ multipliers on some of their chips...

Re:Motherboards ready for 2.5MHz?

[addaon]

Eh, us mac users have lived with a slow bus too long to not want a fast one... because it might not be improved significantly for another four years! But yes, you're correct about the multiplier math. I just seem to remember hearing someone from IBM refer to the 1.8GHz part as having a 2x multiplier, and saying the 1.4GHz would have the same multiplier for a 700MHz (175MHz) bus... and I got the impression, quite possibly incorrectly, that the phrase 'simple multiplier' (they didn't say integer multiplier, note) meant a multiple of four, pre-quad-pumping. But again, all I'm going on here is vague phrases and the fact that the 1.4GHz and 1.8GHz parts had such different bus speeds (which makes upgrading even more fun, come to think of it).

-1, Troll

[addaon]

Pudge, I really appreciate that you read Macslash, and copy there stories here so I don't need to type in a second address. Do you think you could convince some of the editors to read some of the other slashcode sites? Slashdot would be a good start.

Re:-1, Troll

[kuwan]

I actually posted the story to Slashdot first, then MacSlash later, but MacSlash was faster at putting it up. Probably because they don't get as many story submissions as Slashdot.

Kuwan
--
Get HyperSpell [kuwan.net] for OS X - Instant access to OS X's built-in spellchecker.

drool ...imagine dual pro Macs :)

[codeonezero]

Ok, this is great news. I hope Apple decides to use this chip. I could just see dual ppc 970 Power Macs running at 2.5Ghz x 2 :) Why stop there maybe they'll go quad, and that would be awesome :)

I just hope apple doesnt go back to using single chip on their high end systems...its ok if they do use one chip for say the iMac, *book line but the Power Macs should stay with dual if they end up using this chip.

Oh and the obligatory, karma whoring

"Imagine a Beowulf of these!!!!"

When Used....

[johny_qst]

Does this chip match the power consumption and low heat dissipation that we have all come to know and love from the PPC arch? Does anyone know?

Re:When Used....

[Tar-Palantir]

Power consumption is good, according to a recent MacAddict article. It mentioned that the 1.8GHz chip had low enough consumption to be put in a laptop. Drool....

More Information

[robbyjo]

Here [ibm.com] you can find a more technical details than just press release.

Here [ibm.com] is the actual spec about the PowerPC 970.

Ars Technica [arstechnica.com] articles. Apparently, PPC 970 just last year's news. The real news is just the cranked-up speed...

Re:More Information

[Anonymous Coward]

One of the most interesting bits of information from the above IBM pages: In addition to its support of new 64-bit solutions, the 970 retains full native support for 32-bit applications. This not only protects 32-bit software investments, but provides these 32-bit applications with the same high-performance levels that it extends to 64-bit uses. This native, nonemulated, 32-bit support is not limited to application code, which runs unmodified. 32-bit operating systems with minor updates can also take advantage of the PowerPC 970's outstanding performance.

Digital Lifestyle

[anaesthetica]

"It is ideal for very computing intensive applications, for example in the area of simulation like meterology or geological calculations."

Along with the rollout of the 970 chip, Apple will introduce two new insanely great iLife Apps: iWeather and iEarth. Now you can calculate weather patterns in your neighborhood and export the results to iMovie! Also, use iEarth's predictive powers in landscaping your front yard, planning your garden, and preventing cracks in your house's foundation.

Perfect for your digital lifestyle.

Eat that Miscrosoft!

Re:Digital Lifestyle

[questionlp]

Okay... I've got karma to burn...

Microsoft, after several delays, releases Hailstorm XP and Terra XP for their latest operating system, Longhorn. The release announcement was done with Steve Ballmer running around the stage at TechEd 2004 screaming, "Call me daddy! I own the Earth!" Later, Bill Gates corrects Ballmer by saying, "Sorry Steve, I own the Earth!" Reports have been coming in that Scott McNealy of Sun, Larry Ellison of Oracle, and Richard Stallman of FSF all huddled up and crying.

Unfortunately, shortly thereafter, Earth blue-screened and permanently enabled copy-protection on every living person until each person forks over their soul along with $5000 per year for life support.

BSOD

[Ospeovedizer]

Unfortunately, shortly thereafter, Earth blue-screened

Arrgh! The dreaded Blue Sky Of Death! Microsoft has already hit!

If Apple uses this, it will just be the same prob.

[Quarters]

2.5GHz now is interesting. 2.5GHz in 12-18 months if/when Apple gets them into actual production hardware will not be that interesting. By that time we'll probably see >= 4GHz Intel and AMD chips. Apple needs 2.5GHz machines *now*.

Re:If Apple uses this, it will just be the same pr

[cbuskirk]

The following is a simplistic view of things, but we are talking about a 64bit processor. Remember the Itaniums Intel is selling are running at around 1GHz - 1.5GHz I believe and they run circles around the 3Ghz P4.

Re:If Apple uses this, it will just be the same pr

[JCholewa]

> The following is a simplistic view of things, but we are talking
> about a 64bit processor. Remember the Itaniums Intel is selling
> are running at around 1GHz - 1.5GHz I believe and they run
> circles around the 3Ghz P4.

That's overgeneralized. The 3GHz P4 is very much faster at most tasks than the 1.0GHz Itanium II, which is the fastest instance of the chip that has been given entries at spec.org. The reason why the Itanium II appears much faster is that you only see benchmarks that relate to its very narrow field of marketing. It's a server processor. You won't see it tested in areas more suited to general purpose computing (games, office suites, etcetera). And, hell, the Itanium sucks in specint, one half of the single processor version of the most prolific server benchmark suite in the world. The 900MHz (fastest speed submitted -- for some reason, they only gave specfp scores for 1000MHz, unless I missed an entry or few) Itanium II gets 674, compared to scores above 1100 for the 3.06GHz P4. That's a whopping 63% difference! The fastest Itanium II is almost 40% slower than the top of the line non-Xeon Pentium 4!

The Itanium II does fantastically in specfp -- bested, I believe, only by the DEC Alpha, which is sadly being pushed under the carpet for reasons more political than I'd like (Alpha IP is owned by HP and Intel, the companies that created the Itanium's core architecture) -- and many other benchmarks. But you can't simply ascribe a single, simple feature to the performance advantages of the processor. Yeah, the processor can address a 64-bit memory space and, yeah, the processor has 64-bit GP registers. But you're ignoring many other features piled on top. Itanium II is a server processor, so it can afford to have some extra doodads added to it, doodads that would be considered financially unfeasible on mainstream processors.

Hmmm, I did a quick google search, so I apologize if I pulled incorrect info on the following:

The Itanium II has a more than a megabyte and a half of cache memory on the die of the processor. It seems to optionally go up to 3MB on-die L3 cache. In comparison, the Pentium 4 has 512KB cache (there's some more cache, the L1, but that's inclusive), and the Athlon XP has either 384KB or 640KB cache (depending on whether you're counting the older Thoroughbred or the newer Barton). So the Itanium gets about three times as much cache memory on the processor die!

Itanium II has a 400MHz, 128-bit data path to the chipset. Pentium 4 is 533MHz, 64-bit. So the P4 gets a chipset that can send it 4.27 GB per second while the Itanium II gets a chipset sending it data at 6.4GB/s.

The Itanium II has more functional/execution units. The Itanium II gets predication, which is a very expensive (in terms of how much bulk it adds to the die) feature that effectively gets rid of a lot of the penalty associated with branch misprediction (a problem which is rather huge with the trillion-stage netburst microarchitecture of the Pentium 4, though I'm told that the multithreading implementation of the P4 can help alleviate some of that).

The number of bits in the processor don't matter *that* much, not after the 32-bit level. Yeah, it helps, but you have to take the whole package into account. A 64-bit scalar one-stage processor with a ten-byte, off-die cache would get its ass kicked mercilessly by an 80486DX-50.

To take another tack: I'm somewhat interested in possibly purchasing an Athlon 64 late this year or early next year. But if the Athlon 64 was just an Athlon with 64-bit extensions, I wouldn't give it the time of day. I'm interested because the Athlon 64 will have an on-die memory controller. I'm interested because the Athlon 64 will support twice as many registers as a typical x86 chip (which may decrease the need for cache accesses, which could increase performance on my recompiled linux apps). Either of these two advantages promise a far greater advantage for me than the simple increase in register size and memory addressability.

-JC

You assume too much about PC speed

[xtal]

By that time we'll probably see >= 4GHz Intel and AMD chips

You know what, a year ago I would have agreed with you but now I'm not so sure. The prices for the top end chips are very high. I'm not so sure that AMD and Intel are currently going to continue their breakneck R&D budgets into the next year. I suspect you will see a dip or a flat spot in the new PC tech for the next 12 months to let them recoup some of the bazillions that have been invested into fabs and development. In that time frame prices will drop on the higher speeds - but the introduction of even faster chips will slow until new architectures become viable/microsoft gets their head out of their ass. Wouldn't it be ironic if Intel got screwed because Microsoft couldn't get Windows XP stable on a new architecture? The reverse situtation happening to apple, now?

PC speed has become less important .. less important to me than my video card. I have a PC at home pretty much just for gaming, and that's the only upgrade I've done since DDR memory and motherboards were available - a long time ago. I don't think Apple is in any trouble, so long as this chip makes it out the door by this time next year.

*shrug* I have a Apple Powerbook 1Ghz that I use for everything except games. It's fine, zippy, etc. Games I use my PC for. I don't know of any hardcore apple gamers. Apple's focus on notebooks is partially because of this - their powermacs are suffering, but there isn't anything they can do about that right now. In much the same vein, I have a openBSD box, two linux boxes, and a QNX box all running 3-4 year old motherboards and processors fine.

I don't think Apple needs to get involved. The extra time spent making their software better NOW will make it even faster when the new machines come out.

Pick the right tool for the job, duh. Mac isn't the right tool for a FPS or flight sim game monster. It kicks some serious ass as a unixy workstation-to-go, though. Their developer tools are excellent, and free. etcetcetc.

Re:If Apple uses this, it will just be the same pr

[scotch]

A 50% speedup is considered very good

I don't know what you mean by 50% (like, compared to what?), but some applications definitely benefit from SMP. 2 1GHz chips will perform almost as well as 1 2GHz chip for some of these things. In that case, I would say the (unacheivable ideal) for 2-way SMP is 50% speed-up. Time goes from 2 minutes to (just over) 1 minute, for example. Of course, going from 1Ghz to 2Ghz chip for the same application will probably give you somewhat less than a 50% speed up. Hence my confustion at your comment.

I find desktop SMP systems nice not only for the parallel apps I run, but also because the general responsiveness of the system seems to be better on average under load.

I haven't done rendering in a while, but SMP systems seem like they would help there. They definitely help in compiling, in my experience. Don't know about games.

YMMV

Hopefully

[cosmo7]

~Perhaps this will lead to some sort of debate regarding the virtues of Macs compared with PCs, something so rarely discussed on SlashDot.

you gotta wonder...

[Petrox]

how many people have been holding off (or switching to other platforms) on a new Apple computer purchase for these new chips. I'm sure Apple is chomping at the bit waiting for these chips to be mass produced so that they can get them into Powermacs (and hopefully Powerbooks too), like, yesterday.

The POWERLite series (which is basically what the 970 is) is a great alternative to x86 for Apple for quite a few years ahead. Not only does IBM have an incentive to keep producing these chips at ever-greater clock speeds (something that Motorola with the G4 doesn't seem to have a great deal of interest in doing) because IBM actually uses these in their Blade servers, but it sets up a nice roadmap for successive generations of chips (the POWER5 is just around the corner, with a Power5Lite a la PowerPC 980 coming shortly thereafter? Such a chip is probably only a year and a half off and, running MacOSX, would rocksock).

Yum.

Re:you gotta wonder...

[BWJones]

how many people have been holding off (or switching to other platforms) on a new Apple computer purchase for these new chips. I'm sure Apple is chomping at the bit waiting for these chips to be mass produced so that they can get them into Powermacs (and hopefully Powerbooks too), like, yesterday.

Well, for scientific users the debate about which platform to use has *significantly* been mitigated by the presence of a true UNIX with OS X allowing for the easy porting and running of code already written for other *nix distros. I personally have replaced three machines including an older Mac, a Windows box and an SGI with a single dual G4 with a sweet Cinema Display.

Now, could I use more power? Absolutely. Code that is optimized for Altivec is screaming fast. Faster than just about any other platform I have used in fact. However, code not optimized for Altivec gets whomped on by the Wintel platform right now and I would like to see some of the delta in performance go away.

All of that said, OS X is one impressive OS. The best OS out there for the general audience and for a number of specialized audiences as well. It can only get better and is awaiting fast CPU's with fast bus speeds.

I suppose it also might be argued that OS X has matured faster as a result of the lagging performance of the G4 chips in that Apple has had to optimize lots of code to get things running fast, whereas Microsoft tends to rely on fast boxes to get through code bloat. Just look at Safari vs. IE as an example of this.

Re:you gotta wonder...

[g4dget]

Well, for scientific users the debate about which platform to use has *significantly* been mitigated by the presence of a true UNIX with OS X allowing for the easy porting and running of code already written for other *nix distros.

While UNIX compatibility in OS X is great, calling it a "true UNIX" is really rather misleading. First of all, the kernel isn't a UNIX kernel, it's a hacked Mach kernel with a BSD compatibility layer. Furthermore, there are very significant differences in userland, including things like a case-insensitive file system, huge changes in system administration, lack of device nodes for things like audio and video, multiple views of the file system (from Carbon/UNIX), etc. Also, the standard UNIX window system, X11, is at best bolted onto OS X.

Now, you may think all these things are improvements to UNIX, and you might be right. However, they make OS X pretty significantly different from UNIX. And while some applications port with no problems to OS X, others require incorporating Cocoa or Carbon code for porting, which can be a lot of effort.

The constantly moving fencepost horizon

[babbage]

I'm on my third Mac now, and every time I've bought one, I buy used -- they're half the price of a new one (granted, a used PC would tend to be 10% the price of a new one...) but they're still pretty damned good computers. I'm not ready to plunk down for a new one though until the much prophesied next generation machines come along. Articles like this make it sound like it could be just a year off (which is about what I heard a year ago, and a year before that...). Now you're saying that a two generation jump should be available in 18 months? Hell, that's just another disincentive for me to go out & buy a Mac.

To my half thought-through way of seeing things, this is a strong argument for coming up with a product roadmap, even if such things are half-truths in the end. Apple is so secretive about everything that it's impossible to know if something like this -- or something else entirely! -- is going to come out in a month or a year or ever, and consumers like me are perfectly willing to wait. And wait. And apparently, wait indefinitely. Clearing up some of that uncertainty would certainly make me more eager to buy new gear...

</wibbling>

umm..

[overunderunderdone]

Did you read the press release? I doubt it. You saw "Apple" as the subject of the headline and just half-hazardly clicked the reply button and started a schpiel about how Apple really needed this, etc. If you go and check the press release out, you'll see that only the Blade server architectures are even mentioned.

For anyone who has been paying attention to Apple and IBM and the PowerPC 970 the article didn't NEED to mention Apple. It has been an open and obvoius secret that this chip was developed by IBM specifically for Apple - The presense of Altivec (which is largely useless on a server) is proof enough of that even without the coy public statements (and a few explicit slip-ups despite the standard policy of "we never comment on unannounced products" ).

Yeah, Apple hopes to use this some day, but it'll be a long time coming.

They will be using it the moment IBM can produce them in sufficient quantites.

Someone resection this to strictly IBM rather than an Apple > IBM article.

Despite the article itself having nothing to do with Apple it IS of interest to Apple users because it reveals that the chip everyone knows will replace the G4 is reaching speeds up to 2.5 GHz when it had previously been reported to be between 1.4 - 1.8 GHz.

PC == Personal Computer || Wintel architecture?

[Anonymous Coward]

if (PC == "Personal Computer")
printf("Why do we say Mac vs PC?\n");
else if (PC == "Wintel architecture")
printf("Why confuse people with something called 'PowerPC'?\n");
else
printf("WTF?");

Comment removed

[account_deleted]

Comment removed based on user account deletion

AltiVec confirmed

[obi]

Interesting: this PR release seems to confirm the planned extensions are in fact, Altivec. I haven't followed it too closely, but I thought this wasn't confirmed yet.

Guess that makes it clear this is Apple's next chip.

misinformation

[Anonymous Coward]

Here's some:

- The new chip has a 54 stage pipeline, thus making it as effective as a current 700 MHz G4.

- The chip tested eliminated all ability for cache, thus allowing the speedup in clock but making it slower than all current G4s available in Apple computers.

- It is being developed as PowerPC but will be transitioned into x86.

- It will not support multiprocessing and MP applications will have to be done through a hackneyed clustering.

- This chip will help to propel Apple to 20% market share. (I'm a shareholder.)

- When worked hard, the chip gives off an odor vaguely reminiscent of shrimp flavored chips.

- The 970 is slightly faster than a Porsche 944.

Please feel free to add your own misinformation because there's not all that much real information to be discussed, anyway.

Re:misinformation

[joe_bruin]

the 970 achieves 64bit performance by having 4 on-die 16bit 68040 cpu's and doing hardware instruction translation (in realtime) from ppc to 68000.

in a technology leap, this cpu bypasses intel's hyperthreading technology and proceeds directly to 'ludicrous threading'. this technology allows a thread to finish a task before it was even created.

the 970 incorporates hardware acceleration for microsoft's windows media drm technology. Windows Media Player 9 Series(r): If You Struggle It Only Hurts More(tm).

unlike endothermic cpu's commonly manufactured by intel and perfected by amd, the ppc 970 uses exothermic cmos technology. it therefore requires a constant heat source to avoid freezing.

these chips use ibm's patented plutonium-on-silicon manufacturing process, and as such require a license from the nuclear regulatory commission to own.

Implications?

[useruser]

IF Apple happens to be a consumer of these chips, what is IBM likely to charge for them? It really seems that most consumers complaint about Apple computers is the price, given consumers even consider them an option. I can't imagine Apple would take a hit on these to keep PowerMacs at their current prices. And I don't imagine most switchers will really want to pay for speed when they get it for a commodity price in the PC world.

wiggy

[DemiKnute]

Whodathunk that one day we'd be reading a story titled "Apple: ..." with an IBM icon? Maybe I'm getting old, but I think it's kinda cool.

Re:wiggy

[jonbrewer]

Whodathunk that one day we'd be reading a story titled "Apple: ..." with an IBM icon? Maybe I'm getting old, but I think it's kinda cool.

When I pried the heatsink off my brand-new Power Macintosh 7100/66 (um, nine years ago?) I found a gleaming blue plate with IBM in big white letters on top. It's no biggie.

Really we should just come up with one icon for M$ and one for everyone else. (shall we call them the rebel alliance?)

Macs could use the speed

[jmichaelg]

I hired a graphic artist to design a brochure for our product. When we were down to final tweaks, she brought in her Titanium Mac so I could look at the changes as she made them. It was the first time I had seen Illustrator running on OS X on a Titanium. Watching the glacial screen redraws (she had a lot of filters running) made me think that if there ever was a task that would clearly benefit from multiples of more CPU horsepower it was Illustrator drawing complex images. 64 bits at 2.5 Ghz should help a lot.

You have to have the patience of Job to be a graphic designer. That's Job, not Jobs.

Re:Macs could use the speed

[JohnsonWax]

Unfortunately, Illustrator has a problem in that the app double-buffers the display, and OS X automatically double-buffers the display, so you've got a lot of unncessary graphics crap going on. That's a big part of the glacial screen redraws and I don't think that CPU would fix it. The Windows version doesn't suffer from this.

On top of that Illustrator does have some other bug fixes and optimizations to do. Hopefully we'll get a 10.1 version before too long.

I'm sick of you Mac haters

[(1337) God]

You think Apple sucks because they have realised that the traditional MacOS has come to the end of the line and instead of rehashing old rubbish as MS and Intel have been doing, they have gone to great lengths to write a new OS based on highly regarded kernal and system, whereas MS has rehashed NT and, as they usually do, added more and more (mostly unnecessary) features.

You think they suck because they base their computer and OS designs on what their customers want, unlike MS which designs its own ideas and forces them on its customers (HTML email, VBS, ASP and now the new IE5, with it's different rendering of web pages and 96dpi images) because, being the market leader (due to great marketing, not great design), people have no choice.

You think Apple hardware sucks because it uses parts compatible with PC's, despite the fact that Apple hardware components have (for the most part) always been designed by other manufacturers, merely this time they have selected less unique hardware, because this is what their customers wanted and Apple customers are willing to spend extra for this.

You all think Apple sucks because they build computers up to a quality, not down to a price. They suck especially because they took the bold step of designing harware that simple, straightforward and attractive to alot of people (iMac), and in great defiance of the PC market, sells very well. More insulting are the PC owners who discovered their friends' iMacs ran faster.

Oh, and you think Apple sucks most of all because it forces PC owners to realise that they are MS and Intel lemmings - in no control of the chipset's and OS'es they use, as what they do is controlled by both these companies. If it weren't for Apple, AMD and others, everyone, with the exception of companies that can afford expensive un*x workstations, would be complete slaves to MS and Intel.

This is like saying Mercedes Benz sucks because they design innovative cars who's designs influenced car designs for many decades.

Maybe Apple should apologise for shattering people's ideas of what a computer should be.

Join my Slashdot clan! [slashdot.org]

Itanium 2 peaks @ 1 GHz and costs over $3000

[afantee]

Fantastic news for Apple, and trouble for Intel and HP.

For all your Wintel idiots out there who know nothing other than GHz, PPC 970 is a super efficient 64 bit server grade RISC processor with the G4 style Altivec engine, and will blow away your P4, Xeon and Itanium. I home Apple will make a PowerBook with one of these.

According to benchmarks by Intel and HP, the floating point performance of Itanium 2 @ 1 GHz is about 50% faster than P4 @ 3.06 GHz, so clock rate clearly doesn't equal to performance.

In other news, out of 4.5 million servers shipped in 2002, only 3500 were Itanium. In contrast, Apple apparently had already sold approximately 8000 Xserves 6 or 7 months after it was launched in May 2002 - not too shaby for a new product.

MHZ? What about FLOPS?

[silverhalide]

I really wish manufacturers would cut the crap and just give a FLOP rating off of some standard test that could be performed cross-platform. Then they can stop worrying about turning processors into microwave ovens and focus on more efficent silicon techniques. They are starting to run into problems in these high frequencies because on a motherboard, because by the time the signal reaches another side of the board, it has already switched from a 1 back to a 0 or whatever. That's fast.

Apple servers up 370% in Q3 2002

[afantee]

Apple shipped 7484 servers (presumably mainly Xserve) in Q3 2002. In contrast, there were only 3500 Itanium 2 based servers sold in the whole of 2002.

The future looks even better for Apple in the server space, following the recent release of the new Xserve and the Xserve RAID. I can't wait to see an Apple 64 bit PPC 970 blade server to blow the crappy Dell out of the water.

Quoting numbers attributed to Internet World, MacInTouch (Saturday, Jan 12) reports that Apple's share of the server market has more than trebled from 0.2 percent to 0.7 percent (Q3 '01 vs Q3 '02). An equally telling statistic is the fact that approximately 40 percent of growth had taken place by the end of Q2 '02 (ie before Apple's Xserve was released).

In terms of unit sales, Internet World quotes the following for Apple:
? Q3 '01 2,049
? Q2 '02 3,937
? Q3 '02 7,484

Unfortunately, the press release has been removed

[Blondie-Wan]

MacAddict [macaddict.com] and others are reporting that the press release has been removed from IBM's site; clicking the link to it in this story now takes one to a listing of IBM's German press releases. The pr on the 2.5 GHz 970 seems to have been completely removed. Might the announcement have been premature?

Re:Obligatory Questions

[addaon]

Does it run linux?

Yes. Or at least, PowerPC linux works great, and linux is 64-bit clean. I don't know of anyone running linux on a current 64-bit powerpc, but I'm sure it's been done.

How many fps on doom 3

More a function of graphics card than processor these days, no? With any luck PCI-X will be available with these systems. Bandwidth never hurts.

How many keys/s on rc5-72

A surprising number, although presumedly only a linear increase (with clockspeed) over current PowerPC's. Altivec has a number of instructions which are very useful for rc5 (and very useless elsewhere), and the bitwidth of Altivec is, of course, unchanged.

Can i overclock it?

Probably. IBM has been doing so remarkably good clocking design on their consumer chips lately. The 750FX, for instance, used in current iBooks, is software overclockable, takes about 10-30 cycles to change clock speeds, and mine (600MHz on the die) runs at 900MHz stable, although I tend to avoid that for battery life reasons. (Note that os x 10.2 blocks software overclocking by resetting the clockspeed every 1000th of a second or so. Os x 10.1 allows it, and 10.2 can be forced to rather trivially.)

How hot is it?

Not very. Don't have numbers off hand, but I believe the 1.8GHz numbers were at least comparable with current 1.3Ghz G4 numbers... 30-40 watts or so.

Re:Obligatory Questions

[rindeee]

If by "current 64bit PowerPC" you would qualify a Power4, (or Power4+ if you're lucky enough) then yet, many people run Linux on a 64bit PPC. Most of the pSeries line from IBM will run the SuSE and RedHat distros specific to this line and Debian will runs nicely as well.

Re:Obligatory Questions

[addaon]

It's really not hard. I don't have anything formal written up, but just read the IBM docs on the 750FX. Basically, you initialize a register with the multiplier you want, wait a few cycles for the PLL to lock, and then send an instruction which switches the machine from one PLL to the other (there are two). You can then reverse the process. One PLL is initialized from hardware to the speed of your computer, but they're both settable. If you disable clockspeed switching on moving to battery (which does it's own thing, of course), all you need to do under 10.2 is disable the kernel's resetting of the clock. Just grep for the opcode to write the appropriate register in the kernel; if my memory is correct, it occurs twice in the kernel, never figured out what the first one did... may just set the second PLL for battery-removal clocking later on. In any case, no-oping out both of those occurances causes no problems at all, that I've noticed. Of course, every update that changes the kernel (10.2.4 being the latest) requires you to redo this, but it's about one minute with grep and a hex editor. That should be enough to get you going... took me about four hours, and I didn't even know PPC machine code when I started.

Re:Obligatory Questions

[cpeterso]

10 LET MEGAHERTZ = 600
20 MEGAHERTZ = MEGAHERTZ + 1
30 GOTO 20

Explanation

[TWX_the_Linux_Zealot]

"First of all, what is the processor that Apple using now? Isn't it some sort of PowerPC already? I see this one supports Altivec and I know that G3 and G4 Apple computers have the same instruction sets. Is this just another implementation, or is G3 and G4 relatives of this new processor?"

Apple does currently use a PowerPC processor in their computers. They have for the past eight years or so. Currently they're using the "750" edition, a'la G3 and G4, which are supplied by both IBM and Motorola.

"Second: what operating system does the IBM PowerPC run?"

The IBM machines with these series of microprocessors are things like the later generation AS/400s and RS/6000's. There are also some workstation machines (both badged as such and badged differently) with IBM PowerPCs in them. AS/400s use OS/400. RS/6000s can run many different OSes, including Linux and AIX.

"I suspect that the article is just confusing and processor itself is not made by IBM. Right??"

Wrong, at least on who makes the microprocessor. Motorola hasn't been doing so well lately, and even early on they had to deal with IBM to meet quota. IBM's hand in the PowerPC line is visible in Macintosh 5200's, which were common schoolroom computers that are starting to be end-of-lifed. They're dating back to August 1996 or so.

Re:please explain

[MikeMo]

The 970 has the same instruction set (99%) as the G4, but it also has a very, very different internal architecture that should make it quite a bit faster than the G4 at the same clock rate. It's actually a scaled-down version of the Power4 chip, the CPU in a lot of IBM's much larger systems. The Power family is the root of the PowerPC chip, which was actually created by IBM/Apple/Motorola to simply use the same instruction set.

The IBM Power4 runs many of IBM's OS's.

Re:please explain

[binaryDigit]

First of all, what is the processor that Apple using now? Isn't it some sort of PowerPC already? I see this one supports Altivec and I know that G3 and G4 Apple computers have the same instruction sets. Is this just another implementation, or is G3 and G4 relatives of this new processor?

Apple currently uses the G4 and G3 family. The G4 has AltiVec, G3 does not. G4/G3 are product names, whereas 970 are more like model numbers. There all related in that they implement the PowerPC ISA (Instruction Set Archetecture).

Second: what operating system does the IBM PowerPC run?

Depends on who is selling the machine the chip is in. Apple sells OS9 and OSX. IBM has AIX. And of course there's Linux and BSD. These are the most common.

I suspect that the article is just confusing and processor itself is not made by IBM. Right??

Nope, IBM does manufacture the 970. IBM also makes G3's. AFAIK Motorola is the only one making G4's right now (could be wrong here, could be that IBM is cranking some G4's as well). Also note that both Motorola and IBM sell other variations of the PowerPC (most well known is the PPC that powers the Nintendo GameCube).

Re:please explain

[Uller-RM]

PowerPC is an open architecture; several companies make different CPUs based on the design. IBM's historically made them for servers (the 970 was originally intended to be a server chip) while Motorola made them for desktops (Apple). Only problem is, Motorola sucks -- and their growth in the wireless business has gotten them to the point where they don't need Apple's business any more, so they have no real reason to improve their CPU line.

The G3 and G4 are also PowerPC chips -- they just are specific models made by Motorola. It's half new implementation, half relative.

Finally, a CPU doesn't run any specific OS -- OSes just have to be written for that CPU (and more generally, for the system architecture that CPU uses). Linux has supported the PPC for a long time; there's a distro called Yellow Dog that specifically targets Macs, and does a good job of it. Mac OS X's kernel, Darwin, has been backported to Intel IA-32. Windows used to be available for Alpha processors. It's just a matter of coding and hardware knowledge.

Re:please explain

[TheRaven64]

First of all, what is the processor that Apple using now? Isn't it some sort of PowerPC already?

G3 and G4 are Apple marketing terms for current PPC chips, made by IBM or Motorola (the G3s in the iBooks are made by IBM). The only real difference between the two is that the ones with a G4 sticker on it supports AltiVec and SMP (I'm simplifying here for the sake of brevity, before I get flamed). Both are 32-bit chips.

The 970 will probably be called a G5 by Apple (although they may drop the G_ naming convention and call it a PPC64 or something) and is a 64-bit PPC chip based on IBM's Power4 series, with AlriVec tacked on. Power4 is a PPC-derived architecture, specifically designed to run in high-end UNIX servers, where x86 just doesn't cut it. With the 970 IBM are trying to move this technology to the desktop.

Second: what operating system does the IBM PowerPC run?

It will run any OS that runs on current PPC chips (PPC Linux and OS X, for example), although it will probably require OS modifications to take advantage of the 64-bit features of this chip.

I suspect that the article is just confusing and processor itself is not made by IBM. Right??

The chip indeed is made by IBM, as are the G3s in the current iBook range (as I recall Motorola G3s top out at <600MHz, while IBM make them up to 1GHz). Apple is expected to be one of the largest customers for these chips, hence their mention.

Re:please explain

[TheCrazyFinn]

The G3 (PPC750) is a development of the PowerPC 603. It's got superb integer performance, decent FP, no Altivec and extremely low power draw.

The G4 (PPC74x0) is a development of the PowerPC601 and 604. Integer Performance is about the same as the 750, but it has a much faster FPU and Altivec. Moderate power draw and a much more powerful CPU overall.

There are more differences between the PPC750 family and the PPC74x0 Family than just Altivec, although that's the most notable difference.

All of these CPU's are descendants of the Power CPU line. Theoretically Mac OS X could run on teh Power4 with some minor work. Now that would make a killer system, at the expense of cost (A single Power4 CPU package, with multiple cores, costs as much as a PowerMac.)

Re:Help

[presearch]

Although an 8600/300 speed comparison might be
interesting from a historical perspective, it's not
that relevant these days as a benchmark point.
A dual G4 running OS X is a whole 'nuther animal.

Re:Help

[TheRaven64]

Didn't you post this to the last article that mentioned Apple? If you hate your Mac so much, why is it still on your desk? And why do you keep copying this 19MB file around anyway? Your disk must be getting pretty full of copies of the same file by now...

Re:Help

[jo_ham]

That's funny, we had a 9600/300 working as a professional non-linear edit suite, producing programs for TV and video handling multi-gigabyte files and full frame video with no problems.

Your Mac is broken.

Re:So what about the old rumor about IBM chips in.

[pressman]

IIRC. this is the new-fangled Power4 stripped down for use in desktops. It is a 32bit chip with full backward compatibility with 32-bit applications.

Typically Apple would release a machine with this kind of new technology at a big tradeshow like Seybold or something since it is aimed at the more professional user. So, labor day weekend might be when we'll see this baby hit the market. Maybe even Macworld Boston, but that would more likely produce speed-bumped iMacs and iBooks, possibly a Powerbook speedbump too.

Re:So what about the old rumor about IBM chips in.

[aulendil]

...That and it does not fully implement the PPC instruction set...

Well, that's the RISC you run...

Re:May Apple ISNT dead???

[Anonvmous Coward]

"2.5 GHz PPC sure would close the gap with x86."

Yeah!! I can't wait to see my Quake 3 scores then! Damn I want a new game. :(

Re:PowerPC, IBM, and DRM

[binaryDigit]

How much does IBM use PowerPC in its own servers, whether they by AIX or Linux, or do they mostly install them on Intel servers?

"Install them on Intel servers?" I think you're a bit confused here. The PowerPC chips are used instead of Intel chips, not WITH them. At any rate, IBM only uses the PowerPC on their low end. They use PowerIII, RS64, Power4 on their mid-high end stuff. The announcment was about their blade server, blade servers typically use lower end processors that don't run as hot because of the dense packaging.

Is PowerPC going to implement Palladium and DRM

Typically the only thing that a processor lends to the DRM equation is a unique serial number. I don't know if they support it or not. Wouldn't surprise me however if they did as this scheme is very popular on higher end systems to do software licensing.

If so, then this is good. If all computers become hard-wired with DRM as well as Windows, then I could conceivably still assemble my own system with commodity hardware, a PowerPC chip, and run a Linux PowerPC distro on it.

You will not likely be able to assemble a "commodity" box using a PPC. You'd have to either dig up an Apple mobo or an IBM mobo. Possible to do, but far from bopping down to Fry's and grabing the latest VIA PPC mobo and chip.

Re:quick question

[TheRaven64]

will laptops be feasible?

These chips are targetted at blades. Blades require:

1. Low power consumption
2. Low heat dissipation

Laptops, on the other hand, require:

1. Low power consumption
2. Low heat dissipation

Draw your own conclusions

Re:quick question

[A_Non_Moose]

These chips are targetted at blades. Blades require:

1. Low power consumption
2. Low heat dissipation

Laptops, on the other hand, require:

1. Low power consumption
2. Low heat dissipation

Draw your own conclusions


Uhhhh...Blaptops That's it, they're making Blaptops!!!

When you're done with mobile computing you just stick it back in the rack mount docking station.

Heh.

Re:Chip speed won't save Apple

[damiam]

They're over and done with, and have been, for nearly half a decade now.

And they will continue to be over and done with for several more decades, while still turning out incredible computers.

Re:noo

[jo_ham]

You're anonymous, so really I shouldn't but..

You can keep on bashing their 1 button mice, and expensive hardware.

Buy a $5 two button mouse from BestBuy and shove it up your ass, or connect it to a Mac.

You can bash quicktime, which is a POS compared to other formats.

Quicktime is a delivery system that can use a plethora of codecs and formats. Unlike RealScum and Wiblows Media, you can encode and decode quicktime files with various programs to provide content.

You can make fun of the dock.
You can make fun of how cheesy OSX looks.

You can if you want. I can make fun of your silly hair. Different strokes for different folks. I happen to think jagged text and rectanguar grey buttons are soooo last year.

You can bash the superdrives, which only burn on certain dvd+ram formats.

Err, hello? knock knock? Anyone home? I didn't think so. The superdrive is a drive used in PCs too - it can burn DVD-R, -RW and +RW. Moral: when there's doubt, cover all bases.

You can make fun of mac users for buying expensive software when there are plenty of free replacements.

I bow to your 37337 \/\/4r3z 5k111z, or didn't you mean that? i like to buy my software thanks, or use sourceforge/versiontracker/etc to get OSS stuff.

I also use iMovie (free) to edit movies, iTunes (free) to listen to mp3s, AppleWorks (free) to do word processing and spreadsheets, Mail (free) to send and receive email, the Developer Tools (free) to write apps for unix and OS X.

I could use iPhoto (free) to manage and edit my pictures, but I have Photoshop.

I could use iDVD (free with superdrive macs) to burn dvds, but I don't have a superdrive.

I can burn CDs from the Finder (built into the OS) but I bought Roxio Toast. I can also rip, mix and burn from iTunes (free), which I do to make CD compliations quite often.

You can bash Inet explorer and MS Office on Mac.

Yeah, bashing Microsoft seems to be popular. Don't blame Apple for Microsoft's apple software. Who uses IE on the Mac anyway? There are a plethora of faster, more standards compliant browsers for the Mac.

I found Office for Mac to be pretty good myself, but I don't have it on my iBook. I don't need it really, I just use AppleWorks (free with consumer Macs) for the odd bit of word processing.

Bash the Mac for so many things? I think you're a couple of gunmen short of a posse my friend.

Stick to Winblows, we don't need someone like you using a Mac.

Re:Hmmm

[Slarty]

I'd be surprised if there won't always *be* a premium for Apple stuff, although I'll grant you it could be quite a bit less. Apple has a reputation for providing nice, upscale hardware and a better user experience compared to the shoddier, cheaper PC. That's why people (including myself) are willing to pay quite a price premium for a machine that really can't keep up performance-wise.

I'm not saying this is always the case; there are very nicely engineered PC's and Macs that aren't as nice as they could be. But Apple products are perceived as being premium products and are generally priced accordingly... and lots of people are willing to pay. Keeping that in mind, I doubt if Apple will ever really get into a PC price war. They'll keep doing just fine in the upper price scales, and with a better profit margin to boot.

Re:Any takers?

[VRisaMetaphor]

Trust me, if Apple's 970 machines come out in January, it will be like Christmas in January. Mac folk have been waiting way too long for this.

Re:Lets hope...

[Jeremi]

I miss the good 'ol days when Mac were fast

Bah. I miss the days when the fastest Mac around was an Amiga running a Mac emulator. ;^)

Re:Totally overpriced.

[sfgoth]

$1575 total.

First, I'd estimate the value of the skills needed to assemble that pile of gear into a working computer at several thousand dollars.

That is, you have a valuable skill that allows you to assemble a desktop computer for far less than the average human.

Your comparison only goes to show how much both of those above companies are gouging their customers.

The customers of those two companies generally do not have the skill to assemble your pile of lowest-cost components.

And don't even get me started on the nightmare that befalls you when one of the 10 different suppliers you've chosen delivers an incompatible or broken part.

You clearly don't value your time.

I could spend 5 minutes ordering a new Mac or Dell online. Odds are good it would work perfectly on arrival, and all software would be installed and configured.

Or I could order PC components from 10 different suppliers, getting the best deals. Then I'd wait 8 weeks for the slowest shipment to arive. Then I'd spend at least 2 hours assembling it. Odds are definately not good that everything works on the first try. If something goes wrong, or was poorly documented, it might take 5 hours. And if something is truely broken, another 2 hours on the phone, and a few more hours dealing with shipping stuff back. And when the hardware is finally all working, then I get to install software!

I don't describe this out of ignorance. I bet my experiences building computers are pretty similar to those of most people here. It's just not worth it unless you're time is free.

Re:This report caused a relationship to end!

[NeuroKoan]

And at some point, you'd probably try to get the two to ... you know ... network