PPC 970 for Apple... Confirmed?

[MacRumors]

In what perhaps is the first "official" confirmation that IBM's PowerPC 970's will be used by Apple, BusinessWeek (http://www.businessweek.com/technology/content/may2003/tc20030521_2871_tc056.htm) claims that IBM has confirmed that they are developing new set of chips for the Mac:


While Motorola has struggled in chips, IBM has soared. Under CEO Sam Palmisano, Big Blue has poured money into chip research and upgraded its factories. IBM says the new Apple chip will be of the 64-bit variety, which means it can process twice as much information per cycle as existing 32-bit chips.



No specific executives are quoted, however.

Update: The article has been edited with the following correction/retraction:


"IBM did not confirm it was building a chip specifically for Apple, but it does say its new PowerPC chip will work on Apple platforms"

[ZildjianKX]

970 macs around the corner... a bad time to go out and buy a new mac... :)

[Centris 650]

Originally posted by ZildjianKX
970 macs around the corner... a bad time to go out and buy a new mac... :)

Not really. This just confirms, to a point, that the 970 WILL be used by Apple. It doesn't say when.

[mangoman]

Could indeed be a swell summer for Apple!

[Approx]

And I have sould my dual 1ghz MDD.. did get my money back..
a 970 would look nice side by side with an new power mac ;)

[jethroted]

Originally posted by ZildjianKX
970 macs around the corner... a bad time to go out and buy a new mac... :)

Well I am going to go ahead and agree with you. It can't be that far away.

[Kid Red]

Originally posted by Centris 650
Not really. This just confirms, to a point, that the 970 WILL be used by Apple. It doesn't say when.

Some corners are 2 city blocks and some are 8 city blocks, but the ice cream store would still be right around the corner.

As per the article, isn't known now that a 64 bit OS is not twice as fast as a 32 bit OS in general as the article mentions? That leads me to believe the writer had very little real info and the rest he made up.

[freundt]

While Motorola has struggled in chips, IBM has soared. Under CEO Sam Palmisano, Big Blue has poured money into chip research and upgraded its factories. IBM says the new Apple chip will be of the 64-bit variety, which means it can process twice as much information per cycle as existing 32-bit chips.

Uhh.. whoever said this doesn;t know what they are talking about.. As we all know, as it has been beaten into our heads multiple times, in multiple stories, throughout multiple threads, 64 bit != 2x 32 bit speed.

_f

[tazznb]

Originally posted by Kid Red
Some corners are 2 city blocks and some are 8 city blocks, but the ice cream store would still be right around the corner.

As per the article, isn't known now that a 64 bit OS is not twice as fast as a 32 bit OS in general as the article mentions? That leads me to believe the writer had very little real info and the rest he made up.

Well I hope they have chocolate ice cream.... I like chocolate.:)

[mangoman]

Originally posted by tazznb
Well I hope they have chocolate ice cream.... I like chocolate.:)

(I love a good smart ass remark)

[pgwalsh]

Certainly doesn't give any insight to when the 970 will enter the market.

I wonder how much Quark will actually boost sales. I've read so many people switching to InDesign...

[ZildjianKX]

Hey pgwalsh, I just read the petition in your sig... ya know apple would never do that... they'd go out of business... they're a hardware company #1, and a software manufacturer #2... and without the hardware sales they'd die.

[DGFan]

Apple chip will be of the 64-bit variety, which means it can process twice as much information per cycle as existing 32-bit chips.

Originally posted by freundt
Uhh.. whoever said this doesn;t know what they are talking about.. As we all know, as it has been beaten into our heads multiple times, in multiple stories, throughout multiple threads, 64 bit != 2x 32 bit speed.

_f

Actually a 64 bit processor can process twice as much information per cycle as a 32 bit processor. His statement is not synonymous with "twice as fast as a 32 bit computer".

So maybe read it a little closer next time before you rattle off a reactionary response.

[maradong]

well , so i will wait for the ppc 970 and not go for the new powerbook as soon as it is released, apart it has got the 970, but that is fairly unprobable

[Mr. Anderson]

I wonder if IBM's acknowledgement of the 970 being made for Macs is going to be an issue with Jobs and Apple. You know they love their secrecy :D

But there is always the issue of what the thing will actually look like ;)

D

[mdavis]

Originally posted by ZildjianKX
970 macs around the corner... a bad time to go out and buy a new mac... :)

What? Who are you?? Why should anybody listen to you??? lol

[mathiasr]

Originally posted by freundt
Uhh.. whoever said this doesn;t know what they are talking about.. As we all know, as it has been beaten into our heads multiple times, in multiple stories, throughout multiple threads, 64 bit != 2x 32 bit speed.

_f
The wording "...the new Apple chip will be of the 64-bit variety, which means it can process twice as much information per cycle as existing 32-bit chips." is still true, when a 64-bits CPU adds two 64 bits numbers it handles twice as much bits as would a 32-bits CPU while adding two 32 bits numbers.
The problem is that most of the time in most of the apps you do not work with 64 bits datas but rather 32, 16 or even 8 bits.

What is actually fun is when he writes "gigahertz per second" :D

[mdavis]

Originally posted by maradong
well , so i will wait for the ppc 970 and not go for the new powerbook as soon as it is released, apart it has got the 970, but that is fairly unprobable

Judging by history, I really wouldn't expect a G5 PowerBook for at least a year.

[pgwalsh]

Originally posted by ZildjianKX
Hey pgwalsh, I just read the petition in your sig... ya know apple would never do that... they'd go out of business... they're a hardware company #1, and a software manufacturer #2... and without the hardware sales they'd die. You're off topic. There's already threads on this issue so if you'd like to give some good reasons go find them.

[mdavis]

Originally posted by Mr. Anderson
I wonder if IBM's acknowledgement of the 970 being made for Macs is going to be an issue with Jobs and Apple. You know they love their secrecy :D

But there is always the issue of what the thing will actually look like ;)

D

Undoubtedly this was discussed between the two already long ago. Also, I might be wrong, but I don't believe IBM has officially announced the 970 as being "make for Apple." I think it's jsut so obvious so that's what people are saying... I donno though..

[ddtlm]

DGFan:

Actually a 64 bit processor can process twice as much information per cycle as a 32 bit processor. His statement is not synonymous with "twice as fast as a 32 bit computer".
But wait! AltiVec allows the 32-bit G4 to eat 128 bits at a time, which the PPC970 does not double. Woo hoo! But wait, both chips are superscalar, so the question is actually how many units can crunch how many bits at once...

mathiasr:

Hmmm, I'd take a computer that could do even a few khz per second... leave it on a few months and it might get pretty fast. :)

mdavis:

Judging by history, I really wouldn't expect a G5 PowerBook for at least a year.
Economics also suggests that Apple would do a 7457 version first, because its a drop-in replacement for the 7455, which means more mileage out of their R&D dollar.

[Catfish_Man]

Originally posted by mathiasr
What is actually fun is when he writes "gigahertz per second" :D

lol. cycles/second^2. I wish I had a 1GHz/sec computer. It would "accelerate" by 1GHz every second :).

[Escher]

What's intrigueing about this Business Week article is that it was written by Alex Salkever, a regular tech columnist, not Charles Haddad, the pro-Mac columnist. This could mean that the article is more neutral and objective. But it could also mean that the article is less well researched. Could Haddad have fed Salkever the inside scoop to publish during his leave so as not to raise too many eyebrows?

Regardless, coverage of PPC 970 PowerMac in a mainstream publication like Business Week is a good sign. Now we just need the New York Times or another paper of that stature to jump on board. Where are you, David Pogue? ;)

Escher

[Jerry Spoon]

Originally posted by ZildjianKX
970 macs around the corner... a bad time to go out and buy a new mac... :)
I've been waiting almost a year to replace my dual 450 tower. Still runs great, but I want more and I'm not buying a thing until these 970's come out (and maybe I'll wait just a bit after that - Got burned with my bondi blue iMac having some bugs). Hopefully I won't have to wait too much longer.

[mymemory]

If Apple doesn't release the 970 in the keynote I may expect no less than a riot in that place. If I was in the US for sure I would start one at the closest Apple Store:mad:

BTW, I hope a 970 chip for my Pismo very soon too:rolleyes:

[yzedf]

Originally posted by Centris 650
Not really. This just confirms, to a point, that the 970 WILL be used by Apple. It doesn't say when.
I did not see the sequence of characters that spell out either "970" or "Gobi." Whos to say what they are working on. Could be the next generation airport base station, or iPod, or iWalk or iPhone or or or... :rolleyes:

[Kid Red]

Originally posted by freundt
Uhh.. whoever said this doesn;t know what they are talking about.. As we all know, as it has been beaten into our heads multiple times, in multiple stories, throughout multiple threads, 64 bit != 2x 32 bit speed.

_f

Wow, so according to you, iTunes will encode TWICE as fast right off the bat! Photoshop will render, scale, rotate and apply filters in mear seconds!?! Wow. I'm sorry I was unware that 32 bit apps would be twice as fast on a 64 OS on a 64 bit CPU. And to beat into your head some-more, the majority of apps won't be coded to 64 bits. So I guess it won't be twice as fast after-all. Thanks for the info :rolleyes:

[NitzerX]

I don't think this CONFIRMS anything. I think the author just made the assumption that the existance of the 970 means that it is for Apple.

I believe that same assumption. I don't think this article proves anything though.

[gwuMACaddict]

Originally posted by Escher

Regardless, coverage of PPC 970 PowerMac in a mainstream publication like Business Week is a good sign. Now we just need the New York Times or another paper of that stature to jump on board. Where are you, David Pogue? ;)

Escher


uhh... i think at this point i trust what macrumors has to say WAAAY more than anything the ny times puts in its pages...

:eek:

[kentuckyfried]

As dumb as it might be business-wise, it makes one wonder if Jobs meant something extraordinary by "year of the laptop"

Originally posted by mdavis
Judging by history, I really wouldn't expect a G5 PowerBook for at least a year.

[DGFan]

Originally posted by Kid Red
Wow, so according to you, iTunes will encode TWICE as fast right off the bat! Photoshop will render, scale, rotate and apply filters in mear seconds!?! Wow. I'm sorry I was unware that 32 bit apps would be twice as fast on a 64 OS on a 64 bit CPU. And to beat into your head some-more, the majority of apps won't be coded to 64 bits. So I guess it won't be twice as fast after-all. Thanks for the info :rolleyes:

You do know that ! means "not" right
LOL
:p

[ddtlm]

kentuckyfried:

You're too optimistic. If anything is going to be extraordinary it'll probably be the pain and suffering on the PMac front. I think Steve was/is emphasising laptops because the desktops are in bad shape, not because the laptops are especially good.

[hugemullens]

I sure hope so. I would love a PPC 970. I still believe it isnt how fast your computer is but what you can do with it. But sure would be nice to have the FASTEST computer around and be able to do everything you can with a mac.

[deputy_doofy]

Originally posted by Kid Red
Wow, so according to you, iTunes will encode TWICE as fast right off the bat! Photoshop will render, scale, rotate and apply filters in mear seconds!?! Wow. I'm sorry I was unware that 32 bit apps would be twice as fast on a 64 OS on a 64 bit CPU. And to beat into your head some-more, the majority of apps won't be coded to 64 bits. So I guess it won't be twice as fast after-all. Thanks for the info :rolleyes:

Slow down there, killer. He wrote 64-bit != twiceTheSpeed(32-bit).
The ! means not. Therefore, != means NOT EQUAL (found in Java, javascript, C++,etc.).

[Jerry Spoon]

Originally posted by gwuMACaddict
uhh... i think at this point i trust what macrumors has to say WAAAY more than anything the ny times puts in its pages...

:eek:

Ha:D Yep, you're right:p

[Dont Hurt Me]

Maybe we wont have to hear anymore garbage like apple will use the g4 next year or amd is.... or marklar and intel yap yap yap.

[Jerry Spoon]

Originally posted by ddtlm
kentuckyfried:

You're too optimistic. If anything is going to be extraordinary it'll probably be the pain and suffering on the PMac front. I think Steve was/is emphasising laptops because the desktops are in bad shape, not because the laptops are especially good.
I'm agreeing with ddtlm here. While the laptops that Apple has right now are great and I'd be happy to call one my own, they're not blowing me away (in any way besides the ridiculous size of the 17"PB). The desktops are incredibly lame right now on the other hand. How do you draw people's attention away from this? Call it the year of the laptop! Focus on the good (even if it's not unbelievably amazing) and not the bad.

[Escher]

Originally posted by gwuMACaddict
uhh... i think at this point i trust what macrumors has to say WAAAY more than anything the ny times puts in its pages...

Well, if you don't trust the Times, I wonder when Matthew Rothenberg at eWeek will chime in on the PPC 970. He (and his co-author Nick Ciarelli) have been right on the money on a regular basis in the past. I'm also wondering when Think Secret will do more than simply mention the 970 at the end of an article.

Escher

[Bengt77]

Originally posted by Jerry Spoon
Got burned with my bondi blue iMac having some bugs).

What bugs? Well, apart from the video card being too lame for even 1998. And maybe the tiny HD. But really, what bugs?!...

[Bengt77]

Originally posted by Jerry there is no Spoon
Ha:D Yep, you're right:p

Sorry, couldn't resist!

:D

[jettredmont]

Originally posted by DGFan
Actually a 64 bit processor can process twice as much information per cycle as a 32 bit processor. His statement is not synonymous with "twice as fast as a 32 bit computer".

So maybe read it a little closer next time before you rattle off a reactionary response.

Yeah, there's a fuzzy, technical perspective from which he is right, however the problem is that the vast majority of people see "information" and tack on "distinct".

A 64-bit processor can process twice as much information (interelated bits) as a 32-bit processor, but not twice as much distinct information (a single number is a distinct bit of information; 64-bit or 32-bit processor determines tha max/min values of that number, not how many said numbers can be calculated at once).

So, technically, the article is right sorta. Its connotation (that the machine will be twice as fast thanks to 64 vs 32) is dead wrong.

But then, "the public" generally looks at things like a faster front-side-bus and improved OOOE and pipelining and glaze over. The 970 will be twice as fast as the G4. Maybe we shouldn't burden the "public" with "why" and just let them believe what they want ... :)

Folks, welcome to the public misperception that will only get worse.

[Bengt77]

Originally posted by Kid Red
Wow, so according to you, iTunes will encode TWICE as fast right off the bat! Photoshop will render, scale, rotate and apply filters in mear seconds!?! Wow. I'm sorry I was unware that 32 bit apps would be twice as fast on a 64 OS on a 64 bit CPU. And to beat into your head some-more, the majority of apps won't be coded to 64 bits. So I guess it won't be twice as fast after-all. Thanks for the info :rolleyes:

Don't you think that the "!=" part means a streak through the "="? Thus, "64bit != 2x32bit" means that 64bit computing is not twice as fast as 2x32bit computing.

Not exactly sure wether you got that or not. Oh well...

:rolleyes:

EDIT: Sorry, just saw that DGFan already pointed this out.

[Snowy_River]

Originally posted by mdavis
Judging by history, I really wouldn't expect a G5 PowerBook for at least a year.

I think if you look a little farther into history, you'll find that history is not definitive in this matter. If you, instead, look at whether or not a particular chip is well suited to a mobile application, then it becomes clear that Apple tends to release these side-by-side (roughly) with the Power Macs based on the same chip. So, that means the question becomes simply whether or not the 970 is well suited to a mobile application (which we have some evidence to suggest that it is).

[Snowy_River]

Originally posted by ddtlm
Economics also suggests that Apple would do a 7457 version first, because its a drop-in replacement for the 7455, which means more mileage out of their R&D dollar.

There is one problem with this. Is it economical for Apple to wait until the end of the year in order to get the 7457 (when we are given to understand the 7457 will be shipping), rather than update the line to the 970 now (assuming the 970 is available and is suitable for a mobile computer in its initial release version).

Now, what I see as a very likely path is that the PBs would get the 970 in their update this summer. The iBooks would inherit the G4 (thus preserving the R&D that Apple has into the G4), and would get the 7457 later this year or early next year as the next update.

This seems a quite reasonable 'economic' path for Apple to take.

[Vonnie]

Originally posted by mymemory
If Apple doesn't release the 970 in the keynote I may expect no less than a riot in that place.

Not if Steve is able to completely overwhelm us with Panther goodies :-)

"Panther, so good you don't care about PPC970 anymore"

[jettredmont]

Originally posted by ddtlm
kentuckyfried:

You're too optimistic. If anything is going to be extraordinary it'll probably be the pain and suffering on the PMac front. I think Steve was/is emphasising laptops because the desktops are in bad shape, not because the laptops are especially good.

Correct. The "year of the Laptop" was declared amidst multiple slides showing how Apple laptop sales weregrowing relative to desktop sales. In the original context, "the year of the laptop" meant that laptops will continue to gain ground on (Apple) desktops, and are projected to equal desktop sales sometime next year IIRC.

Of course, making laptop sales grow relative to desktop sales can be done two ways ...

[wms121]

the sexy Apple babe with the big consumer spread is walking out the door..and "wiggilin' it" as she goes by..


Hey MOto..get with IBM's program..

Or we will have big Steve call AMD right now...

[noverflow]

What will be sad, is when they come out, people will have to buy a new machine and will not be able to upgrade their current machine.

who wants a 970 on a buss that is over 4 times slower.

we all know that the g4 in its self is memory starved... imagine a 970

[illumin8]

Originally posted by freundt
Uhh.. whoever said this doesn;t know what they are talking about.. As we all know, as it has been beaten into our heads multiple times, in multiple stories, throughout multiple threads, 64 bit != 2x 32 bit speed.

_f The article is not technically incorrect. Processors manipulate data by using these things called registers. A numerical value is moved into a register, then some operation is performed on it, and it is moved back out of the register. 64-bit processor means you can now have 64-bit registers, so technically your processor is now operating on chunks of data that are twice as large as before.

As has been stated before many times, it seems that a lot of modern applications are bottlenecked by the front side bus of the processor, rather than the speed of the processor itself. If you can only move data in and out of the processor at the same old speed, it doesn't help much that your processor is now 7 or 8 times faster than your FSB. The 970 of course will not have this problem so much.

So, in summary, 64-bit != 2x 32-bit performance, but the article is still technically correct in that a 64-bit processor can process data in registers that are twice as large, therefore, process twice as much data at once.

[robotrenegade]

About god damn time!:D

[Freg3000]

Originally posted by Vonnie
Not if Steve is able to completely overwhelm us with Panther goodies :-)

"Panther, so good you don't care about PPC970 anymore"

I can just imagine everything sitting watching the keynote looking at their watches thinking..."Ok, he's spent an hour on a Panther demo......when is he getting to the 970?"

[ddtlm]

Snowy_River:

There is one problem with this. Is it economical for Apple to wait until the end of the year in order to get the 7457 (when we are given to understand the 7457 will be shipping), rather than update the line to the 970 now (assuming the 970 is available and is suitable for a mobile computer in its initial release version).
Despite all the rumors I don't see any reason to think that the 970 will be shipping in anything till September at earliest, and I thought they said the 7457 will be shipping in the 3rd quarter and was already sampling. In addition to be being cheap and easy for Apple, the 7457 should be a compelling laptop chip, and additionally, its not clear that Apple has enough engineers to design radically new motherboards in as rapid sucessession as would be needed for a fast transition to a PPC970 laptop.

illumin8:

64-bit processor means you can now have 64-bit registers, so technically your processor is now operating on chunks of data that are twice as large as before.
Yes, if you ignore the AltiVec registers, and also ignore the floating point unit which could do 64-bit numbers all along.

[Vlade]

If they officially said its for apple, wouldn't that mean that it is coming out soon? It wouldn't be a good idea to announce it now if the PPC 970 is coming out in december, because that would kill powermac sales now.

[ddtlm]

Vlade:

It is possible, even likely, that the reporter pulled the "for Apple" part out of his rear end.

[magitekkn]

Originally posted by mymemory
BTW, I hope a 970 chip for my Pismo very soon too:rolleyes:

As someone else pointed out, putting a 970 on a slower, 32-bit bus would cripple it horribly... For proof of the travesty of putting chips on memory busses that are too narrow look to the 'road apple' section of www.lowendmac.com where you'll see how horrible it can be when a 32-bit processor is put on a 16-bit bus, same thing for a 64-bit 970 on a 32-bit bus.

[mymemory]

This picture was taken this morning down town, I'm the guy with the had. This is the MUG I manage congregate expenting for a new chip.

The National Guard are taking their positions in case no chip is revealed.

[maxvamp]

Despite all the rumors I don't see any reason to think that the 970 will be shipping in anything till September at earliest,

I can... back to school sales... If apple is to have maximum success in selling this chip this year, they need to have at least one machine out with the 970 by mid-august.
While I do not believe that a sing, or even dual 970s will show up in a laptop for quite a long time, this would ideally be the machine to introduce, and then roll out PMs ASAP.

Max

[beulahman]

Originally posted by yzedf
I did not see the sequence of characters that spell out either "970" or "Gobi." Whos to say what they are working on. Could be the next generation airport base station, or iPod, or iWalk or iPhone or or or... :rolleyes:

No, but it did say "64 bit" which Gobi isn't. The 970, however, is. ;)

[Abstract]

I didn't read the entire thread, but is there any doubt that IBM is producing the 970 for Apple at this point? Seriously, disbelieving at this point is just being silly. ;)

[ddtlm]

magitekkn:

The G4's are running on a 64-bit FSB. The bitness of the bus has nothing to do with the bitness of the processor.

maxvamp:

If apple is to have maximum success in selling this chip this year, they need to have at least one machine out with the 970 by mid-august
No, for maximum success they'd have had the 970 out yesterday, or in Janruary, but they didn't have it available because they couldn't do it, and the same may very well be true for some time to come.

[sedarby]

Originally posted by freundt
Uhh.. whoever said this doesn;t know what they are talking about.. As we all know, as it has been beaten into our heads multiple times, in multiple stories, throughout multiple threads, 64 bit != 2x 32 bit speed.

_f

Actually the article is correct. Twice as much information is correct, twice as fast would be wrong.

[pyrotoaster]

Arn, how could you have missed this piece of the article?
From BusinessWeek
That's not even counting an anticipated initial speed boost in the new chip's clock cycle to well over 1.8 Ghz -- and likely well beyond that over the course of the year.
Clock speed confirmations! That's something to get excited about!

With processors beyond 1.8 GHz by the year's end, I see one very happy anniversary coming in January... (I leave us all to speculate here) :D

[The Ancients]

Originally posted by mathiasr
What is actually fun is when he writes "gigahertz per second" :D

Hmmm, let's extrapolate (which is what this game's all about it, isn't it?)

m/s = speed
m/s/s = acceleration

Ghz = speed
Ghz/s = acceleration

Therefore, the new machines will keep getting faster and faster as they're used. Love to see how IBM/Apple solved the heat problems on these babies...

..k

[The Ancients]

Originally posted by Dont Hurt Me
Maybe we wont have to hear anymore garbage like apple will use the g4 next year or amd is.... or marklar and intel yap yap yap.

We can but hope - spoiled with a big fat FSB, hypertransport and an ATI GPU. See, now that's not too much to ask for is it?

Edit: Forgot about Serial ATA.

[Remus]

Originally posted by freundt
Uhh.. whoever said this doesn;t know what they are talking about.. As we all know, as it has been beaten into our heads multiple times, in multiple stories, throughout multiple threads, 64 bit != 2x 32 bit speed.

_f

Like I said in another tread. IT may be that this is just a business writer that does not understand computers. He may have assumed (yes I know never A$$-U-ME anything :D )

[Fender2112]

I read an artical the other day that descibed how the 970 differs from the G4. My terminoloy may be off, so don't blast me. But I think I got the concept right.

The G4 can process 5 instructions per cycle. That's 4 in the pipeline and 1 result. The 970 handles between 8 and 12 depending on what's in the pipeline with one of them being a result. I took this to imply that the 970 can handle about twice as many instructions per cycle. With the 970 starting at 1.8 GHz and the G4 at 1.42 GHz, we get somthing like this:

970: 8x1.8= 14.4 Gig instructions per second
G4: 5x1.42= 7.1 Gig instructions per second.

This implies to me that the 970 will be about twice as fast as a G4 and this speed has very little to do with 64 or 32 bit numbers.

Please toss me a life jacket if I missed the boat on this.

[arn]

looks like the author misspoke.

correction posted/ article updated

arn

[The Ancients]

Uh huh. Looks more like Steve Jobs got wind of it to me!

Originally posted by arn
looks like the author misspoke.

correction posted/ article updated

arn

[josepht]

Now that the statement made has been edited/retracted, I now consider it a confirmation that Apple will use the chip. I was waiting for Apple to get wind of that and make someone change what they said.

[AidenShaw]

Originally posted by josepht
Now that the statement made has been edited/retracted, I now consider it a confirmation that Apple will use the chip. I was waiting for Apple to get wind of that and make someone change what they said.

I'm not sure that I'll buy that - it implies that The Lord God Jobs is OK with the line "it does say its new PowerPC chip will work on Apple platforms" which I find to be extremely unlikely.

[Masker]

Originally posted by The Ancients
Hmmm, let's extrapolate (which is what this game's all about it, isn't it?)

m/s = speed
m/s/s = acceleration

Ghz = speed
Ghz/s = acceleration

Therefore, the new machines will keep getting faster and faster as they're used. Love to see how IBM/Apple solved the heat problems on these babies...

..k

I know all the people that keep talking about this are just being goofy, but this bugs me: your car can accelerate, but does that mean that it keeps getting faster the longer that it runs? :D Simply because it's a higher derivative doesn't mean that it would have a CONSTANT acceleration.... :) [Edit: removed goofiness]

Just because the guy mispoke, doesn't mean that you guys aren't also mistaken. And, if you're going to get all physics on us, use the correct term: velocity not speed. [Edit: Hmmmm. For cps or Hz, velocity isn't exactly right, either...]

[alset]

That update to the article is hilarious. News of the 970 is getting pretty old.

Dan

[P-Worm]

It looks as though Steve is OK with them saying that the 970 can work in Apple computers, just not exculisively (which the first statement sort of implied). Do you think that IBM will be using the 970 for things other than Macintoshs? Maybe there own desktops? Seems a little unlikely, but we don't want to be swept with the current...

P-Worm

[ddtlm]

josepht:

I still think that it is far more likely that the author didn't know what he was talking about. What are the odds that some random journalist who is plainly not knowledgeable about processors got a leak of this importance? What are the odds that if he did get a real leak, that he would just mention it in passing, rather than identifying how important it is?

Also note that if he did really get a leak, Apple could do nothing to make him change his story. This is not the same thing as a product picture.

[Snowy_River]

Originally posted by ddtlm
No, for maximum success they'd have had the 970 out yesterday, or in Janruary, but they didn't have it available because they couldn't do it, and the same may very well be true for some time to come.

True, true. But we have some significant rumors from various sources that suggest that this is no longer the case. And, if the rumors are right, we may well see the 970s very soon...

[mkaake]

Originally posted by ZildjianKX
Well, no shi!t there are other threads on it Sherlock, but I can't just go, "Hey, pgwalsh's sig says..." and you've never even posted there, think about it... and you commenting on it ended up wasting more time than my original post. And if you don't like me posting about it, change your dumbass sig... unless you want Apple to go out of business if they for some stupid reason listened to you.

And for those of you who said "Why listen to me..."... well, the G4 processors that are out now pretty much blow... go ahead and spend your money on a new G4 when it will the 970 will play catchup to the P4s out now and leave the G4s slowly behind.

whew! i think someone forgot their riddilin today!

reminds me of some people I went to high-school with - they liked comlaining and arguing and swearing a lot about a whole lot of nothing....

as far as the article, eh~

i'm pretty bored with 970 stuffs. when i see it, then i'll get really excited. no need in getting worked up any time someone speculates about something anymore.

matt

[hayesk]

I'm glad the general public thinks 64-bit computing is twice as fast as 32.

If Apple produces an ad saying "The new powermac with 64-bit processors can process twice as much data as a 32-bit processor, like those found in Windows PCs", then let the public buy into it.

If Intel can say the P4 makes your colours more vibrant and your internet surfing more rewarding, then why not fight fire with fire?

[Sonofhaig]

I think we're about to see a "new age" for Apple. They've already started it with OS X. Now I believe they'll start making breakthroughs on chip speeds with IBM.
I for one think the future is bright for Apple. And soon. :cool:

[Vonnie]

Originally posted by P-Worm
It looks as though Steve is OK with them saying that the 970 can work in Apple computers, just not exculisively (which the first statement sort of implied). Do you think that IBM will be using the 970 for things other than Macintoshs? Maybe there own desktops? Seems a little unlikely, but we don't want to be swept with the current...

P-Worm

I think they will be used for IBM workstations/entry level servers, preinstalled with Linux.

Which means that IBM will make these chips faster and cheaper to be able to compete with Sun/HP/.. (Where Motorola doesn't really have an incentive to make the G4 faster, except maybe Steve Jobs yelling "i wanna go faster damnit!")

The running Linux part means that IBM, SuSe and the opensource community will invest time and money into optimizing GCC for PPC970. (which Apple will be able to use)

[Snowy_River]

Originally posted by Sonofhaig
I think we're about to see a "new age" for Apple. They've already started it with OS X. Now I believe they'll start making breakthroughs on chip speeds with IBM.
I for one think the future is bright for Apple. And soon. :cool:

Oh man, I hope so. I'd love to see the return of the Golden Age when the G3 came out. Remember the snail with the pentium on its back? :D

[ibjoshua]

"IBM did not confirm it was building a chip specifically for Apple, but it does say its new PowerPC chip will work on Apple platforms..... .. .. .. ouch ouch owww!!. STEVE stop twisting my arm!""



ha ha ha

i_b_joshua

[Cubeboy]

Most compilers support 64-bit (and larger) data types, even on 32-bit CPUs, so the main benefit here is increased performance on large data types that don't fit into a 32 bit computing model.

Another thing to note is that a program that fits into a 32 bit model and doesn't take advantage of a specific 64 bit capability (scalability, memory, high precision arithmetic) will probably perform better compiled as a 32-bit binary than a 64 bit one due to more cache misses associated with the size of the 64 bit binary.

[macdong]

Originally posted by sedarby
Actually the article is correct. Twice as much information is correct, twice as fast would be wrong.

Hmm, you are right.
"Twice as much information" sounds like "twice as fast", but it's not.
Just the words game business writer like to play :)

[Snowy_River]

Originally posted by i_b_joshua
"IBM did not confirm it was building a chip specifically for Apple, but it does say its new PowerPC chip will work on Apple platforms..... .. .. .. ouch ouch owww!!. STEVE stop twisting my arm!""



ha ha ha

i_b_joshua


Hehehe...

I like it...
:)

[rundevilrun]

Originally posted by Vonnie
Which means that IBM will make these chips faster and cheaper to be able to compete with Sun/HP/.. (Where Motorola doesn't really have an incentive to make the G4 faster, except maybe Steve Jobs yelling "i wanna go faster damnit!")
[/B]

lol that made me think of an epsiode of the Simpsons where Mr. Burns is riding on the back of a bike with Smithers pedaling. Faster Smithers!

[Snowy_River]

Originally posted by Vonnie
I think they will be used for IBM workstations/entry level servers, preinstalled with Linux.

Which means that IBM will make these chips faster and cheaper to be able to compete with Sun/HP/...

This is a point that I've tried to make before, but the ever-present nay-sayers have always come up with reasons why IBM won't be using the fastest of the 970s, and those will only show up in Power Macs.

The running Linux part means that IBM, SuSe and the opensource community will invest time and money into optimizing GCC for PPC970. (which Apple will be able to use)

I wouldn't be surprised to see Apple even contributing to such an effort. It would certainly be in their best interest.

[ddtlm]

Sonofhaig:

Now I believe they'll start making breakthroughs on chip speeds with IBM.
Apple won't make breakthroughs any more than Dell does.

I for one think the future is bright for Apple. And soon.
Why is that? Because Apple has a modern OS and "soon" will have a modern processor? All Apple has done here is become compeditive again; the fact that anyone is even excited only demonstrates how large the gap currently is. And I should add that we don't even know that Apple will actually be compeditive on the hardware front yet... it all depends on what sort of hardware backs up the 970. Which, technically, is itself still a rumor.

[Snowy_River]

Originally posted by ddtlm
Why is that? Because Apple has a modern OS and "soon" will have a modern processor? All Apple has done here is become compeditive again; the fact that anyone is even excited only demonstrates how large the gap currently is. And I should add that we don't even know that Apple will actually be compeditive on the hardware front yet... it all depends on what sort of hardware backs up the 970. Which, technically, is itself still a rumor.

I think that you're missing something here. The truth is that the G4 is a modern processor. It happens to have some problems (too-slow FSB, etc.), but it is a robust, powerful, modern processor. And what we're excited about is not the prospect that Apple will be competitive again, but that we may be coming into a new 'Golden Age', akin to when the G3 came out; that 970 based Power Macs will not simply be competitive with P4s, but will significantly exceed their performance; and that, now being with IBM, this will be a Golden Age that will last longer than the reign of the G3 did. Now, it's true that we don't know how the 970 will ultimately compare, and until they are released we won't. All we have is the speculative numbers from rumors and from IBM.

As for the 970 being a rumor, I'd have to flat out disagree with you on that point. It is an announced product from IBM. What the performance of the 970 will be remains in the rumor realm. When we'll see 970 based Power Macs or Blade Servers also remains in the rumor realm. But the 970 itself does not.

[OutThere]

My internet is way too slow to view all the posts in this thread (fussy 1.5mbps T1 going to ~700 ppl, i'm getting 500 b/s download :rolleyes: ) I think that this is great confirmation of something that was pretty much sure in the first place. Can't wait! Will I be getting a computer w/ a 970? No. (Je n'ai pas le $$$$), but I just can't wait to see the PC people go:eek:

[MarkCollette]

Originally posted by Masker
Just because the guy mispoke, doesn't mean that you guys aren't also mistaken. And, if you're going to get all physics on us, use the correct term: velocity not speed. [Edit: Hmmmm. For cps or Hz, velocity isn't exactly right, either...]

Of course we don't have to be redundant and mention velocity, we're talking about a chip that has its own Velocity Engine :)

[Snowy_River]

Originally posted by MarkCollette
Of course we don't have to be redundant and mention velocity, we're talking about a chip that has its own Velocity Engine :)

So that means that it can be driven to much higher speeds, right?

(FYI, just to get all physics-y on you, velocity is a vector quantity and speed is a scalar quantity. As these processors are super-scalar, we may need a whole new term. Either that or we can just decide to overload the existing terms, which is what usually happens anyway. In that case, I think that 'speed' is definitely the better term.)

99...

[ZildjianKX]

Originally posted by mkaake
whew! i think someone forgot their riddilin today!

reminds me of some people I went to high-school with - they liked comlaining and arguing and swearing a lot about a whole lot of nothing....

I don't care about the 970 that much... just got peeved. I still wouldn't buy a G4 now though.

[AidenShaw]

Originally posted by Snowy_River
velocity is a vector quantity and speed is a scalar quantity

But the 970 AltiVec implementation is a super-pipelined super-scalar vector processor.

Ohmygawd, we don't just need a new term, it's a whole new dimension! ;)

[mathiasr]

Originally posted by Fender2112
The G4 can process 5 instructions per cycle. That's 4 in the pipeline and 1 result. The 970 handles between 8 and 12 depending on what's in the pipeline with one of them being a result. I took this to imply that the 970 can handle about twice as many instructions per cycle. With the 970 starting at 1.8 GHz and the G4 at 1.42 GHz, we get somthing like this:

970: 8x1.8= 14.4 Gig instructions per second
G4: 5x1.42= 7.1 Gig instructions per second.

This implies to me that the 970 will be about twice as fast as a G4 and this speed has very little to do with 64 or 32 bit numbers.

Please toss me a life jacket if I missed the boat on this.
There's some mixup in what you wrote.

The G4e (7450+ series) can dispatch up to 3 instructions + a branch and retire 3, the 970 can dispatch up to 4 instructions + a branch.

If you look closer the instructions are not the same, the G4e takes raw PowerPC instructions, whereas the 970 breaks some of the PowerPC instruction in what IBM calls IOPs (for instance the lwzu instruction -Load Word and Zero with Update- will require two IOPs).

But you can still consider that the 970 will dispatch more instructions, another reason is that the 970 has more executions units that will fill up more slowly -2 Floating Point Units vs 1-, -2 Load/Store Units vs 1-. Excepted for integer computations: -2 Complex Units vs 1 Complex Unit + 3 Regular Units- and to some extend Altivec, where 3 of the 4 Units are behind the same Issue Queue, like in the older 7400/10.

The pipeline length has increased (16/25 stages -min/max- vs 7/12), this introduces some benefits: the 970 has more opportunities to take advantage of out of order execution and the frequency of the core could soar (2.5 GHz by Q1-2004 3 GHz by Q3-2004?), on the other side special care must be taken to avoid pipeline bubbles and misspredicted branches (branch prediction logic is way more complex in the 970), data dependencies could also bring pipelines to stall more often.
The instruction throughput should be on the rise, a two fold increase is probably optimistic: instructions process datas and those must be available wherever they result from a previous computation or come from the memory subsystem, they do not just fly straight through the pipelines.

The caches have evolved, the L1 instruction cache is now twice as big 64 KiB (32 previously) but is direct mapped, this could be a drawback if your app uses a lot of small pieces of code and jumps from one place to another.
The L1 data caches have the same size: 32 KiB, but not the same layout: 2 way set associative vs 8 way on the G3/G4 (8 way is supposed to be more efficient), the size of the cache lines has probably changed, they could be 128 bytes wide, this is huge compared to 32 bytes in the other PowerPCs.
The L2 cache is twice as big 512 KiB (the 7457 also has this capacity).
The 970 is supposed to handle more data streams, outstanding reads and cache misses, this will even more increase it's perceived bandwidth.

The PowerPC 970 has a proven core since it is in use in the POWER4+.
The 2 Load/Store Units coupled with the frond busses will benefit many apps, the 2 FPUs and the 64 bits registers pave the way to new workstation class scientific software.
AltiVec will probably be on par with the 7400, excepted that memory bounded apps will fly on the 970.
The integer part of the core could be slightly slower (at the same clock speed) but here a gain with these two LSUs, the superior branch prediction, the OOOE capabilities... it's hard to tell.

The 970 will be faster, especially on double precision floating point math (research, labs...), memory related tasks (most of the multimedia stuff), and of course 64 bits computations (when you have to deal with those).

[mkaake]

Originally posted by ZildjianKX
I don't care about the 970 that much... just got peeved. I still wouldn't buy a G4 now though.

sorry bout the personal jab...

i'd love to see this all come out good for apple, and i'm prolly gonna get flamed for what i'm about to say, - - but - - -

i don't think the g4 is all that bad - i think we're all getting caught up in the mHz myth that we love to bash others about. i mean, i'm writing this on a 266 g3, and it runs just about everything i want it too (except x, of course...) (and yeah, i know there are ways to make it, but it's not worth it on this machine). pump it with ram, and the only times when you see the age of the proc is when you rip and encode in itunes. and the occasional bout when you're running 4 or 5 programs at a time.

i think the g4 bashing has become kind of a sport and we've forgotten that it's still pretty powerfull...

oh well . think what you will.

<braces for impact>

matt

[ZildjianKX]

Oh, I agree with you... it just would be a shame to spend so much money on a new tower or powerbook then have something so much faster coming out for the same price.

[beatle888]

the g4 is nice. im on a 667 ti with 512 of ram. im not complaining. im quite happy. but i havent been doing anything extremely taxing on this system. if i were to do print production i might be singing a different tune but for web work its fine. this will become my leisure computer once the 970 comes out (and i pay off some bills). i love this computer.

[bokdol]

do you guys think this well get rid of those stupid mac on intel proc rumors? and all those apple critics that say if they dont go to intel proc they well go out of business?

[Snowy_River]

Originally posted by AidenShaw
But the 970 AltiVec implementation is a super-pipelined super-scalar vector processor.

Ohmygawd, we don't just need a new term, it's a whole new dimension! ;)

Okay, I'm getting confused. We live in a 3+1 dimensional universe (as far as we can tell, no string theorists please - oh wait, they don't like Macs... :p). In such a universe there are scalars, pseudo-scalars, vectors, pseudo-vectors, tensors. . . and so on. So where do super-scalars fit into all of this?? Maybe the 970 is a computer that doesn't really exist in our universe. Maybe there is just an interface here but the actual processor exists in hyper space........


98...

[Snowy_River]

Originally posted by bokdol
do you guys think this well get rid of those stupid mac on intel proc rumors? and all those apple critics that say if they dont go to intel proc they well go out of business?

If the 970 boosts us up to similar or (dare I even say it...) higher power levels as the P4, then I think that there's no doubt that it will silence such rumors and critics... At least for a while...


97...

[beatle888]

we'll have to wait and see. if ibm makes a big splash with new and constantly improving processors than those predictions will fade.

[Bengt77]

Originally posted by macdong
Hmm, you are right.
"Twice as much information" sounds like "twice as fast", but it's not.
Just the words game business writer like to play :)

It potentially could be, though...

:rolleyes:

[Bengt77]

Originally posted by Snowy_River 97... [/B]

Hehe ... gonna be a '6502' soon, eh?! Congrats! I have to start increasing my post frequency too; I'm not even a 'regular' yet!

:D

[Snowy_River]

Originally posted by Bengt77
Hehe ... gonna be a '6502' soon, eh?! Congrats! I have to start increasing my post frequency too; I'm not even a 'regular' yet!

:D

Thanks! I was wondering if people would figure it out, or ask about it. Not much longer to a 'tar...

94...

[macnews]

64 bit vs 32 bit, at the very least it will be faster. I think the key point is the 970 will be coming some time soon to Apple. I doubt Apple legal would be so quick to request a correction to the article if the 970 would not be used in Apple products. It was only a few months ago when debates were going on about Apple using Motorola or IBM - we may be able to settle that rumor now. I highly doubt we will see a new G5 or "better" G4 in NEW machines. I'm sure the 'G' series chips will live on in the ibooks and maybe emacs. The 970 will be used in the newer machines.

So, this leaves the question as to WHEN will they show up? Say the new chip and OS is introduced in June, give a few months so say late August. Apple seems to be doing hardware and software introductions seperately now though. Perhaps Panther in June and the 970 in July? Ship date then might be September. These would fall in line with Apple's history of announce and ship times.

Worse case, no chip this summer. It wouldn't suprise me but Apple HAS to make some move from a business stand point. It is an economic requirement for them. Laptop sales alone will not keep them afloat. The last thing Apple needs to hear is "I would switch to OS X if the power macs were just faster!"

Knowing our luck, Apple will follow its history and pick the worst case secenario. I hope I am wrong. I won't be holding my breath in June waiting for the 970. (Ok, I will but will try not to)

[mim]

Ok, ok. That just about does it for me - and many other's too I thinks...I'm at 971% of the 970 saturation point. I can't take any more!

There is no smiley for this emotion, damnit! It should look like a fountian of rumors exploding from the top of the smiley. Maybe an ascii version is this:

>~~~{:0

or something.

Let's just start speculating about something else now. Just as long as it isn't MICE. 980's, anyone?!

Futile, futile I know. But I had to try.

<sigh>a.

[Bengt77]

Originally posted by mim
Ok, ok. That just about does it for me - and many other's too I thinks...I'm at 971% of the 970 saturation point. I can't take any more!

Yeah, that's about my feeling too! Let's find a new toy to play with. Let's get it over with this thread (and the PPC970 altogether) and go read a good book, or something like that. Let's all go and see The Matrix Reloaded for the sixth time. Wanna join me? I'm gonna go tonight again...

:o

[The Ancients]

Originally posted by Masker
I know all the people that keep talking about this are just being goofy, but this bugs me: your car can accelerate, but does that mean that it keeps getting faster the longer that it runs? :D Simply because it's a higher derivative doesn't mean that it would have a CONSTANT acceleration.... :) [Edit: removed goofiness]

Just because the guy mispoke, doesn't mean that you guys aren't also mistaken. And, if you're going to get all physics on us, use the correct term: velocity not speed. [Edit: Hmmmm. For cps or Hz, velocity isn't exactly right, either...]

We're not mistaken though - we (knowingly) simplified. Besides, the seriousness surrounding this topic was stifling.

Have you heard these guys calling out for speed? The pedal's already on the floorboards as far as G4 computing is considered, and I can't see it changing when (alright - if!) the PPC970 comes along. The capabilities will be fully utilised. Having said that, Cd may be slightly less important with regard to computers, as opposed to vehicles...

Velocity is not correct for Hz either (cycles) - brain dead this time of night here though, so someone else will have to contribute...

[leo]

Originally posted by Snowy_River
... that 970 based Power Macs will not simply be competitive with P4s, but will significantly exceed their performance

How do you know? Estimating from the SPECmarks (937/1051, int/FP respectively, Altivec left out), the 1.8 GHz 970 will be about as fast as a 2.8 GHz P4 (976/947).
And these machines are available (today) in dual configurations (Xeons) for a price lower than that of a 1.42 GHz G4...

Don't get me wrong here, I'd still prefer the Mac. But I fear that many people here will be very disappointed when they figure out that Apple simply needs the 970 to be taken serious again. The snail-ads are out of place for the time being...

[gotohamish]

Originally posted by mkaake
sorry bout the personal jab...

i'd love to see this all come out good for apple, and i'm prolly gonna get flamed for what i'm about to say, - - but - - -

i don't think the g4 is all that bad - i think we're all getting caught up in the mHz myth that we love to bash others about. i mean, i'm writing this on a 266 g3, and it runs just about everything i want it too (except x, of course...) (and yeah, i know there are ways to make it, but it's not worth it on this machine). pump it with ram, and the only times when you see the age of the proc is when you rip and encode in itunes. and the occasional bout when you're running 4 or 5 programs at a time.

i think the g4 bashing has become kind of a sport and we've forgotten that it's still pretty powerfull...

oh well . think what you will.

<braces for impact>

matt

I have a 333 G3 at home, and it runs jaguar just fine. No installation trouble, no mods. It's a standard G3 with a USB PCI card, original 4MB Graphics card, running the first Apple LCD screen, and 512MB RAM - it's slower than my G4s yes, but fine for my mum's emailing and doing our eBay stuff every week - which means it runs Photoshop 7 and Dreamweaver MX just fine.

It's using a Mac like that that makes me like my 1.3Ghz G4 even more, but makes me desperate for the IBM chip!!!

[Bengt77]

Originally posted by The Ancients
The pedal's already on the floorboards as far as G4 computing is considered, and I can't see it changing when (alright - if!) the PPC970 comes along.

Wrong! The G4 still has some powers not unleashed yet. Just throw in a true DDR FSB (say 400MHz) and use corresponding (duh) DDR RAM and you'll see the (dual) G4's performance go up to quite a competitive level with today's Pentium 4s. At least, that's what I think. The G4 has never been fully utilised to it's full potential, which is a terrible shame, really.

:(

[The Ancients]

Originally posted by i_b_joshua
"IBM did not confirm it was building a chip specifically for Apple, but it does say its new PowerPC chip will work on Apple platforms..... .. .. .. ouch ouch owww!!. STEVE stop twisting my arm!""


Meanwhile, the rest of the Apple faithful are gnawing their arms off waiting...

..k

[mim]

Originally posted by The Ancients
Velocity is not correct for Hz either (cycles) - brain dead this time of night here though, so someone else will have to contribute...

Velocyples, Heforeemers, and Flutermizers.

ipso: Heforeemers = Velocyples/second where Velocyples = a Flutermizer/second * C.

sorted. Now let's go home.

[The Ancients]

Originally posted by Bengt77
Wrong! The G4 still has some powers not unleashed yet. Just throw in a true DDR FSB (say 400MHz) and use corresponding (duh) DDR RAM and you'll see the (dual) G4's performance go up to quite a competitive level with today's Pentium 4s. At least, that's what I think. The G4 has never been fully utilised to it's full potential, which is a terrible shame, really.

Originally posted by The Ancients
The pedal's already on the floorboards as far as G4 computing is considered, and I can't see it changing when (alright - if!) the PPC970 comes along.
:(

True. Perhaps I should have said as far as Motorola G4 computing is considered

[Bengt77]

Originally posted by The Ancients
Meanwhile, the rest of the Apple faithful are gnawing their arms off waiting...

..k

Yeah, or you actually go get some work done on the Mac you own now, instead of just waiting and waiting and waiting. I don't believe in the PPC970 anymore. Of course it'll come, that part I know too, but when it'll come is just plain guessing. There are so many contradictive articles and rumours doing rounds that there's no way at all to 'tell' when they're ready for use in Apple's new Power Macs.

EDIT: When it comes, it'll probably hopelessly lag behind the performance of that moment's Pentiums and AMDs. Darn, I love my iMac, but it's no comparison to some of my friends' PCs, concerning speed. Their respective speeds really are miles apart. Will the PPC970 really bend that situation to our advantage? I don't dare to think so. Not anymore. Damn MacNet article! (http://macnet2.com/more.php?id=338_0_1_0)

:(

[gopher]

Originally posted by alset
That update to the article is hilarious. News of the 970 is getting pretty old.

Dan

Getting pretty old? Well if it is so old, why don't you make your own 970 clone? Apple has not released one machine yet utilizing the 970 for Apple, and neither has anyone else. If the news is old, then you might want to be the first one to make one. Naturally you couldn't. So stop saying news is old when it still is suggesting something that won't happen until some point in the future.

[eric_n_dfw]

I think the G4 with true DDR FSB we have been waiting for will materialize for the portables and iMacs - but it will be the IBM G3 750GX (the rumored G3 + AltiVec). And the 970 will be reserved to the PowerMac's and XServes. (Maybe even just the high end ones)

The 750GX and 970 could even turn into the PowerPC equivelent of the P4 and Xeon in the Intel camp.

When is the 750GX rumored to be available?

[jeffosx]

EDIT: When it comes, it'll probably hopelessly lag behind the performance of that moment's Pentiums and AMDs. Darn, I love my iMac, but it's no comparison to some of my friends' PCs, concerning speed. Their respective speeds really are miles apart. Will the PPC970 really bend that situation to our advantage? I don't dare to think so. Not anymore. Damn MacNet article! (http://macnet2.com/more.php?id=338_0_1_0)

:( [/B]

I am writing this on an AMD 2400+ PC running XP. Is it faster than my dual 1.25 machine at work? No, why because tonight for an hour, instead of doing stuff on my PC, I figured out how to get my SCSI card to stop crashing the computer and how to uninstall a tax package so I could reinstall it (gave up in the end and may have to rebuild, again).

At work we have about 1000 PCs and 12 Macs. The PCs run NT 4 and they all suck. There are exactly 12 happy people at any one time on computers. People are using their serial Zip disks and watching the bar move for 10 minutes while they transfer 50 Meg files. They look at a USB flash drive likes its from Mars. Whenever I even dare to "bitch" about speed of computers I get screamed at. I love it that when we decide to get a new Mac, we have all of 3 choices, good, better and best not obsolete, slow and barely useable that we get for PCs... We are only ordering new macs now because people love the OS, hardware and software once they see it next to the competition.

The best part, our IT dept dont get Macs at all so they leave us alone...

My 2c worth

[matznentosh]

Originally posted by Snowy_River
Okay, I'm getting confused. We live in a 3+1 dimensional universe (as far as we can tell, no string theorists please - oh wait, they don't like Macs... :p).

98...

Actually, there have to be at least 4 spatial dimensions plus the time dimension. Space is curved as can be seen clearly by the bending of light rays coming from distant stars. That curve has to occur in a different spatial dimension than the 3 we experience with our senses. As for string theory, most of my physics friends use unix boxes. They haven't gotten the Mac bug yet.

[Zeke]

Originally posted by matznentosh
Actually, there have to be at least 4 spatial dimensions plus the time dimension. Space is curved as can be seen clearly by the bending of light rays coming from distant stars. That curve has to occur in a different spatial dimension than the 3 we experience with our senses. As for string theory, most of my physics friends use unix boxes. They haven't gotten the Mac bug yet.

I don't think so...it may seem this way but the fact that we can represent the bending of light using relativistic 4-vectors shows that all you need is 3 spatial and 1 time. If 4 were necessary, 4 would have been made when the results from these experiments were seen.

[MisterMe]

Originally posted by Snowy_River
Okay, I'm getting confused. We live in a 3+1 dimensional universe (as far as we can tell, no string theorists please - oh wait, they don't like Macs... :p). In such a universe there are scalars, pseudo-scalars, vectors, pseudo-vectors, tensors. . . and so on. So where do super-scalars fit into all of this?? Maybe the 970 is a computer that doesn't really exist in our universe. Maybe there is just an interface here but the actual processor exists in hyper space........


98... Unlike you, I actually know string theorists and they like Macs. Real scientists like to get their work done, not futz around with computers. As for the term velocity, there is really only one relevant dimension in computation, the line between the beginning and end of the job. In that respect, velocity would denote the rate at which you are moving forward or backward. Since your computer task can't move backward even on a Windows machine, speed is the more appropriate term.

[Rustus Maximus]

Originally posted by Bengt77
When it comes, it'll probably hopelessly lag behind the performance of that moment's Pentiums and AMDs. Darn, I love my iMac, but it's no comparison to some of my friends' PCs, concerning speed. Their respective speeds really are miles apart. Will the PPC970 really bend that situation to our advantage? I don't dare to think so. Not anymore. Damn MacNet article!

Ohhh, blah, blah, blah, BLAHHHH
who cares what this bitter on Apple maroon has to say?

John Manzione is a big, fat idiot.

[Kid Red]

I love the updated article, as if Steve saw MacRumors and said 'What?!!? Confirmed!?!" and then gave someone a call, hehe.

[allpar]

In some tasks, PCs are indeed faster. However in normal use, my Athlon XP 2.2 (266 bus) is (a) four times faster at Distributed Folding, (b) twice as fast at Internet Explorer, and (c) the same speed at GoLive and Photoshop...as my blue and white G3-upgraded-to-G4, at 400 MHz. The B&W is from 1998...so I wonder how a dual 1 GHz machine would fare.

To be fair (fare), my PC cost as much as a blue and white G3 plus a G4 upgrade. But it requires a lot more maintenance.

At least peripherals are the same price now for Macs and PCs, remember when you had to pay $100 more for printers and scanners and stuff? But I do wish the computers were closer to parity, I also remember when a Mac and PC were close in price. With the cheapest tower at $1,600 I can't buy a new Mac. When the 970 comes out, MAYBE. Or maybe I'll try to grab a used dual-G4.

[Snowy_River]

Originally posted by MisterMe
Unlike you, I actually know string theorists and they like Macs. Real scientists like to get their work done, not futz around with computers...

Excuse me, but how do you know who I know and who I don't?

The fact of the matter is that there are a couple of string theorist in our physics department, and I've met several others when they've come through and given colloquia. None of them have been Mac users. None of them have been Windows users, either. All of them have been Linux users, and are proud of it, based on what conversations I've had with them on the topic. Those that I did talk to were fairly quick to put down both Mac and Windows operating systems.

That you know string theorists that like Macs is great. I had never even heard of one, and certainly never met one, despite the fairly large number of string theorists I've met, before now.

As far as real scientists liking to get work done (i.e. liking Macs), I couldn't agree more. That why I like my Mac. :D


84...

[littlerich]

just bought my shares while their low :D

[Frobozz]

PS8 Won't Work on OS 9 (http://maccentral.macworld.com/news/2003/05/22/photoshoprelease/)

Could this mean something more than a simple Carbon to Cocoa conversion? I think it might. What other reason would they have for dropping OS 9?

*drum roll*

Perhaps it's because they will be incorporating 970 enhanced code? Is there any reason why supporting the 970 would exclude OS 9? If not, it may just be a reason to stop QA'ing OS 9 support? Who knows.

[Masker]

Originally posted by MisterMe
Unlike you, I actually know string theorists and they like Macs. Real scientists like to get their work done, not futz around with computers. As for the term velocity, there is really only one relevant dimension in computation, the line between the beginning and end of the job. In that respect, velocity would denote the rate at which you are moving forward or backward. Since your computer task can't move backward even on a Windows machine, speed is the more appropriate term.

Man, not to be a hard-a$$ or anything, but:

ve·loc·i·ty __ (_P_)__Pronunciation Key__(v-ls-t)
n. pl. ve·loc·i·ties
Rapidity or speed of motion; swiftness.

Physics. A vector quantity whose magnitude is a body's speed and whose direction is the body's direction of motion.

The rate of speed of action or occurrence.

The rate at which money changes hands in an economy.


Velocity only implies that there could be more than one direction of motion, it doesn't (as far as I can see) require there to be. And, the guy wasn't just speaking about computation, if you looked at the original post; he also said: m/s speed, m/s/s acceleration. So, in that case, I said he should...

Oh, never %*#(& mind. ;)

And, it does look like the term "frequency accleration" can be used: http://216.239.41.100/search?q=cache:mQ7ch-zXBSYJwww.rakon.com/generated/rakpdf/Dips-slope.PDF+frequency+definition+acceleration&hl=en&ie=UTF-8. Though, I have to say that I, myself, prefer velocyples, now that someone said it! :D

And (to whomever it was, I can't remember), nice try to deflect the angst over the 970 by bringing up John Manzione... :p

[EDIT: Stupid mistakes]

[cubist]

Originally posted by Bengt77
Wrong! The G4 still has some powers not unleashed yet. Just throw in a true DDR FSB (say 400MHz) and use corresponding (duh) DDR RAM and you'll see the (dual) G4's performance go up to quite a competitive level with today's Pentium 4s. At least, that's what I think. The G4 has never been fully utilised to it's full potential, which is a terrible shame, really.
:(

The G4's that exist are being used even beyond their full potential. They don't have a true DDR FSB. You are describing the 7457-RM, which doesn't exist and probably never will.

[robotrenegade]

about time

[jettredmont]

Originally posted by Masker
And, if you're going to get all physics on us, use the correct term: velocity not speed. [Edit: Hmmmm. For cps or Hz, velocity isn't exactly right, either...]

Frequency is the word you are looking for. "Velocity" and "Speed" both refer to distance per second. "Frequency" refers to cycles per second.

:)

Not sure if a steadily increasing freuency would be refered to as accelleration, though ...

Gosh, all this talk reminds me of the "Windows Accellerating" video cards of the early '90's ...

[jettredmont]

Originally posted by P-Worm
Do you think that IBM will be using the 970 for things other than Macintoshs? Maybe there own desktops? Seems a little unlikely, but we don't want to be swept with the current...

P-Worm

IBM has already announced a line of blade servers based on the 970.

So, Apple exclusivity was never assumed nor accurate.

[Vlade]

Will the 970 have DDR400 or what?

[jettredmont]

Originally posted by hayesk
If Intel can say the P4 makes your colours more vibrant and your internet surfing more rewarding, then why not fight fire with fire?


True, true ... but I'd like to think despite all the evidence to the contrary that we're better than that ...

[jettredmont]

Originally posted by Cubeboy
Another thing to note is that a program that fits into a 32 bit model and doesn't take advantage of a specific 64 bit capability (scalability, memory, high precision arithmetic) will probably perform better compiled as a 32-bit binary than a 64 bit one due to more cache misses associated with the size of the 64 bit binary.

Um, no. If your application doesn't use 64-bit ints, compiling with the "use64" (or whatever) compiler switch will change nothing besides the pointer addresses (and, I'd suspect that the compiler will have a separate switch for allowing >4GB addressable memory which would twiddle the pointer size back down to 32 bits as 90% of all apps won't need that much addressable memory). The instructions are still, as always with PPC, 32 bits wide. The only thing compiling specifically for the 970 would do would be allow you to use native 64-bit int registers (and memory addresses).

But, yes, blindly changing 32-bit ints to long longs (64-bit ints) will increase your memory usage, which is the #1 performance bottleneck on the G4 (although not as bad on the 970). This is the same as using 32-bit ints for 8-bit or 16-bit data types today. Proper variable sizing will remain a primary concern for developers who want optimized code.

[AidenShaw]

Originally posted by Vlade
Will the 970 have DDR400 or what?

No, it'll have magnetic core memory. :cool:


Seriously, though, the PPC970 has no memory other than cache and scratch space.

Whatever memory it uses will be decided by the chipset and motherboard designers.

Since there haven't been any specs announced, anything could happen. MacB did claim PC3200, however, in the proto system that they supposedly saw.

[jettredmont]

Originally posted by mkaake
i don't think the g4 is all that bad - i think we're all getting caught up in the mHz myth that we love to bash others about. i mean, i'm writing this on a 266 g3, and it runs just about everything i want it too (except x, of course...) (and yeah, i know there are ways to make it, but it's not worth it on this machine). pump it with ram, and the only times when you see the age of the proc is when you rip and encode in itunes. and the occasional bout when you're running 4 or 5 programs at a time.

i think the g4 bashing has become kind of a sport and we've forgotten that it's still pretty powerfull...

oh well . think what you will.

<braces for impact>

matt

"occasional bout when you're running 4 or 5 programs at a time" ... Dude, I'm hardly ever running fewer than 4 programs! I mean, you've got (aside from Finder), Mail and iTunes and Project Builder going 100% or the time, throw in Safari and you're up to 4!

Having a beefier machine broadens your horizons in ways you'll never understand until you have one ...

The G4 is a fine chip, with a really crappy front-side bus design. It just physically can't get enough data to keep the processor busy. That having been said, even with a significantly better FSB I'd be surprised if the G4 core could compete with the top-of-the-line P4s. It just doesn't do that much more per clock cycle to counter its lower frequency.

[AidenShaw]

Originally posted by jettredmont
Um, no.

Maybe yes and no.

The "size of the binary" statement is pretty far off (unless all data is statically allocated).

Using 64-bit pointers, however, does increase the runtime footprint of a program. For some programs, the pointers represent a fair proportion of the total data. Programs that keep their data in lists, double-linked lists, or trees often have that issue.

The larger data size lowers performance in two ways:

- more memory bus bandwidth is needed to move the pointers
- the pointers occupy more space in cache, thereby reducing the effective size of the caches

So, the original poster had more or less the right idea, but made a mistake by referring to the size of the binary image.

[jettredmont]

Originally posted by matznentosh
Actually, there have to be at least 4 spatial dimensions plus the time dimension. Space is curved as can be seen clearly by the bending of light rays coming from distant stars. That curve has to occur in a different spatial dimension than the 3 we experience with our senses. As for string theory, most of my physics friends use unix boxes. They haven't gotten the Mac bug yet.

The effects of any dimension above 3 is manifested as time. Any series of events in the n-dimensionl universe from our 3-dimensional perspective can therefore be described using 3+1 dimensions.

For purposes of predicting events, it is often useful to count on a fourth dimension, and sometimes useful to utilize further dimensions. If it takes 6 dimensions to explain an occurence which could also be explained using 4, then the 4-d explanation wins (re Occam). However, in the absence of a 4-D simplification, one must run with 6 dimensions.

That having been said, the correct answers to "how many dimensions are there?" is one of "3+time" or "infinite".

Okay, let's drop the physics now except as it applies to the 970 processor ... :)

[Rincewind42]

Originally posted by Frobozz
PS8 Won't Work on OS 9 (http://maccentral.macworld.com/news/2003/05/22/photoshoprelease/)

Could this mean something more than a simple Carbon to Cocoa conversion? I think it might. What other reason would they have for dropping OS 9?

Perhaps it's because they will be incorporating 970 enhanced code? Is there any reason why supporting the 970 would exclude OS 9? If not, it may just be a reason to stop QA'ing OS 9 support? Who knows.

Or it could simply be that they are using Carbon calls that are exclusive to MacOS X. Or they have switched to MachO and are using other MacOS X Frameworks. It is complely possible (and I bet very likely) that Adobe will continue to use Carbon for it's existing applications. Remember, they were one of the early companies that complained about having to rewrite for Cocoa - why would they do so now _after_ getting a Carbon version on MacOS X (as opposed to before when they had tons of lead time and inside access that numerous other devs didn't).

And of course, it is also possible that they will be putting out a 64-bit version of Photoshop - but they will still put out a 32-bit version for the majority of people that won't have 970s.

[ddtlm]

Snowy_River:

The truth is that the G4 is a modern processor. It happens to have some problems (too-slow FSB, etc.), but it is a robust, powerful, modern processor.
It's no more modern than an AMD K6-3 (which was of course a K6-2 with the on-die L2 and motherboard L3). In addition to the similar caches, they have similar slow FSB's, weak scalar floating point units, poor clock speed scaling, and no hardware prefetch. I'm not interested in looking up K6 details, but I'd be surprised if it had significantly worse out-of-order or superscalar execution capabilities than a G4. Perhaps someone else feels motivated to continue the comparison.

As for your assertion that the G4 is powerful, well thats just rediculous. There are plenty of benchmarks that illustrate what happens to G4's that venture outside of an hand-sewn Altivec cocoon.

And what we're excited about is not the prospect that Apple will be competitive again, but that we may be coming into a new 'Golden Age', akin to when the G3 came out; that 970 based Power Macs will not simply be competitive with P4s, but will significantly exceed their performance
There is nothing that suggests the PPC-970 will outperform the Intel chips of its time in most apps. Already Intel has P4's with an equally fast FSB and similar caches, that score better in SPEC (the only performance numbers really available for a PPC970). Intel's next revision, needless to say, will not be slower. The current P4 core has been around since January 2002 and the next one will be out this year. Intel is a tough compeditor.

jeffosx:

So what do 1000 ancient NT boxes have to do with modern PCs?

Bengt77:

The G4 still has some powers not unleashed yet. Just throw in a true DDR FSB (say 400MHz) and use corresponding (duh) DDR RAM and you'll see the (dual) G4's performance go up to quite a competitive level with today's Pentium 4s.
This looks to be pure speculation. Wishful speculation at that. Yes a 400mhz FSB and solid RAM would boost certain AltiVec benchmarks a lot, but since when has that been the problem with the G4? If bandwidth were the problem, don't you think that Apple's new 166mhz FSB computers would be able to demonstrate a nice performance boost? Don't know about you, but I was troubled by the 17" AluBook's unimpressive CPU performance compared to the old PC133 15" TiBook.

[Rincewind42]

Originally posted by jettredmont
(and, I'd suspect that the compiler will have a separate switch for allowing >4GB addressable memory which would twiddle the pointer size back down to 32 bits as 90% of all apps won't need that much addressable memory).

Actually, I suspect that such a switch would be incompatable with the runtime. After all, there would then need to be some kind of switch to tell memory allocators that they couldn't go above 4GB, even though they have access to the memory. 64-bit support in MacOS X would already require 2 versions of every framework (you can't use a 32-bit framework in a 64-bit application and vice versa). Allowing 64-bit runtime with 32-bit pointers would only make the problem worse.

[Rincewind42]

Originally posted by AidenShaw
Using 64-bit pointers, however, does increase the runtime footprint of a program. For some programs, the pointers represent a fair proportion of the total data. Programs that keep their data in lists, double-linked lists, or trees often have that issue.

The larger data size lowers performance in two ways:

- more memory bus bandwidth is needed to move the pointers
- the pointers occupy more space in cache, thereby reducing the effective size of the caches

But if you are using so many pointers, then you data has already violated the locality of reference principle and thus you would have likely made minimal usage of the caches anyway. There are data structures that make heavy usage of pointers that can take advantage of being in the cache (hash tables come to mind). If you are using that many pointers, even at 32-bits you are losing a lot of performance.

[AidenShaw]

Originally posted by Rincewind42
But if you are using so many pointers, then you data has already violated ....If you are using that many pointers, even at 32-bits you are losing a lot of performance.

Losing performance compared to what?

Your statements seem rather naive - some algorithms naturally run the fastest by using pointers. Think of a b-tree with small nodes, sure the pointers will be a fair percentage of the data - but you're quite unlikely to come up with a faster way of solving the problem.

Many other important applications (fluid dynamics, semiconductor design, ...) also have a fair number of pointers.

[Abstract]

Originally posted by ddtlm
Snowy_River:

As for your assertion that the G4 is powerful, well thats just rediculous. There are plenty of benchmarks that illustrate what happens to G4's that venture outside of an hand-sewn Altivec cocoon.


Agreed. A G4 doesn't scare anyone anymore. It had a much longer competitive life than a Pentium or AMD chip, but as of now, its not in the same league as the others. Its true that other factors were holding it back, but the G4 has to go.

[dongmin]

Originally posted by Rincewind42
Or it could simply be that they are using Carbon calls that are exclusive to MacOS X. Or they have switched to MachO and are using other MacOS X Frameworks. It is complely possible (and I bet very likely) that Adobe will continue to use Carbon for it's existing applications. Remember, they were one of the early companies that complained about having to rewrite for Cocoa - why would they do so now _after_ getting a Carbon version on MacOS X (as opposed to before when they had tons of lead time and inside access that numerous other devs didn't).

And of course, it is also possible that they will be putting out a 64-bit version of Photoshop - but they will still put out a 32-bit version for the majority of people that won't have 970s.

well i don't know if cocoa will improve the performance but the recent versions of Photoshop and Illustrator for OS X really really blow. They need to do SOMETHING to make them run better.

[Rustus Maximus]

Rewriting it exclusive for Cocoa should help the speed since all of the legacy code wil be gone finally. Of course for me Photoshop 7 doesn't really blow now...Illustrator is a slug...but Photoshop is fairly snappy on my Dualie 1 Gig.

[Rincewind42]

Originally posted by AidenShaw
Losing performance compared to what?

Your statements seem rather naive - some algorithms naturally run the fastest by using pointers. Think of a b-tree with small nodes, sure the pointers will be a fair percentage of the data - but you're quite unlikely to come up with a faster way of solving the problem.

Many other important applications (fluid dynamics, semiconductor design, ...) also have a fair number of pointers.

I never said that there were not algorithms that would benefit from structures that rely stricly on pointers - your example was a linked list. A linked list where you have 1 or 2 pointers per node and a small amount of data is grossly inefficient - such lists are typically implemented as pointing to a block of data and you chain additional nodes in blocks that point to the next block (a linked list of arrays). I can easily think of an algorithm that would get a huge performance win because of pointers: page flipping. But the speed up comes from not having to do a block copy on a huge amount of data, the data size still dwarfs the pointer size regardless of if it is 32, or 64 bits in size.

But regardless, if your jumping all over memory, then you are losing the benefit of the cache to some degree. 4-8 extra bytes in the cache per node aren't going to increase that hit significantly. Caches are designed to take advantage of linear access patterns, not effectively random ones that you get with linked lists and trees (especially when you are allowed to delete and insert at any location within the data structure).

[Rincewind42]

Originally posted by dongmin
well i don't know if cocoa will improve the performance but the recent versions of Photoshop and Illustrator for OS X really really blow. They need to do SOMETHING to make them run better.

And I'm sure that they are, the real question is if you will be willing to live with the minimum requirements :D. (I refer to OS version - there are far to many that have bitched about upgrading to 10.2 and say that they may not upgrade to 10.3 because of one reason or another. I'm willing to bet that Adobe will require 10.3 for their next versions of software, if only because the rest of the industry will likely head that way by the time PS8 comes out).

Originally posted by Rustus Maximus
Rewriting it exclusive for Cocoa should help the speed since all of the legacy code wil be gone finally. Of course for me Photoshop 7 doesn't really blow now...Illustrator is a slug...but Photoshop is fairly snappy on my Dualie 1 Gig.

Rewriting in Cocoa won't necesarily do anything at all for the speed. And they could just as easily remove legacy code while staying in Carbon. Cocoa isn't a magic bullet and Carbon isn't an instant indicator of legacy.

[Gymnut]

Jeezus not another PPC 970 thread. It'll get here when it gets here.

[AidenShaw]

Originally posted by Rincewind42
Caches are designed to take advantage of linear access patterns, not effectively random ones that you get with linked lists and trees (especially when you are allowed to delete and insert at any location within the data structure).

More to the point, caches are designed for access patterns where repeated accesses are made to the same data.

They also optimize for short stretches of linear access - for example 256bits (32 bytes) is a common "cache line" size. When you get a cache "miss", the 32 bytes containing the missed item will be moved from memory into the cache.

If one is looking at other data nearby (locality), then the large read is good. If one is truly bouncing around, then memory bandwidth is wasted (and extra latency introduced) by these large transfers.

A bad case for a cache is a purely linear access pattern - when you are making a single pass sweeping through memory that's much larger than the cache. In this cache each level of cache just adds latency, without helping (kind of like a layer of middle management that just has to approve and sign paperwork).

[mathiasr]

Originally posted by AidenShaw
Using 64-bit pointers, however, does increase the runtime footprint of a program. For some programs, the pointers represent a fair proportion of the total data. Programs that keep their data in lists, double-linked lists, or trees often have that issue.

The larger data size lowers performance in two ways:

- more memory bus bandwidth is needed to move the pointers
- the pointers occupy more space in cache, thereby reducing the effective size of the caches

So, the original poster had more or less the right idea, but made a mistake by referring to the size of the binary image.

I agree, but there is another case where the code could actually schrink.
This could happen if your app does a lot of 64 bits computing.

A small example, that:
- reads two 64 bits values from 2 different memory location
- compute their sum
- store it in another location
- prepare to do the same on the next value in memory.

Consider r6, r7 and r8 as pointers to the begining of the memory locations (could be arrays or matrices), and r4 as an index inside those locations.

in a high level langage (C like):
r8[r5]=r6[r5]+r7[r5]
r5++

PowerPC64:
ldx r10,r4,r6 loads the 64 bits value stored at memory location r6+r4 in register r10
ldx r11,r4,r7 loads the 64 bits value stored at memory location r7+r4 in register r11
add r12,r10,r11 adds both registers and puts the result in r12
stdx r12,r4,r8 stores the sum in memory location r8+r4
addi r4,r4,8 adds 8 (64 bits = 8 bytes) to the index to point to the next values

Total size of the code: 5 instructions (20 bytes)


This time consider r6, r7, r8 as the sum of rx+r4

PowerPC32 (based on code produced by GCC 3.1):
lwz r10,0(r6) loads the high word of the 64 bits value stored at memory location r6 in register r10
lwz r11,4(r6) loads the low word of the 64 bits value stored at memory location r6+4 in register r11
addi r6,r6,8 adds 8 to point to the next value
lwz r12,0(r7) loads the high word of the 64 bits value stored at memory location r7 in register r12
lwz r13,4(r7) loads the low word of the 64 bits value stored at memory location r7+4 in register r13
addi r7,r7,8 adds 8 to point to the next value
addc r14,r11,r13 adds the two low words in register r14 keeps the carry bit
adde r15,r10,r12 adds the two high words and the carry bit in register r15
stw r15,0(r8) stores the high word of the sum in memory location r8
stw r14,4(r8) stores the low word of the sum in memory location r8+4
addi r8,r8,8 adds 8 to point to the next value

Total size of the code: 11 instructions (44 bytes)
When you work with 64 bits datas on a 32 bits CPU, you need 2 loads or 2 stores to move them from/to memory, the values are split across the 32 bits registers (this could lead to register starvation) and require at least 2 times more operations.

[mathiasr]

Originally posted by jettredmont
The only thing compiling specifically for the 970 would do would be allow you to use native 64-bit int registers (and memory addresses).
This gives you access to the PowerPC64 Instruction Set Architecture, and some new instructions like:
fcfid (Floating-point Convert from Integer Doubleword)
fctid(z) (Floating-point Convert to Integer Doubleword(with Round to Zero))
fsqrt (Floating-point Square Root)

The others are ment to support the wider registers:
cntlzd (Count Leading Zeros Doubleword)
divd(u) (Divide Doubleword (Unisgned))
extsw (Extend Sign Word)
ld(u)(x) (Load Doubleword (with Update)(Indexed))
ldarx (Load Doubleword and Reserve Indexed)
lwa(u)(x) (Load Word Algebraic(with Update)(Indexed))
mfasr (Move from Address Space Register) supercedes mfsr
mtasr (Move to Address Space Register) supercedes mtsr
mulhd(u) (Multiply High Doubleword (Unsigned))
mulld (Multiply Low Doubleword)
rld(i)cl (Rotate Left Doubleword (Immediate) then Clear Left)
rld(i)cr (Rotate Left Doubleword (Immediate) then Clear Right)
rldic (Rotate Left Doubleword Immediate then Clear)
rldimi (Rotate Left Doubleword Immediate then Mask Insert)
sld (Shift Left Doubleword)
sr(a)d(i) (Shift Right (Algebraic) Doubleword (Immediate))
std(u)(x) (Store Doubleword (with Update)(Indexed))
stdcx. (Store Doubleword Conditional Indexed)
td(i) (Trap Doubleword (Immediate))

[Edit removed a mnemonic]

[mathiasr]

Originally posted by AidenShaw
A bad case for a cache is a purely linear access pattern - when you are making a single pass sweeping through memory that's much larger than the cache. In this cache each level of cache just adds latency, without helping (kind of like a layer of middle management that just has to approve and sign paperwork).
Latency will not strictly add, for instance L2 and L3 caches are polled simultaneously; data coming from memory is forwarded to the Load/Store Units first.
And chances are that datas that belong to the same cache line will be avaible in the L1 cache, if you do not fire a load after another and do some computations in between.

Never heard of data streams and cache hints ?
You can request a cache line before you actually need it:
http://developer.apple.com/hardware/ve/performance_memory.html
http://developer.apple.com/hardware/ve/caches.html

Even if it will not help once the bus has reached peak bandwidth.

[AidenShaw]

Originally posted by mathiasr
Latency will not strictly add, for instance L2 and L3 caches are polled simultaneously; data coming from memory is forwarded to the Load/Store Units first.

If the multi-level cache logical introduces zero latency, you're right. I haven't seen any of these mythical beasts, however, it seems that real levels of electronic circuitry do need some time.


Never heard of data streams and cache hints ?

Of course, who hasn't?


Even if it will not help once the bus has reached peak bandwidth.

BINGO! Give that guy the prize!

[jeffosx]

So what do 1000 ancient NT boxes have to do with modern PCs?

It (NT) creates modern PCs that suck...

The only option for us is Win2000 not XP and noone is eager to go through an MS OS upgrade when the server upgrade problems are still going on almost 1 yr after rollout and the team of support staff contracted was huge. WRT to XP noone here will even look at it due to the licence.

My point is that the CPU is only part of the speed issue whereas the bulk of it IMO is the sw and the OS. When arguing about getting Macs here we "won" because of stability and software equalling speed/efficiency not CPU related SPEC scores.

Cheers

[mim]

Originally posted by jeffosx
My point is that the CPU is only part of the speed issue whereas the bulk of it IMO is the sw and the OS. When arguing about getting Macs here we "won" because of stability and software equalling speed/efficiency not CPU related SPEC scores.

Cheers

Exactly. Spec scores only tell part of the storey. I sat here last week with a brand new mint 1Ghz 12"PB, and a mint Dell dual xeon 2.4ghz, and guess what. The PB felt like it was flying next to the Dell. Open a window, move things around, minimize a browser, open photoshop - you name it the PB did it faster. Now, actually doing some "hard" work in photoshop, well ofcourse the dell was faster. But redraws when zooming, paning etc were better on the PB!

My point (and your) - doing the things that most people spend their time on everyday - the Mac is clearly superior. If you ever have that chance, just do it - get two machines side by side and try it.

But yes, the G4 is underpowered for intensive work. But the only time my computers are sitting still with a full processor load, not dealing with multiple windows opening and closing is when they are rendering. This is >not< when your average user needs speed!

I'm not trying to exuse the G4. I just think that some people who want to go to a Pentium system because of a perceived lack of speed in the current Macs will be >sorely< dissapointed. Bring on the 970's and OSX.

[Snowy_River]

Originally posted by jettredmont
The effects of any dimension above 3 is manifested as time....

I just have to say that this statement is absolutely absurd. There are a number of theories (more or less practical and applicable) that include up to, I think it is, 27 spatial dimensions, and they all only have one (1) time dimension. I've even done some research, when I was working for the high-energy group here, into detecting higher compactified spatial dimensions through very close gravity detection.

On the other hand, the only theories that I've ever heard of that have more than one time dimension have been pie-in-the-sky theories that lack applicability.

Okay, let's drop the physics now except as it applies to the 970 processor ... :)

Alright. Back to the 970. That is, the PPC970 processor, not the year 970, as we all know that it's impossible to travel back in time... ;)


80...

[Snowy_River]

Originally posted by mim
...I sat here last week with a brand new mint 1Ghz 12"PB...

I think you meant an 867 MHz 12"PB. Or do you have a line on a new upgrade to the PB line that we don't know about?

As to everything else you said about OS X, I couldn't agree more. I've compared it to both Windows and Linux, and I have consistently enjoyed the smoother feel of the system under OS X. That is the real reason that I stick with Macintosh computers...


79...

[jettredmont]

Originally posted by Snowy_River



Originally posted by jettredmont
The effects of any dimension above 3 is manifested as time....


I just have to say that this statement is absolutely absurd. There are a number of theories (more or less practical and applicable) that include up to, I think it is, 27 spatial dimensions, and they all only have one (1) time dimension. I've even done some research, when I was working for the high-energy group here, into detecting higher compactified spatial dimensions through very close gravity detection.

On the other hand, the only theories that I've ever heard of that have more than one time dimension have been pie-in-the-sky theories that lack applicability.


Okay, sorry to bring dimensioning back up, but just to clarify: I don't mean that all of the infinite number of conceptual dimensions are "time" in their own rites, but, from the 3-d perspective, we observe the effects of all such dimensions on our own as the passage of time (imagine a 1-D world lying on a piece of string ... that string being whipped around our 3-D universe sees its state change dramatically, but in and of itself could attribute all such changes to just the passage of time ... one second it has "gravity" flowing in the positive direction, the next in the negative direction, that is all it can directly observe). Which pretty much goes without saying when the only dimensions we can observe directly are the 3 spatial dimensions, and the passage of time (ie, the change in the state within those three dimensions).

But, yes, we can conceptualize about multiple, countless, other dimensions to explain phenomenon in these 3+1 ... In the same way our "string world" might be able to theorize that these strange shifts in "gravity" at their root are the consequence of movement through a 3-D universe where gravity is (fairly) constant.

Which is why, later, I said that there are only two correct answers to how many dimensions exist: 3+time (the number of directly observable dimensions) or infinite (the number of conceptually observable dimensions). "4+time" is not correct as an overall rule, although a particular theory might well only make use of 4 dimensions+time to explain its phenomenon.

OTOH, I have to say I haven't come across the theory using 27 dimensions yet!

[pdickins]

Just looking on the macbidouille site they have a new rumor of PPC970 Powermacs apparently boxed and ready to ship after the WWDC. Apologies for the google translation:-

Before arriving at the heart of the subject, remember that what follows is a rumour, without tangible proof. However if we chose to publish it, it is that it has very good chances to be true.

First Computers PPC 970 left the production lines and are even already packed on pallets. Pallets are covered with the opaque and sealed film. There are above stickers with following information:



"tamper proof seal, confidential property inside, prosecution may result personal yew opened by unauthorized"

They will start to be delivered to the wholesalers of confidence very soon with absolute order of not the défilmer before June 23. APPLE had already used this method during launching of the Cube and more recently of the iMac G4.

:D

[mim]

Originally posted by Snowy_River
I think you meant an 867 MHz 12"PB. Or do you have a line on a new upgrade to the PB line that we don't know about?

As to everything else you said about OS X, I couldn't agree more. I've compared it to both Windows and Linux, and I have consistently enjoyed the smoother feel of the system under OS X. That is the real reason that I stick with Macintosh computers...


79...

Whoops, ofcourse you're right. Just makes it even more impressive ;)

Also now, this translation above is interesting. MacB are going to be rumors gods, or scum of the earth. And the best thing is that we'll know for sure in under 1 month now.

As much as I was impressed by the PB, I am holding off buying one until I see what goes down at the end of June.

This count-down is really starting to get intense Snowy. Couldn't you have started at 10 or something?! ;)