970 Motherboard and Chip Delivery?

[astray]

Heres the latest from MacB:

Here of other exclusive rumours on the mother chart of the PPC 970. The source can be described as extrèmement reliable. But for lack of evidence they remain rumours.

This information relates to a mother chart of PPC 970 of preproduction sent to very rare APPLE partners.

- the mother chart has a form more rectangular than square (we had already had one moment ago of information on a chart "all in length").
- the processor is welded above (traditional for a preproduction) surmounted of a traditional squanderer.
- But especially, there are 8 connectors of RAM above (PC3200 a priori) with which 4 are covered with enormous a sticker "not uses" above. These 4 are cablés differently of the 4 others (not more infos).

One can imagine several explanations to the presence from these 4 slots nonfunctional. Here by order ascending of probability.
1) (not very probable) They were abandoned in the final version
2) (possible) on the mother chart dual, each processor will have its own RAM for more band-width
3) (probable) technology Twin Bank was not implemented yet on this chart of preproduction and will be it then.

Go more than 6 weeks for any knowledge!
- [ Rumour ] PPC 970 Rumors Loop give a layer from there - Lionel - 16:58:13
LoopRumors published rumours which corroborate those completely that we had given you a few weeks ago.

Foxconn (which is supposed to manufacture the machines containing PPC 970) would have received 20 000 Processors PPC 970 to 1,4 GHz, 40 000 to 1,6 GHz. IBM would have 50 000 Processors with 1,8 GHz in stock including 40 000 for Foxconn.
IBM would also have processors with 2 GHz in less number. APPLE would wait until there are 40 000 in stock of them to use them.
To finish, the PPC 970 should reach 2,3 to 2,5 GHz before being replaced by the PPC 980 derived from Power 5.

All this resembles so much so that we have told for a few weeks that there are 2 assumptions:
1) All information of our sources is perfectly exact. (always let us think We it).
2) the source of this information read the rumours of Macbidouille....

With you to choose:) ""

or go here: http://www.macbidouille.com/niouzcontenu.php?date=2003-05-13#5529

[MacRumors]

MacBidouille (http://www.macbidouille.com/niouzcontenu.php?date=2003-05-13#5529) posts some details about prototype motherboards for the PowerPC 970. As reported before, they indicate that the motherboards are more rectangular than square and have 8 RAM connectors -- 4 of which were covered by a Do Not Use sticker. They speculate on the reasons why this might be the case, but have no definitive information.

Meanwhile, LoopRumors (http://www.looprumors.com) posts what they claim to be shipment information to Foxconn. They report that Foxconn has already received 20,000 1.4GHz 970s and 40,000 1.6GHz 970s. 40,000 1.8GHz 970s are reportly due tommorrow.

[dornball]

whats the timeframe of a production run?

looks like there will be 4 pmac configurations, instead the ususal 3:

fast: SP 970 1.4 Ghz
faster: DP 970 1.6 Ghz
fastest: DP 970 1.8 Ghz
ultimate: DP 970 2.0Ghz

that's my guess for the lines, whenever it comes out....around june or july.

-dornball

[DrGruv1]

Yeeee - HAAAAA

[barkmonster]

Let's hope the prices arn't too far off the current line up when they ship.

That's if this rumour amounts to anything that is.

[pimentoLoaf]

Should I begin clearing my workspace (including installing a newer desk) for one of these wonderful new Mac desktops?

:D :cool:

[fussball]

If this is true, it sounds quite promising for a release of the 970s in June!

[nuckinfutz]

I can't wait any longer. We need speeeeeeeed

[Falleron]

If a Dual 2Ghz 970 was released then I would be very tempted to get one! This is even though I have a Dual 1Ghz now! Would have to sell mine + get a new machine!

[NicoMan]

guys you must be watching MacBidouille 24/7: you post their items very quickly indeed... (or do they send you a notification ?).

NicoMan

[dabirdwell]

Please be true...

Can the 1.4's go in PowerBooks? What are the power usage figures?

[Groovsonic]

I think the fact that two rumors sources makes this more weighty.

Now if they'd only announce them as "starting at $999", I'd be first in line!

(giggles in anticipation)

Whatever.

[IJ Reilly]

The most definitive report yet suggesting that the 970 will not only be announced next month, but that 970 Macs will go on sale then or shortly thereafter. Great news!

[mathiasr]

Originally posted by dabirdwell
Please be true...

Can the 1.4's go in PowerBooks? What are the power usage figures?
The PowerPC 970 is not supposed to have power saving features, you'd rather not expect to see it in a PowerBook.

[jch200]

boy, that sounds like some pretty hard evidence. I can't wait!

[Mudbug]

Bring it on!!!!

[Macmaniac]

I've said it once and I'll say it again, WWDC, 10.3 is the 64bit solution complete with new powermacs to top it all off.
I hope you have tickets!!!

[Mudbug]

now with all this info about chipsets and board designs, why can't we get a glimps (rendering, whatever) of the new case? Those boards have to go in something?

[Cabrewolf]

Originally posted by dornball
whats the timeframe of a production run?

looks like there will be 4 pmac configurations, instead the ususal 3:

fast: SP 970 1.4 Ghz
faster: DP 970 1.6 Ghz
fastest: DP 970 1.8 Ghz
ultimate: DP 970 2.0Ghz

that's my guess for the lines, whenever it comes out....around june or july.

-dornball

1.4 for the powerbook
1.6-2.0 for the powermac

Wolf

[dornball]

Originally posted by Cabrewolf
1.4 for the powerbook
1.6-2.0 for the powermac

Wolf

wolf,
i hope your right. i prefer your specs. if there was a 970 powerbook available, i would order it in a heartbeat.

-dornball

[Christner]

Check out Steven Den Beste's opinion on Apple's new music store strategy and the likelihood that the 970 will be its salvation:

http://www.denbeste.nu/cd_log_entries/2003/05/Applesexitstrategy.shtml

Yet another doom-and-gloomer or does he have the facts right?

[maradong]

wahoo.. :D

hence, with 8 ram slots. it seems not to be a pb mobo ... :(
I know it is fairly unpossible, but i want a pb with a 970 before august :D apple do somethin'

[d.f]

Originally posted by dornball
whats the timeframe of a production run?

looks like there will be 4 pmac configurations, instead the ususal 3:

fast: SP 970 1.4 Ghz
faster: DP 970 1.6 Ghz
fastest: DP 970 1.8 Ghz
ultimate: DP 970 2.0Ghz

that's my guess for the lines, whenever it comes out....around june or july.

-dornball

i hate to piss on your chips, but IMO: you won't see then use the 2.0Ghz. just because they exsist, doesn't men we (the consumer) get to see them. it doesn't look like they are in any sort of bulk production either.

i'd still be happy with your line up regardless.

[barkmonster]

I got bored reading, it's like Dvorak's drivel. I love the way they think If IBM charge a lot for the 970 and If that means apple can't compete in the long term on price they're screwed. Why not be more positive or does that just not get the hits someone needs on their site to give their word credibility ?

USS Clueless ? Damn Right!!!

[Flowbee]

Originally posted by Christner
Check out Steven Den Beste's opinion on Apple's new music store strategy and the likelihood that the 970 will be its salvation:

http://www.denbeste.nu/cd_log_entries/2003/05/Applesexitstrategy.shtml

Yet another doom-and-gloomer or does he have the facts right?

Looks exactly like every other 'death of Apple' article I've ever read. Complete with "facts" and MBA-student-wannabe business analysis.

Of course, someday in the future Apple *will* stop making computers. When that eventually happens all of these people will say, "See, I predicted that 20 years ago." :rolleyes:

Edit: or "50 years ago" :D

[adamberti]

Originally posted by Christner
Check out Steven Den Beste's opinion on Apple's new music store strategy and the likelihood that the 970 will be its salvation:

http://www.denbeste.nu/cd_log_entries/2003/05/Applesexitstrategy.shtml

Yet another doom-and-gloomer or does he have the facts right?

I dont know about his facts, but they sound like they could be somewhat reasonable. Its been said numerous times on this board that it would be great if Apple could get millions and millions of dollars from the Music Store to help offset Hardware costs. Pretty much windows users would help reduce the cost of Apple Machines . And then it turns into a nice cycle - More and more windows users switch because the price comes down, so volume continually goes up while they still continue to purchase music no matter what side of the fence they are on.

However this guy makes it sound like a new 1.6 GHz machine is going to cost about $3000 - I think hes being a little pesimestic. I do believe that they will be the same price or more expensive, but not by that much.

[apemn88]

Here is some food for thought:

If apple does end up using the IBM ppc970 (looks like it) and designs the OS (.3 pehaps to handle 64 bit architecture -- also likely) they have options.

Because the 970 can use both 64 and 32 bit code without penalty on either, apple could release OS X 10.3 for Intel 32bit procs.

Here is the marketing strategy: Runs better on 64 bit (2x faster) and only iApps run on Apple hardware, but all else will run on intel/AMD.

They could sell their hardware at the current premium and sell the OS for other hardware. Seems like a lot of $$ yo be made.

I know this is not likely, but it does make some sense. The OS margin would be incredible, windows folks are looking for a way out without buying new hardware, and Apple could pick up all the Linux users on PCs.

Thoughts?

[drastik]

Originally posted by Mudbug
now with all this info about chipsets and board designs, why can't we get a glimps (rendering, whatever) of the new case? Those boards have to go in something?

I think the prototypes boars usually come in blank grey boxes that are even sometimes welded together, they don't neccesarilly come in the finished case.

[RalphNumbers]

Originally posted by Christner
Check out Steven Den Beste's opinion on Apple's new music store strategy and the likelihood that the 970 will be its salvation:

http://www.denbeste.nu/cd_log_entries/2003/05/Applesexitstrategy.shtml

Yet another doom-and-gloomer or does he have the facts right?

Well, he says: "They're unlikely to ship more than a few tens of thousands of 970s in the first year."
And the MacB article this thread started on has them allready recieving shipments of 90,000 PPC970s. :rolleyes:

[nagromme]

"surmounted of a traditional squanderer"

About time! PCs have had this for years, while Apple has bullheadedly continued surmounting of proprietary squanderers.

[nuckinfutz]

Originally posted by Christner
Check out Steven Den Beste's opinion on Apple's new music store strategy and the likelihood that the 970 will be its salvation:

http://www.denbeste.nu/cd_log_entries/2003/05/Applesexitstrategy.shtml

Yet another doom-and-gloomer or does he have the facts right?

This illustrates the problem of Internet Publishing. Any idiot with a little time and money can spout garbage. I stopped reading when he mentioned John Manzione the Bipolar Bushwacker is what I call this guy.

Because the 970 can use both 64 and 32 bit code without penalty on either, apple could release OS X 10.3 for Intel 32bit procs.

What do you Developers do. Scrap their Altivec optimations and knowledge of Mac API's to start programming for X86 which is already in transition to 64bit?

Not gonna happen.

[rickag]

Originally posted by Christner
Check out Steven Den Beste's opinion on Apple's new music store strategy and the likelihood that the 970 will be its salvation:

http://www.denbeste.nu/cd_log_entries/2003/05/Applesexitstrategy.shtml

Yet another doom-and-gloomer or does he have the facts right?

Very disappointing article. I guess Steven Den Beste wrote this article, it wasn't signed.

He rambled on about Apple's business model without citing any facts. Only generalizations were brought up, not a good writing technique.

He made assumptions about the price of IBM's 970 without any support for its' supposed high price. Maybe he's right, but where is any of his logic? Assumptions that IBM will price the cpu based on previous server pricing, huh?

To top it all off he begins the article citing Mr. John Manzione at MacNet, who broke his powerbook by forcibly prying it open and blames Apple! When Apple calls Mr. John Manzione bluff, he uses his website to shamelessly slam Apple, while in the meantime gouges his credit card company for the cost of the computer he damaged.

I say balderdash, these guys need to get a life accept responsibility for their actions and move on. phew, what a diatribe.:)

[blueBomber]

Originally posted by apemn88
Here is some food for thought:

If apple does end up using the IBM ppc970 (looks like it) and designs the OS (.3 pehaps to handle 64 bit architecture -- also likely) they have options.

Because the 970 can use both 64 and 32 bit code without penalty on either, apple could release OS X 10.3 for Intel 32bit procs.

Here is the marketing strategy: Runs better on 64 bit (2x faster) and only iApps run on Apple hardware, but all else will run on intel/AMD.

They could sell their hardware at the current premium and sell the OS for other hardware. Seems like a lot of $$ yo be made.

I know this is not likely, but it does make some sense. The OS margin would be incredible, windows folks are looking for a way out without buying new hardware, and Apple could pick up all the Linux users on PCs.

Thoughts?

yep, that is some wild speculation. Also, someone mentioned earlier that the 970 wasn't designed with massive power saving features built in, so it wouldn't be ideal for notebooks. Hmmmm.... kinda makes me wonder if that new G3 with Altivec will end up in all the notebooks across the line...

[PretendPCuser]

Apple doesn't need to ship a dual 970 if the chip is prohibitively expensive. Nor would they have to if it is such a great performer. Yet the rumor mills seem to say that there will be a dual (or at least that's what we are all hoping). Who knows, if they make them all dual, they will be a little closer to volume discounting. :)

[seamuskrat]

Originally posted by apemn88
Here is some food for thought:


Here is the marketing strategy: Runs better on 64 bit (2x faster) and only iApps run on Apple hardware, but all else will run on intel/AMD.
Thoughts?

64 bit OS will NOT make it run FASTER. A misconception at work here. A 64 bit Os will allow for more memory and will allow for some efficiency with large memoroy intesnsive files. In SOME rare cases, it would actually slow a process down if it was re-written to be 64 bit.
Having an OS that is 64 bit capable with a chip that can handle 64 bits is great, but the speed we are hope will not come from the bit paths, but the chips themselves and other code enhancements on Panther.

[catalystx]

Originally posted by apemn88
Here is some food for thought:

Here is the marketing strategy: Runs better on 64 bit (2x faster) and only iApps run on Apple hardware, but all else will run on intel/AMD.

Thoughts?

Sorry, but there's at least one very large problem with your idea - 64 bit processors and software are NOT automatically twice as fast as 32 bit. There isn't much of an advantage to them other than support for a lot more RAM and the ability to handle very large numbers more efficiently, so you probably won't notice a difference.

On top of that, all mac software is 32bit right now and won't be recoded for 64 for quite awhile, if ever. Many programs won't benefit at all from being 64bit so I doubt the developers will waste time doing it.

CatalystX

[PaisanoMan]

Originally posted by apemn88
Here is some food for thought:

If apple does end up using the IBM ppc970 (looks like it) and designs the OS (.3 pehaps to handle 64 bit architecture -- also likely) they have options.

...

Here is the marketing strategy: Runs better on 64 bit (2x faster) and only iApps run on Apple hardware, but all else will run on intel/AMD.


Well, a 64-bit architecture isn't going to yield any theoretical speed gains for normal users -- none whatsoever. The speed gains will come from the improved speed and architecture of the chip itself. 64-bit CPUs are not inherently "2x faster" (but I do agree that Apple will probably try to take that marketing slant).

They will not be writing Panther to "handle 64 bit" because that won't really be necessary. The words "64-bit" refer to the size of the CPU's registers, meaning that the new chips can crunch numbers that are far more precise or larger than the 32-bit chips, but that doesn't necessarily mean they do it faster.

It's fun speculating about Apple's future, but it also helps to stay grounded a bit. I just want to make it clear that 64-bit != 2x faster. :)

[greg6028]

I heard of talk about a dual processor in a PowerBook.
Will this happen now with the 970?

Ultimate PowerBook with Dual 970
Fastest PowerBook with 970
Faster PowerBook with Dual G4
Fast PowerBook G4

I have a feeling this will happen in winter of 2003. The desktops will be first. Are not the desktop to oldest in the Apple line now?

[maxvamp]

Let me understand this...

When I am downloading , or working with data off the web through a cable modem, the 128 bit encryptions on various data objects can't benefit from a 64 bit machine?

When I am using journaling( like BeOS's 64 bit file system, which technology from this system is rumored to be in Panther) there won't be any file system performance improvements? Sherlock can't take advantage of this? RAID 5 won’t make aannnnyyy use of this?

When I am opening a .dmg, or stuffit archive with encryption, or need to do a MD5 check, Are you saying that there will be no advantage to the 64 Bit Proc?

All, I understand that most of performance increase to be gained from the 970 is from basic architectural design changes, and most apps will not take advantage from the increased memory addressing available, but people keep forgetting that computer security has a bright future, and we will ( with the war on terrorism ) see encryption show up in more and more components of the average computer system. Anyone that thinks 32-bit encryption is enough, or thinks that 256 bit encryption will be processed in the same time on either a 32 bit or 64 bit machine, is sorely mis-informed.

You see, 64 bits won’t be needed for the average user, or app, but for the average system for the sole purpose of security. Now, isn’t this what UNIX seems to be good at?

Just my two cents.

Max

[york2600]

According to the PDF from yesterday the 970 uses about 8X more power than the G4 used in the PowerBook. It'll be a while until there's a version for laptops.

Originally posted by dabirdwell
Please be true...

Can the 1.4's go in PowerBooks? What are the power usage figures?

[ffakr]

Originally posted by dabirdwell
Please be true...

Can the 1.4's go in PowerBooks? What are the power usage figures?
there is one point that I've never seen addressed. There is more to notebook viability than average or max thermal output. Most modern processors have powersaving features built into hardware that make them more attractive as portible processors.
The real question is, can the lower power 970s cycle through multiple levels of sleep. Can they dynamically shut down sections of the chip for micro-naps (Like Intel's Mobile P3s can)...
or is it a true spin off of Power-4. It it designed to just run 24x7.

this is what will make or break the processor as a mobile cpu. Maybe this is the reason that there are rumors of an IBM G3 with Altivec tacked on. That may be the future of macintosh portible cpus... at least for a while.

[nuckinfutz]

Originally posted by york2600
According to the PDF from yesterday the 970 uses about 8X more power than the G4 used in the PowerBook. It'll be a while until there's a version for laptops.

That PDF only compared the 1.3V PPC 970. The orginal pdf from the Microprocessor Report shows a 1.2Ghz 1.1volt that dissipates 19 watts. That's still higher than the 1Ghz G4 so I don't think Apple attemtps a PPC 970 notebook until 970's are fabbed at 90nm

[ffakr]

Originally posted by maxvamp
Let me understand this...

When I am downloading , or working with data off the web through a cable modem, the 128 bit encryptions on various data objects can't benefit from a 64 bit machine?

When I am using journaling( like BeOS's 64 bit file system, which technology from this system is rumored to be in Panther) there won't be any file system performance improvements? Sherlock can't take advantage of this? RAID 5 won?t make aannnnyyy use of this?

When I am opening a .dmg, or stuffit archive with encryption, or need to do a MD5 check, Are you saying that there will be no advantage to the 64 Bit Proc?

All, I understand that most of performance increase to be gained from the 970 is from basic architectural design changes, and most apps will not take advantage from the increased memory addressing available, but people keep forgetting that computer security has a bright future, and we will ( with the war on terrorism ) see encryption show up in more and more components of the average computer system. Anyone that thinks 32-bit encryption is enough, or thinks that 256 bit encryption will be processed in the same time on either a 32 bit or 64 bit machine, is sorely mis-informed.


I think this depends heavly on what type of math in involved with the type of operations you're talking about. The PPC 970 will bring native support for 64bit integer ops but the G4 can process double precision floats already (64bit). So the places where you'll see the biggest increase in performance would be applicaions that could benefit from 64 bit integer math.
Personally, I don't know enough about encryption to say what the algorithms look like. A 64bit filesystem would certainly be much faster because memory addresses could be stored in one register.

Personally I wouldn't be surprised if all of the areas you mentioned benefited from the 64bit'ed'ness of the 970, but I guess we'll have to wait and see... (or talk to the developers at WWDC)

[-hh]

Originally posted by apemn88
Here is some food for thought:

If apple does end up using the IBM ppc970 (looks like it) and designs the OS (.3 pehaps to handle 64 bit architecture -- also likely) they have options.

Because the 970 can use both 64 and 32 bit code without penalty on either, apple could release OS X 10.3 for Intel 32bit procs.

Here is the marketing strategy: Runs better on 64 bit (2x faster) and only iApps run on Apple hardware, but all else will run on intel/AMD.

They could sell their hardware at the current premium and sell the OS for other hardware. Seems like a lot of $$ yo be made.

I know this is not likely, but it does make some sense. The OS margin would be incredible, windows folks are looking for a way out without buying new hardware, and Apple could pick up all the Linux users on PCs.

Thoughts?

Well, the "2x faster with 64 bits" is wrong.

But what might be a different twist on this is that the iApp's do run on Intel hardware -- but only under an"OS X for x86" bundle, instead of under Windows.

The reason that this makes something interesting is because of Apple's move into selling music. We need to keep in mind that the Music Mavens are scared of the Windows platform because they've been burned by a lot of pirating (Kazaa, etc).

Currently, they're willing to "experiment" with Apple because its a very small market...very little downside risk. A way that you could get into the Intel hardware but to limit your risk would be to limit the compatible hardware, and one way to do this is to only support one OS. This is where OS X for x86 comes in.


-hh

[ktlx]

Originally posted by maxvamp
Anyone that thinks 32-bit encryption is enough, or thinks that 256 bit encryption will be processed in the same time on either a 32 bit or 64 bit machine, is sorely mis-informed.

A lot depends upon the algorithms chosen and how they are implemented. If the implementation uses AltiVec, 32-bit versus 64-bit will not make a difference. If you are choosing a streaming cipher over a block cipher, you probably are not going to notice a difference. If you are using public key encryption, you probably are not going to notice a difference.

A block cipher using 128-bit to 256-bit encryption without AltiVec help should be significantly faster on a 64-bit processor compared to 32-bits. Lazy implementations of 3DES, AES, Blowfish, etc. will show the most benefit.


You see, 64 bits won?t be needed for the average user, or app, but for the average system for the sole purpose of security. Now, isn?t this what UNIX seems to be good at?

Encryption != Security

[ktlx]

Originally posted by ffakr
I think this depends heavly on what type of math in involved with the type of operations you're talking about. The PPC 970 will bring native support for 64bit integer ops but the G4 can process double precision floats already (64bit). So the places where you'll see the biggest increase in performance would be applicaions that could benefit from 64 bit integer math.
Personally, I don't know enough about encryption to say what the algorithms look like.

Mainstream encryption algorithms are all integer math based. All of the "secret key" algorithms (DES, 3DES, AES, ...) benefit greatly from AltiVec so any good implementation is going to rely on that. The "public key" algorithms (RSA, ...) require very large numbers of bits (1024-bits to 2048-bits) but are only used for a brief period probably will not be all that noticeable.

Hopefully generating good, large random numbers should be significantly faster. This operation is not helped by an AltiVec unit so 64-bit is definitely better than 32-bit.

[maxvamp]

Encryption != Security

My point was more of that encryption is a facet of security that will be used everywhere ( eventually ). Thank you, however for pointing out that they are not synonymous.

Another poit I was trying to point out was thate there will clearly be places where the 64-bitness well help an application. That while the speed of 64 bit procs will not mean an absolute 2x increase in speed, there will be areas in common apps where there will be an increase.

In short, I am trying to debunk the thought of 'There will be no increases what so ever in using a 64 bit app for the common user.'

This is not quite right...

Max

[yzedf]

apple needs to offer something comparable to the following:

$2,249.00 (US)

P4 3GHz 800MHz bus
1GB DDR 400MHz RAM
128MB ATi Radeon 9800
200GB UATA 100 hdd
16x DVD
48x/24x/48x CD-RW
56k PCI modem
10/100 ethernet
19" CRT
Harman Kardon® HK-395 Speakers with Subwoofer
Keyboard / Mouse
XP Home
Wordperfect Productivity Pack
90 day McAfee
6 months Earthlink or AOL

As of right now the closest priced Apple PowerMac is over $3k (US). LCD does cost more, RAM is way overpriced, so is the hdd upgrade, Radeon 9700 Pro, Combo drive instead of seperates, No subwoofer, No AOL / Earthlink, no anti-virus (not that it's needed but switchers do want it), and a single button mouse. And that is for the single proc 1GHz G4! :eek:

I fully understand that comparing a Dell system to a Mac is not fair, but that is the market Apple has chosen to be in (personal computers). And in 3 months, the target will have moved again; either better pricing, or better hardware. Most likely both will happen :(

It is time for SJ to deliver. Year of the notebook or not, the PM needs help.

And the sad part is, there is no proof yet that Apple will get access to the IBM PPC 970. If Apple does get them, a increase in price would be a disaster.

[jettredmont]

Originally posted by maxvamp
Let me understand this...

When I am downloading , or working with data off the web through a cable modem, the 128 bit encryptions on various data objects can't benefit from a 64 bit machine?


A good point, that I hadn't thought of. Yes, security is one area where hardware 64-bit ints will help.


When I am using journaling( like BeOS's 64 bit file system, which technology from this system is rumored to be in Panther) there won't be any file system performance improvements? Sherlock can't take advantage of this? RAID 5 won’t make aannnnyyy use of this?


64-bit file system? I'm not sure there will be many performance improvements here on a 64-bit processor, but there will likely be some. Most of the work of a 64-bit file system can be done in 32-bits; its just the addresses which require munging in a 32-bit system.

Sherlock? I don't see how that would directly benefit frm 64-bit (aside from encryption, which you mentioned before).

RAID 5? I don't see a direct performance boost there with 64-bits, although both Altivec and the faster bus of the 970 would help it.

But encryption, that's one that hasn't been mentioned here (that I've seen) before, and should benefit from a 64-bit processor.

Note, again, though, that the chief benefits we'll see in a 970-equipped machine will not be from its 64-bit registers, but from its overall enhanced performance and much more matched FSB size.

[Freg3000]

Is Foxconn the place where the Powermacs are made now? Or will this plant be a new place for Apple (for their Powermacs).

[maxvamp]

apple needs to offer something comparable to the following:

$2,249.00 (US)

P4 3GHz 800MHz bus
1GB DDR 400MHz RAM
128MB ATi Radeon 9800
200GB UATA 100 hdd
16x DVD
48x/24x/48x CD-RW
56k PCI modem
10/100 ethernet
19" CRT
Harman Kardon® HK-395 Speakers with Subwoofer
Keyboard / Mouse
XP Home
Wordperfect Productivity Pack
90 day McAfee
6 months Earthlink or AOL


I think the system you will probably see for that price would be

apple needs to offer something comparable to the following:

$2,249.00 (US)

dual 970 1.6 GHz 900MHz bus
1GB Dual DDR 400MHz RAM
128MB ATi Radeon 9700
250GB UATA 100 hdd
4x DVD-R/RW
56k PCI modem
10/100/1000 ethernet
Keyboard / Mouse
Mac OSX 10.3
AppleWorks
Maybe .Mac

A couple of things I want to point out here that makes up for the differences from your list but equal out are :

- dual 1.6 procs. If IBM's numbers are to be believed, a single 1.6 will give a P4 3GHz a run for it's money ( but won't beat it ). Following Apple's logic, if you add two procs together you get get about the same speed as a competitor's single ( dual 1 Gig G4s to compare against a 2 GHZS P4, for example ). This configuration would eat the single P4 alive

- DVD Reader with CDRW. In my opinion, this is a rotton configuration. Why would you want redundant CD drives, and have a 5" drive bay waisted? this combo approaches a single DVD-R in cost, so why not just get a single drive. It looks less cludgy

- Ethernet while 10/100 cards are a dime a dozen, I do run a small network in my home, and take a little comfort knowing that the nic in the Mac is going to be reliable, that it isn't from the cheapest bid that Apple could get. I have seen a lot of crappy 10/100 cards out there. Furthermore, I like longevity, and I like knowing that when I upgrade my network, that there is one less card to have to buy.

- Mouse : When in Rome.....

- Windows XP Home: To be honest in your comparisons, you need to add $199 to upgrade to WindowsXP Professional. WinXP Home has to many crippled features. One would be no dual proc support, another is networking diversity.

- I believe that AppleWorks can compare to Wordperfect rather easily. In both cases, if you want to standardise, you have to upgrade to MS Office.

- Virus scan? - See .Mac

I did leave off the speakers and the monitor. I also am not going into the scenario of the performance you can gain or lose in the Dells depending on what chipset they put in it ( they have been known to cripple good procs with bad chipsets ), but honestly, I think you can, and will continue to get good comparable machines from Dell and Apple for about the same price, even though they will not be exactly the same machine. There are some trade offs ( 1000 ethernet nics are expensive ), but that is the way it goes.

Max

[drastik]

Originally posted by yzedf

As of right now the closest priced Apple PowerMac is over $3k (US). LCD does cost more, RAM is way overpriced, so is the hdd upgrade, Radeon 9700 Pro, Combo drive instead of seperates, No subwoofer, No AOL / Earthlink, no anti-virus (not that it's needed but switchers do want it), and a single button mouse. And that is for the single proc 1GHz G4! :eek:



I don't see how you get the 1 ghz powermac to over $3k. Even is you bought the extra HD and RAM from apple and the 19 CRT seperately from Dell or wherever, it doesn't get up to three grand.

[macmunch]

I have an idea on this !
A very good I think

If there are 4 Models that would be cool !
and dont forgett the DP coudnt ne so expensice because than there werent 3 models of them !!!!

So look at this idea:

1.4 SP low Price Tag 1199 - 1399
1.6 DP 1699 - 1899
1.8 DP 2099 - 2399
2.0 DP 2799 - 2999 or even 3099


But if they introduce so many models with DUAL I see a big chance to get this Single PPC970 very cheap !

[ktlx]

Originally posted by jettredmont
64-bit file system? I'm not sure there will be many performance improvements here on a 64-bit processor, but there will likely be some. Most of the work of a 64-bit file system can be done in 32-bits; its just the addresses which require munging in a 32-bit system.

RAID 5? I don't see a direct performance boost there with 64-bits, although both Altivec and the faster bus of the 970 would help it.

I am skeptical that 64-bit CPUs will help much for either of these cases. In my opinion, the address manipulation work is a small part of the total time taken. For file systems, there is still a bandwidth I/O issue and for RAID 5 it is still computing the parity and striping information that is the bottlekneck.

I think the increase in clock speed and much faster memory I/O will be where you see the benefit here.

Please don't misunderstand me, I am not saying 64-bits is worthless, I just think too many of us think of 64-bits as this magic nirvana when we would see just as much performance increase from a 32-bit version of the PowerPC 970 (all other factors being equal).

If you are not doing video editing, 3D rendering or something else with very large datasets, 64-bits doesn't help enough to be noticeable. Encryption and random number generation will see some benefit, but look at how much this is really happening on a typical system. Not enough to be noticeable.

[IVIIVI4ck3y27]

Originally posted by greg6028
I heard of talk about a dual processor in a PowerBook.
Will this happen now with the 970?

Ultimate PowerBook with Dual 970
Fastest PowerBook with 970
Faster PowerBook with Dual G4
Fast PowerBook G4

I have a feeling this will happen in winter of 2003. The desktops will be first. Are not the desktop to oldest in the Apple line now?

How about them Apples?!?

Not likely in Winter 2003 on them Powerbooks, I figure sometime in mid-late Q2 (May-June 2004) or as late as early Q3 2004 (usual August-September-ish release spot), and not likely a PPC 970, but a further evolution of the PPC 9xx lineup. The next upgrades to Powerbooks will likely be faster G4's. Those will likely fill the gap until Apple can get a PPC 9xx that is laptop ready. You "MIGHT" see a 9xx make it into the iMac, which has moved from the bottom of the line machine to a more "midrange" machine, but even that to me is a bit curious as it'd further drive the costs up on the iMac over the eMac, which is basically it's CRT-based fraternal twin sold at a slightly cheaper price (due to monitor costs). My bank is, Apple will release these processors "ONLY" in top of the line machines, with Apple Pro and Apple XServes getting the first 970's, and it trickling down into the other desktops (next iMacs and eMac together on similar architecture to keep costs relatively low, followed by Powerbook and eventually iBook) by the time the next generation of 9xx processors hit.

As noted earlier by someone, the PPC 970 doesn't have any "power saving" features for battery efficiency. Unless Apple is on the verge of some incredible battery technology that compensates for this... don't count on it anytime soon. I mean... I don't think Marty McFly and company are going to just slip Apple the Flux capacitor tomorrow, with a USB-based Mr. Fusion for added oomph. ;)

The PPC 9xx, while less energy intensive than the current top of the line desktop G4 variant (also not laptop suitable at around 30w), is not as efficient as the current Powerbook variant of the G4 (they're not all the same model of G4, last I checked), which is already accused by many to be a "lap scorcher" at it's 12w of consumption, even with energy management/power saving features. Unless they can get the 970 down to that similar temp and to that level of wattage or better (mind you, the G3 in the iBook is around 7w, and it's barely lukewarm to the touch), don't expect to see it in a laptop.

I know you all want them... but even in Apple's history, the laptops were always the last one's to get the new generation of processors. Where were the G4's launched? Desktops. Where were the G3's launched? Desktops. Depending on the complexity and the time to get the heat down... it could be a short period (6 months) or a full year to year and a half before we see a PPC 9xx Powerbook. At which point Apple will still not be G3/G4-free, as obviously the iBook will likely transition to a faster G3 or uprated G4 before too long. Perhaps even using a hand-me-down Powerbook G4 motherboard, obviously updated for better I/O so as to make it faster than the current Powerbooks, on a more budget-minded philosophy, of course.

1-970-FOR-MEEE

There's a cost outlook to look at... and then a volume standpoint. Apple is going to be selling desktops like crazy as the desktop people have sat on G4 with the same enclosure for far too long. That is the #1 priority for Apple right now because all other product ranges are selling well, but the Pro models which are a staple of the Creative market are sitting damn near stagnant in sales, and losing ground to the PC at an alarming rate. The odds of Apple having enough PPC 970's to fill out an entire lineup is hard to fathom, because it usually takes a bit to ramp up processor technology, much less bring the efficiency down to be suitable for laptops... and PPC 970 is like bleeding edge first generation of this platform.

Then there's the ability to mfg. all of these at the same time and meet demand. Apple has "NEVER" revamped the entire lineup in one swing... and I don't expect to see it now. Even if Apple could, you'd want to minimize the ties to something new until you have it ironed out so that if it's erroneous, you're not doing a mass recall and hurting your image (remember the Pentium floating point disaster? Apple couldn't withstand that level of PR right now). If all of Apple's machines were based on 970, which not even any PC mfg.'s are based all on Athlon XP or Pentium 4; that'd be a substantially large risk, you'd have a flatlined price philosophy, and why would anyone want to buy a Pro Desktop if they could get an iMac with the same processor and speed for less? If you had Powerbooks with the same 970's... then you'd basically be telling me that the desktop is obsolete because the Powerbook is the same speed and same performance range? Notttt gonna' happen. Even the PC's use Centrino's and Durons for their laptops, while having a midrange Celeron/Duron, and a top of the line Athlon XP/Pentium 4, followed by Pentium 4 Xeon and Athlon MP.

Apple doesn't have as complex a lineup as the PC... but I do expect to see G3 iBooks, G4 Powerbooks, iMacs, and eMacs, and PPC 970 Pro Desktops and XServes; then seeing the PPC 9xx Powerbook lineup next year when the next variants of the PPC 9xx roll out (along with uprated versions of the 9xx in desktops; one more efficient and slightly slower or similar to current speeds... the other breaking 2.2-2.8 Ghz. and still requiring more energy than the laptop version), then PPC 9xx eMacs and iMacs (likely same processors as the Powerbook), with the iBook moving to G4 or faster G3's briefly before getting a 9xx variant as the other processors move ever upwards in speed (likely third evolution of the PPC 9xx; with the iBook getting the old PowerBook's revised processors). It's how Apple's done it in the past, and it just makes sense.

How about that Sodium plated Powerbook?!? ::whistling::

The aluminum laptops were just released a short time ago... and they have yet to launch an uprated replacement for the titanium 15" model. I expect a G4 aluminum accompaniment to the 12" and 17", much as Mac OS Rumors spoke of, likely at around 15.x inches. Some expect to see 9xx launched in this model, but I can't fathom it, not with the lack of power management features and it's higher than current laptop G4 wattage. I could see Motorola scaling down their G4 desktop processor in wattage and bumping up the speeds of the G4's so that at the time of the 970 Pro desktops and XServes... that Apple bumps the iMac and eMac lineup up past the current models in speed, and uprates the Powerbooks with a faster and more efficient wattage version of the G4, perhaps somewhere in the 1.2-2 Ghz. range. That same variation of G4 processor might be found in Powerbooks, eMacs, and iMacs where heat is a major concern. At that point we might see 1 Ghz. G4 iBooks too, or a faster G3 from IBM, although I expect the iBook to take advantage of SIMD before too long and make "Velocity Engine" a bigger standpoint. Especially since I figure the next "MAJOR" Powerbook design next year will get the Pro laptops up to 9xx.

Dual Quad 4-barrel... phooey

The odds of dual processor Powerbooks isn't that good... for one that's an extra processor chewing up juice (desktops it makes sense, laptops... unless they can get dual G4's or 9xx's running at 7w like the current iBook, you're talking even more heat than a current laptop G4 which is already hot to a lot of people's chagrin), generating more heat, and eating up more battery life. Yet if it does happen, it'll likely be some hybridization of G3/G4... and that's just not logical at this stage. I doubt we'll see this happen for quite some time, if ever. For one, I doubt IBM is going to invest in making a new desktop-based G3 processor when they're moving towards PPC 9xx as their next generation (likely to replace their 64-bit G3's they use in their server platforms), effectively phasing out much need for desktop G3's outside of the iBook which will likely get to a low-end 9xx (likely go G4 as interim or a uprated speed G3, although I doubt IBM will keep evolving it as it is) before too long after the Powerbooks finally get one. They might focus on embedded, but adding SIMD to a G3 would require a lot of work, work that could be better focused on making a laptop variation (with power management, shrunken die, etc.) on the 9xx series of processor which already has it. There's also the fact that the Apple variation of the G3 itself isn't designed for SMP, at least not the Apple compatible variations of the PPC architecture made by IBM, so IBM would have to invest extra time and technology, when they could be better off making a whole new architecture based off the 9xx line which supports SMP and could be made to work in laptops with some efficiency work and streamlining. Which is what I'm expecting more than anything.

[Abstract]

*looks above* Geezus!!!!


Originally posted by macmunch
I have an idea on this !
A very good I think

If there are 4 Models that would be cool !

So look at this idea:

1.4 SP low Price Tag 1199 - 1399
1.6 DP 1699 - 1899
1.8 DP 2099 - 2399
2.0 DP 2799 - 2999 or even 3099


But if they introduce so many models with DUAL I see a big chance to get this Single PPC970 very cheap !

Is there any guarantee that the new PM's will have dual 970 processors? I mean, couldn't there be a single proc 1.8 and 2.0 GHz IBM 970 out before they release the duals? If these processors only go to 2.5GHz, there won't be too much room for Apple to offer speed bumps over the next 3-4 years or so unless they can offer singles for now, and duals later.

If dual 970's will truly be released immediately, then I think this config is more like it:

1.4 SP iMac
1.6 SP iMac

1.6 DP PowerMac
1.8 DP PowerMac
(or maybe 1.4 and 1.6 DP PowerMacs)
I can't see them releasing the 1.8 and 2.0 GHz 970 processors immediately because of the upgrading reasons I previously mentioned. I also can't see there being 3 processor choices for the PM's with the 970 processor.

[copperpipe]

Well, most people here have been saying that 64 bits doesn't really make any difference except in encryption, which is to say that the difference they will make is miniscule at best. Now the people saying this definitely know more than I do, because I can't even understand what they are talking about in some cases. But, I just don't understand why Intel, AMD, and IBM are all investing billions of dollars in the race for 64 bit? It doesn't make sense to me, for such a tiny gain. Maybe we should go back to 16 bit? or 8? did they make a big difference? The POWER 4 uses 64, and it descimates every processor out there, but I suppose that it could be 32 and would descimate every processor, except when it's decoding an encryption. I dunno, maybe everyone here is right about 64 bit not making any noticable difference, but I'm having a hard time believing it.

PS - I truly don't mean to upset anyone by this, and I don't doubt that everyone has good reasons for their beliefs...

[rjwill246]

Originally posted by Christner


Yet another doom-and-gloomer or does he have the facts right?

A number of things don't make sense here and that is the "fact" that all Macs are wierd or too slow to be useful etc. This is an untenable line since not all Dells or HPs etc are the fastest most loaded machines on the planet and XP isn't the most blazing OS either but like OS X it hasn't been around that long and it is quite likely that both Apple and Microsoft will continue to work on the bloat etc. in their respective OSes in order to speed them up.
The author has assumed that Apple will be the only user of the 970s and that is a very poor assumption... does he think that IBM is about to go out of business too and wouldn't have any need for them either?
While the user comes off as a long time Apple fan, the words ring hollow and sound much like those of "flamers" etc in these forums. In any case, the comments about the AAC format are not entirely true.. there is a difference between an AIFF formatted CD and a transcoded AAC format file but it is not huge and to claim otherwise means that the person doing the transcoding had no idea what they were doing.
Apple's demise ( note that their market share is now 2.9% and falling..mmm where did that come from?) is clearly apparent in the 50% increase in just 2 weeks of their share value!
Still, it is troll-like articles like this that make one think and then be glad that you are a Mac user and that Apple is far from doomed. Btw, the writer sounds like a ZD-net reviewer where any Apple product (notable exception, the iPod) is just terrible compared to any flavored Dell.

[speechgod]

Something is wrong. Foxconn makes connecters. They don't make mobos, cases, or anything else. They, for example, make the ADC connector. Why would they currently be sitting on the world's largest supply of 970's?

This puts the LoopRumors rumor is bad light.

[Frobozz]

Originally posted by d.f
i hate to piss on your chips, but IMO: you won't see then use the 2.0Ghz. just because they exsist, doesn't men we (the consumer) get to see them. it doesn't look like they are in any sort of bulk production either.

i'd still be happy with your line up regardless.

I tend to agree that just because the 2.0 is out, doesn't mean we will have them. There will be at least one revision in January, and probably another next June/July before the 980's are ready. If the 970's will only reach 2.5 GHz at their current process, I would think you'd see two revision cycles:

initial (june):
sp 1.4 970
dp 1.6 970
dp 1.8 970

1st rev. (jan. '04):
sp 1.8 970
dp 2.0 970
dp 2.2 970

2nd rev. (jun. '04) if still using 970's instead of 980's:
sp 2.0 970
dp 2.2 970
dp 2.5 970


That would space it out nicely based on current numbers. The only variable is if they can crank out .09 process chips. If they can, then we may see speed bumped 970s, but why not make the 970's only in laptops and consumer computers at that point? Then move the pro line to 980's.

Either way the lineup is going to be ludicrously faster than my DP 1.0 G4 Quicksilver... and that's a FAST mac. ;-)

[nawk]

Originally posted by speechgod
Something is wrong. Foxconn makes connecters. They don't make mobos, cases, or anything else. They, for example, make the ADC connector. Why would they currently be sitting on the world's largest supply of 970's?

This puts the LoopRumors rumor is bad light.

A simple trip to their website will show that they make more than connecters. Their section on PC enclosures even shows an G3 powermac tower.

[IVIIVI4ck3y27]

Originally posted by apemn88
Here is some food for thought:

If apple does end up using the IBM ppc970 (looks like it) and designs the OS (.3 pehaps to handle 64 bit architecture -- also likely) they have options.

Because the 970 can use both 64 and 32 bit code without penalty on either, apple could release OS X 10.3 for Intel 32bit procs.

Here is the marketing strategy: Runs better on 64 bit (2x faster) and only iApps run on Apple hardware, but all else will run on intel/AMD.

They could sell their hardware at the current premium and sell the OS for other hardware. Seems like a lot of $$ yo be made.

I know this is not likely, but it does make some sense. The OS margin would be incredible, windows folks are looking for a way out without buying new hardware, and Apple could pick up all the Linux users on PCs.

Thoughts?


Putting the (Mac OS) X in x86

::buzzer::

Nada.

Apple will never release their OS (as in not just Darwin, but the whole enchilada) on other people's hardware, unless the Mac goes the way of NeXT, or Be Inc. Not very likely...

With Jobs at the helm and a healthy dosage of applications vendors available, and with a successful launch of products like the iPod (for Windows and Mac now), the further evolution of the iPod, and the further evolution of Apple into being more than just a computer developer... Apple is even less concerned about processors than they are just flat-out innovating and making $.

I heard some tunes through my window...

Diversification is something Apple will likely do a lot more of, by deploying products like iTunes on Windows, so they can exploit the Apple iTunes internet store for all it's worth, while also increasing brand awareness to the Windows crowd with having an elegant MP3 player with a nice interface, great sound, AAC support, an integrated online music store experience, and support for CD-burning directly from the player.

I know, I know... "...but give them iTunes and why would they want to switch?!?"

Simple, because...

Any other iApps to Windows will likely come at a cost, if it's even available at all. I mean, Apple doesn't want to just give away the greatest assets to luring people to switch. Yet, if Apple doesn't at least give Windows users a chance to help their bottomline (via something as nifty as the Apple music store that will appeal to anyone), and also give them something that they can download for free and use to see how much better it is than anything on the Windows platform (and hell... why not support Linux too?!? I'm all for an x11 based iTunes variation using KHTML in KDE)... it's sort of like... if a tree falls in the forest... will anyone hear it?

The iPod is a great component that showed the Windows crowd what Apple is about. A free download of iTunes for Windows that 1) interconnects with the iPod, 2) trumps any and all MP3 software players for Windows (if Winamp is the best they have... y'know it's pretty sad), and *WILL* likely be the only AAC-compatible player on Windows (outside of QuickTime, eventually), and 3) offers Apple's iTunes KHTML storefront? Pure genius, limited costs to Apple, and considerable rewards in terms of mindshare and marketing for Apple, as well as music sales and secure music sales to Windows users that lines Apple's, and the major recording studios, pockets. It's a win-win and a definite "MUST DO" for Apple...

I also look to see some coders (not necessarily Apple, and in fact... I doubt we'll see Safari persay on Windows) bring a KHTML-based browser experience that pseudo-integrates with Windows XP (much like Konqueror does in KDE) and allows you to navigate through the system much like IE does in XP (perhaps KDE with Konqueror for Windows?!?). Especially if Microsoft is forced into not bundling IE with their system, or is forced to give users the option to install Konqueror or IE on startup. If the browser situation was opened up on Windows to choice like it is on the Mac (and all variants of browsers should be included on the OS CD's, much like Netscape, IE, and Cyberdog were before on the Mac)... it could be a coup for KHTML, and as a result... Apple/KDE. After all, if Apple and KDE could win the browser war back from Microsoft, who has been incredibly sluggish with IE updates to increase it's usability on the Mac, much less improve it's look/feel on the PC... KDE and Apple via KTHML could generate a coup to make KHTML and W3C more prevalent... especially with the DOJ's rulings requiring Microsoft to unintegrate IE from XP in future versions by default.

Apple supporting PC cloning with OS X would be a nightmare due to the incredibly large myriad roster of components that a PC is built with. Be Inc. (remember BeOS on Intel?) even struggled at supporting all of the video cards, all of the processors, et al. Apple trying to support their own hardware and chase their tail on the PC side? Not a chance. If Apple ever does support AMD/Intel outside of Windows... it'll be in proprietary made enclosures, with proprietary motherboards, and a closed circle of supported hardware that barring a leak of architectures (or reverse engineering)... wouldn't even run Windows most likely (because Apple wouldn't want it to where you could buy a Mac and replace their OS with their arch-enemies). Any vendors wishing to support said hardware would have to create their own drivers... and either submit them to Apple or ship them on disk themselves. Microsoft does what they do because they don't build their own PC's, they're #1 priority is based on cloning (as a result of not making their own hardware), and the only OS that comes even remotely close to competing with Microsoft on sheer amount of hardware supported is Linux; and that's more because it's an open-source movement than a company with a ridiculously large engineering staff (bought and supported via the monopolistic funding they receive by own 90+ % of the marketshare).

I may be a Mac enthusiast, but I'm not a foolish zealot... and I do have to give credit where credit is due. Microsoft went from Plug and Pray in Windows '95 to a freakin' Plug and Play miracle with 2k and XP on a large myriad of machines. The fact that they support anywhere near close to 40-50% of the currently available PC hardware is downright amazing, especially with some of the shotty crap hardware by no-name vendors lurking in the wings (and some of the shotty drivers for that shotty crap). This might be the one thing Microsoft's done the best... it's not so much that they've innovated in doing this, it's that they've selected and copied the better ideas and worked at doing them equally as good or better, or they cannibalized the more successful competition via guerilla tactics so that they couldn't spend $ to out-develop them. Either way... if Apple had to support a myriad of clone hardware vendors... it'd be a time period before everything was running at full song anywhere near to what Microsoft is. I don't doubt that Apple could do it... but I doubt Apple would take such a plunge when they make the whole kit and kaboodle and reap the profit margin rewards as a result.

For some things though... it's like brand equity. It gets Apple known. Apple will be an applications provider for Windows (not an OS X provider for x86), with stuff like Keynote and a future Office suite, along with iTunes with iTunes music store for Windows, the further evolution of QuickTime, and more breakthrough products like iPods that cater to all computer users near and far. After all... to lure them in, you have to let them at least kick the tires... and what better way than from in the privacy of their own P.C. (piece of crap).

:)

[Freg3000]

Originally posted by Abstract
*looks above* Geezus!!!!




Is there any guarantee that the new PM's will have dual 970 processors? I mean, couldn't there be a single proc 1.8 and 2.0 GHz IBM 970 out before they release the duals? If these processors only go to 2.5GHz, there won't be too much room for Apple to offer speed bumps over the next 3-4 years or so unless they can offer singles for now, and duals later.

i think that the biggest piece of evidence for dual processor Powermacs came today in the chip numbers. 20,000 for the 1.4, yet 40,000 for the 1.6 and 1.8. Why twice as much?
Twice as many processors per machine. :)
Dual configurations for machine carrying 1.6 and 1.8 processors, and single for the 1.4.

[posixstudent]

I hate to bring this up, but I have never heard any verification that the 970's would be in PowerMacs. I have a feeling that they will appear in Xserves first with a 64-bit version of Mac OS X Server. This would make more since to me. If Apple could improve their market share for servers then they could push for a better volume discount for the chips. The concept is called "economies of scale." The last thing Apple needs to do is bet the farm on a new processor that could cause more 3rd party software incompatabilities then the Release of Mac OS 10.2.

[Abstract]

*points up (again)* Why the novel,IVIIVI4ck3y27? No offense, but I didn't read all of it. Skimmed.....yes, but I didn't read it, per se. :o


I think Frobozz has a similar idea as myself when it comes to the processors that come out. Although, I think the SP 970's will be available for iMacs, not for PM's. I'm not quite sure how the single processor PM's are selling, but I think its a mistake to have them in the first place, and the single proc will be relegated to the iMac only while the single proc PM is eliminated.

Thanks alot, Freg. I didn't notice that. :)

[Frobozz]

Originally posted by apemn88
Here is some food for thought:

If apple does end up using the IBM ppc970 (looks like it) and designs the OS (.3 pehaps to handle 64 bit architecture -- also likely) they have options.

Because the 970 can use both 64 and 32 bit code without penalty on either, apple could release OS X 10.3 for Intel 32bit procs.

Here is the marketing strategy: Runs better on 64 bit (2x faster) and only iApps run on Apple hardware, but all else will run on intel/AMD.

They could sell their hardware at the current premium and sell the OS for other hardware. Seems like a lot of $$ yo be made.

I know this is not likely, but it does make some sense. The OS margin would be incredible, windows folks are looking for a way out without buying new hardware, and Apple could pick up all the Linux users on PCs.

Thoughts?

Well, to be honest I think the odds of Apple using Intel/AMD is zero. The only way it would happen is if there was no longer a PowerPC chip available.

Also, the 970 is in the same ballpark for price as a G4. It might end up being cheaper in the relatively close future.

I'm not knocking you at all on this. Sincerely. I think your post deserves a lot of merit... but I did get me thinking. After all, what incentive is there if you eleminated everything but the financial factors? First, I don't think Apple's price point has much of anything to do with their success. They're a success now. Maybe if they could knock $500 off their pro lines... but their consumer lines are actually cheaper than comparable PC systems. But, let's take the financial factor into account on it's own.

If Apple was only able to save $100 a chip, the Intel/AMD thing it mute. Never gonna happen. If the diff. was $500, then maybe. If it was $1000, then def. a possibility. The bottom line is Apple's bottom line. :-) They will charge the same as they always have, plus or minus a couple hundred dollars. The reason is that is what the marketplace is capable of withstanding. Apple makes huge profit on their hardware and it's the only way they can sustain themselves with their smaller marketshare.

Intel/AMD will not make people switch to the Mac unless it meant that Apple could sell a machine for $500. They never will, because they can't make a margin on that and stay in business. They won't switch based on brand recognition, either. The only people that care about the chips in their machines are dorks like us. Ask your average PC user what CPU model and speed they are running. They haven't a clue. Yes, your gamers and your younger peple might, but Apple isn't doing as bad there as one might believe, IMHO.

[ktlx]

Originally posted by copperpipe
Well, most people here have been saying that 64 bits doesn't really make any difference except in encryption, which is to say that the difference they will make is miniscule at best. Now the people saying this definitely know more than I do, because I can't even understand what they are talking about in some cases. But, I just don't understand why Intel, AMD, and IBM are all investing billions of dollars in the race for 64 bit? It doesn't make sense to me, for such a tiny gain. Maybe we should go back to 16 bit? or 8? did they make a big difference? The POWER 4 uses 64, and it descimates every processor out there, but I suppose that it could be 32 and would descimate every processor, except when it's decoding an encryption. I dunno, maybe everyone here is right about 64 bit not making any noticable difference, but I'm having a hard time believing it.

You are talking cats and dogs here and even then, not everything you say is correct.

Except for AMD, all of the mainstream players (Intel, IBM, Sun, HP) are going 64-bit for servers and high end workstations. You really do see a benefit there for large databases and working with large data sets. The work being done on those machines and the work being done on Apple Power Macs and Xserves have almost nothing in common.

AMD is mostly targeting servers but they are also going after high end desktops (in the same belief that many have the 970 based Power Macs) that there are some desktop applications which will benefit from 64-bit processors. However, it should be noted that while AMD believes there is a market there, Intel has stated publicly they do not feel there will be one until later in the decade. I think Intel is wrong but their argument might be why develop a new 64-bit processor for a $3500 desktop when a low end Itanium 2 workstation is in this range.

Also, IBM's POWER4/4+ does not decimate every other processor out there. For 32-bit integer math, it is beaten soundly by the Pentium 4 which is the reigning king for 32-bit integer math. For floating point, it is beaten soundly by the Itanium and probably by the Alpha.

But that is not where the POWER4/4+ is targetted. It is targetted for large databases and transaction processing. In that arena it is king. Although due to its high cost, you can generally get a Sun or HP that can compete with almost any IBM server at a similar price point. You need more UltraSPARCs to do an equivalent amount of work, but Sun's are cheaper per processor so it washes out unless your software is per-processor licensed.

[IVIIVI4ck3y27]

Originally posted by copperpipe
Well, most people here have been saying that 64 bits doesn't really make any difference except in encryption, which is to say that the difference they will make is miniscule at best. Now the people saying this definitely know more than I do, because I can't even understand what they are talking about in some cases. But, I just don't understand why Intel, AMD, and IBM are all investing billions of dollars in the race for 64 bit? It doesn't make sense to me, for such a tiny gain. Maybe we should go back to 16 bit? or 8? did they make a big difference? The POWER 4 uses 64, and it descimates every processor out there, but I suppose that it could be 32 and would descimate every processor, except when it's decoding an encryption. I dunno, maybe everyone here is right about 64 bit not making any noticable difference, but I'm having a hard time believing it.

PS - I truly don't mean to upset anyone by this, and I don't doubt that everyone has good reasons for their beliefs...

Rollin' in my '64

It's quite simple actually. The reason for mor-125ts + a processor is that there's a need for more RAM. For most desktop services that us casual users are doing right now, 64-bit is overkill for the "NEAR" term. Eventually as programs get more and more advanced, a traditional inevitability... and as more and more "featuritis" is added to the OS resulting in bloat, the ability to make use of more RAM, more drive space, etc. etc. will be a major concern.

Why's everyone tramplin' each other?!?

Simple. Desktop processor-based computer sales only make a small margin of product sales for most PC companies. You're selling processors made in large volumes, at low cut-rate prices in order to draw people in. Therefore your profit margin per machine is cheap, and the costs to research and develop said processors is expensive if they're based on a "SINGULAR" task.

Now... where is 64-bit "NEEDED".

Enterprise, and I don't mean Star Trek

By eventually shifting the desktop PC from Pentium/Duron/Celeron to an Itanium based architecture, much as AMD shifts from Duron/Athlon XP/Athlon MP to Hammer; the advantage is that they can do their R&D work for their server processor families, and trickle that down to desktop-based versions of their high end processors, limiting the wide-ranging R&D and creating a singular roadmap that branches to serve needs, rather than two separate roadmaps. It's common logic.

Why is Apple going 64-bit?

IBM. IBM previously had no interest in SIMD, and in truth... the AltiVec compatible SIMD unit in the PPC 970 *ISN'T* put there for IBM. IBM's servers that the PPC 970 will reside in will likely "NEVER" make usage of the AltiVec part of the chip. However, having it there makes the processors viable to Apple, and allows Apple to continue to evolve the XServe line, while IBM can recoup some R&D development costs and increase sales of it's PPC 9xx platform... thereby making a little extra $ on the side by helping Apple, and in turn helping themselves.

Why is it so apparent that IBM won't use SIMD?

Simple. AltiVec is a vector-processing SIMD chipset. It's designed for handling more graphical tasks. It's exactly why Apple was so adamant on using it in the G4, and exactly why IBM and Motorola split in their roadmaps, with IBM continuing to evolve the 32-bit & 64-bit versions of the G3 rather than go Motorola's route in developing the G4 with a SIMD unit.

The deal is...

1) IBM later realized that they weren't going to fit into Apple's roadmap for very long if the G4 took off.

2) They also realized that the PowerPC, after the split, wasn't as strong.

3) IBM realized that if Apple dumped the PowerPC, which was verrrry likely after Motorola ditched out on the G5 (Motorola's always focused on embedded moreso than the desktop side anyways... whereas IBM uses the PowerPC more in servers than in embedded sales)... if Apple bailed on the PowerPC, what's the sense in contining on with the PowerPC?

Not much really.

IBM doesn't use PowerPC's in workstations... because the only OS's they use on PowerPC are AIX and Linux, both more geared towards server than workstation because neither is optimized with Assembly calls, there's no vector processing calls, and there's not likely to be any anytime soon. Why? Linux and Unix are designed to be portable. Any application or part of the system is written to be ported easily through some mild alterrations and a recompile. The minute you specialize the code for MMX, or 3DNow, or AltiVec... is the minute you have a lot more porting work ahead of you to gut out, remove, and reoptimize said items.

This is why SIMD is not of interest to IBM.

Apple, on the other hand, has a "PROPRIETARY" set of API's with AltiVec support written into OS X. Even Apple's own x11 version includes support for AltiVec. They took the time to add it because so much of Apple's future is centered around vector processing because of the way they're gearing the OS as a "MEDIA" OS. OS X, unlike the other Unix variations, is more of a graphical workstation OS. Yes it can do ample serving work... but if Apple decides to gun for Enterprise, as I've said before, they're more than likely to work on different principles to innovate themselves into the market. They more than likely won't go for the leaders jugular... but they are going to become the next SGI, in that they're more than apt to eventually create their own rendering farms, and having that 64-bit advantage there will help them, much as the added sales will help IBM on their Enterprise "SERVER" sales of Linux-based PPC's. Apple and IBM in this way complement each other very nicely.

Apple will likely gear towards low-end Enterprise sales, and especially hammer hard on the SoHo front, an area that IBM is too massive and monolithic to support. So 64-bit will help as small web servers and mom and pop shops that need print and file servers will be able to buy an easy to administrate server (especially one-click Apache built-in) and upgrade it via 1u and 3u rack updates. I eventually see Apple going beyond this... but Apple's niche of Enterprise or their move into Enterprise (if they do ever attack the big wigs) will be a slow process full of innovation. It'll be like taking the conventional ideas of what an IT expert is used to and throwing it out the window... simply because IT experts cost $, and if Apple can make an easy to administer server that is reliable, easy to setup, and practically runs itself... IT WILL be successful in this market.

So 64-bit doesn't buy the average user anything... but it buys Intel and IBM and AMD a chance to move it towards the desktop, cutting the costs, and increasing the volume and validity of the platform. After all... if AMD were to beat Intel to 64-bit, they could gain a slight advantage and if they can transition the platform to the desktop from servers... you have one inclusive architecture that scales far and wide, and has a strong degree of longevity left in it.

Mark my words... PPC 9xx will be around for longer than 2.5 Ghz. The PPC 970 has been said to only reach that far... but there will be further evolutions past that, and quite likely the 980 or 990 or 975 or whatever comes in between or beyond will keep taking us just as far as the Pentium 4 and Duron/Athlon/Athlon T-bird/Athlon XP/Athlon MP has taken AMD. For the person above that didn't think we'll see the 2.0's... I'd count on it. The minute Apple gets ample enough volume, it'll be the next processor in line... whereas the bottom rung processor then, and only then, will likely find it's way into something else. Perhaps even the Powerbooks with some revamping (like a PPC 970e; similar to what happened with the PowerPC 603e).

[jayscheuerle]

Originally posted by macmunch
I have an idea on this !
A very good I think

If there are 4 Models that would be cool !
and dont forgett the DP coudnt ne so expensice because than there werent 3 models of them !!!!

So look at this idea:

1.4 SP low Price Tag 1199 - 1399
1.6 DP 1699 - 1899
1.8 DP 2099 - 2399
2.0 DP 2799 - 2999 or even 3099


But if they introduce so many models with DUAL I see a big chance to get this Single PPC970 very cheap !

The cheap tower is an area that Apple needs to address. If you can get a low end PC for $400 (with monitor, speakers, printer, etc.), you should be able to get a low-end tower Mac for under a grand. Other than marketing strategy, there's no reason you shouldn't.... - j

[mathiasr]

Based on the rumors:
http://apmalaga.free.fr/mb/Mach64.gif
If Apple uses 1.4 and 1.6 GHz PPC 970 CPUs they will probably not be able to keep the front side bus at 900 MHz and are more likely to use a more conservative 800 MHz frequency (400 MHz DDR, x3.5 and x4 respectively).

[Bengt77]

Originally posted by posixstudent
I hate to bring this up, but I have never heard any verification that the 970's would be in PowerMacs.

I surely hope you'll be proven wrong here. Of course, and I know that too, there has indeed been no announcements whatsoever (perhaps maybe that PDF MacBidouille was speaking of, that came from the Micro Processor Forum) regarding Apple's commitment to using the PPC970 in their next lines of computers. But still, every bit of information now available (or should 'bit of information' be stated as being 'rumour') actually does point in the direction of it.

Again, I really hope you'll be proven wrong. I'd hate to see the xServe get them first, and then Power Macs only next year, or something. I don't know how big this rumourmill is, but I'm sure it's not that the whole Mac community is expecting the PPC970. The majority of the community probably doesn't even know of it's very existence. Apple could care less (probably, but hopefully not) about 'us' rumour mongors. So why would Apple feel the pressure just because all the rumours say it will do this or do that? They never have. Look at the iMac. Mac rumour sites said, even like one and a half year before the very introduction of the LCD iMacs, that a new model was coming. The whole community was deeply dissapointed because some rumour turned out to be wrong. That's a shame. Why should Apple be penalised becaus there are some rumours saying they would do A, while they did B?

Some rumours are wrong. Some rumours are right. Who knows which are what? This one might prove right. And hopefully rather sooner than later. I'd love Apple to have some serious power computing ready to be introduced at the Create-Expo-or-whatever-the-new-name-was-again. But just don't bet on it.

Darn, that's exactly what you said. Okay, so I agree with you, but I just hope you're wrong...

:D

Edit: the bold 'right' was 'wrong' until just yet. That was not what I meant to say (or write, for that matter)!

[ktlx]

Originally posted by IVIIVI4ck3y27
This is why SIMD is not of interest to IBM.

I have been thinking about this and while I generally agree with you, I see one situation where IBM might be interested in SIMD.

IBM is going to put PPC 970s in blade servers. One of the things blade servers do well is handle Web servers. Currently high volume transaction sites use add-on hardware for HTTP/S acceleration. I could see IBM pursuing using the SIMD unit as a cheaper way to provide the same functionality.

Of course it would still not perform as well as the dedicated hardware accelerators, but I wonder how many customers might say good enough when comparing a Linux Web server running on a PPC 970 blade to a Linux Web server running on an Intel Pentium 4 blade with an HTTP/S hardware accelerator given the cost savings.

[AidenShaw]

Originally posted by maxvamp
- dual 1.6 procs. If IBM's numbers are to be believed, a single 1.6 will give a P4 3GHz a run for it's money ( but won't beat it ). Following Apple's logic, if you add two procs together you get get about the same speed as a competitor's single ( dual 1 Gig G4s to compare against a 2 GHZS P4, for example ). This configuration would eat the single P4 alive

- Windows XP Home: ...One would be no dual proc support....


Hmmm.... You knock off XP Home for not supporting dual CPU, yet you don't position the 970 against dual P4 (Xeon, of course).

Methinks a dual 3.06GHz Xeon with Hyperthreading probably wouldn't be "eaten alive"! :p

[ktlx]

Originally posted by jayscheuerle
The cheap tower is an area that Apple needs to address. If you can get a low end PC for $400 (with monitor, speakers, printer, etc.), you should be able to get a low-end tower Mac for under a grand. Other than marketing strategy, there's no reason you shouldn't.... - j

Or business reasons. Look at Apple's volumes. Look at the R&D they would have to invest in creating the machine. At the bottom end PCs, there is almost no R&D because they are just using yesterday's components. It would also seriously hurt their iMac and low end Power Mac sales.

Apple is smart. The companies making $500 PCs are either loosing money in that market or existing on a razor's edge. There is some business you just don't want. If someone wants a sub $1K Power Mac, there are lots of them on e-Bay.

I am not a business major, but all of the business major types I talk to hammer one thing in over and over again. Increased revenue in one market segment does not mean increased profit overall. If your business model is low volume, high margin (i.e. Apple and not Dell), there is lots of business out there you just don't want.

[PaisanoMan]

Originally posted by maxvamp
In short, I am trying to debunk the thought of 'There will be no increases what so ever in using a 64 bit app for the common user.'


That's not true, either, of course -- try not to be too extreme. The idea that a 64-bit CPU will automatically be twice as fast, however, is just naive; I think that's what most of us are trying to debunk.

[IVIIVI4ck3y27]

Originally posted by Bengt77
I surely hope you'll be proven wrong here. Of course, and I know that too, there has indeed been no announcements whatsoever (perhaps maybe that PDF MacBidouille was speaking of, that came from the Micro Processor Forum) regarding Apple's commitment to using the PPC970 in their next lines of computers. But still, every bit of information now available (or should 'bit of information' be stated as being 'rumour') actually does point in the direction of it.

Again, I really hope you'll be proven wrong. I'd hate to see the xServe get them first, and then Power Macs only next year, or something. I don't know how big this rumourmill is, but I'm sure it's not that the whole Mac community is expecting the PPC970. The majority of the community probably doesn't even know of it's very existence. Apple could care less (probably, but hopefully not) about 'us' rumour mongors. So why would Apple feel the pressure just because all the rumours say it will do this or do that? They never have. Look at the iMac. Mac rumour sites said, even like one and a half year before the very introduction of the LCD iMacs, that a new model was coming. The whole community was deeply dissapointed because some rumour turned out to be wrong. That's a shame. Why should Apple be penalised becaus there are some rumours saying they would do A, while they did B?

Some rumours are wrong. Some rumours are right. Who knows which are what? This one might prove right. And hopefully rather sooner than later. I'd love Apple to have some serious power computing ready to be introduced at the Create-Expo-or-whatever-the-new-name-was-again. But just don't bet on it.

Darn, that's exactly what you said. Okay, so I agree with you, but I just hope you're wrong...

:D

Edit: the bold 'right' was 'wrong' until just yet. That was not what I meant to say (or write, for that matter)!

Again... there's no visible evidence nor will there be any that there's new PowerMacs using 970's until release. I mean, nothing is for certain "UNTIL" it happens... that's just a truth in life.

Yet, if IBM is bothering to make PowerPC chipsets with SIMD when they, themselves, won't use them... why? If they weren't meant for Apple... IBM would just make a further evolution of the PowerPC without SIMD and just focus it towards their own needs... which have a decisively server slant.

Also... what would Apple use?

Motorola's officially announced that their G5, as previously announced, is dead as a door nail. Kaput. Not happening...

So Apple is stuck with Motorola and the G4 forever?

Riiiiiight...

Apple moving to Intel/AMD?

Ooooookay... so Apple, so quickly after getting the OS rewritten, integrating Carbon, and trying to optimize as much as they can for PowerPC is just going to bail?

pffffffftttt ::snickering::

Ain't no way.

For those rumor mongers hoping for AMD/Intel....

Keep dreaming, in 5-10 years time you might get your wish.

But not now...

Let's face it... didn't Apple just publically say they're tied to PowerPC for the near term, but after that it could get interesting?

Count on PPC 970, it's Apple's strongest offering on the table.

With SIMD that is "BACKWARDS COMPATIBLE" with AltiVec?!?

It's "TAILOR MADE".

In fact, I'd not be surprised if Apple didn't even commission to have this made, and foot some of the R&D $ just so they could continue to compete. They're losing ground to their closest competition and most bitter rival. They rely heavily on workstation-level performance to remain competitive in the creative field.

PPC 970 gives them that... and retains compatibility with all of the applications that are in the process of being ported, or have been ported already. That includes Photoshop, Office X, Illustrator, Flash MX, Director MX, etc. etc. etc.

Even Quark 6, coming soon...

Apple bails on PowerPC... everyone has to start the porting deal "ALLLLLL" over again. Carbon becomes damn near irrelavent at this early a stage, and a ton of companies will almost immediately bail on Apple and not develop for them again. Soooo... Apple has to ween the developers off Carbon eventually by fusing the API's into Cocoa and slowly removing them one by one, much like Microsoft did with the WIN_16 API's over time.

You really want to wait 6 years for Quark? LoL

I know most graphic designers don't.

Like I've said on here before... it's not "IF" we'll be on PPC 970...

It's When...

[maxvamp]

Hmmm.... You knock off XP Home for not supporting dual CPU, yet you don't position the 970 against dual P4 (Xeon, of course).

Methinks a dual 3.06GHz Xeon with Hyperthreading probably wouldn't be "eaten alive"!


A dual Xeon would not compare in price. Will XP home ( who has no concept of more than one processor )be able to handle a chip (system) that says it actually has two processor?

I doubt with HyperThreading, that a single P4 3.2 GHz would be able to compete with the dual 1.6 PM. If you want to compare a dual Xeon with HT, build a quad 970 @ 1.6 and compare. That would be a fair comparison.

Max

[rog]

When the G4 733 came out after 18 months stuck at 500 MHz. They wen't from duals to a single processor, even on the high end. It wouldn't surprise me at all not even to ship a dually at first, or only on the top model at an outrageous price to drive buyers to the most expensive model.

Apple has made it clear they aren't interested in being like the Wintel world and go for low prices. They are perfectly happy in their own little sub 3% market share world.

They are never going to get to even 5% market share unless they slash prices. Why do they currently have the lowly Radeon 9000 on their top tower as the standard card? Why is there a $300 premium for the outdated GF4 Ti?

when the 970 comes out, they aren't going to suddenly be kind to everyone and drop prices.

I'll be shocked to see a DP 970 under 3 grand.

[rjstanford]

Originally posted by copperpipe
Well, most people here have been saying that 64 bits doesn't really make any difference except in encryption, which is to say that the difference they will make is miniscule at best. Now the people saying this definitely know more than I do, because I can't even understand what they are talking about in some cases. But, I just don't understand why Intel, AMD, and IBM are all investing billions of dollars in the race for 64 bit? It doesn't make sense to me, for such a tiny gain. Maybe we should go back to 16 bit? or 8? did they make a big difference? The POWER 4 uses 64, and it descimates every processor out there, but I suppose that it could be 32 and would descimate every processor, except when it's decoding an encryption. I dunno, maybe everyone here is right about 64 bit not making any noticable difference, but I'm having a hard time believing it.


One thing to keep in mind ... the bit-length refers to nothing more or less than the size of number that the processor can "think about" easily. Processors can handle larger numbers, but at a surprisingly high cost for their size (ie: an 8 bit processor can do 64 bit math, but its very expensive). Combine this with the fact that some operations (say, checking memory) need to be very fast indeed, and you'll see where I'm heading.

Those number sizes?

2^08 == 256
2^16 == 65,536 (or 64Kb)
2^32 == 4,294,967,296 (or 4Gb)
2^64 == 18,446,744,073,709,551,616 (or around 17 million Tb)

The main reason that most 32-bit processors are faster than the 16-bit processors they replaced is that they were made later. In other words, they were faster because they were bigger and better, not just because of the word length.

One of the main reasons that computers jumped to 32-bits so eagerly though was for that fast memory access. 32-bits allows the processor to address a memory location with one piece of information. 16-bits required at least two -- traditionally, one to refer to a "page" of memory, and the other to position within that page.

Now, there isn't much that requires more than 2^32 indexes in the personal computer realm. Today, that's pretty much limited to disk filesystems (where the physical disk access is unbelivably slower than the extra computing time that's needed to locate something). Tomorrow? Who knows what people will come up with. Memory sizes above 4GB are a good start, although intel, et al, are using 36bit memory keys in their newer processors to help with that very problem.

Now, in the enterprise realm, things are very different. Its easy to want to track more than 4 billion different business events, for example. Or if you're doing medical modeling. Or serious 3D raytracing. And on, and on. This is why the enterprise community is excited about true 64-bit processors, with the OSs to take advantage of them (such as AIX 5, Linux, etc).

Also, I hope that this helps to explain why the move to 64-bits isn't as big a deal as the move to 32 was.

[AidenShaw]

Originally posted by maxvamp
A dual Xeon would not compare in price.

How do you know what a dual or quad 970 would cost?

A dual 3.06GHz 1GB Xeon (Dell PWS450) is $3426, dual 2.8GHz only $2976.

Will XP home ( who has no concept of more than one processor )be able to handle a chip (system) that says it actually has two processor?

Who cares? XP Pro is about a $60 option even on low end systems, and the $60 is lost in the noise of a loaded dual or even a high end single. XP Home and XP Pro are identical, except for the restrictions placed on Home. Home vs. Pro is a silly non-issue, unless you're making your decision based on a $60 price difference.

I doubt with HyperThreading, that a single P4 3.2 GHz would be able to compete with the dual 1.6 PM. If you want to compare a dual Xeon with HT, build a quad 970 @ 1.6 and compare. That would be a fair comparison.

No, I'll build a quad Xeon with HT and big caches, and we'll check on the "eaten alive".

And, incidentally, I *did* just buy a quad Xeon.... (x440 2GHz/2MB). Where's your quad 970 ???????????

[mcs37]

I am crossing my fingers for Rev B of 12" PowerBook to be a 1.4 GHz SP PPC 970. :D

[IVIIVI4ck3y27]

Originally posted by ktlx
I have been thinking about this and while I generally agree with you, I see one situation where IBM might be interested in SIMD.

IBM is going to put PPC 970s in blade servers. One of the things blade servers do well is handle Web servers. Currently high volume transaction sites use add-on hardware for HTTP/S acceleration. I could see IBM pursuing using the SIMD unit as a cheaper way to provide the same functionality.

Of course it would still not perform as well as the dedicated hardware accelerators, but I wonder how many customers might say good enough when comparing a Linux Web server running on a PPC 970 blade to a Linux Web server running on an Intel Pentium 4 blade with an HTTP/S hardware accelerator given the cost savings.

It's possible, if IBM wanted to go through that trouble. But for IBM, I'm sure they probably have some of the hardware accelerators lying around. As much as they develop stuff... it'd likely be better to compete with the Pentium 4 blade with the hardware accelerator. After all... IBM machines in this segment tend to be overpriced... if it can't perform faster for the $, it's not going to be a value, and damn straight IBM's not going to make sales. Their services, which are a huuuuuuuuge part of Enterprise (and where the real profits at) are good... but you can almost hire your own IT staff to slap a custom blade server together and add their own version of Linux, and have a permanent on-site staff member for what it'd cost for the IBM machine and support and services for a year. So IBM would most likely offer the same hardware accelerator... and I doubt they'd go through extensive trouble to support SIMD. They might... but I seriously doubt it, especially *NOT* in AIX. Linux maybe... but that's still a big ?

[mcs37]

Originally posted by mathiasr
The PowerPC 970 is not supposed to have power saving features, you'd rather not expect to see it in a PowerBook.

A 1.4 GHz PPC 970 only draws like 23 W, I thought? That's not so bad!

[mathiasr]

Originally posted by ktlx
Also, IBM's POWER4/4+ does not decimate every other processor out there. For 32-bit integer math, it is beaten soundly by the Pentium 4 which is the reigning king for 32-bit integer math. For floating point, it is beaten soundly by the Itanium and probably by the Alpha.
I would not say that the POWER4+ is an under dog, here are some SPECfp2000 figures:

SPECfp2000 (base/peak)
1124/1482 : Alpha 21364@1150 MHz HP AlphaServer GS1280 7/1150
1391/1404 : Intel Itanium2@1000 MHz Bull NovaScale 4040
1202/1266 : POWER4@1300 MHz IBM pSeries 690 Turbo
1004/1228 : SPARC64 V@1350 MHz Fujitsu PRIMEPOWER900
1122/1219 : AMD Opteron144@1800 MHz Einux A4800
1097/1158 : POWER4+@1450 MHz IBM pSeries 630 Model 6C4
945/1106 : UltraSPARC IIICu@1200 MHz Sun Netra 20
1092/1103 : Intel Pentium4@3066 MHz Dell Precision WorkStation 350
1053/1063 : Intel Xeon@3066 MHz Dell Precision WorkStation 650
776/ 869 : AMD AthlonXP3000+@2167 MHz ASUS A7N8X Deluxe
602/ 650 : AMD AthlonMP2600+@2133 MHz MSI K7D Master
499/ 529 : MIPS R14000@600 MHz SGI Origin 3200
437/ 456 : Intel PentiumIII@1400 MHz Dell PowerEdge 1500SC

IBM has announced the POWER4+ running at 1.5 and 1.7 GHz not covered here, and the Itanium is expected at 1.5 GHz anytime soon; notice that an IBM p690 server build around 32 POWER4+ 1.7 GHz processors has outperformed a 64 Itanium 1.5 GHz HP Superdome server in the TPC-C benchmark:
http://www.theregister.co.uk/content/61/30642.html

[maxvamp]

--------------------------------------------------------------------------------
Originally posted by maxvamp
A dual Xeon would not compare in price.
--------------------------------------------------------------------------------



How do you know what a dual or quad 970 would cost?

A dual 3.06GHz 1GB Xeon (Dell PWS450) is $3426, dual 2.8GHz only $2976.


I guess $3426 == $2200 . I know I probably have an extra $1200 in my couch cushions alone.

This original thread tried to start out comparing $2200 machines.

Based on Apple's general price steps, there will pobably be a 1.6 in the low to mid $2k range.

If you want to derail this train try making a valid argument with the dual 970 1.8 or 2.0 against the Xeon 3.06. I believe that would be closer to a valid comparison, that is if you are into fair comparisons. IBM has already published some "Conservative" numbers on this. BTW: the dual and Quad PPC 970s are coming. They will be labled IBM for sure. Maybe Mac ( anyone think there will be a Quad Xserve? ).

In all honesty, you sound like you are just trying to start a 'Why my PC is better' fight. I think you would have a better chance trying this crap over at http://www.amdzone.com . There are many reasons why people prefer Macs.

Speed of processor != Productivity.


Good Day,

Max

[copperpipe]

Thanks for more info on the 64 bit discussion, Ktlx and IVIIVI4ck3y27 especially. Your well thought out replies have helped me to understand things a little bit more.

[macdong]

Originally posted by greg6028
I heard of talk about a dual processor in a PowerBook.
Will this happen now with the 970?

Ultimate PowerBook with Dual 970
Fastest PowerBook with 970
Faster PowerBook with Dual G4
Fast PowerBook G4

I have a feeling this will happen in winter of 2003. The desktops will be first. Are not the desktop to oldest in the Apple line now?


You are way over your head, dude.
I don't want a steaming fried pan on my laps. :rolleyes:

[AidenShaw]

Originally posted by maxvamp
In all honesty, you sound like you are just trying to start a 'Why my PC is better' fight.

No, just trying to point out the inconsistency in the comparison of single and dual CPUs, and the information which shows that while the POWER4 (and estimates for the PPC970) are certainly very good, being "eaten alive" by a PPC970 is a bit of a stretch.

Look at it another way - if you listen to me (and other calm voices), you'll most likely be pleased when the PPC970 shows up. If you listen to the wild statements, you'll be quite disappointed when it arrives....

[mathiasr]

Originally posted by IVIIVI4ck3y27
Why is it so apparent that IBM won't use SIMD?

Simple. AltiVec is a vector-processing SIMD chipset. It's designed for handling more graphical tasks. It's exactly why Apple was so adamant on using it in the G4, and exactly why IBM and Motorola split in their roadmaps, with IBM continuing to evolve the 32-bit & 64-bit versions of the G3 rather than go Motorola's route in developing the G4 with a SIMD unit.

[snip]

IBM doesn't use PowerPC's in workstations... because the only OS's they use on PowerPC are AIX and Linux, both more geared towards server than workstation because neither is optimized with Assembly calls, there's no vector processing calls, and there's not likely to be any anytime soon. Why? Linux and Unix are designed to be portable. Any application or part of the system is written to be ported easily through some mild alterrations and a recompile. The minute you specialize the code for MMX, or 3DNow, or AltiVec... is the minute you have a lot more porting work ahead of you to gut out, remove, and reoptimize said items.

IBM 64 bits CPUs are not based on the G3, they are related to the RS64 or POWER3 chips:
http://www.research.ibm.com/journal/rd/461/tendler.html

IBM offers some assembly hand tuned libs like MASS (Mathematical Acceleration Subsystem):
http://www.rs6000.ibm.com/resource/technology/MASS
and give you some hints to speedup your apps:
http://www.redbooks.ibm.com/pubs/pdfs/redbooks/sg247041.pdf

[mcs37]

Originally posted by seamuskrat
64 bit OS will NOT make it run FASTER. A misconception at work here. A 64 bit Os will allow for more memory and will allow for some efficiency with large memoroy intesnsive files. In SOME rare cases, it would actually slow a process down if it was re-written to be 64 bit.

True but enhancements will come once enough software takes advantage of the 64 bits. Number-crunching intense applications like Final Cut Pro will most definitely be much faster with that wider pipeline.

[ktlx]

Originally posted by mathiasr
I would not say that the POWER4+ is an under dog, here are some SPECfp2000 figures:

A much more expensive processor loosing to a cheaper processor by almost 15% is getting soundly beaten in my book. I can buy more Alphas or Itaniums than POWER4/4+ for the same amount of money and get a faster processor for floating point.

IBM has announced the POWER4+ running at 1.5 and 1.7 GHz not covered here, and the Itanium is expected at 1.5 GHz anytime soon; notice that an IBM p690 server build around 32 POWER4+ 1.7 GHz processors has outperformed a 64 Itanium 1.5 GHz HP Superdome server in the TPC-C benchmark:
http://www.theregister.co.uk/content/61/30642.html

That is true but TPC-C has absolutely nothing to do with the SPECfp marks of a processor. It has much more to do with L3 cache sizes, I/O bandwidth and all of those things that I mentioned in the paragraph you left out of your quote.

As I said, on a per processor basis, there isn't anything out there that competes with the POWER4/4+ line for databases (except maybe IBM mainframes :D). The only negative is the high cost per processor on these servers.

The link points out the problem I mentioned. The 64 processor Itanium 2 machine was $600K cheaper than the 32 processor IBM. IBM had to pay 7% more money to get 3% more performance.

[mcs37]

Originally posted by IVIIVI4ck3y27

The odds of dual processor Powerbooks isn't that good... for one that's an extra processor chewing up juice (desktops it makes sense, laptops... unless they can get dual G4's or 9xx's running at 7w like the current iBook, you're talking even more heat than a current laptop G4 which is already hot to a lot of people's chagrin), generating more heat, and eating up more battery life. Yet if it does happen, it'll likely be some hybridization of G3/G4... and that's just not logical at this stage. [/B]

I disagree here. First, it would be worth's Apple's time to attempt to release the PowerPC 970 into their PowerBook line as close the PowerMac line as possible since many users would simply wait 6 months or longer until they were available, resulting in lower sales for Apple until they fill the gap.

Second, dual processors in a PowerBook is a fantastic idea. But you are right about power consumption. Solution? The OS shuts down the second processor when the computer is running on battery only. Should be a pretty straightforward feature that would give PB users all the power of a desktop when plugged in and still a powerful box when on the plane.

[type_r503]

64 bits will increase performance after software makers learn how to use the extra bits. As an example, you can fetch 2 32 bit ints in a single clock cycle or 4 bytes, and you can fill an Altivec register in half the time. Take a look at first generation PS2 games compared to Enter the Matrix. If the tools are there they will get used.

[jettredmont]

Originally posted by copperpipe
But, I just don't understand why Intel, AMD, and IBM are all investing billions of dollars in the race for 64 bit?


First, 64-bit computing will be quite useful, and will drive an entire wave of new computing technologies (judging from the past). What you are hearing people say here is that there will be little to no immediate performance jump due to having a 64-bit processor. The things you do today work just fine in 32 bits; the only apps which would benefit from 64 bit CPU are those using 64-bit-manipulation-using-32-bit-registers kludges today.

That having been said, there are existing applications for 64-bits, but they are centered around the area where 64-bit machines have existed for a while: on the server. These include databases, file/web servers, etc.


It doesn't make sense to me, for such a tiny gain. Maybe we should go back to 16 bit? or 8? did they make a big difference? The POWER 4 uses 64, and it descimates every processor out there, but I suppose that it could be 32 and would descimate every processor, except when it's decoding an encryption. I dunno, maybe everyone here is right about 64 bit not making any noticable difference, but I'm having a hard time believing it.


Again, the Power 4 decimates other 64-bit processors, not because it is 64-bit (so is its competition) but because it is a damned fine implementation on an excellent architecture.

Note that the 8- and 16-bit comparisons are not really applicable. In both of those transitions, mainstream software existed which used kludges to manipulate higher-width integers (16 and 32 bit ints, respectively), and the limits of memory addressing were a very real and pressing concern (personally, I know no one with 2GB of memory on their desktop; everyone I knew had their 286's completely maxed out with one (then very expensive) MB of RAM and still were constantly fiddling to conserve just a little bit more memory).

This is not exactly the case today. That is not to say that soon we won't be hitting the 32-bit limitations, but we haven't really hit it en masse yet like we had with 8- and 16-bit limitations (4-bit limitation being a bit ahead of my time, except in terms of video colors ... )

As for why Intel and AMD are falling over themselves trying to be first out with a 64-bit desktop computer: well, first off Intel surrendered and took its ball (Deerfield) home; secondly the main driving force there is marketing (64-bits is obviously better) and bragging rights. Do you remember the "race" to 1GHz? Did that mean diddly squat? Of course not. Except it meant that suddenly 800 and 866MHz machines were dirt cheap. "1GHz" was a bragging rights benchmark, and so in a large part is "64-bit desktop".

That having been said, there are real and lasting benefits to having 64-bit processors on the desktop. It's just not an overnight or even one-compile-away type of benefit. It enables new concepts and new paradigms to blossom and create the 64-bit "killer app".

[freundt]

As for linup... they will keep it as simple as it is now.

1.4 SP Power Mac
1.6 DP Power Mac
1.8 DP Power Mac

However, I'm not so sure about the powerbook. I think we will have a 970 based powerbook in the near future. I mean, it's ok to have a 1 generation behind processor(or multiple if you look at other chipsets) in a consumer based laptop - G3 ibook -, but it is not ok to have a 1 generation behind processor in the pro laptop area - especially when that processor is behind all other chipsets in regards to speed.

I still think the 15" is the flagship laptop, and they have been holding out for a major upgrade avaiable for it before releasing a newer version. (I think the Lapzilla is a flash in the pan product that will probably not be carried on throughout future iterations - it's too impratical, and I believe it was released because Apple was/is stuck with slower processors and they needed a novel product to boost sells)

Anyways, that's my flawed thoughts on the whole mess...

[maxvamp]

Look at it another way - if you listen to me (and other calm voices), you'll most likely be pleased when the PPC970 shows up. If you listen to the wild statements, you'll be quite disappointed when it arrives....

I seriously doubt taking a comparison of two machines, and heavily skewing it to include a machine that cost a third more to prove that the IBM based machine is not as good as it most likely will be ( IBM has an excellent track record in this area, even based on the IBM numbers provided ) is acting in a calm way. If I listen to you, I will be buying those dells that you found nessesary to try to compare as a dollor for dollar machine.

As Judge Judy would say : Don't pee on my leg and tell me it is raining. Your attack on the comparison did not come across as calm.

Again, If you and a few others want to compare machines on a dollar level, lets talk about current and projected machines that fit that range. If you want to compare fastest, then acknowledge that there is a difference in price.

A $2200 dual 970 **WILL BEAT** a single $2200 P4, especially from Dell. Dell's dual lines, as well as server lines are built nicely, but the lower the cost of the Dell, the more the preformance drops, even with the same processor. They tend to cut back on leading technolgy that makes the machines faster, as performance costs money.

If you would like to discuss this without trying to directly compare more expensive Intels to less expensive Apples, we can, but for now, I am going back to my AMD 3000+ and my PM 733. Oddly enough I seem to get about the same amount, but different, work done on each.

Must not be the clock speed.....

Max

[hvfsl]

A 64bit chip on a 64bit OS is quite a bit faster than a 64bit chip on a 32bit OS. What people are forgeting here is that every clock 64bits of data are processed instead of 32bits. So twice as much data. Although in the real world there will not be a 2x performance boost, much like a dual G4 is not twice the speed of a single G4. IF you look at the new figures for the AMD 64bit on www.futuremark.com you will see a 1.4Ghz AMD is 70% faster than a 2.26Ghz P4.

[AidenShaw]

Originally posted by type_r503
As an example, you can fetch 2 32 bit ints in a single clock cycle or 4 bytes, and you can fill an Altivec register in half the time.

An AltiVec load or store instruction already does 128 bits per operation. (Same for SSE2 on Pentium)

The internal datapaths are 128-bit to 256-bits wide already, so the increase in width from 32-bit registers to 64-bit registers is helpful, but not a big improvement. (Besides, getting the data across the system memory bus is still slower by far than any internal data movement - even if multiple smaller internal moves are needed.)

As many before have said, 64-bits will have 2 main advantages:

- algorithms which need intensive use 64-bit integer arithmetic will be faster

- programs which need more that 2GB to 4GB of actual RAM per program will be able to run

And, by the way, 64-bit filesystems (which are basically any filesystems with UNIX semantics that can support files larger than 2GB) are always 64-bit filesystems - they don't shift modes for larger files. The system has to refer to files with 64-bit arithmetic even if they are only a few bytes in length!

This does not count as "intensive 64-bit use", though, since a filesystem has to do a lot of work beyond calculating file offsets. One would probably be unable to measure any improvement in filesystem performance due to 64-bit integers (but you might find a huge improvement with filesystem caches that are 64-bits (i.e. caches larger than 2GB)).

[maxvamp]

Aiden: In the file system stuff, For the most part you are right. I would ask what is your take on any speed impact when the processor has to manage the upper and lower set of bits of a given file. I know that the Win32 API takes care of this rather transparently. Wouldn't you see some performance on disk intensive applications?

Just curious,

Max

[arn]

For what it's worth, PowerJack (MacWhispers) does not believe this to be the case:

http://www.spymac.com/forums/showthread.php?s=&threadid=25573&perpage=15&pagenumber=3


Foxconn is not manufacturing either the new 970 PowerBook or the 970 PowerMac. There have actually been zero PPC 970 chips delivered to Foxconn.

Shame on LoopRumors.

I know some people have issue with MacWhispers' reliability... but LoopRumors isn't known to have reliable sources either.

The original article (LoopRumors) was posted on MacRumors as it corresponds with other information floating around (namely the MacBid info)

arn

[visor]

OK guys,

so a lot of people noticed that for the average typing singletasker at home, 64bit doesn't make such a great difference - true.

But what is apple aiming at?
MAC - THE DIGITAL HUB FOR A DIGITAL LIVESTYLE
or something like that, right?

Now for video editing, especially with all the new dimensions coming up these days (hdtv etc) and anyone creating and athoring dvd's - people can make a lot of use of HUGE memory. Something like 512GB RAM is adressable in the ppc970. Also numbercrunching is quite necessary for encoding videos in a reasonable time.
Then, look at all those grafic guys - they always want faster computers with larger memory - because there will always be a resolution that doesn't fit in the memory you have.
Just recently I was confronted with a specially processed 'image' that allocated 120GB on the harddisk. 512GB RAM would come in handy on this kind of problems.

So next: let those pictures walk - 3d rendering raytracing animations. OK - it is the pro's that use these features, not many people can even think 3d enough to get even a simple figure look nicely, but Apple sees a market in the low cost workstation market, and they do have quite a good position to get it - most simulations soewhat unix based ... u know unix based.... can be quickly ported to osx.
And so on ....

[MOM]

Originally posted by arn
For what it's worth, PowerJack (MacWhispers) does not believe this to be the case:

http://www.spymac.com/forums/showthread.php?s=&threadid=25573&perpage=15&pagenumber=3


Ther is more from the same source as a recap:



Missions Completed 2291

Online



Posted on: 05-14-2003 12:09 AM


quote:

I've already published what I actually can say on this one. Unfortunately, I am tangled up in a situation where the actual manufacturer is also building two products for me later in the year, and everyone with whom I deal there knows I publish MacWhispers... as does an Apple developer channal person involved in my projects. in other words, I actually have more first hand info on this topic than (probably) anyone else on the Mac web, but can't say squat.

- The PPC 970 is real, is ahead of schedule, and is slated for both 1 and 2 processor Power Macs... very, very soon.

- The 15.4-inch PowerBook is also real, has been nearly completely redesigned since January, will be released with a PPC 970 chip, and will have a Chi Mei Optoelectronics-produced 15.4-inch LCD with a non-standard higher resolution than 1280x800... also, very, very soon.

- The Power Mac will move to a new enclosure, one with an anodized aluminum front panel, mathcing the new PowerBooks.

All of this I have previously published. And, sadly, that's all I can say about any of it, other than this: None of this is guesswork or speculation. It's dead-level fact, straight from the people doing the work.

I have to dance a fine line with the MacWhispers site, and what info I spread. My business must come first.
end quote

Sounds too good to be true, but we can hope!

[Freg3000]

:(

I hate to say it, but I think we are all going a bit overboard. I want a PPC 970 Powermac as quickly as everyone else does but that doesn't mean that we should believe any info that comes out about it.

As for PowerJack definitively saying no to Foxconn, well, that's gutsy. I doubt he'd say it unless he was 100% sure.

[macrumors12345]

Originally posted by AidenShaw
Hmmm.... You knock off XP Home for not supporting dual CPU, yet you don't position the 970 against dual P4 (Xeon, of course).

Methinks a dual 3.06GHz Xeon with Hyperthreading probably wouldn't be "eaten alive"! :p

Probably not. But if you build a machine like that (with Dual 3.06 Xeons and all decked) on Dell's website, it will easily set you back $5,000. So instead of the PowerMac matching price and winning on performance (assuming the 970 configs people are conjecturing), the PowerMac would match performance and win on price. Two sides of the same coin.

[IJ Reilly]

Originally posted by Freg3000

As for PowerJack definitively saying no to Foxconn, well, that's gutsy. I doubt he'd say it unless he was 100% sure.

For a guy who claims he can't say nothin', this powerjack says quite a bit -- which all by itself seems kind of suspect. In the end all he really is saying is that Foxconn is not the contract manufacturer, somebody else is. As if that really matters.

[Rocketman]

Originally posted by dornball
wolf,
i hope your right. i prefer your specs. if there was a 970 powerbook available, i would order it in a heartbeat.

-dornball

Again we are a small company but we will be ordering 8. Powerbooks are high margin products for Apple.

I believe this will be the first Apple laptop purchase we make, with equal support of Mac and Windows users, ever, as well.

Rocketman

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

[Rocketman]

Originally posted by PretendPCuser
Apple doesn't need to ship a dual 970 if the chip is prohibitively expensive. Nor would they have to if it is such a great performer. Yet the rumor mills seem to say that there will be a dual (or at least that's what we are all hoping). Who knows, if they make them all dual, they will be a little closer to volume discounting. :)

It is specifically designed to handle quad to 8+ Nobody is posting rumous of a 4 way or 8 way APPLE CPU. That might be the missing link.

I also find it notable that figures of processor shipments are being posted to a general readership rumor site probably for the first time.

This indicates alot of excited people are letting stuff leak because the secrecy is KILLING them.

Rocketman

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

[macrumors12345]

Originally posted by ktlx

The link points out the problem I mentioned. The 64 processor Itanium 2 machine was $600K cheaper than the 32 processor IBM. IBM had to pay 7% more money to get 3% more performance.

You are confusing what IBM has to charge in order to break even with what it CAN charge w/o losing many sales (i.e. what the market will bear). Even pricing the p690 at 7% more than the Itanic Superdome, IBM is in danger of losing essentially 0 sales to HP because the p690 matches or beats the Superdome in performance AND it can actually run a lot of software out there, as opposed to Itanic, which has almost no codebase out there (but don't worry, it can emulate x86 ever so fast).

The latest estimate I've heard is that Intel has sold all of 4500 Itanic 1s and Itanic 2s since their debut (for obvious reasons - i.e. because it would be embarrassing - Intel will not disclose the actual numbers). So if they price it at $100,000 per processor or so, maybe they will be making back their $1 billion plus R&D investment in just the initial versions of the chip. Somehow I doubt their prices are that high, however.

And in terms of the marginal cost of production, the chips are both the same size: the .18 micron Itanic 2 is 421 square mm and the .18 micron Power4 is 414 square mm. So assuming the yields are both pretty good (well, maybe that is a heroic assumption for Itanic 2 given the Itanic bug that Intel just announced, but we'll give them the benefit of the doubt), then the production costs of each chip are probably about the same. But, of course, one Power4 equals two Itanic 2s, so Power4 clearly has a major cost advantage.

The bottom line is that Intel is hemorraging cash on Itanic right now - nobody would dispute that - while IBM is making nice profits on Power4. So saying that Itanic is as good as Power4 on a cost basis because the 64 proc Superdome can almost match the 32 proc p690 (at a similar price) is like saying that Apple could totally blow away Dell's sales numbers if they just lowered the price of the PowerMacs to just 20 bucks (technically true....and I'm sure they could make it up on volume, right?).

[Rocketman]

Originally posted by IVIIVI4ck3y27
How about them Apples?!?

Dual Quad 4-barrel... phooey

The odds of dual processor Powerbooks isn't that good... for one that's an extra processor chewing up juice (desktops it makes sense, laptops... unless they can get dual G4's or 9xx's running at 7w like the current iBook, you're talking even more heat than a current laptop G4 which is already hot to a lot of people's chagrin),



I do not know if the 970 has powersaver features built-in but the OS does.

I do not know how hot the 970 will get but cooler than any Pentium!

I do actual, real rocket science and I for one would be an early adopter of a dual processor powerbook. I admit even I would not need the 2nd processor 95% of the time, but for those times I do the $500-800 premium would be worth it.

For email and web I can run the single processor I do have at 1/2 speed in the sleep software.

Rocketman

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

[Rocketman]

Originally posted by copperpipe
Well, most people here have been saying that 64 bits doesn't really make any difference except in encryption, which is to say that the difference they will make is miniscule at best. Now the people saying this definitely know more than I do, because I can't even understand what they are talking about in some cases. But, I just don't understand why Intel, AMD, and IBM are all investing billions of dollars in the race for 64 bit? It doesn't make sense to me, for such a tiny gain. Maybe we should go back to 16 bit? or 8? did they make a big difference? The POWER 4 uses 64, and it descimates every processor out there, but I suppose that it could be 32 and would descimate every processor, except when it's decoding an encryption. I dunno, maybe everyone here is right about 64 bit not making any noticable difference, but I'm having a hard time believing it.

PS - I truly don't mean to upset anyone by this, and I don't doubt that everyone has good reasons for their beliefs...

The main practical benefit is more memory can be addressed all at once. That makes bigger more complex operations possible.

So the benefit is practical and has nothing to do with so-called 64 bit software.

Software that also is 64 bit clean does something similar with only incremental benefits unless working on HUGE datasets.

Rocketman.

[joelc]

I for one believe him, and not just because I want to. It's true that he has said a lot considering his reluctance, but his business story seems very plausible. He didn't give any specific information. Unless Apple made him sign his life away on that too, the amount of info he gave on the 970 is not obscene.

Also notice his info on the iPod's hidden features. He's an apple certified (or something) developer.Sounds legit to me.

[macrumors12345]

Originally posted by AidenShaw
How do you know what a dual or quad 970 would cost?

A dual 3.06GHz 1GB Xeon (Dell PWS450) is $3426, dual 2.8GHz only $2976.



Nice try. Equipping it like the machine discussed at the beginning (1 GB of RAM, 200 GB of storage), it cost $4,365, with the possibility of up to $300 in rebates. Throwing out the 19" monitor would lower the cost to $4,115. But it still is not actually as good as the machine quoted earlier in this thread, because it has a crappy 32 MB Radeon VE instead of a the 128 MB Radeon 9800 Pro (that alone will add several hundred) and no speakers or subwoofer. And compared to the equivalent Apple machine (as people are projecting) it would lack the Superdrive and have an inferior video card (32 MB Radeon VE vs. at a minimum a 64 MB Radeon 9000 Pro for the PowerMac).

Incidentally, the "equivalent" dual G4 (i.e. up the RAM and storage to 1GB/180 GB, throw out the Superdrive, and downgrade vid card to a 64 MB GeForce 4MX) is currently $2,850 from Apple. In fairness, the Dell comes with an extended warranty, so including Applecare the pricing would be $3,100 vs. $4,100. At any rate, the point is that clearly even if Apple were to raise its pricing points for the PowerMac towers by a large chunk, for example $500 or more (relative to what they are today), they would clearly still be very price competitive with the high end Dual Xeon workstations. Which is more than can be said today.

[ktlx]

Originally posted by hvfsl
A 64bit chip on a 64bit OS is quite a bit faster than a 64bit chip on a 32bit OS. What people are forgeting here is that every clock 64bits of data are processed instead of 32bits. So twice as much data.

Bzzzt. Wrong. Thanks for playing our game.

Although in the real world there will not be a 2x performance boost, much like a dual G4 is not twice the speed of a single G4. IF you look at the new figures for the AMD 64bit on www.futuremark.com you will see a 1.4Ghz AMD is 70% faster than a 2.26Ghz P4.

Next time please read the article you are quoting. What the report at AMD Board said (the actual source of the article) is that at the same clock speed, the Athlon 64 is about 70% faster not that a 1.4Ghz Athlon 64 is 70% faster than a 2.26Ghz P4. The 1.4Ghz Athlon 64 actually scored lower than the 2.26Ghz P4 in every test but the CPUMark 99.

Here is the link for those who are interested:

http://www.amdboard.com/hn05120301.html

Here is the quote from the article:

The results, even though me must considere them as temporary, show some impressive datas. Athlon 64 looks to be 70% faster than competitors running at similar speed (1.4GHz).

[P-Worm]

Ok, so AltiVec is like a 64 bit emulator right? So why do we need it in a 64 bit machine. Will it double the emulation to 128? Or am I just getting my numbers screwed up?

I guess what I'm really asking is, am I going to see a noticable speed boost in video rendering if FCP is already coded for AltiVec?

P-Worm

[Rincewind42]

Originally posted by hvfsl
A 64bit chip on a 64bit OS is quite a bit faster than a 64bit chip on a 32bit OS. What people are forgeting here is that every clock 64bits of data are processed instead of 32bits. So twice as much data. Although in the real world there will not be a 2x performance boost, much like a dual G4 is not twice the speed of a single G4. IF you look at the new figures for the AMD 64bit on www.futuremark.com you will see a 1.4Ghz AMD is 70% faster than a 2.26Ghz P4.

You are Wrong. The 1.4Ghz AMD is 70% faster than the 2.26 P4 because the AMD chip is a better design, not because it is 64-bit. A 64-bit chip running a 32-bit OS will only be slower than running a 64-bit OS if the chip runs 32-bit software slower than 64-bit software (which the 970 does not). You will not process 64-bits of data on average every clock, but only when the instruction calls for such processing. If you look at the instruction stream on a typical 32-bit processor, you will probably find that they spend half or more of their time processing 16-bit or smaller integers, even though they can handle 32-bit integers natively. Please stop spewing this carp, so that people in the know don't have to keep replying to correct you. Please help increase the Signal-to-Noise Ratio.

[AidenShaw]

Originally posted by maxvamp
what is your take on any speed impact when the processor has to manage the upper and lower set of bits of a given file.

Well, assume the integer unit has a 10 stage pipeline. Add 32-bits, then "add with carry" the 2nd 32 bits (the way 64-bit synthetic integer additions are done).

That's 20 cycles, or 10 nanoseconds for a 2GHz CPU.

But that's really worst case - in a superscalar, o-o-o (out-of-order) CPU both adds could be started at about the same time, along with many other instructions (the 970 and P4 can have 1 or 2 hundred instructions in progress at once). So other things are happening at once, so the 10 nanoseconds is hidden by other things that need to be waited on.

It's also probably not even 10 nsec worst case - since several of the pipeline stages are decoding the instruction (which can happen in parallel). It's also common that the result (in this case, the "carry" bit) is available several pipeline stages early (the later pipeline stages retire the instruction and store the result in the destination).

So maybe the 2 32-bit integer operations take 12-15 cycles, or 6 to 7.5 nsec. The main point is that it is not twice the time it takes to do one operation, but often much less.

----

What if the data is not in cache? Latency on a cache miss is often from several dozen to a hundred or so cycles - suddenly the 15 cycles for the arithmetic is 50 or 100 cycles. At this point - 10 cycles for a 64-bit add vs. 15 cycles for a synthesized add is hardly relevant.

----

Suppose we're doing a 64KB read and the data is in the filesystem cache. If the system bus is 8GB/sec, then reading and writing 64KB will take about 16 usec, or 32,000 cycles.

----

Suppose the disk head has to move - that's about 8 msec - 8,000 usec - 8,000,000 nsec - or a whopping 16,000,000 cycles.

----

So, that's why I claim that an extra 5 cycles (or even 10) to synthesize 64-bit integer arithmetic won't be measurable in actual I/O operations.

[centauratlas]

From a tech point of view, Apple has some problems, which will be addressed with the combination of OS X 10.3 and the 970, and which Apple will address shortly:
1. 2GB of addressable RAM. OS 10.3 will address this, but processor support is required. This impacts machines across the upper end of the product line and will impact lower machines over the next few years.
- in particular it hits the xserve line, 2GB is not enough for high end servers, esp multi-processor machines.
- it hits the higher end desktop machines. 2GB is also kind of skimpy for lots of photo/music/video editing etc. Think about this: compare the performance of iTunes to iMovie and iDVD. Apple wants to have iMovie and iDVD perform like iTunes - no more hour wait to "encode assets" on a DVD on a DP 1.x. They know that for the Digital Lifestyle to pan out, performance like iTunes is the key for those applications.
- a 64 bit processor will allow more efficient use of VM, RAID, DBs etc.
--> in short, Apple needs a 64 bit processor and soon for all the other pieces of its puzzle to fall into place (digital lifestyle, xserve etc). It will have it in the 970 and 10.3.

2. Disk sizes. 180GB (+ or -) being the top end drive is low for the upper end machines. Even the upper end xserve RAID has "only" (I put only in quotations because the 1st hard drive we had was 5 MB (yes, megabytes on the Apple ][, then ][ plus), and I recall the sort-of-hard drive fixed platters < 1 MB) 2.5 TB. This is not bad, but...

--> not a large impact on the 970, but relevant.

3. Something is <b>obviously</b> up with the 15 inch PB. Apple would not leave a huge hole in their product line without a good reason. Many people are holding off on the 15 inch PB because of the lack of Airport Extreme. I have seen *no* credible reports of design problems, manufacturing problems etc on the 15 inch PB, and their would be rumors if indeed that was the problem. Lets just face the facts: the PB is going to have something quite different than the current PBs. Will it be the super-new 15 inch display alone? I doubt it, why hold off using the old display for 6-9 months just to have a different 15 inch, there would be enough time to refresh the product at that point and not give up the sales --- this leads me to believe that they are *racing* to get these out ASAP. They know that they are losing sales (or at best people are going down to the 12 inch, lower margins). The processor is the only possible reason besides criminal insanity to delay the 15 inch update for 6 months. Releasing the 15 first lets them work out the bugs with 1 design at a time and gives a safety net while doing so (e.g. they still have proven 12 and 17 inch designs). Once the 15 is running smoothly, then the 12 inch and 17 inch PBs will be updated ASAP since most of the design work will be completed.

4. You will see DP machines. The 970 is a good MP processor and since Apple isn't matching the MHZ/GHZ values, it is a good PR move, plus a good performance move. It will definitely be in the xserves and the upper end PowerMacs as we see now. Everyone at Apple knows that the xserves require MP machines if they are to compete with everyone else. Why use a completely different design when you can amortize the cost over the PMs and the xserves? It would make no sense. So, they can re-use the designs, and put a 2nd (or 3rd or 4th) processor in there at their cost while charging a nice markup.

All of these problems will hit all over the entire product line during the next 2-3 years as the whole "digital hub" really kicks in. Sharing music is the beginning. We'll be sharing iPhoto photo libraries next. Then iMovie libraries shortly thereafter. These require more memory, more processing power, and more disk space. Ditto for the smart display/tablet, you can trade of processor power for network performance or visa versa, so the more processor power the better.

The people at Apple aren't dumb, they know the products (software) that are in the pipeline and the processing power needed to do them justice. That is why 10.3 is important as is the 970, they depend upon each other and other products depend on them.

[alset]

At this point, it's nearly impossible to believe that there won't be a lot of broken hearted Mac users, out there. The hype is getting so big that I half expect a rumor to come out saying Steve will personally deliver the new machines to your place of residence and wash your car.

I hope it's all true, but it's not fair to myself to bet on it as hard as that. I'd rather be delighted, rather than disappointed, when the new machines arrive.

Dan

[Remus]

At this point, it's nearly impossible to believe that there won't be a lot of broken hearted Mac users, out there.

Yes that is why they call them rumors. Some of these rumors may be based on fact, some may actually be good guesses. BUT THEY ARE RUMORS....

ONLY RUMORS..... ;)

Let us put a little perspecitve on this. :p

Enjoy the day for tomorrow may bring us new positronic multi processors.... :D

[mathiasr]

Originally posted by P-Worm
Ok, so AltiVec is like a 64 bit emulator right? So why do we need it in a 64 bit machine. Will it double the emulation to 128? Or am I just getting my numbers screwed up?

I guess what I'm really asking is, am I going to see a noticable speed boost in video rendering if FCP is already coded for AltiVec?
Not really, AltiVec works on 128 bits (16 bytes) data chuncks and treat them as if they were:
16 times 8 bits
or
8 times 16 bits
or
4 times 32 bits (these could also be single precision floating point numbers)

Say for exemaple you have a grayscale picture, each pixel is represented by a single byte, and you would like to turn it somewhat darker.
Without a SIMD (Single Instruction Multiple Data) extension in our CPU, your application would have to load each byte composing your picture (one by one) in a register and subtract say... 5 to its value to make it look darker, and once this is done put it back in memory.
AltiVec like SSE2 is a SIMD engine, and this will definitely speedup the process since your application could load 16 bytes at once, subtract 5 to all these 16 values, and put them back.

Pseudo SIMD code:
load16 in vector register A from memory location B
sub16 value 5 to each cell in vector register A
store16 vector register A to memory location B
add 16 to register B

Pseudo non SIMD code:
loadbyte in register A from memory location B
sub value 5 to register A
storebyte register A to memory location B
add 1 to register B

loadbyte in register A from memory location B
sub value 5 to register A
storebyte register A to memory location B
add 1 to register B

loadbyte in register A from memory location B
sub value 5 to register A
storebyte register A to memory location B
add 1 to register B

loadbyte in register A from memory location B
sub value 5 to register A
storebyte register A to memory location B
add 1 to register B
...
should be repeated 16 times to produce the same result as the SIMD code, guess which one is the fastest?


FCP could be faster, not because AltiVec instructions are going to be faster (it will probably the same compared to a G4 at the same clock speed), but since the PowerPC 970 is expected to have 2 to 3 times more memory bandwidth, moving large data sets -like pictures- from memory to the vector registers and back should be way faster.
This is especially true if the slow bus on the G4 is the bottleneck of you app, it could be considered memory bound in this case: it cannot go faster than memory access, the CPU waits on data, and all CPUs wait at the same speed, whether they are RISC, CISC, FISC, run at 20 MHz or 4 GHz ;)

[ffakr]

Originally posted by hvfsl
A 64bit chip on a 64bit OS is quite a bit faster than a 64bit chip on a 32bit OS. What people are forgeting here is that every clock 64bits of data are processed instead of 32bits. So twice as much data. Although in the real world there will not be a 2x performance boost, much like a dual G4 is not twice the speed of a single G4. IF you look at the new figures for the AMD 64bit on www.futuremark.com you will see a 1.4Ghz AMD is 70% faster than a 2.26Ghz P4.

NO!

You still aren't getting it. This has been explained many, many times.
If you require operations with 32bit precision math, it doesn't matter whether you use a 32bit, 64bit, or 256bit processor, and it doesn't matter whether you use a 32bit, 64bit, or 256bit OS... it will still only fetch 32bit words!!!
Why is this so difficult to understand?

Your analogies aren't relevent.
Dual processor rigs aren't 2x as fast as single processor rigs because they have limited bandwidth, because they have to keep cache coherency between processors, because non-multi-threaded apps can't use both processors, because multi-threaded apps may stall threads if they are waiting on results from other threads.....
The AMD Opteron is 70% faster on some tests because it is a different, more efficient architecture. The athlon is faster than the P4 on a per cycle basis too and it's only 32 bit. Sure, the Opteron is WAY faster when it is benched against the Pentium 4 while performing 64bit integer math, but it isn't faster on a per clock basis just because it is 64bit. Most people don't require 64bit precision integer math, plain and simple, so most people won't benefit from 64bit processors.
Opteron and the 970 are fast because of their architecture not because they are 64bit.

[macrumors12345]

Originally posted by P-Worm
Ok, so AltiVec is like a 64 bit emulator right? Or am I just getting my numbers screwed up?

P-Worm

Uh, yeah. Altivec is a vector unit, so it works with either 4 32-bit numbers, 8 16-bit numbers, or 16 8-bit numbers. Thus, IF your code can be vectorized (BIG if), then Altivec can in theory crunch between 4 to 16 times the number of integers every clock cycle that a single scalar integer unit can. That is why it is "up to 4 to 16 times speedup" on code that can be vectorized.

The fact that PPC 970's integer units are 64 bit just means that they can crunch one 64 bit number per clock cycle. But it is still just one. So unless you needed to use big 64 bit integers (and most code doesn't), then it will not be inherently faster than a 32 bit integer unit, because both of them still process only ONE number per cycle. In contrast, Altivec can theoretically process between 4 to 16 numbers per cycle.

Nevetheless, the PPC 970 will still be MUCH faster than the G4 on a per clock cycle basis, but that will be true because it is a much better designed chip, not because it is 64 bits per se. The upside of this is that you will NOT need to see software be recoded as 64 bit in order to see an immediate performance gain when using the PPC 970.

[mim]

Originally posted by ffakr

If you require operations with 32bit precision math, it doesn't matter whether you use a 32bit, 64bit, or 256bit processor, and it doesn't matter whether you use a 32bit, 64bit, or 256bit OS... it will still only fetch 32bit words!!!


I agree with you in principle, but something just nagged in the back of my brain, thus:

The 970 does not have a single 64 bit data bus (each direction) feeding it, but 2x32bit ones. It also has not one, but 2 load/store units, 2 fixed point units, 2 floating point units, and 1 simd unit - that just happens to have 2 sub-units.

Now, I know next to nothing about proc design so these are just my thoughts.

What I do know is that every other chip I've seen data on has 1X data bus (64 bit procs like the AMD have 1x64bit data buses, even the power 4 does too), they all have 1 floating point unit, and I've never heard of a a simd unit that has 2 sub units.

Is it possible that the reason that IBM chose 2x32bit busses rather than 1x64bit (which must be less effecient for 64bit data read/writes?) is that it >can< call and send 2x32bit words each cycle?

Just a though, just a thought.

Flame proof suit is on! Go for it boys (and girls).

a.

[eric_n_dfw]

I kind of wish Motorola could have gotten DDR support on the 7400 series FSB. Unlike many here, I am not a G4 basher, except for that FSB. AltiVec is so bottlenecked by it. Final Cut Pro rendering and Photoshop filters could be so much faster if the vector registers (and/or the cache memory) didn't have to wait so long to refill from main memory. Maybe we'd be seeing IBM and Moto having some competition for one-an-other if that had happened. (coulda', shoulda' woulda')

[illumin8]

Originally posted by apemn88
Here is the marketing strategy: Runs better on 64 bit (2x faster)Why does everyone seem to perpetuate the myth that a 64-bit OS is twice as fast as a 32-bit OS? This is absurd. You gain a small performance benefit due to being able to use 64-bit registers for greater floating point precision, but the performance benefit is negligable.

The number one (and almost only) benefit of a 64-bit OS is being able to address more than 4GB of memory.

That's it... 64-bit is not some holy grail (well, it is if you need that much memory), and most apps won't even benefit from it at all.

Where it does come in handy is that pretty soon most desktops will have 8GB or 16GB of RAM. It will be nice to be able to use all of that memory without using some funky PAE extensions.

[illumin8]

Originally posted by copperpipe
But, I just don't understand why Intel, AMD, and IBM are all investing billions of dollars in the race for 64 bit? Remember how many years ago Bill Gates said "640k memory should be enough for anyone", or something like that? Well, we are quickly reaching the point where 4GB of memory will not be enough for anyone. When we reach that point, the big chip manufacturers like Intel, AMD, and IBM don't want to be stuck for a couple of years trying to engineer their 64-bit products. They want to be ready ahead of time, because whichever vendor has the most solid 64-bit implementation will win major market share.

Another consideration is large enterprise databases. These suckers live on 64-bit, take for example a Sun Fire 15000 which supports up to 576GB :eek: of RAM! That's over half a terabyte of memory... The Intels and AMDs of the world would love to be able to capture some of that market share of the servers that sell for a few cool million a piece...

64-bit really doesn't matter too much for the desktop for the next year or so, but I can see by about 2005 it will be a differentiating factor.

[mathiasr]

Originally posted by ffakr
NO!

You still aren't getting it. This has been explained many, many times.
If you require operations with 32bit precision math, it doesn't matter whether you use a 32bit, 64bit, or 256bit processor, and it doesn't matter whether you use a 32bit, 64bit, or 256bit OS... it will still only fetch 32bit words!!!
Why is this so difficult to understand?

Yes, this should be pointed out. 64 bits registers speed up computations only if you need to work on 64 bits data, and quite often (most often indeed) CPUs work only on 8, 16 or 32 bits data.
Eg. your doing a sensus survey and want to identify each person with a given number, excepted if your survey covers the entire Earth population you do not need 64 bits numbers, it's the same with most common task, you'll never have more than 4 billions songs in your play list, music samples are 16 bits wide, pixels are 24 or 32 bits elements, and you could handle a couple or two using a SIMD extension (the G4 is actually a 32/128 bits processor)
Only a few tasks require 64 bits figures, mostly sciences, accountancy... and if your program needs to handle a 64 bits data from time to time a 32 bits CPU can do the job, it will only require more time (we are speaking in tenth of microseconds here), and this is the only time you whould actually see a benefit having a 64 bits CPU.
Computing the size of a file on a 64 bits file system, is not the same job as crunching through a 1000 by 1000 matrix in Mapple.
64 bits CPUs are interesting if you have a heavy usage of such datas, or if you need to point to more than 2 GiB of memory (as would the database of all the parts of a jet plane, or eventually keep an entire movie clip in memory, not your personal stamps collection, nor an MP3 file); in many many other cases a SIMD engine can bring you much more benefit.

128 bits SIMD = handle 4 CD quality music samples at the same time.
64 bits CPU = handle a single sample that is I cannot figure howmany times more precise and that not even a Vulcanian needs ;)

[ffakr]

Originally posted by mim
The 970 does not have a single 64 bit data bus (each direction) feeding it, but 2x32bit ones. It also has not one, but 2 load/store units, 2 fixed point units, 2 floating point units, and 1 simd unit - that just happens to have 2 sub-units.

Now, I know next to nothing about proc design so these are just my thoughts.

What I do know is that every other chip I've seen data on has 1X data bus (64 bit procs like the AMD have 1x64bit data buses, even the power 4 does too), they all have 1 floating point unit, and I've never heard of a a simd unit that has 2 sub units.

Is it possible that the reason that IBM chose 2x32bit busses rather than 1x64bit (which must be less effecient for 64bit data read/writes?) is that it >can< call and send 2x32bit words each cycle?


Apple is using two uni-directional 32 bit busses because that is what Hypertransport is... Hypertransport.org (http://www.hypertransport.org/technology.html). Hypertransport (as used in the 970) sends 32bit blocks in packets... kind of in the way that a serial ethernet cable delivers data in packets. This is why you hear about 6.4GB of effective bandwidth... 2buses*32bit/8bits_per_byte*900MHz=7.2GB/sec... but once you subtract off the overhead associated with routing (and packetizing) the Hypertransport data, you get around 6.4GB/sec. :)

As for the altivec sub-units... the current G4s have no less than FOUR subunits that make up Altivec. :-)
Probably the coolest feature of the 970 that most people don't mention is that it can issue up to 8 instructions per clock cycle (though 3 of those are load/store). The 970 has so many discrete units because it can use so many of them at once!

[Rincewind42]

Originally posted by mim
The 970 does not have a single 64 bit data bus (each direction) feeding it, but 2x32bit ones. It also has not one, but 2 load/store units, 2 fixed point units, 2 floating point units, and 1 simd unit - that just happens to have 2 sub-units.

I'm pretty certain you are correct about that (not looking at the spec sheet, and I don't quite remember the functional unit counts...). None the less, functional unit count doesn't have anything to do with 64-bitness, but does with performance.

And it does have 2 32-bit busses, but they are each unidirectional - one is used to read(load) and the other to write(store).

What I do know is that every other chip I've seen data on has 1X data bus (64 bit procs like the AMD have 1x64bit data buses, even the power 4 does too), they all have 1 floating point unit, and I've never heard of a a simd unit that has 2 sub units.

Actually, the Power4 does use dual busses that are very similar to the 970 - but they are 128 bit instead of 32. And the 745x G4s also have the same (or similar) division of the Altivec unit.

Is it possible that the reason that IBM chose 2x32bit busses rather than 1x64bit (which must be less effecient for 64bit data read/writes?) is that it >can< call and send 2x32bit words each cycle?

No, each bus can only be used to read or write, not both. This is the same reason why you won't see much of a benefit from Dual Channel DDR RAM on a single proc PowerPC 970 system. Unless you are communicating with different RAM chips you can't use the full read & write bandwidth at the same time (on a dual proc system you could be reading or writing to the same RAM chips with both CPUs and thus gain some benifit).

[mim]

Originally posted by Rincewind42

No, each bus can only be used to read or write, not both. This is the same reason why you won't see much of a benefit from Dual Channel DDR RAM on a single proc PowerPC 970 system. Unless you are communicating with different RAM chips you can't use the full read & write bandwidth at the same time (on a dual proc system you could be reading or writing to the same RAM chips with both CPUs and thus gain some benifit).

Sorry, you're right (I just checked the data sheet which I should have done in the first place...<sigh>). I had thought that it had 4 busses (2 read and 2 write), but it does only have 2 and they are unidirectional.

Thanks for the clarifications, and the details on hypertransport from ffakr. :)

[chicagdan]

I was more interested in this quote from PowerJack:

"I also have a pile of Apple documentation here describing some mind-bending capabilities lurking inside the new iPods."

[scem0]

I am praying for cheaper prices not for speed. Lets just hope these machines aren't overly expensive. ;)

[mim]

Originally posted by chicagdan
I was more interested in this quote from PowerJack:

"I also have a pile of Apple documentation here describing some mind-bending capabilities lurking inside the new iPods."

Everyone said that about the original pods too (a whole unused chip?) - but nothing ever came of it.

Not saying that these capabilities don't exist - but Apple have to let someone develop them (if they don't themselves).

a.

[BaghdadBob]

Since some of you here are so well informed I'm going to phrase this as a question, since I do not know the answer to it.

Why wouldn't Altivec benefit largely from a 64 bit processor? If Altivec is designed to facilitate the crunching of multiple operations at once instead of one at a time (in select cases) would a 64-bit processor allow Altivec to fit twice as many of these instructions into a clock cycle?

I really don't know, because I am Altivec stupid, so someone who does please enlighten me.

And try to refrain from flaming people who think a 64 bit processor will be twice as fast. Just tell them it won't. Although -- from what I understand it will be not only twice but several times as fast in 64 bit operations as a 32 bit processor ends up having to cycle these things not twice but a few times. I could be wrong...it's only what I've heard.

[BaghdadBob]

Originally posted by mim
Everyone said that about the original pods too (a whole unused chip?) - but nothing ever came of it.

Not saying that these capabilities don't exist - but Apple have to let someone develop them (if they don't themselves).

a.

There is at least one hidden ability here, recording. (http://www.macrumors.com/pages/2003/05/20030502185918.shtml) You might have to rig something to get it to work, but with the curtain pulled back, Apple will probably end up releasing a new attachment and SW update with this generation....eventually...

[Rincewind42]

Originally posted by BaghdadBob
Why wouldn't Altivec benefit largely from a 64 bit processor? If Altivec is designed to facilitate the crunching of multiple operations at once instead of one at a time (in select cases) would a 64-bit processor allow Altivec to fit twice as many of these instructions into a clock cycle?

Altivec is designed to work with 128 bit quatities as 16 8-bit, 8 16-bit, or 4 32-bit values. That's it, nothing more or less (although that something is pretty sweet in the right hands! :D).

A 64-bit processor is one that is defined (typically) as manipulating 64-bit pointers. Since pointers are almost always manipulated in the integer unit of the CPU, this means that a 64-bit CPU can manipulate 64-bit integers.

Since the Altivec unit doesn't interface with the integer unit in this manner (the only effect that a 64-bit integer unit has on the altivec unit is that vectors can be loaded beyond the 4GB value - just like any other data type).

Now, since all instructions on the PowerPC platform are 32-bits you may thing that you could load 2 instructions at once and execute them both. This isn't how it works. In reality some larger number of instructions (that depends on the actual CPU architecture) is loaded and dispatched at once. This is completely independent on the integer unit - it is completely uninvolved in instruction dispatch & execution (aside from actually executing instructions dispatched to it).

And try to refrain from flaming people who think a 64 bit processor will be twice as fast. Just tell them it won't. Although -- from what I understand it will be not only twice but several times as fast in 64 bit operations as a 32 bit processor ends up having to cycle these things not twice but a few times. I could be wrong...it's only what I've heard.

Well, I don't think that any of us are delibrately trying to flame anyway - we just don't want others to be confused about what is going on. Since inevitably this leads to "Why isn't X twice as fast on this chip? 64-bit is supposed to be twice as fast as 32-bit!". It's a preemptive strike on ignorance :D.

And yes, 64-bit number crunching will be more than twice as fast on a 64-bit CPU vs a 32-bit CPU :cool: . But this is probably not as big a deal as some people want to make it :D.

[mathiasr]

Originally posted by mim
The 970 does not have a single 64 bit data bus (each direction) feeding it, but 2x32bit ones. It also has not one, but 2 load/store units, 2 fixed point units, 2 floating point units, and 1 simd unit - that just happens to have 2 sub-units.

Now, I know next to nothing about proc design so these are just my thoughts.

What I do know is that every other chip I've seen data on has 1X data bus (64 bit procs like the AMD have 1x64bit data buses, even the power 4 does too), they all have 1 floating point unit, and I've never heard of a a simd unit that has 2 sub units.

Is it possible that the reason that IBM chose 2x32bit busses rather than 1x64bit (which must be less effecient for 64bit data read/writes?) is that it >can< call and send 2x32bit words each cycle?

Just a though, just a thought.

Flame proof suit is on! Go for it boys (and girls).
You have to know that putting a lot of wires on a mobo renders its drawing difficult, prone to interferences... thus IBM choosed to reduce the bus width and dramatically increased its clock frequency.
The announced 900 MHz bit rate is in fact a 450 MHz bus with DDR (Double Data Rate). In comparison the Athlon 3200+ has a 200 MHz DDR (400 MHz bit rate) FSB, the Pentium 4c has a 200 MHz QDR (800 MHz bit rate) FSB. Both x86 CPUs have a 64 bits bus, the 970 has two 32 bits buses, and nominally clocked more than twice as fast (the result is that it should be in the same ballpark as the P4).

The Athlon has 3 FP units ;)

On the bus datas do not travel alone, they move with their entire neighbourhood in what is called a cache line. This is due to the cache logic, it would be damn hard to track bytes one by one, having flags telling if they have been modified and so on. And chances are that if you requested a byte you'll also need the one next to it.
Cache lines are usually 32 bytes wide (I'm not sure about the PowerPC 970 it may be 64 bytes), this is wider than any bus be it 64 bits or 128 bits, a single byte read can produce many waves of data transmission on the bus.
You also have to know that the buses between the CPU core and its L1 and L2 caches are way wider than the CPU front side bus, for instance the PowerPC 970 can read 8 32 bits instructions from its L1 instruction cache at once.

The 970 is a fast and wide design, faster and wider than the G4.

[HasanDaddy]

Why are people knocking on LoopRumors so much???

They have a MUCH BETTER track record than MacWhispers

LoopRumors, after all, was the only site to get info on the Steve Jobs speech at INTEL.....with all due respect to TS and MacRumors (who are pros at this game), every other rumor site snoozed on that one

MacWhispers's rumors have not come to fruitation yet (as far as I know)....as a matter of fact, wasn't MacWhispers going to shut their website off completely after so many, self confessed, inaccuracies???

I love reading all rumors and I love checking all rumor sites.....but at this moment in time, I have more faith in LoopRumors than I do in MacWhispers

[porovaara]

Originally posted by HasanDaddy

I love reading all rumors and I love checking all rumor sites.....but at this moment in time, I have more faith in LoopRumors than I do in MacWhispers
I have more faith in Steve Jobs showing up at my doorstop tomorrow with a batch of 970s and unrelased NeXT-pyro based machines than I do in either of the above sites. They have no credibility, none.

Also as to altivec being on the 970, doesn't it appear that the functionality was tacked on to the 970? (My limited understanding from following the huge thread at Ars).

[BaghdadBob]

Originally posted by Rincewind42
Well, I don't think that any of us are delibrately trying to flame anyway - we just don't want others to be confused about what is going on. Since inevitably this leads to "Why isn't X twice as fast on this chip? 64-bit is supposed to be twice as fast as 32-bit!". It's a preemptive strike on ignorance :D.

And yes, 64-bit number crunching will be more than twice as fast on a 64-bit CPU vs a 32-bit CPU :cool: . But this is probably not as big a deal as some people want to make it :D.
Well, some people are treating those who are not in the know a little harshly. If someone gleefully exclaims "Blahblahblah will be twice as fast on a 64 bit chip!" I'm quite sure it is out of ignorance, not blatantly misinforming the public, as some are treating such comments with their "WHY are you perpetuating this myth, dumbass?" remarks.

Anyway, as far as what will benefit from 64-bit processors, I am sure that once optimized code is widespread that there are a great many popular uses it will have, such as with rendering and graphic manipulation. And really, what else do you need from a processor once you get past a GHz or two?

Thanks for answering my Altivec question, here's another, and it's stupid too: am I wrong in assuming that before instructions get to the Altivec hardware they have to pass through the processor? If I am not, lets say you have a 64 bit processor, does that allow you twice the path through which to pass Altivec instructions, assuming you have twice as much Altivec hardware? Did I misunderstand that Altivec is hardware based? Does the pair of 32 bit unidirectional busses basically eliminate this possibilty as a 32-bit processor would have access to these instructions to pass them along just as quickly?

Should I just read up on this since the technology's been around what...8 years or more? If so just give me a link and I'll shut up and figure it out for myself.

[Rincewind42]

Originally posted by BaghdadBob
Anyway, as far as what will benefit from 64-bit processors, I am sure that once optimized code is widespread that there are a great many popular uses it will have, such as with rendering and graphic manipulation. And really, what else do you need from a processor once you get past a GHz or two?

Optimized code for the 970 will likely come from one of 3 sources: Updates for programs that can make wide usage of 64-bit integers (which would only run on 64-bit hardware), Upgrades that add Altivec code, or Updates to compilers that allow for optimized code generation for the 970 (which would run on other PowerPCs unless the program is also compiled for 64-bit, but would also possibly make this code slower on older processors). In general, the latter two optimizations would make for larger performance gains than the first.

Thanks for answering my Altivec question, here's another, and it's stupid too: am I wrong in assuming that before instructions get to the Altivec hardware they have to pass through the processor? If I am not, lets say you have a 64 bit processor, does that allow you twice the path through which to pass Altivec instructions, assuming you have twice as much Altivec hardware?

Altivec instructions are just like any other instructions, it's just that they are only available on certain CPUs. The Altivec unit is exactly like any other processing unit. Like the FPU & Integer units, it has it's own set of registers that it shares with the Load/Store unit (for the sole purpose of moving register contents to and from main memory).

The integer width has nothing to do with how many instructions you process on a particular clock cycle, as instructions do not pass through the integer unit for dispatch. Basically, the hardware fetches instructions and from those instructions determines which unit they should be sent to - Integer, Floating Point, Altivec, Branch, or Load/Store. By the time an instruction enters an execution unit, more instructions have already been loaded and prepared to execute immediately afterward.

The PowerPC 970 can fetch up to 8 instructions per cycle (that's 32 bytes - 256 bits) dispatch/complete 5 of them per cycle. It would be possible to create a 32-bit (or 16-bit, or any other bit-ness) CPU that could fetch even more instructions per cycle. So in the end, the bitness and bus archetecture of the CPU have nothing to do with how many instructions can be fetched for execution per cycle (although the latter can affect how fast this can happen).

Should I just read up on this since the technology's been around what...8 years or more? If so just give me a link and I'll shut up and figure it out for myself.

Altivec technology has been around for about 4 years now if I'm remembering correctly. You can find loads of information on it at http://www.simdtech.org/apps/group_public/documents.php

edit: edited for clarity

[Gyroscope]

If, after all this rumors and high hopes we get yet another G4 incranation I will laugh my guts out.

What a crazy sick laugh that will be.

[mim]

Originally posted by Gyroscope
If, after all this rumors and high hopes we get yet another G4 incranation I will laugh my guts out.

What a crazy sick laugh that will be.

heheHEmwah,mwahmwahMWAHMHWAMEHAAAARRRRGGGGGGG****IT!

just practicing.

[BaghdadBob]

Is it the kind of laugh that starts out hysterically and degenerates into sobbing, dropping your gun, and trying to remember what this whole crazy "Mac" thing was all about in the first place?

Yeah, that sounds about right...

[wwworry]

Originally posted by HasanDaddy
Why are people knocking on LoopRumors so much???

They have a MUCH BETTER track record than MacWhispers

LoopRumors, after all, was the only site to get info on the Steve Jobs speech at INTEL.....with all due respect to TS and MacRumors (who are pros at this game), every other rumor site snoozed on that one

MacWhispers's rumors have not come to fruitation yet (as far as I know)....as a matter of fact, wasn't MacWhispers going to shut their website off completely after so many, self confessed, inaccuracies???

I love reading all rumors and I love checking all rumor sites.....but at this moment in time, I have more faith in LoopRumors than I do in MacWhispers

It makes no difference if the rumor sites are true or not. Machines come out when they come out.

[AidenShaw]

Originally posted by maxvamp
what is your take on any speed impact when the processor has to manage the upper and lower set of bits of a given file.

Updated after reading the excellent Ars Technica article just posted http://arstechnica.com/cpu/03q1/ppc970/ppc970-0.html In particular, that article has the line

...but to summarize, Mac users should not expect any inherent performance benefits from the move to 64 bits. The 970's performance advantages will come from the many microarchitectural features that I'll cover in this article, and not from the fact that it's a 64-bit processor.

----

Well, the simple integer instructions execute in a single cycle. Add 32-bits, then "add with carry" the 2nd 32 bits (the way 64-bit synthetic integer additions are done) would take two serial instructions.

That's 2 cycles, or 1 nanoseconds for a 2GHz CPU.

But that's really worst case - in a superscalar, o-o-o (out-of-order) CPU both adds could be started at about the same time, along with many other instructions (the 970 and P4 can have 1 or 2 hundred instructions in progress at once). So other things are happening at once, so the 1 nanosecond could be hidden by other things that need to be waited on.


----

What if the data is not in cache? Latency on a cache miss is often from several dozen to a hundred or so cycles - suddenly the 2 cycles for the arithmetic is 50 or 100 cycles. At this point - 1 cycle for a 64-bit add vs. 2 cycles for a synthesized add is hardly relevant.

----

Suppose we're doing a 64KB read and the data is in the filesystem cache. If the system bus is 8GB/sec, then reading and writing 64KB will take about 16 usec, or 32,000 cycles.

----

Suppose the disk head has to move - that's about 8 msec - 8,000 usec - 8,000,000 nsec - or a whopping 16,000,000 cycles.

----

So, that's why I claim that an extra cycle to synthesize 64-bit integer arithmetic won't be measurable in actual I/O operations.

[ktlx]

Originally posted by BaghdadBob
Well, some people are treating those who are not in the know a little harshly. If someone gleefully exclaims "Blahblahblah will be twice as fast on a 64 bit chip!" I'm quite sure it is out of ignorance, not blatantly misinforming the public, as some are treating such comments with their "WHY are you perpetuating this myth, dumbass?" remarks.

When multiple people repeat the same misinformation in the same thread thread, it is pretty tough to second through nth person with kid gloves.

This gets especially hard when you are dealing with the fifth or sixth person in the thread to say it in such an asinine way.

Okay, I am not perfect or all knowing, but I at least expend the effort to read the posts in a thread before saying something stupid.

[medazinol]

Folks, does anyone here know that Foxconn is a trade-name that a large Taiwanese manufacturer uses?

That manufacturer is Hon Hai.

Go look them up (http://www.foxconn.com, http://www.foxconn.com.tw , http://hr.honhai.com.tw ) They DO made boards for Apple.

While were at it, Quanta in Taiwan makes the PowerBooks for Apple.

I think the reports are true to a certain degree. I think we're going to see 970 machines, soon.

[mcs37]

Originally posted by macdong
You are way over your head, dude.
I don't want a steaming fried pan on my laps. :rolleyes:

Eh, it's not entirely unimaginable that there wouldn't be a dual 970 17" PowerBook. Just make sure it only runs 1 processor when running on battery! Wooha! That would drain the battery pretty fast otherwise.

With the amount of area that the 17" PB provides, and the negligible heat it puts out thanks to Apple's great designs, I highly doubt heat would be a problem. I am all about the dual 970 PB.

[leo]

Went to Foxconn's site and found this:

http://www.foxconn.com/products/alphabet.asp?fmletter=M

What's an "Apple Monster Bus" (Customer Special)?

*feeds the fire* :D

leo


p.s.: At least Apple has been working with Foxconn in the past to some extent. Some of the connectors in my b/w G3 are labelled "Foxconn". I know, it's just connectors...

[maxvamp]

Aiden, I would like to note two things....

1.) you jumped all over my posts because they mentioned that there would be performance increases in the 970 and assumed that it was solely because the 970 proc was 64-bit. If you go back in this thread, you will see that my original post had the following, which I saud before the ars article was announced :


All, I understand that most of performance increase to be gained from the 970 is from basic architectural design changes, and most apps will not take advantage from the increased memory addressing available, but people keep forgetting that computer security has a bright future, and we will ( with the war on terrorism ) see encryption show up in more and more components of the average computer system.

I did, however try to explain that there will be apps that will be able to make use of this processor. I even tried to give a few examples of some I thought might. Your basic stance so far has been that 64-bits will not, nor ever make a difference. and quite frankly, I do not think that is right. Even on the disk example I give, I believe one application that will take advantage of all of this is a good backup program. They have databases to deal with and do a ton of I/O calculations, along with ( often ) software compression. There is a lot of math there... I don't know how this processor will not benifit in this area.

Long and short of this dialog is... We must agree to disagree. I make my stance that this proc will be faster, as I stated before. If you choose to read into it that I am saying this is because it is 64 bits, so be it ( but I am not ).

Thanks again,

Max

[AidenShaw]

Originally posted by maxvamp
1.) you jumped all over my posts because they mentioned that there would be performance increases in the 970 and assumed that it was solely because the 970 proc was 64-bit.

Actually, I thought that I "jumped all over" your inconsistency in comparing dual PPC systems with single P4 systems, and then criticizing XP Home for not supporting duals. ;)

Most of the 64-bit comments were other discussions....

[jettredmont]

Originally posted by IJ Reilly
For a guy who claims he can't say nothin', this powerjack says quite a bit -- which all by itself seems kind of suspect. In the end all he really is saying is that Foxconn is not the contract manufacturer, somebody else is. As if that really matters.

Yes, I agree that MacWhispers says a bit too much if he's really being watched closely. If any of the information he is publishing is part of his NDA, even if he's also gotten it from other sources, he's liable to be brought into court for an NDA violation (and, at the very least, designated personna non gratis at Apple which will kill the likelihood of him working on Apple-related products pretty quickly).

On the other hand, if he is right, the implication there is that since FoxConn is not using the 970 chips then the 20k/40k/40k "arriving at Foxconn" is a complete fabrication. There's no way you could get information about how many units are arriving at an asembly plant and not get the plant itself right.

We'll see soon enough.

[Mr. Anderson]

After going through the original fiasco with Apple on the introduction of the first G4s over three years ago - I'm thinking I'm going to wait until the second version of the 970 comes out before I make a new purchase - even though I'm still using that original G4....

The potential here is fantastic, its going to be very hard not to buy one immediately.

D

[dongmin]

Originally posted by leo
Went to Foxconn's site and found this:

http://www.foxconn.com/products/alphabet.asp?fmletter=M

What's an "Apple Monster Bus" (Customer Special)?

*feeds the fire* :D

leo


p.s.: At least Apple has been working with Foxconn in the past to some extent. Some of the connectors in my b/w G3 are labelled "Foxconn". I know, it's just connectors...

Great find! Could this be the mysterious 'Apple Processor Interconnect Bus' that was rumored a while back? Could be huge.

If you do a google search for hon hai and apple, you'll see that they've done quite a lot of work for Apple. Hon Hai (Foxconn's their trademarked named) produced the B&W cases for Apple.

[cc bcc]

Foxconn also has this one:

Cable Assembly, Modubus____Harness, Apple Monster Bus____1.27mm [0.050in] Cable Flat

link (http://www.foxconn.com/products/alphabet.asp?fmletter=C)

Can anyone tell us what this means?

[maxvamp]

Actually, I thought that I "jumped all over" your inconsistency in comparing dual PPC systems with single P4 systems, and then criticizing XP Home for not supporting duals.



Ok. Quick question then.... Will XP Home support a 3GHz P4 with hyperthreading in HT mode ( i.e. the system looks like it has multiple procs)? This is the bets way to wring extra performance out of those chips.

Max.

[ktlx]

Originally posted by maxvamp
Ok. Quick question then.... Will XP Home support a 3GHz P4 with hyperthreading in HT mode ( i.e. the system looks like it has multiple procs)?

Yes. Windows XP Home will support two logical processors but not two physical processors. So as long as the motherboard supports it and the feature is turned on, Windows XP Home will recognize the HT-enabled Pentium 4s as being two logical processors.

[silvergunuk]

Im no tech geek so i was wondering if some one could help me out. As a Power 4 is a dual core and a 970 is a single core....couldn't a dual 970 set up act as a dual core chip? it could explain that dodgy bryce render.

[Rincewind42]

Originally posted by silvergunuk
Im no tech geek so i was wondering if some one could help me out. As a Power 4 is a dual core and a 970 is a single core....couldn't a dual 970 set up act as a dual core chip? it could explain that dodgy bryce render.

There is a small but significant difference between a Dual Core chip and a Dual CPU system. As far as the OS & Software is concerned they are identical, but from an engineering standpoint there are significant advantages to a Dual Core CPU design (and to a lesser degree advantages to a Dual CPU design). The Bryce rendering benchmarks post by MacBid could be either a beta of Bryce 6 that does take advantage of multiple CPUs/Cores or just made up, but either way Bryce 5 doesn't take advantage of multiple CPUS.

[silvergunuk]

Thanks for the explanation

[anonmac]

while there are people claiming that the bryce 6 beta does not exist, if you search google, you will find several people who claim to be in on the 'beta test'. if you're not one of them, who can say the truth is "this"?

[maxvamp]

INNNTERESTINK....

Max

[jettredmont]

Originally posted by Rocketman
I do not know if the 970 has powersaver features built-in but the OS does.


Powersaving works in one of two (preferably both) ways:

1) Shut down internal components (modem, HD, monitor) when not in use, and support hibernate (suspend to disk) and/or suspend (shut off everything but memory and monitor for wake).

2) Lower the voltage (and hence frequency and hence performance) of the CPU, turn off specific unused units on the processor itself.

(1) is implemented in the OS, and in large part does not need anything special from the CPU (although it does require that the firmware or bios support turning off subsystems, but that's been pretty universal since '98 or so). (2), however, requires CPU support.

I can't say for sure, but others here are convinced that the 970 does not support anything in group (2) above. Essentially, then, you will get the same design headaches putting the 970 into a laptop as you get putting a non-mobile Intel design into a laptop (relatively low battery life, heat generation a problem, fan noise).

On the other hand, there have been quite a few notebooks produced, even in the last couple of years, with non-mobile processors, and they have sold fairly well. I don't think this rules out a low-frequency (1.2GHz or less) 970 in laptops.

[jettredmont]

Originally posted by P-Worm
Ok, so AltiVec is like a 64 bit emulator right? So why do we need it in a 64 bit machine. Will it double the emulation to 128? Or am I just getting my numbers screwed up?


Altivec does not emulate 64-bit integer operations (nor 128-bit!). It handles multiple 32-bit (or 16- or 8-bit) operations in a single instruction instead of in multiple (4-16) operations.

Note, also, that the Altivec registers are not any wider in the 970 than they are in the G4. They will of course benefit from the increased FSB bandwidth, but they'll still work on 128 bits at a time.

[AidenShaw]

Originally posted by ktlx
Windows XP Home will recognize the HT-enabled Pentium 4s as being two logical processors.

And Windows XP Pro recognizes a dual HT Xeon as 4 logical processors, even though XP Pro is restricted to 2 physical processors.

To wit:
OS Name Microsoft Windows XP Professional
Version 5.1.2600 Service Pack 1 Build 2600
OS Manufacturer Microsoft Corporation
System Name COCO
Manufacturer Dell Computer Corporation
System Model Precision WorkStation 650
System Type X86-based PC
Processor x86 Family 15 Model 2 Stepping 7 GenuineIntel ~3055 Mhz
Processor x86 Family 15 Model 2 Stepping 7 GenuineIntel ~3056 Mhz
Processor x86 Family 15 Model 2 Stepping 7 GenuineIntel ~3056 Mhz
Processor x86 Family 15 Model 2 Stepping 7 GenuineIntel ~3056 Mhz
BIOS Version/Date Dell Computer Corporation A00, 11/7/2002
SMBIOS Version 2.3
Windows Directory S:\WINDOWS
System Directory S:\WINDOWS\System32
Boot Device \Device\HarddiskVolume2
Locale United States
Hardware Abstraction Layer = "5.1.2600.1106 (xpsp1.020828-1920)"
User Name COCO\aiden
Time Zone Pacific Standard Time
Total Physical Memory 2,048.00 MB
Available Physical Memory 1.70 GB
Total Virtual Memory 5.85 GB
Available Virtual Memory 5.41 GB
Page File Space 3.85 GB
Page File S:\pagefile.sys

[BaghdadBob]

So can someone tell me how it helps multiple processors for Windows to treat one processor as two? I don't get it. Are you saying that Windows XP treating one processor as two enables it to treat two processors as two, or are they then four?

[adamfilip]

any chance of Serial ATA interface on the new 970 MB?

i would like to have a Western Digital 36 gig Raptor SATA drive

and then a larger slower drive for regular backups and general archiving like 250 gig or so

[AidenShaw]

Originally posted by BaghdadBob
So can someone tell me how it helps multiple processors for Windows to treat one processor as two? I don't get it. Are you saying that Windows XP treating one processor as two enables it to treat two processors as two, or are they then four?

Yes, XP shows one processor as two, and two processors as four - when those processors have Hyperthreading.

Hyperthreading is a cross between a single CPU chip and a dual-core (2 CPU) chip. It has some of the circuitry of 2 CPUs, but not 2 complete CPUs. They are called "logical CPUs", so that you have 2 logical CPUs per chip.

If one logical CPU is using the floating point units, the other logical CPU can use the integer units at exactly the same time. This can improve performance.

It'a not double the performance (YMMV), but it's very cheap to add to a chip.

Look at http://www.reseller.co.nz/Reseller/Reseller.nsf/ArchiveSubCategory/86256ABD006E93FCCC256C780072D42F?OpenDocument&More=Product+News, or the Intel pages at http://developer.intel.com/homepage/land/hyperthreading.htm.

[jettredmont]

Originally posted by BaghdadBob
So can someone tell me how it helps multiple processors for Windows to treat one processor as two? I don't get it. Are you saying that Windows XP treating one processor as two enables it to treat two processors as two, or are they then four?

If Windows were to treat a HT processor as a single processor instead of dual processors all benefits of HT would be erased. Windows treats a HT-enabled processor as two, thus keeping two threads active on the processor at once.

HT-CPUs are not the same as dual core CPUs nor of course as dual CPUs, because they "share" most of the CPU between what Windows would consider the two processors. This is why Intel's implementation gets about 25% better performance with HT instead of 100% better performance (note, however, that IBM's Power5 is said to get much higher benefit, close to 100%, from SMT aka HT ... must be that IBM Special Sauce ...).

[maxvamp]

From what I remember from my OS/2 days, the most one could expect expect from a second processor was about 89% performance of the first. Even this took some IBM trickery. I would say that if someone is claiming 100%, that this would be more of a theory, than a constant statistic. Even the 89% was a peak rating.

BTW, thanks for the headsup on the XP HT info. I stopped keeping up with extreme details after Win2k. XP turned out to be such a piece of work, that I lost some interest in details. Win2k3, so far has been interesting though..

Max.

[MoldyJohn]

Per the MacBidouille article of the new mobos ?8 RAM connectors - 4 of which were covered by a Do Not Use sticker? makes some sense. OSX10.3 (64bit) will not come preloaded on the 970 boxes. OSX10.2 (32bit) can only handle, what, 4MB memory? The extra slots are there waiting for 10.3 which will then open up a full 8MBs of memory. Voile!

[mim]

Originally posted by adamfilip
any chance of Serial ATA interface on the new 970 MB?


We'll, you'd think there'd be no reason >not< to include one, after all Apple is pretty hot on the video editing market and it's ripe for SATA drives (ie - speed without RAIDing)....
...but this is Apple. Who knows what they'll give us.

[trebblekicked]

Originally posted by mim
We'll, you'd think there'd be no reason >not< to include one, after all Apple is pretty hot on the video editing market and it's ripe for SATA drives (ie - speed without RAIDing)....
...but this is Apple. Who knows what they'll give us.

funny. HD is the one aspect of the 970 innerds that hasn't been speculated to death. SATA would be interesting, but i wonder how XRAID fits in with the afore mentioned Xstation rumors. A prosumer (power mac) level 970 would probably still have UATA, with expandability leaning towards FW800 drives/raids, IMO.

[mathiasr]

Originally posted by maxvamp
From what I remember from my OS/2 days, the most one could expect expect from a second processor was about 89% performance of the first. Even this took some IBM trickery. I would say that if someone is claiming 100%, that this would be more of a theory, than a constant statistic. Even the 89% was a peak rating.
The theory is called the Amdahl's Law (http://home.wlu.edu/~whaleyt/classes/parallel/topics/amdahl.html). In practice you also have to consider how resources outside the CPU, especially memory bandwidth, will be shared.

100% is achieved by the distributed.net client, since it does scarcely access memory outside the L1 caches. The distributed.net client is not representative at all, it also uses AltiVec on a tiny data set for instance; but it does exist.

[mathiasr]

Originally posted by MoldyJohn
Per the MacBidouille article of the new mobos ?8 RAM connectors - 4 of which were covered by a Do Not Use sticker? makes some sense. OSX10.3 (64bit) will not come preloaded on the 970 boxes. OSX10.2 (32bit) can only handle, what, 4MB memory? The extra slots are there waiting for 10.3 which will then open up a full 8MBs of memory. Voile!
I think you meant gigabinarybyte GiB (http://members.optus.net/alexey/prefBin.html) and not MB.

[AidenShaw]

Originally posted by MoldyJohn
OSX10.2 (32bit) can only handle, what, 4MB memory? The extra slots are there waiting for 10.3 which will then open up a full 8MBs of memory. Voile!

Windows 2000 (32bit) can handle up to 32 GiB of memory, Windows Server 2003 (32bit) supports up to 64GiB.... Both the G4 and the P4 support up to 64GiB of RAM, you don't need a 64-bit operating system to make good use of the extra RAM.

If max memory support is the only issue, it would make more sense to simply restrict the quantity of installed memory, not the number of slots. One could use 8 of the (often cheaper) 512 MiB DIMMs to get to 4GiB.

If the 8 slot story is true, I suspect that the final system will have interleaved (dual channel) memory, where DIMMs have to be used in pairs. You'd need one DIMM in the lower bank, and an identical DIMM in the matching slot in the upper bank.

If MacB really did see a proto mobo with the slots blocked off, I would be more inclined to believe that the proto unit didn't support the dual channel memory controller, and therefore the upper bank was blocked.

[jettredmont]

Originally posted by AidenShaw
Windows 2000 (32bit) can handle up to 32 GiB of memory, Windows Server 2003 (32bit) supports up to 64GiB.... Both the G4 and the P4 support up to 64GiB of RAM, you don't need a 64-bit operating system to make good use of the extra RAM.


Depends on what you mean as "good use" of the 64GB of memory. 64GB systems work great for servers which require the extra memory because they have multiple separate processes running, but not so well for, say, a video editting app which might want to allocate 5GB of memory all for itself (IIRC, the P4 36-bit memory addressing only allows an individual program to access a 32-bit window of memory, so any one app cannot have access to more than 4GB memory).

On the other hand, no Apple system today is bumping against the 4GB memory barrier either (2GB is the limit). Is there something in the PPC or Mac architecture that forbids use of the 32nd bit of pointers? Granted, 2GB is a practical limit for physical memory on a consumer system, but you'd think that if it were possible for Apple to use 4GB of memory on the XServe they would have ...

[Rincewind42]

Originally posted by jettredmont
On the other hand, no Apple system today is bumping against the 4GB memory barrier either (2GB is the limit). Is there something in the PPC or Mac architecture that forbids use of the 32nd bit of pointers?

IIRC the Memory Controller that Apple currently uses doesn't support more than 2GB (I refuse to use GiB, sorry, just too old =p) Because it is no problem for any single process in MacOS X to use a full 4GB of memory (and in fact, many system routines are loaded into a process' memory space above the 2GB line).

[visor]

Originally posted by BaghdadBob
So can someone tell me how it helps multiple processors for Windows to treat one processor as two? I don't get it. Are you saying that Windows XP treating one processor as two enables it to treat two processors as two, or are they then four?

Oh, thats quite simple. You have to pay on a per processor basis - make one look like two - pay double.
Makes sense right?

[jettredmont]

Originally posted by visor
Oh, thats quite simple. You have to pay on a per processor basis - make one look like two - pay double.
Makes sense right?

Actually, Windows XP Home handles either a single physical processor or dual logical processors (ie, P4 3.0GHz with HT) with no extra cost. Windows XP Pro, required for dual physical processors but which can't handle 3+ processors, handles 4 logical processors (2 HT-enabled P4s) at no extra cost.

On the other hand, applications like Oracle et al might have different licensing policies, but that has nothing to do with Windows reporting multiple logical processors.

[astray]

Well, i was reading Macworld Uk today and came across this article from yesterday (15/5/03), i havent seen any references posted to it b4, but it looks mighty tantalising:

""IBM last night made additional details regarding its PowerPC 970 public.

The company released formerly limited circulation excerpts from October 2002's Microprocessor Review to selected media outlets, including Macworld UK.

The report, written by senior editor Tom Halfhill, confirms some details about the chip that have been circulating through the Internet.

Halfhill said he found it 'hard to imagine' that Apple would use anything else in its desktop Macs and servers."

The report begins: "Nobody at IBM would confirm rumours that a leading customer for the PowerPC 970 is Apple - and Apple is even more tight-lipped. Nevertheless, the 970 is such an obvious improvement over today's Motorola G4 family PowerPC chips that it's hard to imagine Apple using anything else in its desktop Macs and servers."

Claiming the chip to be "tailor-made" for professional publishing and media-processing applications, the report confirms: "It has 64-bit datapaths and memory addressing, yet it's natively compatible with 32-bit PowerPC software."

Additional features confirmed within the report include: a deeper data pipeline; bus rates of 900MHz; data bandwidth of 6.4GB/s; AltiVec. The PowerPC has 52 million transistors and is a stripped down version of IBM's Power4 processor, used in large-scale server installations.

"The deeper pipeline is especially welcome because it could allow the 970 to reduce the growing clock-frequency gap between today's PowerPC chips and the speedy x86 competition."

Calling Motorola's G4 and G4+ data pipelines "stunted" in comparison to Pentium 4, Halfhill suggests that initial estimates of 970 processor speeds are "conservative". In October it appeared the chips would offer speeds of 1.2-1.8GHz.

The report reveals the 970 to offer a 16-stage pipeline - 9 more than the G4+ and 12 more than the G4 and G3 processors. The processor offers two built-in floating point units, AltiVec support, a 64K L1 cache with a 512K L2 cache and a front side data bandwidth (FSB) of 2 x 3.2GB/s. The G4+ offers a 1GB FSB.

The FSB is the part of the processor that allows data to be moved from memory into the processor to be manipulated, and back again.

"The PowerPC 970 is clearly in a different class than existing G4+, G4 and G3 PowerPC chips. Its deeper pipelines and much faster FSB fix the most serious shortcomings of today's PowerPCs."

Looking at the history of the AIM (Apple, IBM, Motorola) alliance, the report says: "In fact, a 64-bit PowerPC was planned right from the start, when IBM, Motorola and Apple began creating the PowerPC architecture in the early 90's, the alliance promised to deliver three 32-bit processors - the 601, 603 and 604 and one 64-bit implementation, the 620."

The latter chip was never used on a Mac, but the inherent architecture of the PowerPC has always supported 64-bit memory addressing.

Execution is significantly faster - the 970 can fetch up to eight instructions per clock cycle, can dispatch up to five instructions per cycle to the function units, issue up to eight instructions per cycle and retire results for up to five instructions per cycle. "The 970 can juggle an unusually large number of instructions in its piopelines," Halfhill writes.

The FSB implementation is crucial. The processor drives this at up to 900MHz. The Pentium 4 offers 533MHz and the Athlon XP gets 333MHz.

The report offers several comparisons with competing processors, and the 970 seemingly surpasses or competes with x86-based competition. Its adoption would help Apple remain competitive in the market.

Halfhill concludes: "It's a good bet the 970 will also end up in a Mac - unless Apple's thinking is even more different than advertised."

Online, Mac rumour sites have begun to claim 970 processors are already arriving with manufacturer's in the Far East - who are working for a client called Apple.

Apple does not comment on rumour or unreleased products.""

The bits i liked best were:

"The report offers several comparisons with competing processors, and the 970 seemingly surpasses or competes with x86-based competition. Its adoption would help Apple remain competitive in the market."

and "Halfhill concludes: "It's a good bet the 970 will also end up in a Mac - unless Apple's thinking is even more different than advertised.""

[Rincewind42]

Originally posted by astray
Well, i was reading Macworld Uk today and came across this article from yesterday (15/5/03), i havent seen any references posted to it b4, but it looks mighty tantalising:

""IBM last night made additional details regarding its PowerPC 970 public.

The company released formerly limited circulation excerpts from October 2002's Microprocessor Review to selected media outlets, including Macworld UK.

Sigh

I wish that article had never been released at this point - about the only thing it offers that everything else that has been published up to this point is Speculation on Apple from a non-Mac rumors source :D. Not trying to flame you, just wishing there really was new information out there...

[skunk]

Just in: they surmise that the absence of releases of Darwin code since February except for official updates is because there's too much PPC970 stuff in there these days to hide. Same goes for Developer Tools: no visible progress since December. Another thing: confirmation that 970s at 1.7GHz are due out in July, manufactured using SiLK (low-K silicon) at 0.13microns, which will support an eventual processor speed of 2.3GHz or more. When they move to .09micron wafers at the start of 2004, the material will be something else again, enabling speeds of 2.5GHz, as originally announced. At the end of 2004, IBM will add "strained silicon", enabling the Power 5+ to reach 3GHz, and the PPC970/980 4.5GHz. If all goes according to plan.....

[BaghdadBob]

OK, that's either total b*******, or OH MY GOD. I'm not holding my breath though...

[adamfilip]

regarding the memory issue

i thought that i read somewhere that OSX can only allocate 1gb of memory to any application

so if you have 1.5gb and run photoshop . the max osx can give photoshop is 1gig..


is this accurate?

[Snowy_River]

Originally posted by skunk
Just in: they surmise that the absence of releases of Darwin code since February except for official updates is because there's too much PPC970 stuff in there these days to hide. Same goes for Developer Tools: no visible progress since December. Another thing: confirmation that 970s at 1.7GHz are due out in July, manufactured using SiLK (low-K silicon) at 0.13microns, which will support an eventual processor speed of 2.3GHz or more. When they move to .09micron wafers at the start of 2004, the material will be something else again, enabling speeds of 2.5GHz, as originally announced. At the end of 2004, IBM will add "strained silicon", enabling the Power 5+ to reach 3GHz, and the PPC970/980 4.5GHz. If all goes according to plan.....

Well, here's to some nice optomism...

'The future's so bright...' :cool:

[Kamu-San]

Alas, so much for that theory, skunk:

The Darwin team is pleased to announce the immediate availability of
the Darwin 6.6 and Darwin 6.5 source code corresponding to Mac OS X
10.2.6 and Mac OS X 10.2.5.
http://developer.apple.com/darwin/

[skunk]

Originally posted by Kamu-San
Alas, so much for that theory, skunk
Don't shoot the messenger...I was only quoting MacBidouille

[barkmonster]

regarding the memory issue

i thought that i read somewhere that OSX can only allocate 1gb of memory to any application

so if you have 1.5gb and run photoshop . the max osx can give photoshop is 1gig..


is this accurate?

I'm sure that's OS 9, you were limited to 999,999K as the maximum allocation.

OS X has dynamic memory allocation, no limitations at all apart from available disk space for paging and the amount of physical ram that can be addressed by the cpu or installed in the mac itself. The G4 cpu itself can handle 4Gb of physical RAM and 64Gb (possibly wrong here) of virtual memory.

[mathiasr]

Originally posted by barkmonster
[B]OS X has dynamic memory allocation, no limitations at all apart from available disk space for paging and the amount of physical ram that can be addressed by the cpu or installed in the mac itself. The G4 cpu itself can handle 4Gb of physical RAM and 64Gb (possibly wrong here) of virtual memory.
The G4 has 36 lines to select an address on its external bus, cache logic could also work in 36 bits mode. The point is Mac OS X will probably never use the memory managment hacks to take avantage of those 4 extra bits, since by the time people will ask for more than 4 GiB all the Macs will probably ship with 64 bits CPUs.
The PowerPC 970 can physically address 2^42 bytes of memory that is 4398046511104 bytes, 4096 GiB.

[AidenShaw]

Originally posted by barkmonster
The G4 cpu itself can handle 4Gb of physical RAM and 64Gb (possibly wrong here) of virtual memory.

You've got that backwards.

The G4 can handle 64GiB of physical RAM (those 36-bits of address lines). No Apple mobo has supported more than 2GiB, however.

An individual process gets 4GiB of virtual memory (the 32-bit virtual address). This memory is often divided into system and process spaces, often 2GiB for process and the other 2GiB for system. (Windows has an option to move the split to 3GiB process and 1GiB system, with Linux you can modify the kernel if you want to move the split.)

[AidenShaw]

Originally posted by mathiasr
The PowerPC 970 can physically address 2^42 bytes of memory that is 4398046511104 bytes, 4096 GiB.

This is exactly the way to describe it - the 42-bit physical limit is a design choice for the PPC970, not a PPC architectural limit. Individual chip designs can stop at practical limits.

The designers probably thought that 4TiB of RAM was enough headroom for the life of any PPC-970 derived chip. There's no point in wasting transistors doing a full 64-bit physical addressing implementation, when something far narrower will never be a bottleneck.

[pimentoLoaf]

Four terabytes... :eek:

imagining a small box of to the side...

[Snowy_River]

Originally posted by AidenShaw
This is exactly the way to describe it - the 42-bit physical limit is a design choice for the PPC970, not a PPC architectural limit. Individual chip designs can stop at practical limits.

The designers probably thought that 4TiB of RAM was enough headroom for the life of any PPC-970 derived chip. There's no point in wasting transistors doing a full 64-bit physical addressing implementation, when something far narrower will never be a bottleneck.

Just to be nit-picky, that should be '4TeB', or '4TB', as it's four tera-bytes.

But, really, I doubt it will be long before 4TB seems like a completely reasonable amount of memory for our computers to have. After all, I can remember all too well when 1MB of RAM seemed like a substantial amount...

[Rincewind42]

Originally posted by AidenShaw An individual process gets 4GiB of virtual memory (the 32-bit virtual address). This memory is often divided into system and process spaces, often 2GiB for process and the other 2GiB for system. (Windows has an option to move the split to 3GiB process and 1GiB system, with Linux you can modify the kernel if you want to move the split.)

MacOS X makes no such seperation, but rather each process gets the entier 4GB address space, and then system libraries loaded into that space and mearly take the amount that they require. In theory, the OS uses 512MB of address space for frameworks, 256MB for the stack, and little bits here and there for minor services (like page 0 for NULL page fault checks). But if system frameworks only need 128MB then that space can be allocated to the process itself.

[BaghdadBob]

Originally posted by Snowy_River
Just to be nit-picky, that should be '4TeB', or '4TB', as it's four tera-bytes.

But, really, I doubt it will be long before 4TB seems like a completely reasonable amount of memory for our computers to have. After all, I can remember all too well when 1MB of RAM seemed like a substantial amount...

Depends on what your definition of "long" is. Right now you are considered to have a buttload of RAM if you have 2 GB, and a buttload of HD space if you have 500 GB (250x2GB). It's going to have to become common for a TB of HD space to be in your computer long before even 1 TB of RAM is considered normal.

How much space will your Photoshop folder take up then, eh? 5 GB? :eek:

I was just reminiscing how much the CD-ROM changed computing by changing the realistic sizes you could make applications before someone would go through a 20 disk installation process....ughhh....remember floppies, anyone?

Of course, we have all these revolutions to thank for application bloat (along with Windowsfication).

Anyone here know off the top of their head what a DVD-ROM holds?

[Kamu-San]

4.75 Gb (where 1 Gb = 1 billion bytes)

http://www.extremetech.com/article2/0,3973,822425,00.asp

[ollywilson2003]

Im pretty sure a DVD-ROM holds 4.7GB

Feel free to correct me Im not very sure.

[barkmonster]

The G4 has 36 lines to select an address on its external bus, cache logic could also work in 36 bits mode. The point is Mac OS X will probably never use the memory managment hacks to take avantage of those 4 extra bits, since by the time people will ask for more than 4 GiB all the Macs will probably ship with 64 bits CPUs.
The PowerPC 970 can physically address 2^42 bytes of memory that is 4398046511104 bytes, 4096 GiB.

and

quote:
------------------------------------------------------------------------
Originally posted by barkmonster
The G4 cpu itself can handle 4Gb of physical RAM and 64Gb (possibly wrong here) of virtual memory.
------------------------------------------------------------------------

You've got that backwards.

The G4 can handle 64GiB of physical RAM (those 36-bits of address lines). No Apple mobo has supported more than 2GiB, however.

I'm well aware of this but I've also read that it's awkward to implement a 36bit address space with a 32bit cpu. (read it on here not on a technical site like arstechnica or anything like that).

Also, I know that not all G4s support the 36bit address space, only the G4+ cpus can. Even then, only the real (phsyical ?) address space is 36bit, the virtual address space is still only 32bit. The G4 as a whole (as in ANY G4 past or present) isn't capable of using more than a 32bit address space. I guess this doesn't matter so much for models with the 745x series cpus but it would be wrong to claim the G4 has a 36bit address space across the board.

There was a link on here recently to an IBM pdf of the presentation last year on the PPC970 with this info in a table for comparison with G3, Power4 and PPC970 cpus. I can't be bothered searching the motorola site for more info because of those awful javascript menus they use :D

[AidenShaw]

Originally posted by barkmonster
I'm well aware of this but I've also read that it's awkward to implement a 36bit address space with a 32bit cpu. (read it on here not on a technical site like arstechnica or anything like that).

It's not difficult for an operating system to control >4GiB, and let multiple <4GiB processes use memory at the same time. Of course, each process is 32-bits, but together a number of large processes can use 16, 32 or up to 64GiB of memory.

It is possible, but as you say quite awkward, for a 32-bit program to remap memory into different windows. This can let it address more than 4GiB over time, even though at any instant it is limited to 4GiB. This isn't really important any more - most of the programs that needed to do this have migrated to true 64-bit computers.

Also, I know that not all G4s support the 36bit address space, only the G4+ cpus can. Even then, only the real (phsyical ?) address space is 36bit, the virtual address space is still only 32bit. The G4 as a whole (as in ANY G4 past or present) isn't capable of using more than a 32bit address space.

You're right - on the Moto pages http://e-www.motorola.com/webapp/sps/site/taxonomy.jsp?nodeId=03C1TR04670871 the MPC7410 is 32-bit, the MPC7441 and higher are 36-bit.

Moto does claim that even the G3 can support 4 PiB of virtual memory (52-bit virtual addressing), but that's using a segment addressing scheme.

[AidenShaw]

Originally posted by Snowy_River
Just to be nit-picky, that should be '4TeB', or '4TB', as it's four tera-bytes.

No, 4 TB is 4,000,000,000,000 bytes, or 10^12.

4 TiB is 2^42, or 4,398,046,511,104 bytes.


To wit:

http://physics.nist.gov/cuu/Units/binary.html

http://www.theregister.co.uk/content/54/22734.html

[mathiasr]

Originally posted by AidenShaw
4 TiB is 2^42, or 4,398,046,511,104 bytes.
4 tebibytes TiB
4,096 gibibytes GiB
4,194,304 mebibytes MiB
4,294,967,296 kibibytes KiB

4.4 TB
4,398 GB
4,398,046 MB
4,398,046,511 kB
43,980,465,111 hB
439,804,651,110 daB
4,398,046,511,104 B
43,980,465,111,040 dB Huuuuh, this is loud! :D

[Genie]

Should I buy one right away or wait for the 2nd revision?
How much faster do you think it'll be than my dual 1G?
I just put an acard raid in and that sped Photoshop up some but I need more speed!;)

[ColoJohnBoy]

As nice as it would be, and I am holding out hope, I sincerely doubt that the PPC 970's will be used until sometime this fall, and about a year later they'll be relegated to basic consumer level with the onslaught of the Power5 chip. But, hey, here's to hoping. I'd love the following:

15.4" Aluminum PowerBook, 1" Thick
Slot-Load DVD-R/CD-RW Drive, with 2x DVD capability
1.4 GHz PPC 970 Processor
2 GB PC3700 DDR-RAM
100 GB Hard Drive
ATI Mobility Radeon 128 MB Video Card (If there is one)
Built-in Bluetooth
AirPort Extreme
Light-up Keyboard
FireWire 400 & 800
5.3 Lbs.

Visit Blue Pudding!
http://bluepudding.1hwy.com

[Snowy_River]

Originally posted by AidenShaw
No, 4 TB is 4,000,000,000,000 bytes, or 10^12.

4 TiB is 2^42, or 4,398,046,511,104 bytes.


To wit:

http://physics.nist.gov/cuu/Units/binary.html

http://www.theregister.co.uk/content/54/22734.html

Gads, this is awkward. Tebi-bytes? Uck. I understand where how they derived it, but still... Kibi-bytes is even worse.

In my defense, while this seems to be a five year old "standard", I can honestly say that I have never heard of it before now, despite being fairly in touch with tech matters. Everyone I've ever talked to have used the SI units with the full knowledge that in binary references it is used in powers of 2^10, not 10^3. (Though I was aware that disk manufacturers used decimal when reporting disk size...)


36...