2GHz IBM Processors [Archive]

bertinman

Aug 21, 2002, 05:49 PM

I think some of you have forgotten that Apple does do alot of their own hardware design. It is true that the actual chips/bits/and pieces are not made by them, but they do put them together or at least experiement with them then send the designs to others to build. I'm new to the whole Apple world but I got the idea somehow that Apple makes their own motherboards. Those are very important indeed in my oppinion.

Apple does make contracts that should not be taken lightly. If Apple is as innovative as I'm hoping, the newest motherboards should be able to support (or be able to easily modified so that they support) newer chips, mainly IBM's more powerful chip (power?) or Motorola's more powerful chip (mpc85??).

This is my big wish*, IBM and Motorola start to work together somewhat again. The PowerPC chip is a strong and useful chip but will die if technologies are split and the two companies go their seperate ways. I hope this new IBM chip does have a vector processor similar to Alitevec so that maybe the two could be interchangable thus closing the wide vector processing gap between them.

I'm a big PowerPC fan, got it from my dad. He was all ready to throw mounds of cash at IBM for it's OS/2 Warp PPC version.

Anyway, hope you enjoyed my 3rd post... (:

-- Bert :cool:

big

Aug 21, 2002, 05:54 PM

nice third post, you are definitly a person whom has something to contribute, and can express your thoughts well through written word.

I appreciate you actually using paragraphs and proper puncuation, as well as not waisting all our time on some babbleing phrase like "COME TO ME G5"

I think I might becoming a Bert fan

TyleRomeo

Aug 21, 2002, 06:01 PM

Originally posted by Macmaniac
Hey if they can make them fast and put em in a Apple so be it! Apple should embrace this processor if Moto can't deliver. If there is no G5 by next MWNY apple should look into IBMs powerPC proccesor. I really hope they are nearly rdy, it would be a smack in the face to PC users if Apple had 2ghz by christmas:)

Keep on praying for that G5 at Macworld San Fran. It ain't happening. The same rumor crap circled last fall and we got iMacs at MWSF instead of these ellusive G5s. Have some patience and be happy with what apple offers right now. OSX.2 is amazing and it's onoy going to get better. How fast do you really have to go on your computer?

Shrek

Aug 21, 2002, 06:01 PM

For some reason I cannot find the article on the UK site. Where is it?! :confused:

vniow

Aug 21, 2002, 06:03 PM

Originally posted by arn
. No online version of the article is available.

:rolleyes:

arn

Aug 21, 2002, 06:07 PM

Originally posted by JamesDP
I also think it's fair to say that if they're already planning to announce this chip at the Microprocessor Conference, then they're already making them in precent decent quantities and are either working out the bugs or have done that already.

Actually, from my understanding, processors that are talked about at these sort of conferences are often still on the drawing table... not even close to production... hence the "lag time" discussed in the article.

Of note, a G3 processor 750fx? - was discussed last year, I believe, and took them 7 months or so to get towards production if I recall correctly.

arn

Shrek

Aug 21, 2002, 06:09 PM

Originally posted by arn
Unfortunately, the article also points out that the lag from announcement to production can be months to years.

Years? I'm still hoping that news (http://news.com.com/2100-1001-257421.html) of IBM reaching 2GHz by late this year will come true. I'll just keep praying. :)

JamesDP

Aug 21, 2002, 06:21 PM

That makes sense, arn. I'm not really up on how the whole chip biz works - all I know is cables (since I work at a cable manufacturer).

I enjoy all of the conjecture about the new processors though - I've learned a lot crusing the boards here and at MacNN. Really looks like an interesting time for Apple, although personally I'm more concerned with when I'll finally be able to buy an iBook and get rid of my PC :D

bertinman

Aug 21, 2002, 06:23 PM

What has been the previous tactic from IBM conserning releasing info about processors for Apple use? meaning: Motorola only releases info about the 'G4' processors when Apple unviels their new line of computers. Did IBM release the iBook 'G3' processors before or after Apple ungraded?

Just a thought. If indeed IBM does wait like Motorola does, could we expect them to break away from that now? Also, if they do/are going to wait, this chip couldn't possible be for Apple.

-- Bert :cool:

ps: props to BIG/akk, very much appreciated and I hope I live up to your comments! :)

Foocha

Aug 21, 2002, 06:49 PM

Not sure this article sheds new light on anything.

These days MacUser UK seems to get all its news from Macrumors.com and Thinksecret.com!

gregorypierce

Aug 21, 2002, 06:58 PM

Hey if they can make them fast and put em in a Apple so be it! Apple should embrace this processor if Moto can't deliver. If there is no G5 by next MWNY apple should look into IBMs powerPC proccesor. I really hope they are nearly rdy, it would be a smack in the face to PC users if Apple had 2ghz by christmas

Why would it be a smack in the face to PC users? By Christmas AMD and Intel would still be faster in both terms of CPU clock and raw overall performance.

skunk

Aug 21, 2002, 07:12 PM

More of a tickle than a slap, I'm afraid :p

macmunch

Aug 21, 2002, 07:37 PM

Why would it be a smack in the face to PC users? By Christmas AMD and Intel would still be faster in both terms of CPU clock and raw overall performance.

Hm, thats not right I think

Look: 6,4 GPs troughput
and dont forget !!
8-way superscalar

Thats very good a 2 GHz version of this chip is theoraticly very very fast !! faster than a 3 GHz P4, when you see the facts.

Mr.Hey

Aug 21, 2002, 07:58 PM

G4scott

Aug 21, 2002, 07:59 PM

Goodbye motorola :(

These seem like dark times for Apple, with not much light ahead (of course, it's not as bad as Apple pre-98...) From a software standpoint, Apple seems to be doing ok, but their hardware really needs work.

Personally, I've really given up all hope on Motorola... The G4 is a nice processor and all, but It can't keep up with the competition, and they have yet to even officially mention a desktop processor that blows the pants off of x86 processors. Right now, IBM seems to be Apple's best hope. Hopefully they can put out this new processor within 6-8 months, a year at the most.

I love the Mac platform (not like that :p ), and I know that the user experience is much better than anything else out there. I won't threaten to switch to windoze or anything, but I will say that Apple needs something good to keep attracting the switchers, and the people who are actually willing to use windoze...

alex_ant

Aug 21, 2002, 08:07 PM

Originally posted by gregorypierce
Why would it be a smack in the face to PC users? By Christmas AMD and Intel would still be faster in both terms of CPU clock and raw overall performance.
I think if IBM can manage to put out a 2GHz chip with performance similar to a 1.3GHz POWER4, this chip will be roughly on par with or slightly slower than a 3GHz P4 in integer speed; however, I wouldn't be surprised to see it pull way, way ahead in operations that take advantage of AltiVec. The AltiVec-like unit will, I'm guessing, be able to handle double-precision FP in its new incarnation, and that means that if the OS X compiler can be sufficiently improved to automatically vectorize code to some degree, this new IBM chip will be very very very very fast at FP, faster by far than anything the x86 world will be able to offer for quite a while. Of course the chip's plain-jane FPU will likely be nothing to sneeze at, either.

The 6.4GB/s memory bandwidth figure quoted is suspiciously the same throughput offered by HyperTransport. So this new chip will certainly not be starved for data thanks to a crappy old G4-style bus.

Alex

danman

Aug 21, 2002, 08:07 PM

On the processor rumors / roadmap for Apple:

Processors announced at the Microprocessor forum are usually some ways off, usually 6 months or more, though this is by no means a hard and fast rule. It is conceivable that through Apple's usual influence on it's suppliers the situation may be different in this case (their sales are effected more than other manufacturers by announcements like this), though there is no real reason to believe this is the case in actuality.

We also know that there is still life left in the old dog (Motorola) yet, and G4s with faster FSB's are around the corner, and will undoubtedly be used by Apple at some stage.

So, looking at the picture this way, our best guess has to be that true DDR machines with 7500 (G4++s) will probably appear in at the beginning of next year, and if there is to be a move to IBM processors it is going to happen n the mid to second half of next year.

Just got to put the realistic viewpoint here.

This isn't such a bad outlook. DDR-wise G4s will be formidable beasts, though we will still be looking at a performance deficit with the x86 world, unless Motorola can give us one last gasp and deliver impressive clock speeds. I for one wouldn't turn my nose up at a speedy DDR-aware G4.

ConradG4

Aug 21, 2002, 08:09 PM

OMG OMG OMG!!!!

2GHz G5s!!!!!!!!!!!!

No sorry, just had to say it...

-Conrad;)

alex_ant

Aug 21, 2002, 08:19 PM

Originally posted by G4scott
These seem like dark times for Apple, with not much light ahead (of course, it's not as bad as Apple pre-98...) From a software standpoint, Apple seems to be doing ok, but their hardware really needs work.
I think if anything is making these times seem dark at the moment, it's Apple's business practices with regard to .Mac and Jaguar pricing. There is plenty of light ahead with regard to next-generation CPUs, and even more light when one considers what other options Apple has to stay competitive besides brute-force-quick CPUs. It seems like all the pieces, big and small, are in place for a Macintosh renaissance (by that, I mean, say, a doubling of market share) - the only missing piece is that new, next-generation Mac that wipes the floor with everything else. I think this new IBM chip is Apple's big chance. What Jobs has to worry about in the meantime is retaining the Mac customers he already has. I'll bet that for every switcher to the Mac platform, there is at least one switcher moving to the PC because it's such a better value (or at least apparent value). I don't think it would hurt terribly much for Apple to publicly state that the current Power Macs are upgradeable to the next-generation Mac CPU down the road, and to make a processor card upgrade available when the new IBM chip is available.

Alex

lazyrighteye

Aug 21, 2002, 08:20 PM

If it takes "years" to move the Mac to a whopping 2G processor, will anyone care?

Fact is, next to price, the other 95% look at processor speed as one of THE major buying incentive. If Apple intends to sway any of that 95%, our clock speeds must begin competing with the Dark Side... now. It seems that simple to me (which means it must not be that simple).

And while I'm typing...
**** the other 95%.
Let them keep doing their stupid things their stupid way. The more of them there are, the better we all look.

Keep up the good work Arn!

lazyrighteye

G4scott

Aug 21, 2002, 08:28 PM

Originally posted by alex_ant
There is plenty of light ahead with regard to next-generation CPUs, and even more light when one considers what other options Apple has to stay competitive besides brute-force-quick CPUs...

With motorola, it seems like that light moves 2 steps away from us for every step we take forward.

IBM's chip seems to be the processor that will wipe the floors with all other pee-cee's...

I was going to say something else, but I forgot...

damm...

G4scott

Aug 21, 2002, 08:30 PM

Originally posted by lazyrighteye
If it takes "years" to move the Mac to a whopping 2G processor, will anyone care?

Fact is, next to price, the other 95% look at processor speed as one of THE major buying incentive. If Apple intends to sway any of that 95%, our clock speeds must begin competing with the Dark Side... now. It seems that simple to me (which means it must not be that simple).

And while I'm typing...
**** the other 95%.
Let them keep doing their stupid things their stupid way. The more of them there are, the better we all look.

Keep up the good work Arn!

lazyrighteye

Wow, you're the most Apple loyal newbie I've seen in quite a while... Most other newbies are saying "what's wrong with intel", and you're saying ***** them all... I like that :p Just don't get too hardcore. Apple does need more market share to stay competitive.

ElRayOX

Aug 21, 2002, 08:37 PM

We're going to know a lot more about all this once IBM gets to the podium and announces the new chips.

Say what you want about the megahertz myth. Windows machines feel very snappy in use, Macs tend to feel more sluggish. We need the speed IBM can promise. It's unfortunate Motorola has dropped the ball (being a Chicago-based company, I have a TON of cousins working there ... wait a minute, maybe they've been laid off...), but maybe Big Blue can jack up the MHz and pull us out of this.

We have the Best OS and the Best Industrial Design. We just need the Horsepower.

gandalf55

Aug 21, 2002, 08:43 PM

Ok - I would like to announce a 128-bit processor running at 8Ghz. Of course that may mean months to years. :)

SPG

Aug 21, 2002, 08:50 PM

Last night I installed four HD's into my new dual 867 and I realized that this is the best case design I have ever seen. The fan is a little noisy, but what do you expect for something that will keep two processors, two optical drives, and four HD's cool. This evolution built on good design and good design theory has resulted in a machine that is nearly revolutionary...except for it's processors. jaguar is finally a solid optimization of a really good OS, so now that only leaves one point where Apple is not in the forefront, the processor.
The current processors are good, but they aren't as far ahead of the pack as the other elements. A G5 with real DDR and a faster bus should be untouchable in any debate or any benchmark. Let's just get one soon.

SPG

Aug 21, 2002, 08:52 PM

Originally posted by ElRayOX
Say what you want about the megahertz myth. Windows machines feel very snappy in use, Macs tend to feel more sluggish.

We have the Best OS and the Best Industrial Design. We just need the Horsepower.

Jaguar fixes a lot of that. I've found that it's damn snappy.

MacSlut

Aug 21, 2002, 08:55 PM

What I would like is a machine that I can buy now (or very very soon) that takes into account that new things are going to be coming. I find it very hard to buy a new dual 1.25GHz machine today knowing that it meets my needs, but knowing that there are technologies coming that would be much, much better.

Give us a road map Apple!

I would love to be able to buy a machine today that had USB2, FireWire2, HyperTransport and the ability to be upgraded by swapping a daughter card. Or if that isn't doable, then give us a motherboard upgrade option.

I've been sitting on my G3 for waaaaay to long, constantly being underwhelmed by the new models and knowing that 6months after 6months there will be another speed bump.

I can understand keeping tight lipped about stuff, but being a little more open with the direction of things would have resulted (and would result) in more sales as far as people like me are concerned.

I'm not looking for anything free...I'm perfectly happy to buy a motherboard or preferrably a daughter card that results in a tidy profit for Apple. I'm just afraid to jump in the river, and Apple is making it that much worse by not providing any kind of a road map.

To make things worse, the rumors are vastly exceeding not only reality, but expectations. Remember all of those rumors of a G5 at the last MWSF? With no word from Apple, it seemed plausible. Then with nothing substantial announced there, it seemed like MWNY would be the place for the G5 to debut...now they're rumoring MWSF '03.

Now granted, these rumors are mostly generated by 12 year olds and shouldn't be believed, but the discrepency between the rumors and the reality is getting way to big and hurting Apple in the long run. Apple can prevent this by either providing more information to curb the rumors, or provide products that exceed the rumors (aint gonna happen).

See ya all at the Apple Store on Friday (Palo Alto for me)

Macmaniac

Aug 21, 2002, 09:09 PM

Originally posted by skunk
More of a tickle than a slap, I'm afraid :p
Well at least it would make the speed gap seem like less. 1 is very different from 2, if an Apple can catch a PC at 2ghz imagine a Mac at 2ghz makes u think:rolleyes: :cool: :eek:
Plus OS X.2 would make it even more impressive.

(Steals MacSlut's pants);)

Nipsy

Aug 21, 2002, 09:18 PM

Originally posted by gregorypierce

Why would it be a smack in the face to PC users? By Christmas AMD and Intel would still be faster in both terms of CPU clock and raw overall performance.

While it is true that PC users will still have the clock speed advantage, a Power 4 Lite at 2GHz will outperform anything (single or dual) in the PC world.

A 1GHz Power4 is roughly equivalent to 4 2.2GHz Pentium IVs.

beatle888

Aug 21, 2002, 09:27 PM

Well, I'm not thinking of switching either but after
talking to some friends about windows, and playing
around with the windows systems, I think I'd be
happy enough if I did switch.

I would seriously consider a windows machine for
my next system, but all my software is for the mac.

I've seen what the mac can offer. I've been using
a mac exclusively for almost fifteen year's. However,
I think that windows is good enough for me to work
with and the hardware isn't an issue as it always
seems to be with the mac.

Honestly, I don't see why a seasoned computer user
would switch to a mac. But the new, or inexperienced
computer user would definitely be better off with a mac.

Nipsy

Aug 21, 2002, 10:00 PM

Originally posted by beatle888
Well, I'm not thinking of switching either but after
talking to some friends about windows, and playing
around with the windows systems, I think I'd be
happy enough if I did switch.

Honestly, I don't see why a seasoned computer user
would switch to a mac. But the new, or inexperienced
computer user would definitely be better off with a mac.

I think that the reasons to leave Windows are many.

Having just payed around with the machines of others, you are unlikely to have experienced the myriad problems Windows users face day to day.

I get the klez virus at lease three times a week (doesn't matter, as I read mail on my Mac), but for a Windows user this is a problem.

On my Windows machines, I get one BSOD a week (between 2 machines). 25% of the time, this is unrecoverable, which means serious repairs, and often reinstalling Windows. Either way, its 2 wasted hours a month.

Furthermore, while Intel and AMD are both faster at raw computation, Windows slows them considerably. The interface is still clunky, slow, and counterintuitive. I don't want to see Windows is shutting down for 5 seconds. I don't want to get Properties to find out a folder's size. I don't want to spend 10 minutes a day closing pop up windows in IE. I don't want to sign my first born to Mr. Gates in order to have a legal license.

While having a slew of hardware makes things cheaper, it also makes them less successful. This MoBo won't work with that card. This IRQ is already in use for that port, etc. My time is valuable enough that I would rather pay a premium to avoid the hassles.

The software argument is also pretty easy. There are 1,000,000 Windows titles. 9,990,000 of them are poorly coded crap, bloatware, spyware, etc. There are 10,000 titles for Mac....you do the math.

As an aside, if gaming is your thing, try a PS2...

I have to use Windows as a testing platform, and it sucks...a lot of developers are making the switch as a Mac is now a pretty UNIX box which works in a corporate environment, which is kind of a hold grail...

Anyway, there are a lot of good reasons to switch to Mac, and very few to leave. Power 4 Lite would seal the deal for a lot of people...

rice_web

Aug 21, 2002, 10:10 PM

While 2GHz might be out of the question for a while, 1.6GHz might be about right, with something in the 1.4-1.5 range about perfect for a January release.

This would allow Apple several regular updates to the G5 to last them into 2004, when the next revision of the G5 would be released.

This would roughly follow Apple's patterns of upgrading.

daijones

Aug 21, 2002, 10:29 PM

There's been a lot of referring to Motorola's roadmap for the PowerPC in the past: it might be worth looking at IBM's roadmap:
http://www-3.ibm.com/chips/products/powerpc/rdmap/
Looking at what's planned, we see a new series of PowerPCs that are:
multicore superscalar
SMP capable
Integrated SIMD (ie, vector processing, or "Alti-Vec like")
RapidIO
n-way crossbar CoreConnect
Call me an optimist, but this sounds much like the 64-bit PowerPC to be announced in October. So far, so obvious. The interesting thing is that this processor seems to coincide with the introduction of a low-k dielectric insulation. Coincidentally, IBM's new East Fishkill plant ( http://www-916.ibm.com/press/prnews.nsf/jan/B1F96D38480E6BC385256C070063FD88 ) has been set up to make low-k processors, and is currently gearing up to volume production by the end of the year. We can but hope that by the end of December this plant will be churning out large quantities of 64-bit PowerPCs. Question is, who'll want to buy them? Apple is one obvious possibility, but the scary thought is that IBM may be planning it's own family of desktops and entry-level servers running Linux.

D

Gigglebyte

Aug 21, 2002, 10:35 PM

now here is a question for all of you...is there a COMMON benchmark that can be run between a Wintel and Apple system? I am not concerned about the video as I know my new 16VRAM iBook or even a new DVI PowerBook won't hold a candle in video to my GF4 Ti4600 but on the business side or just computational processing power is there anything?

Newtonboy

Aug 21, 2002, 10:45 PM

I would love it if apple could put these puppies into the next rev. of powermacs. The problem I see is that I remember seeing a post a while back saying that apple's current hardware won't support the power 4's. Even though its a PPC, its just incompatable w/ the current hardware. I don't know if this is true, or used to be true, but not anymore... But if that possible hurdle could be crossed, I'm so getting a new Pmac! My 8500 is just about maxed out.

giovanni

Aug 21, 2002, 11:55 PM

You know, I really wish some of you (most of you?) stopped once and for all teh b/s about windows computers. Do you really need to do that ? does it make you sleep better at night ?? Are you so frustrated you have to come up with all this pure b/s about windows ?

I mean, come on. grow up. To me it sounds like looking for excuses to justify something (like yours is bigger than mine but mine is curved).

Two things I fail to understand: (a) why some of you do that at all (b) wtf are your arguments ? On (b) what I mean is that I have worked now for quite a few years in companies with pc's only and I cannot recall having all these problems at all. I can't remember the last time I had a crash and I consistently run many applications at the same time and the things are pretty fast.

Then I come home and enjoy my Mac

Kethoticus

Aug 22, 2002, 12:04 AM

Sorry folks. I really don't mean to always be the negative nilly here, but I just don't think we'll be seeing anything like 2GHz G5s, Power4s or whatever they're being called today, anytime soon, if ever. Do I hope I'm wrong? Sure do. Do I think I'm wrong? Of course not.

This just sounds way too good to be true. Over the past 3 years I've been reading all these rumor sites, and I've yet to see anything in reality even close to the pre-MWExpo rumors hype (probably the worst by Apple itself this past January, but that's another story).

We have all read about how this or that particular new techology was gonna make Apple the king of computer manufacturers, how the new OS X would bury Microsoft, how the new PPC was going to crush Intel, etc, etc, etc. I mean I for one am just sick of this stuff. I simply can not latch onto all this fantasizing anymore.

My prediction? It ain't gonna happen. Apple will move to Intel or AMD first. In the near-term, Apple will compensate for hardware performance ineptness via quad-processor G4s.

ddtlm

Aug 22, 2002, 12:31 AM

Kethoticus:

This time around though, the rumors center around an actual chip that has actually been announced. This is starkly contrasted to the G5 rumors last year as well as the endless talk about some sort of 7470 or 7500 G4, or a full DDR FSB.

The fact is that the Power4 clocked in at 1.3ghz more than a year ago on 180nm technology. It is easy to believe it will hit 2.0ghz next year. I fully expect it to turn up during 2003, perhaps not at 2.0ghz, but then again it doesn't need that clock speed to perform well. We may not catch the P4... but we will be so much closer.

kenohki

Aug 22, 2002, 12:55 AM

Originally posted by Kethoticus
Sorry folks. I really don't mean to always be the negative nilly here, but I just don't think we'll be seeing anything like 2GHz G5s, Power4s or whatever they're being called today, anytime soon, if ever. Do I hope I'm wrong? Sure do. Do I think I'm wrong? Of course not.

My prediction? It ain't gonna happen. Apple will move to Intel or AMD first. In the near-term, Apple will compensate for hardware performance ineptness via quad-processor G4s.

I doubt Apple will take the Intel route. Things aren't too rosey on that side of the fence either. P4 has a high clock rate but look at how Intel is getting sued over that now. x86-64 (Athlon, Opteron) hasn't proven itself yet and neither has IA-64. (Plus there's a lot of risk associated with IA-64. It's a whole different school of thought and another thread on it's own.)

However, quad processor G4s won't happen at least until the 7470 and really only if that processor goes back to using the full MERSI cache coherency protocol. The current batches of G4 class chips only use the four state MESI which makes them less efficient in quad processing environments without separate cache controller hardware, software, etc.

POWER4 Lite (this new PPC from IBM) looks, from what has been released about it so far, like it could be a winner. It would provide binary compatibility (investment protection), and a familiar environment (PPC ISA). It also has gobs of memory bandwidth in comparison to what we have today and should be a screamer if it's comparable to POWER4 (even if you do have to crank up the clock to make up for the fact that you don't have an enormous cache like on POWER4). It is also much less risky for Apple than the Intel or AMD strategy.

Hopefully this chip will come sooner rather than later (complete with auto-vectorizing compilers). What I find interesting is that the other desktop processors being discussed in that group (according to the schedule for the forum) are somewhat near term (Itanium 2, Athlon/Opteron). Maybe this is a good sign for this chip to see the light of day soon. *shrug* We can only hope.

Rocketman

Aug 22, 2002, 12:57 AM

Originally posted by alex_ant

I think if anything is making these times seem dark at the moment, it's Apple's business practices with regard to .Mac and Jaguar pricing. There is plenty of light ahead with regard to next-generation CPUs, and even more light when one considers what other options Apple has to stay competitive besides brute-force-quick CPUs.
Alex

1. Apple heard a backlash on .Mac re maintaining email addresses from people who do not use the premium services of that offering. They listened. They responded. In about 48 hours.

2. Apple heard a backlash on 10.2 (Jagwire) regarding lisencing upgrade pricing and responded with a "family pack" offer, which apparanlty they had planned to a strong degree all along. They also made minor concessions on other customers. More to the point Jagwire is universally considered a "major" increase.

3. Apple has now released significantly faster and more advanced motherboards in CONSUMER low price computers ($1700-$2500). They are "more than twice as fast as their prior counterparts".

4. Apple has released $1100 low end "supercomputers" (literally).

5. There are now verifiable rumours of a legit G5 processor on the "immediate" horizon.

It is hard to find the bad news here. I have looked really hard. I failed.

Rocketman

beatle888

Aug 22, 2002, 02:41 AM

Originally posted by giovanni
You know, I really wish some of you (most of you?) stopped once and for all teh b/s about windows computers. Do you really need to do that ? does it make you sleep better at night ?? Are you so frustrated you have to come up with all this pure b/s about windows ?

I mean, come on. grow up. To me it sounds like looking for excuses to justify something (like yours is bigger than mine but mine is curved).

Two things I fail to understand: (a) why some of you do that at all (b) wtf are your arguments ? On (b) what I mean is that I have worked now for quite a few years in companies with pc's only and I cannot recall having all these problems at all. I can't remember the last time I had a crash and I consistently run many applications at the same time and the things are pretty fast.

Then I come home and enjoy my Mac

I agree, the pc's are getting easy enough for ME to use. I think
that if I didnt have to repurchase all of my software titles, I would
definitely consider a PC. I know that sounds f'd up to my fellow mac
users but it's true.:eek:

pgwalsh

Aug 22, 2002, 02:47 AM

I don't see IBM taking a year to release this chip. They just spent 5 Billion on a new fab plant. They allow other companies to fab chips like Apple or Motorola.

I could see Apple using resources (ie licensing, engineers, etc) from Motorola and IBM and then using IBM's new plant to produce chips. The "plant" is supposed to allow extremely fast times to market since R&D is done in house. So take your damn embedded G5 or G3/G4/Power4, license the technology and use IBM's plant to produce the chip to your specs with Alti-Vec. Then follow suit with the rest of the industry and spruce up your FSB, Rapid I/O, Serial ATA or whatever.... But down get so down and disappointed. Good things are coming.

The plant will allow us more options, and we like options.

ddtlm

Aug 22, 2002, 03:14 AM

kenohki:

That lawsuit against Intel is pathetic. The P4 is in fact faster than the P3, and only for a short period of time was it in doubt. This has been very well shown by benchmarks. It seems that these people are claiming that it is wrong to make a processor that does less work per clock than one that came before, which is hard to believe. The whole point of the P4 was to trade per-clock performance for more clocks!

The Itanium would make a fine, in fact great platform for Apple if they did not have to worry about it's very high cost (minimum of $1300 for a single chip) and if they did not have the huge installed base of PPC apps already.

Like it or not, the Itanium II is one hell of a fast processor. (Plus, it can heat your house as a bonus.)

You also mention a "7470". Rumor. There is less proof of the 7470 than there is of the Power4-based G5, which we can't be certain of either until Apple says so.

The auto-vectorizing compiler will probably arrive in some version of GCC 3.

Rocketman:

Quite the optimist, aren't you? I'm waiting for benchmarks showing how the new PM's are "more than twice as fast" and I absolutely do not buy your "$1100 supercomputer" claim. A 100mhz FSB G4 without L3 sucks. I don't care how many gigaflops Apple tells you it could do in some contrived situation, the fact of the matter is that it has got a terrible memory system. To even call that a supercomputer is an insult to yourself. (Alternatively, we could just call every new consumer computer on the market a supercomputer since they are all capable of well over a gigaflop.)

bretm

Aug 22, 2002, 03:36 AM

My roommate is running an UPGRADED pc that the motherboard was upgraded to a 1.5 ghz. He's running IE 5 and win 98. It is hooked up to my airport which is in turn hooked up to fiber optic DSL. Anyway, his machine is just dang snappy. No wait for anything. Much snappier than a dual gig.

BUT BUT BUT. I just finished helping out a friend who has Windows XP running on a brand new 1.2ghz Sony VAIO laptop. It was sluggish. Much like OSX on my G4 350 (which I am perfectly happy with in operating speed - just not rendering speed).

So I think the dark side is suffering the same ailments. Windows 98 is graphically and systematically simpler, like OS9 and is therefore snappier. Both are matured. OSX and XP are heavy on graphics - one has drop shadows, tansparency, animaton. The other has the color palette of fisher price. Both are quite a bit more sluggish on machines that would smoke with their predecessors.

aaroncd

Aug 22, 2002, 03:39 AM

Originally posted by ElRayOX

Say what you want about the megahertz myth. Windows machines feel very snappy in use, Macs tend to feel more sluggish. We need the speed IBM can promise. It's unfortunate Motorola has dropped the ball (being a Chicago-based company, I have a TON of cousins working there ... wait a minute, maybe they've been laid off...), but maybe Big Blue can jack up the MHz and pull us out of this.

ok I could not let this pass, I have a 400Mhz G4 tower at home (in the US), I am working in Kosovo at the moment, using nice new Fujitsu-Siemens 1.6 Ghz P4's, and sluggish is not the word, they are painfully slow, I really cant comprehend people saying windows is faster at all, i have a 1 Ghz P3 Toshiba laptop here as well, and that is faster than this desktop, and it is still a LOT LOT slower than my G4 400, especailly in perceived speed. Yeah windows may win on gaming speeds, and some other things, but for every day usage, there is NO comparison to a Mac, period. Here i struggle to get work done, I need 2 computers to do what i could on one mac (server and client here for web development).

Aaron

addsapple

Aug 22, 2002, 03:40 AM

DESPITE IBM'S CHIP-MANUFACTURING ENTERPRISE, THE COMPANY HAS NOT PRODUCED A G4 PROCESSOR FOR THE DESKTOP. THAT IS DUE TO CHANGE IN OCOTBER.

IBM is set to inviel a new chip that may push the performance of future Mac beyond 2GHZ, and put and end to Motorola's monopoly on processors in professional Macs.
The as-yet-unnamed chip, which IBM intends to announce at this year's Microprocessor Forum conference on 15 October, will be the first 64-bit PowerPC-compatible processor intended for desktop computers. It will also include a system compatible with the AltiVec vector processing unit used in current G4's.
According to the conference programme, Peter Sandon, a senior processor architect at IBM's PowerPC organisation, will give the first technical description of the chip. Although the programme does not mention specific speeds for the new chip, IBM sources of 2GHz for any new PowerPC.
Significantly, the chip, which is described as 'designed for desktops at entry-level servers', has as 160-register vector processing unit similar to Motorola's AltiVec.
The inclusion of an AltiVec-like system indicates that the chip is destined for Apple, rather than for IBM's computers. Apple has coded much of its own software - inclding Final Cut Pro and Mac OS X - to take maximum advantage of AltiVec. If the IBM processor is compatible with AltiVec, it will allow Apple to take the company on as a second supplier of processors, alleviating its dependancy on Motorola.
The Chip will also be the first true 64-bit desktop PowerPC. This means that data travels around the processor in 64-bit chunks, leading to a potential improvement in speed. However, 64-bit chips must either have software rewritten for them or run 32-bit code in a form of emulation. It is likely that Apple would quickly rewrite parts of Mac OS X to be 64-bit compatible.
The Power4 architecture, on which the new processor is based, is a high-end multichip package designed for server applications. Each Power4 is capable of fetching and processing eight instructions per clock cycle, and of running at 1GHz. However, power consumption for the processor is far too high for it to be used unaltered in a desktop machine.
Despite the announcement, it is unlikely that Apple will be adopting the new processor in the short term. Usually, there is a gap of months and often years between the announcements of a chip at the Microprocessor Forum and its shipping to customers for testing.

bretm

Aug 22, 2002, 03:42 AM

Originally posted by Rocketman

1. Apple heard a backlash on .Mac re maintaining email addresses from people who do not use the premium services of that offering. They listened. They responded. In about 48 hours.

2. Apple heard a backlash on 10.2 (Jagwire) regarding lisencing upgrade pricing and responded with a "family pack" offer, which apparanlty they had planned to a strong degree all along. They also made minor concessions on other customers. More to the point Jagwire is universally considered a "major" increase.

3. Apple has now released significantly faster and more advanced motherboards in CONSUMER low price computers ($1700-$2500). They are "more than twice as fast as their prior counterparts".

4. Apple has released $1100 low end "supercomputers" (literally).

5. There are now verifiable rumours of a legit G5 processor on the "immediate" horizon.

It is hard to find the bad news here. I have looked really hard. I failed.

Rocketman

How am I supposed to take anything you say as serious or researched when you keep saying "jagwire." Please stop.

SubFredZero

Aug 22, 2002, 05:19 AM

Thanks for typing the whole article, addsapple...

synp

Aug 22, 2002, 05:22 AM

Rocketman said:

1. Apple heard a backlash on .Mac re maintaining email addresses from people who do not use the premium services of that offering. They listened. They responded. In about 48 hours.

Really? How have they responded? I might have missed something, but when I look at the pages on www.mac.com they say you need to purchase email-only accounts for $10 each. Has that changed?

Also, is that a one-time payment or an annual fee like the rest of .Mac?

Thanks

pev

Aug 22, 2002, 05:40 AM

[QUOTE]Originally posted by SPG
Last night I installed four HD's into my new dual 867 and I realized that this is the best case design I have ever seen.
Well, I like the 2x867 I received this week too, and yes, two opticals and four hard drives is great. The problem is, I dont like the fact that two hard drives are sitting on end, and the other two are *upside down*. The upside down two annoy me the most as theres NO reason they couldnt have had the mountings on the carrier hold them the other way up.

Still. I think it was worth the money, and smokes my old G3. Roll on audio apps for Jaguar.

~Pev

Pauls

Aug 22, 2002, 06:10 AM

If apple is wooed by IBM's offering, I suspect that Macs may soon be split into 2 camps. IBM's powerPC for pro models and Motorola's G4 - G5 for iMac, eMac and laptops. Though motorola's chips aren't as powerful as Athlons or P4's there is a reason they are what they are - efficiency. They have half the transistors of the other chips and half to a 3rd the die size of the behemoths. This gives them advantages in radical motherbard profiles of the iMac (try fitting an Athlon in that canteloupe, you would probably only get a celeron) or the 5 hour battery life of the notebooks. Both aspects are industry leading. Mac notebooks are unique in their portablilty, but they still have decent power to edit 20Gb movie files without breaking a sweat. I don't think apple will give up this advantage just to catch up with a CPU rating.

The NeXt people at apple are said to have experience creating single binaries which run on various microprocessors. IBM and Motorola both collaborated on the Book E spec. You can sort of see a pattern emerging where macs have a larger range of processors and a greater degree of strengths.

Moto want to concentrate on an embedded strategy (thats their main customer base); there is no mention that G5 is shelved, rather what die size, POC features, power rating and efficiency do the bulk of their customers want.

IBM have conceded to making a desktop rated CPU with a vector processing unit similar to Altivec, contrasting one of the reasons why they left AIM in the first place. The power4 is a mighty beast, but IBM also wants greater market share for powerPC, and Apple can provide this.

I wouldn't however expect anyone but Intel winning the clock speed war.

tazznb

Aug 22, 2002, 06:59 AM

Originally posted by G4scott
Goodbye motorola :(

Personally, I've really given up all hope on Motorola...

:(
Me? I seriously think that Motorola either (1) Wants to return the pain from the banned cloning business, or (2) Someone is compensating them to keep the chip slow as possible to keep them from being as attractive to users that don't know the Apple experience;

Intel / Microsoft could be lining Motorola's wallets for this. :mad:

alex_ant

Aug 22, 2002, 07:46 AM

Originally posted by daijones
We can but hope that by the end of December this plant will be churning out large quantities of 64-bit PowerPCs. Question is, who'll want to buy them? Apple is one obvious possibility, but the scary thought is that IBM may be planning it's own family of desktops and entry-level servers running Linux.
The thing is though, why would they have Linux machines with PowerPCs and not Pentiums? That just seems a little suspicious to me. Why spend all the money on R&D and manufacturing to put out a Linux machine with a PowerPC, and have to constantly struggle with Intel and AMD and Sun etc. for the performance crown, when they can just slap a cheap P4 inside all those boxes and be done with it. I can't imagine IBM developing a 64-bit PPC CPU just to run Linux. In all their existing workstations and low-end servers that have PowerPCs, these machines run AIX and the specific PPCs they use are byproducts of past developments, usually inherited from high-end servers. Power3, RS64, 604e, none of those were originally designed for an IBM desktop/low-end server.

Alex

alex_ant

Aug 22, 2002, 07:50 AM

Originally posted by Gigglebyte
now here is a question for all of you...is there a COMMON benchmark that can be run between a Wintel and Apple system? I am not concerned about the video as I know my new 16VRAM iBook or even a new DVI PowerBook won't hold a candle in video to my GF4 Ti4600 but on the business side or just computational processing power is there anything?
SPEC_CPU2000 would probably be the best and most thorough benchmark, although if you have any emotional affinity towards your Mac, you would probably be best off not viewing the results, as they might make you want to cry. :)

www.spec.org (http://www.spec.org/)

alex_ant

Aug 22, 2002, 08:04 AM

Originally posted by Rocketman
1. Apple heard a backlash on .Mac re maintaining email addresses from people who do not use the premium services of that offering. They listened. They responded. In about 48 hours.
I'm not sure about this. Are you referring to that out-of-date FAQ?
2. Apple heard a backlash on 10.2 (Jagwire) regarding lisencing upgrade pricing and responded with a "family pack" offer, which apparanlty they had planned to a strong degree all along. They also made minor concessions on other customers. More to the point Jagwire is universally considered a "major" increase.
And a fat lot of good that does us, right? The main thing people were complaining about was having no upgrade price, and what does Apple respond with? A family pack? Good golly, it's like Apple is almost trying to piss off its customers. Whether or not what Apple did was the right thing to do, people were still quite intensely pissed off.
3. Apple has now released significantly faster and more advanced motherboards in CONSUMER low price computers ($1700-$2500). They are "more than twice as fast as their prior counterparts".
"More than twice as fast as their prior counterparts" according to Apple. While in the benchmark(s) that have appeared so far, they are barely any faster at all and feature a broken DDR implementation alongside a barely-improved CPU with less L3 cache. Sure they're less expensive than they were, but people want fast.
4. Apple has released $1100 low end "supercomputers" (literally).
Yeah, keep lapping up that marketing jive. The fact that Apple continues to call them "supercomputers" when just about any idiot knows they're not is yet another point that continues to annoy Apple's customers.
It is hard to find the bad news here. I have looked really hard. I failed.
When you're a Mac zealot, all news is good news. Some of us who like to think we're a little closer to reality are seeing what we think have been questionable business practices on Apple's part lately. This is not only my opinion, this is a widespread sentiment that is easy to pick up whenever you browse the appropriate forums on this and other Mac-related sites.

Alex

kenohki

Aug 22, 2002, 08:39 AM

Originally posted by ddtlm
kenohki:

That lawsuit against Intel is pathetic. The P4 is in fact faster than the P3, and only for a short period of time was it in doubt. This has been very well shown by benchmarks. It seems that these people are claiming that it is wrong to make a processor that does less work per clock than one that came before, which is hard to believe. The whole point of the P4 was to trade per-clock performance for more clocks!

Yes, this is true but you have to keep the pipeline fed. Stretching it out to a billion stages and cranking up the clock is not always the best way to get things done. It's not all that efficient. Plus throw in bus multipliers and the P4 design philosophy doesn't seem all THAT smart. Intel clearly had their marketing department's input on some of the decisions on the P4.

The Itanium would make a fine, in fact great platform for Apple if they did not have to worry about it's very high cost (minimum of $1300 for a single chip) and if they did not have the huge installed base of PPC apps already.

Like it or not, the Itanium II is one hell of a fast processor. (Plus, it can heat your house as a bonus.)

I wouldn't consider that a bonus. Especially in these nice fanless and portable designs Apple has. Yes, Itanium 2 is fast, but there are a lot of fundamental questions about EPIC/VLIW designs that aren't answered yet. Many new and exciting technologies in microprocessor design (hyperthreading, MPSOC design, etc) are heavily based on dynamic scheduling. How is this going to be handled with the EPIC/VLIW design philosophy. Are they going to make it more RISC-like or can they make the compiler smarter?

My point with the original post was not to poo-poo Itanium 2 but to point out that there is more risk for Apple to move to that architecture. IBM clearly has a POWER4/5/6 roadmap which should eventually translate into PowerPC performance. PowerPC is still safe for Apple.

You also mention a "7470". Rumor. There is less proof of the 7470 than there is of the Power4-based G5, which we can't be certain of either until Apple says so.

Well, I wasn't talking about Apple product, but Motorola and IBM product. A POWER4 based PPC is not rumor, but a fact. IBM announced it. Whether or not Apple uses it in their desktop...well who knows. I like AIX machines though so it's good news for me. :D

As for the 7470 or 7500 or whatever...true, no product announcements as of yet. But I'd be willing to bet that there's one more revision of the Apollo in the works. (I mean, for chrissake, Mot is still revising 680X0 technology.) My original post wasn't meant to intend that Apple would use anything of the like but to point out that the 7450 family of processors will not likely be used in some sort of quad processing system because it isn't as efficient at the 7400 in SMP environments due to the fact that it uses MESI. If Apple wanted quads, they'd also want a chip revision that goes back to supporting full MERSI.

topicolo

Aug 22, 2002, 10:05 AM

As for the Motorola topic, our current situation seems pretty similar to that of late '93 to early '94, when the fastest macs were 68040s. These macs were being smoked by 486s and pentiums.

It was pitiful.

When the original 68000 was released, it was more advanced than any other desktop chip out there, but as usual, Motorola screwed up and was overtaken by Intel, trailing to the point where the fastest 68040 were almost 3 times slower than the fastest pentium. There were rumors of a new chip on the horizon that was extremely fast (the PowerPC) which kind of corresponds to the rumors we have today (the Power4 variant). When the PowerPCs were announced in April of '94 (?), they were definately superior to even the fastest Pentium, which topped out at a measly 66Mhz, while the fastest PowerPC was a whopping 80Mhz. This was a good 21% faster!

Let's hope that IBM's new chip will repeat the PowerPC launch, but not follow Motorola's path with the 68k and the G4.

MacArtist

Aug 22, 2002, 10:05 AM

For all of you complaining about the price of OS X.2 and their not being an upgrade option except for those who purchased on or after July 17:

Windows XP Home upgrade is $96.50 as per pricescan (http://www.pricescan.com/items/item129571.asp), while the full version is ~$199

So to get a full copy of OS X.2 for $129 and a 5 user home license for $199 isn't that bad.

As for those of you hell bent that MHz is the end all be all of judging a computer's performance, this is a little bit of info from specbench.org (http://www.specbench.org):

CINT2000
Company--System--Result--Baseline--# CPU

IBM Corporation--IBM eServer pSeries 690 Turbo (1300 MHz)--839--804--1

Dell--Precision WorkStation 340 (2.53 GHz P4)--922--893--1

AMD--Epox 8KHA+ Motherboard, AMD Athlon (TM) XP 2200+--765--738--1

CFP2000
Company--System--Result--Baseline--# CPU
IBM Corporation--IBM eServer pSeries 690 Turbo (1300 MHz)--1266--1202--1

Dell--Precision WorkStation 340 (2.53 GHz P4)--901--878--1

AMD--Epox 8KHA+ Motherboard, AMD Athlon (TM) XP 2200+--671--624—1

In the integer benchmark, the 1.3GHz Power4 is faster than the XP2200+ and only 10% slower than the 2.53GHz P4.
Where as, in the floating point benchmark, the 1.3GHz Power4 is clearly the superior processor.

So, if IBM and Apple were to team up and release this 2GHz, Power4 inspired, 64bit, Alti-vec compatible, Hyper-transport ready chip in a PowerMac, it would definitely give both AMD and Intel a run for their money.

Personally I couldn't care less what MHz/GHz my computer is as long as it does what I need it to do, and right now my PowerMac 933 does everything just fine.

mrMahann

Aug 22, 2002, 10:07 AM

= os =
growth is the key; being freeBSD under the hood makes it easier to get cred and functionality.

we're growing in the scientific community, hopefully will reverse teh slide in EDU if haven't already.

decent hardware will keep us in the game in the movie industry and arts and design...

= hardware =
there used to be talk of UMA and UMA2 providing one momboard for all segments of the matrix. for good reason; lesser resources tied to that than where apple can really innovate, which is form and ergonometrics.

tho, don't know why no USB/firewire up front on new cases (or USB2...)

pb, ib are still good and competitive or even leading the pack in lotsa ways. consumer, still competitive, tho would be nice to see emacs a bit cheaper.

but, pro desktop momboards are just behind, and have always been slower. am hoping there is some collusion w/ nVidia as they seem to have their noggin on straight w/ their new momboard; would be nice to see apple borrowing most of that tech from someone; this would save apple's tech to the adaptation and tothe portables in that the track record has not been good for jsut about ever. engineers, know how much would be to adapt an x86 board to power4? is it just techically undoable, or can stuff be borrowed?

gig is w/ power4, should it be the saving grace, ibm is proven. moto has been bleeding engineers for a long time, and stories of its corporate environ are not promising for a turnaround. if ibm can get into the driver's seat, that's even more promise for hte future.

itanium: well, mac app devs just switched over. are they gonna be willing to do it all again so soon? recompile, but there must still be lotsa tweaks.

= windows =
windows seems faster, and i/o seems faster but that's an x86 or rather momboard thing. like someone said, windows really isn't that bad; its just a kludgey interface. when things are working, they're great. when not, your screwed. to some extent, mac users are subject to same thing just its seems easier to me to fix my mac stuff. but, i'm still fixing things for others that they have no clue where to even start.

things seem to be getting better for windows people, tho gimme linux on my x86 boxen. windows is less the problem than m/s and horrible biz practices.

Rocketman

Aug 22, 2002, 10:36 AM

Originally posted by bretm

How am I supposed to take anything you say as serious or researched when you keep saying "jagwire." Please stop.

Being a direct quote from Steve Jobs, I felt it accurate and amusing if not proper english :)

Don't throw the baby out with the bathwater!

Rocketman

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

Chryx

Aug 22, 2002, 11:23 AM

Originally posted by topicolo
When the original 68000 was released, it was more advanced than any other desktop chip out there, but as usual, Motorola screwed up and was overtaken by Intel, trailing to the point where the fastest 68040 were almost 3 times slower than the fastest pentium.

Except that the 68040 wasn't the fastest 68k chip, it was merely the fastest 68k chip that _Apple_ used.

the 68060 was a BEASTLY chip for it's time.

Rocketman

Aug 22, 2002, 11:35 AM

Originally posted by synp
Rocketman said:

1. Apple heard a backlash on .Mac re maintaining email addresses from people who do not use the premium services of that offering. They listened. They responded. In about 48 hours.

Really? Ho w have they responded? I might have missed something, but when I look at the pages on www.mac.com they say you need to purchase email-only accounts for $10 each. Has that changed?

Also, is that a one-time payment or an annual fee like the rest of .Mac?

Thanks

I do believe it is $10 per year forever. Compard to $99 that is a deal. Compared to $0 it is a steal.

But for those who converted all their mail to username@mac.com the ability to keep an email address is not bad at $10. To be charged for virtual disc and other services when ALL you use is email is silly and thankfully Apple recognized that if you are not wasting their bandwidth and server space they should not charge you for it either.

Rocketman

"Jagwire." - Steve Jobs
"Jaguar." - Product package and marketing department
"Jag-u-ar" - Queen's English pronunciation
TiG4 owners: NO Free or low cost upgrade. Foiled again!
o

MacArtist

Aug 22, 2002, 12:17 PM

The $10 mac.com email is for converting any itools account to an email only account. This is $10 per year and requires that you have a full .Mac membership ($49 for existing itools members, $99 for new members). So you can have up to 11 email addresses with one .Mac subsription for a price of up to $199 per year.

Back to the topic at hand...

Not that I really care about MHz, but I really want to see more powerfull processors in the PowerMacs so that the Mac community can have bragging rights for more than a great OS.

topicolo

Aug 22, 2002, 01:35 PM

Originally posted by Chryx

Except that the 68040 wasn't the fastest 68k chip, it was merely the fastest 68k chip that _Apple_ used.

the 68060 was a BEASTLY chip for it's time.

I don't know what your point is since that I didn't say that the 68040 was the fastest 68k chip at all. I said that the fastest 68040 was slower than a pentium. Besides, the '060 came out after the PPC 601 came out and by then, macs were going PPC all the way.

Quixcube

Aug 22, 2002, 01:46 PM

Processor speed is the critical factor in computing, but in this thread only one processor is being acknowledged--the central processor. Isn't anyone excited by 10.2's attempts to offload work from the CPU to the GPU? I am excited by this because it is a wonderful example of Apple (and nvidia) engineers using ingenuity to offset the obvious shortcomings of the Motorola CPUs. If the CPU can't handle the load, send the load elsewhere. I hope to see more of this kind of innovation in the future with more task-specific chips cooperating to get the job done instead of throwing all instruction at a CPU--even a Power4 derived one. QE is the wonderful result of scouring the machine to identify and tap into potential that was already in place. Go Apple.

Now that I complimented Apple, I have to get in a jab at them too. Why did they chose to equip all of their high-end machines with dual processors when both processors share a single bus? In high-end PCs and workstations, dual and quad machines are orders of magnitude more expensive than single processor machines because each processor has a replicated set of equipment attached to it. From what I can find, the Apple dual processor machines aren't designed that way. They seem to just sprout two processors at the end of the bus. How is this optimal? Shouldn't Apple be doing everything humanly possible on its high-end machines to work around the known limitations of the bus feeding the CPU, including replicating the bus for each processor? They just designed a new controller chip for the motherboard, why didn't they include an obvious improvement like this?

bertinman

Aug 22, 2002, 02:15 PM

Originally posted by Quixcube
Processor speed is the critical factor in computing, but in this thread only one processor is being acknowledged--the central processor. Isn't anyone excited by 10.2's attempts to offload work from the CPU to the GPU? I am excited by this because it is a wonderful example of Apple (and nvidia) engineers using ingenuity to offset the obvious shortcomings of the Motorola CPUs. If the CPU can't handle the load, send the load elsewhere. I hope to see more of this kind of innovation in the future with more task-specific chips cooperating to get the job done instead of throwing all instruction at a CPU--even a Power4 derived one. QE is the wonderful result of scouring the machine to identify and tap into potential that was already in place. Go Apple.

I was going to say something like this in my prev. post, but I didn't want it to be too long, plus I knew hardly anyone would read it or care since they all want to talk about G5's and such.

I believe Apple is doing a good job at trying to innovate around their bottle-necks in technology that surround them.

BTW, I think the new motherboard is a stronger helper in offloading the CPU by letting the GPU have some of the DDR ram bandwidth that the CPU can't use.

Now that I complimented Apple, I have to get in a jab at them too. Why did they chose to equip all of their high-end machines with dual processors when both processors share a single bus? In high-end PCs and workstations, dual and quad machines are orders of magnitude more expensive than single processor machines because each processor has a replicated set of equipment attached to it. From what I can find, the Apple dual processor machines aren't designed that way. They seem to just sprout two processors at the end of the bus. How is this optimal? Shouldn't Apple be doing everything humanly possible on its high-end machines to work around the known limitations of the bus feeding the CPU, including replicating the bus for each processor? They just designed a new controller chip for the motherboard, why didn't they include an obvious improvement like this?

I'm not an expert about this stuff, but I believe I read somewhere a comparison between using 2 proc. on one bus and having two busses. It seemed to me that they were certainly not equal, but both had advantages. If I find my source I'll post it, but I think it mainly had to do with when there was one bus, one proc took over part of a job when the other was busy, while when there are two busses, the two proc are given two different jobs. Could be wrong on this.

-- Bert :cool:

alex_ant

Aug 22, 2002, 02:29 PM

Originally posted by Quixcube
Processor speed is the critical factor in computing, but in this thread only one processor is being acknowledged--the central processor. Isn't anyone excited by 10.2's attempts to offload work from the CPU to the GPU? I am excited by this because it is a wonderful example of Apple (and nvidia) engineers using ingenuity to offset the obvious shortcomings of the Motorola CPUs. If the CPU can't handle the load, send the load elsewhere. I hope to see more of this kind of innovation in the future with more task-specific chips cooperating to get the job done instead of throwing all instruction at a CPU--even a Power4 derived one. QE is the wonderful result of scouring the machine to identify and tap into potential that was already in place. Go Apple.
Absolutely! The x86 Mac folks say they want Mac hardware to become more and more like PC hardware. I say Apple should slope the playing field as much as it can and use as innovative a system design as it sees fit, no matter how much that design happens to deviate from the x86 world.
Now that I complimented Apple, I have to get in a jab at them too. Why did they chose to equip all of their high-end machines with dual processors when both processors share a single bus? In high-end PCs and workstations, dual and quad machines are orders of magnitude more expensive than single processor machines because each processor has a replicated set of equipment attached to it. From what I can find, the Apple dual processor machines aren't designed that way. They seem to just sprout two processors at the end of the bus. How is this optimal? Shouldn't Apple be doing everything humanly possible on its high-end machines to work around the known limitations of the bus feeding the CPU, including replicating the bus for each processor? They just designed a new controller chip for the motherboard, why didn't they include an obvious improvement like this?
I guess it's a limitation of the MPC7450 CPU and the way it is not fully MERSI-compliant. I don't think Apple crippled the memory bus like this because it wanted to. I'm still awaiting word on whether this limitation resides on the motherboard or on the processor card, because if it resides on the CPU card, that means the current systems could possibly upgraded to whatever future CPU that supports a more efficient bus.

Alex

kenohki

Aug 22, 2002, 02:45 PM

Originally posted by Quixcube
If the CPU can't handle the load, send the load elsewhere. I hope to see more of this kind of innovation in the future with more task-specific chips cooperating to get the job done instead of throwing all instruction at a CPU--even a Power4 derived one. QE is the wonderful result of scouring the machine to identify and tap into potential that was already in place. Go Apple.

Exactly! Quartz Extreme is an extremely innovative use of the hardware and of OpenGL. Modern GPUs have lots and lots of calculation power but usually sit idle unless you're playing UT or something.

It's interesting though, this used to be something that was more common in the industry. The Amigas had a few coprocessors for graphics and audio, the NeXTcubes had an on-board DSP and the NeXTdimension board had an Intel i860 for DPS processing, etc. Even the Apple Quadra AVs had an AT&T 3210 DSP for AV and telephony features.

I hope we see more of this cuz it's got potential. Heck, we could even name the chips like in the Amiga. lol ;)

jerryobrecht

Aug 22, 2002, 03:04 PM

The IBM chip is real. A quote from IBM: "The POWER4 chip provides the processing power for eServer p690, the recently introduced high-end, IBM 64-bit POWER-architecture, 8-to-32-way server system." So, IBM's chip is not only in production, but has been implemented in one of their high-end servers.

The current PowerMacs have an excess power supply capacity of 250 watts. The Power4 chip running at 1.1 GHZ consumes 115 watts! Everything else staying equal, die size, applied voltage design, # of transistors, then at 2 GHz the chip would consume ~ 230 watts. This would just about eat up all of that excess PM power supply capacity and would explain why the PM has such a huge, out of proportion to current needs, heat sink. Maybe the next gen PM will use a Power4. Also, the Power4 implements, and extends, the AIM PowerPC instruction set.

The Power4 has 174 million transistors! Explains the power consumption. Probably will never see it in a PowerBook, unfortunately.

Personally, I see a Power4 chip inside Macs before a Moto G5 or an x86 architecture chip like from Intel or AMD.

jerryobrecht

Aug 22, 2002, 03:13 PM

Talk about number of processors and such...from IBM the Power4 implements two identical processors on the chip. Neither of these is the AltiVec equivalent vector processor that speculation claims IBM is now integrating onto the Power4. Also, the chip scales to 8, 16, 24, or 32 processors (4 Power4 chips = 8 processors). Of course, we are talking of a differently designed chassis to accomodate all of the required power and heat dissipation. This would be a very exciting approach, expecially given OS 10s (UNIX's, and the Mach kernal's) ability to wring all of the available processing out of many processors (SMP).

Dave K

Aug 22, 2002, 03:31 PM

Originally posted by jerryobrecht
The IBM chip is real. A quote from IBM: "The POWER4 chip provides the processing power for eServer p690, the recently introduced high-end, IBM 64-bit POWER-architecture, 8-to-32-way server system." So, IBM's chip is not only in production, but has been implemented in one of their high-end servers.

This is not the chip we will potentially be gettting.

For the simple reasons listed in each and every example you listed below the above, plus the fact that the current Power4 requires 700 lbs of insertion force for it's socket.

It's a mainframe server chip design, not a desktop server chip design.

IBM's upcoming announcement is of a Power4 variant for use in desktops and entry level servers. In other words, it will incorporate design elements of the Power4, but toss those that get in the way of making it cost effective or impedes hardware design for those markets.

The end result will not be a true Power4. However, if we're lucky, it won't be a 486SX either...

eirik

Aug 22, 2002, 04:18 PM

Apple is faced with a menacing obstacle to enticing a chip maker to build it a competive CPU: low market share. As mentioned many, many times in this forum, Motorola sells a hell of a lot more CPU's to embedded widget makers than to Apple. Consequently, Apple doesn't necessarily get in the front row when it comes to Motorola setting design priorities.

In comes IBM with junior, the Power4 offspring with a sleeker profile. We talk about IBM's new plant in New York, implying a direct correlation to this and Apple.

This is ridiculous insofar as Apple alone is way too small of a fish to justify a multibillion dollar investment. Before jumping, yes of course, the sum of sales to other customers and Apple is the driver for IBM. Also, junior, if indeed manufacturered at the New York plant, will undoubtedly be one among many different chips that IBM manufacturers there.

While I seem to be undermining my own argument, its now time to get to my point regarding Sun and SGI in my subject line. Surely IBM has more customers in mind than Apple and itself for Junior.

Rumors not too long ago suggested that SGI was considering Motorola's fabled G5. Also, Sun, I BELIEVE (not sure), had considered embracing the Itanium but jumped ship having seen the initial results.

Though Sun and SGI both design their CPU's and outsource their production to other companies to fab, their core competancies really aren't CPU design. That's not to say they're not good at it. I'm just saying that their customers would buy Sun or SGI systems whether they had Sparcs or Mips chips in them or not. They buy overall system performance.

The Itanium and fabled G5 tanked from their perspective so they have been sticking with their in-house designed semiconductors.

That said, if presented with a 3rd party source of CPU's that offered both performance and sound economies of scale, I'm confident that they'd happily embrace it. Naturally, they wouldn't jump over night and transition as one changes from one T-shirt to another. It would be a major strategic move with tectonic implications regarding adaptions of their software/OS's.

All that said, I'll be watching for signs of Sun and SGI being interested in Junior. I'm not predicting per se; I'm suggesting that such signs would be positive reinforcement for Apple embracing Junior and Apple enjoying long-term positive prospects for competitive hardware relative to the x86 folk.

The three of them have very common needs from CPU's. The three of them could potentially benefit from a signfiicant boost in economies of scale from Junior--POTENTIALLY.

But Sun and SGI, undoubtedly, don't want to open themselves to renewed and emboldened competition from Apple. If the three of them share a common CPU family, Sun and SGI would only do so if they could maintain a means to differentiate themselves from Apple.

Again, I'm not predicting the formation of this Troika. To be honest, I know very little about Sun and SGI. But, you can clearly see how Apple could benefit from such a Troika.

You know Book E being highly modular, suggests that Sun, SGI, and Apple might share the same core of Junior but may have alternate CPU-components such as memory controllers or what not. Obviously, Sun and SGI might go with considerably large L1 and L2 cache than Apple (higher cost).

If I were Steve Jobs, I'd have deployed some of my brain trust to find commonality with Sun and SGI to determine if an IBM Junior-centric Troika could be practical and beneficial to all concerned parties.

Can you guys think of how Sun and/or SGI might be interested in moving to Junior? I'm sure its easier to think of reasons for them not. I don't mean to stick our collective heads in the sand by ignoring the 'cons'. I'd like to ask the folks here where common needs may exist for the potential Troika.

A Troika would mean that IBM would invest very heavily in Junior, relative to an Apple and IBM only market for Junior. So, do you see where I'm coming from? If by some unlikely chance that the Apple braintrust hasn't even looked at the formulation of a Troika, our discussion would of it would not go unnoticed by Apple.

Cheers,

Eirik

alex_ant

Aug 22, 2002, 05:30 PM

Originally posted by eirik
While I seem to be undermining my own argument, its now time to get to my point regarding Sun and SGI in my subject line. Surely IBM has more customers in mind than Apple and itself for Junior.
Perhaps, but... I don't know, it seems like it could make sense. It's not a completely new chip - it's just a 64-bit PPC for desktops derived from a chip that already exists. So it can't be that huge of an engineering effort. If its only intended recipients are Apple, IBM, and a few minor embedded device and rack-mount server vendors, I don't think that would be too far-fetched. If all these companies combined could ship a million units in a quarter (didn't Apple sell 800k Macs last quarter?), I think that would be enough to sustain the platform. Maybe. :)
Rumors not too long ago suggested that SGI was considering Motorola's fabled G5. Also, Sun, I BELIEVE (not sure), had considered embracing the Itanium but jumped ship having seen the initial results.
I'm not too familiar with Sun, but I do have some familiarity with SGI. I remember the rumors about IRIX 7.0 being ported to PowerPC, but I don't remember them coming from particularly reputable sources. Ryan Meader's macosrumors.com was where I read it, so if that's where the rumor came from, I'd say it's probably about as likely as a comet crashing into the moon and knocking it into the Pacific Ocean in the next 18 hours.
Though Sun and SGI both design their CPU's and outsource their production to other companies to fab, their core competancies really aren't CPU design. That's not to say they're not good at it. I'm just saying that their customers would buy Sun or SGI systems whether they had Sparcs or Mips chips in them or not. They buy overall system performance.
From a hardware obsolesence standpoint, it's true that customers buy overall system performance, but when a company forks over $50k+ for a Sun or SGI server, they are also making an investment in that platform's future. They usually don't want to see their vendor move to another CPU platform, as that will invalidate their hardware & software upgrade path. One of the big attractions of SGI systems is their great scalability; when a company buys a 4-way Origin server, they know they will be able to grow it over many years to fit their gradually increasing performance needs. There are still Challenge servers from 1994 in use today thanks to the fact that software and hardware compatibility with early-'90s SGIs is still intact. A move from MIPS to PowerPC would break this; so either PowerPC would have to coexist for a good while alongside MIPS on the roadmap, or it would have to replace MIPS, causing existing SGI customers to scream.

SGI is no longer as proud or influential as it once was, but it still has its niches in the high-end scientific, technical and visualization markets, and those niches appear to be pretty well locked up. So I certainly don't think MIPS is going anywhere. (And SGI doesn't either, as they've got the whole next decade covered in their roadmap, to the R18000 and beyond.) So this reinforces my opinion that a PowerPC SGI would have to coexist with the MIPS lineup.

The current desktop SGIs get their butts kicked by PCs in raw CPU performance, but they still own their respective niches because they can do things PCs just can't do. One thing SGI and Sun don't want to do is step into the ring (again) against commodity x86 machines. They don't have much choice but to add value to their products elsewhere. If SGI's machines were available with fast, x86-crushing PPC processors but cost the same very high prices, would they sell much better than they do now (enough to justify the transition)? I'm not sure they would. A faster processor would be nice, but if it weren't available, would this fact hurt sales? I'm not sure it would. But the situation as it pertains to Sun may be different.

The fastest CPU available in an SGI today runs at 600MHz and performs very well in SPEC (at least for its clock speed), besting the 1GHz Pentium III by a good amount. But one thing to consider is that it consumes only 18 watts of power. SGI makes a big deal of this; its VP of whatever says that they've given up competing for raw performance and are instead aiming for 16-20 watts in their designs. Why? Because SGIs have fantastic multiprocessing capabilities and performance increases in direct, linear proportion to the number of CPUs added, and because these CPUs can be packed very densely into racks whereas Itanium2s and POWER4s and SPARCs cannot because of their cooling requirements. So MIPS is not a blazing fast architecture at the moment, but it is still unique and healthy with a bright future.
Can you guys think of how Sun and/or SGI might be interested in moving to Junior? I'm sure its easier to think of reasons for them not. I don't mean to stick our collective heads in the sand by ignoring the 'cons'. I'd like to ask the folks here where common needs may exist for the potential Troika.
I'll let someone else handle this one... for me, it's a lot easier to think of reasons why Sun/SGI wouldn't be interested in moving to "Junior," but that's only me. :)

Here's one more reason: Wouldn't it be weird if Sun and SGI used IBM CPUs in the same machines that are competing directly against IBM's machines? :) Sun and IBM are bitter rivals. I'm not sure what the SPARC roadmap looks like - do they need a new CPU that badly?

Alex

Kethoticus

Aug 23, 2002, 03:32 AM

ddtlm wrote:

This time around though, the rumors center around an actual chip that has actually been announced. This is starkly contrasted to the G5 rumors last year as well as the endless talk about some sort of 7470 or 7500 G4, or a full DDR FSB.

I do see your point. My problem is just simply that this seems too magnanimous. I mean, this is beyond-incredible news. Every time I hear something like this it slowly disappears and fades into the darkness of the collective Mac-user memory, or it's continually recycled and fanned to great intensity every six months just before an Expo.

The fact is that the Power4 clocked in at 1.3ghz more than a year ago on 180nm technology. It is easy to believe it will hit 2.0ghz next year. I fully expect it to turn up during 2003, perhaps not at 2.0ghz, but then again it doesn't need that clock speed to perform well. We may not catch the P4... but we will be so much closer.

Even closer would be wonderful. Shoot, I'd happily get a new Mac. Unfortunately, until it's officially announced as a Mac processor, I'll reserve my excitement. I mean, I hope you're right. But recent history does not make me optimistic.

kenohki wrote:

I doubt Apple will take the Intel route. Things aren't too rosey on that side of the fence either. P4 has a high clock rate but look at how Intel is getting sued over that now. x86-64 (Athlon, Opteron) hasn't proven itself yet and neither has IA-64. (Plus there's a lot of risk associated with IA-64. It's a whole different school of thought and another thread on it's own.)

Doesn't have to be a 64-bit x86 processor that Apple buys. The most recent 32-bit Athlons announced are somewhere around 2.2GHz. I'd welcome that in a second.

However, quad processor G4s won't happen at least until the 7470 and really only if that processor goes back to using the full MERSI cache coherency protocol. The current batches of G4 class chips only use the four state MESI which makes them less efficient in quad processing environments without separate cache controller hardware, software, etc.

Charming. Oh well!

POWER4 Lite (this new PPC from IBM) looks, from what has been released about it so far, like it could be a winner. It would provide binary compatibility (investment protection), and a familiar environment (PPC ISA). It also has gobs of memory bandwidth in comparison to what we have today and should be a screamer if it's comparable to POWER4 (even if you do have to crank up the clock to make up for the fact that you don't have an enormous cache like on POWER4). It is also much less risky for Apple than the Intel or AMD strategy.

Agreed. Jumping over to x86 would be much more challenging. I just don't believe that this gorgeous piece of IBM hardware is going to be found in any Mac any time soon, if ever. But whatever Apple does, they're going to have to do it soon. (Of course, we've been saying THAT for how long now? Apple survives by hanging on to a thread that refuses to break.)

Hopefully this chip will come sooner rather than later (complete with auto-vectorizing compilers). What I find interesting is that the other desktop processors being discussed in that group (according to the schedule for the forum) are somewhat near term (Itanium 2, Athlon/Opteron). Maybe this is a good sign for this chip to see the light of day soon. *shrug* We can only hope.

Indeed. I hope my pessimism is misguided. But only time will tell for certain.