...seems iteresting that while the 970 is garnering the lion's share of attention, the fact that a 1.42GHz G4 came out on a 180nm process has escaped mention.
Additonally, just last summer, Philips, Motorola, and STMicroelecronics announced they were preparing a facility capable of churning out 90 nanometer microprocessors on 300mm silicon....by the end of 2002. So if preproduction silicon is coming out by the end of 2002, whats keeping Moto from introducing a 2+GHz G4 on a 90nm process 2Q '03?
[QB]Forgive me if this has been asked and answered, but what is the shortest time between upgrades that Apple has ever done?
[QB]<hr></blockquote>
I think that the PM G4 came only three months or so of the BW PM G3. <a href="http://www.apple-history.com"; target="_blank">www.apple-history.com</a> is slower than dirt right now, or I'd check for sure.
[quote] It'll also have a DMA engine and perhaps the DSP-like features that were talked about last year. We can hope for a direct AGP 8x port as well. Is this what you are refering to TO? <hr></blockquote>
Well, those wouldn't be suprises, would they? Well, maybe the DSP.
The Wallstreet PDQ series was rushed out within three months of the Wallstreet. I think that's a record. It wasn't an Earth-shattering upgrade, but it was needed.
[quote]Originally posted by mooseman:
<strong>...seems iteresting that while the 970 is garnering the lion's share of attention, the fact that a 1.42GHz G4 came out on a 180nm process has escaped mention.
Additonally, just last summer, Philips, Motorola, and STMicroelecronics announced they were preparing a facility capable of churning out 90 nanometer microprocessors on 300mm silicon....by the end of 2002. So if preproduction silicon is coming out by the end of 2002, whats keeping Moto from introducing a 2+GHz G4 on a 90nm process 2Q '03?
Just some thoughts. Any opinions on it?</strong><hr></blockquote>
I've been talking about that for a while now. The STM facility in Grenoble is a potential ace in the hole for Mot. They've said that since the issues involved in designing for .13μ and .09μ are essentially the same, they might as well leap all the way down to .09μ. Since it's not their fab, it shouldn't have the problems that their own .13μ facility has been having due to draconian cost-cutting measures.
If Mot actually pulls this off this year, they'll suddenly have an attractive little chip. Perfect for iBooks. And if they feel like bringing back the ballyhooed Eleven on that process, it might suddenly run cool enough not to explode in Apple's test mules. I'm not expecting an answer to the 970 out of Mot any time soon, though, but I wouldn't turn down a tiny little G4 on a really fast MaxBus.
But this line of discussion is more appropriate for the 7447/7457 thread next door.
Well, with IBM getting into the desktop market MOT may be changing their tune with respect to processor design. They may be worried that IBM will make them look bad in the embedded market. Lets hope for some good-ol' Intel/AMD battling on the CPU front. Bragging rights sometimes drive markets
<strong>...seems iteresting that while the 970 is garnering the lion's share of attention, the fact that a 1.42GHz G4 came out on a 180nm process has escaped mention.
Additonally, just last summer, Philips, Motorola, and STMicroelecronics announced they were preparing a facility capable of churning out 90 nanometer microprocessors on 300mm silicon....by the end of 2002. So if preproduction silicon is coming out by the end of 2002, whats keeping Moto from introducing a 2+GHz G4 on a 90nm process 2Q '03?
Just some thoughts. Any opinions on it?</strong><hr></blockquote>
You're saying you wouldn't take a 5 watt 1.5 GHz G4+ w/ 512K L2 cache? The FSB is important folks, but its not everything. And the 7457-RM is always a possibility for early 2004 according to Moto's roadmap.
Faster G4s are kind of good as it means faster Macs and faster upgrades. But as far as desktop CPUs the G4 is dead end and speed boosts only extend the lenght of the dead end. Sure a 2 GHz G4 in a powerbook would be fantastic but given Motorolas track record the last 10 years, is it likely that they will do that in a resonable time frame?
You're saying you wouldn't take a 5 watt 1.5 GHz G4+ w/ 512K L2 cache? The FSB is important folks, but its not everything. And the 7457-RM is always a possibility for early 2004 according to Moto's roadmap.</strong><hr></blockquote>
I don't know about boots, but I wouldn't. Really, the CPU has been fast enough for me for a while now. What I can't stand is the overall system architecture. slow disks, slow FSB, slow memory, slow PCI, slow AGP, mediocre built-in sound.
I'm a big fan of fast and wide.
having said that I don't think my B&W can hold out much longer. As soon as the 9700 Pro becomes available I'll pick up a new machine and then sell it when something I like comes out.
...Additonally, just last summer, Philips, Motorola, and STMicroelecronics announced they were preparing a facility capable of churning out 90 nanometer microprocessors on 300mm silicon....by the end of 2002. So if preproduction silicon is coming out by the end of 2002, whats keeping Moto from introducing a 2+GHz G4 on a 90nm process 2Q '03?
...Any opinions on it?<hr></blockquote>
I remember those press releases. I personally got excited. They mentioned something like high end processors ?? manufactured by the end of 2002.
My opinion now, press release bologna. Suprise me Motorola, let's have another press release announcing ANYTHING is being manufactured using a 0.09µm process - ANYTHING AT ALL.
edit: originally wrote 0.9µm process above. Ha, I actually showed Motorola going backwards.
It's clear that next year the whole range will be unrecognisable in terms of performance, and these boards will go quite quiet. However in the mean time...
I think that we are not seeing the real performane of the current processors because of the bottlekneck caused by the FSB. If we can get a decent FSB then the performance on current machines and processors will leap.
I doubt that Moto would make the current processors on the 0.09 process, I am sure they are fully aware of the shortcommings too. Any move to 0.09 would be accompanied with a revised FSB.
<strong>It's clear that next year the whole range will be unrecognisable in terms of performance, and these boards will go quite quiet. However in the mean time...
</strong><hr></blockquote>
Are you saying that we won't find anything to bitch about? Is that some sort of challenge?
<img src="graemlins/lol.gif" border="0" alt="[Laughing]" /> Watch what happens if Apple releases these 970 mahines and it turns out they are several orders of magnitude faster than todays machines. There will be a banshee wail of screaming/bitching/moaning that Apple has screwed us all again by making our current machines look pathetic in comparison. <img src="graemlins/lol.gif" border="0" alt="[Laughing]" />
I for one am quite eager to see what pops up next but in the meantime I may just have to get the wifey one of those new 17" iMacs to replace her old reliable Rev. A iMac.
That mantra about that slow bus speed throttling the G4 is everywere but were is the evidence for this?
Can anyone show that a dual 1.2 GHz G4 on a G4/400 (with a 100 MHz bus) is much slower CPU wise than a dual 1.25 with a halfway DDR bus at 167 MHz?
According to xlr8yourmac test of dual 1GHz CPUs with 133 and DDR167 the differecen between them is 10% or less even if the DDR is at least 25% faster in the bus speed.
I would guess that a dual 1.42 GHz G4 could saturate the 30 MHz bus on a PM 6100. However, I have yet to see any evidence that the main problem of the G4 is slow bus speed. The fact that that it is a common opinion does not make it true <img src="graemlins/oyvey.gif" border="0" alt="[oyvey]" />
<strong>The aluring siren songs about the bus speed.
That mantra about that slow bus speed throttling the G4 is everywere but were is the evidence for this?....The fact that that it is a common opinion does not make it true <img src="graemlins/oyvey.gif" border="0" alt="[oyvey]" /> </strong><hr></blockquote>
There's a variety of computationally-bound programs designed to take full advantage of multiprocessing that see a miserable speedup going from a single 1GHz G4 to a dual 1GHz G4. That in itself doesn't prove anything - but when the same program sees almost the complete doubling when going from a 500MHz G4 to a dual 500MHz dual.... Strongly indicates that the second G4 isn't doing so much _in_some_cases.
A second important note is that the two G4's share a single bus -> there's conflict there. And it makes a Quad insane. There wouldn't be any screaming about price/performance if there was a real bus + quads available (on the high end, there'd still be millions screaming for a $500 box).
You can calculate the 'max' data consumption rate, it is something like 10x the FSB max throughput, way out of whack. It isn't crippling... in an _single_ CPU situation.
A second important note is that the two G4's share a single bus -> there's conflict there.</strong><hr></blockquote>
Please forgive my ignorance, but this brings up a question for me. How are the duals connected to the FSB? As I understand it, they are connected in such a way that the FSB is part of Motos fab, and Apple cannot change the bus. This led me to assume the FSB was part of the G4 cpu, and that Duals would have two busses? And, if the FSB is not on the cpu but rather on the chipset, what about the design has made, altering it too expensive?
Ok, I assume that the 970 is going to be the next processor for Apple. But here is the rumor I don't get:
"They are working on software so that 2 processors will work seamlessly like 1." If that is true, then why wouldn't they have just asked IBM to make an actual (dual core) Power4 with the Altivec unit???
What is the probability that they will even debut with ANY dualies? I realize their are some gains by using multiple processors, but I would think prices will be fairly high in the beginning when yields of this new processor are low.
Those 2 issues alone make me doubt a lot of the talk that is going on about the 970. Especially when people start spouting off saying "I know a guy who knows a guy that was working on x, y, and z for the dual 970 ..."
I would love something that resembles a fact about the whole situation, but until I see it otherwise I will assume any 970 based mac debuts as a single processor. And I would think that is a tricky situation when you debut a "best" system with a single 1.8 Ghz 970 system next to a dual 1.42 Ghz G4 at "better". At least for the marketing department.
Additonally, just last summer, Philips, Motorola, and STMicroelecronics announced they were preparing a facility capable of churning out 90 nanometer microprocessors on 300mm silicon....by the end of 2002. So if preproduction silicon is coming out by the end of 2002, whats keeping Moto from introducing a 2+GHz G4 on a 90nm process 2Q '03?
Just some thoughts. Any opinions on it?[/QB]<hr></blockquote>
Yeah, here's my thoughts, no way. First off Crolles, the facility you speak of is a R&D center first and foremost. It has limited production capabilities and is more of a pilot line for development work on 90nm and sub 90nm processes.
As for your time frame there is little chance that anyone will beat Intel, IBM, or AMD to 90nm for high performance complex CMOS production. Even they are shooting for 90nm production in Q4 '03 at best. There have been a number of issues that have arisen trying to get 90nm going and now a good segment of the industry has pushed out adoption to late '04 or early '05. It is becoming paramount for designers to take into account the production challenges present at 130nm and below. This means simple scaling is no longer as feasible for a design intended for an older technology like .18um.
Comments
Additonally, just last summer, Philips, Motorola, and STMicroelecronics announced they were preparing a facility capable of churning out 90 nanometer microprocessors on 300mm silicon....by the end of 2002. So if preproduction silicon is coming out by the end of 2002, whats keeping Moto from introducing a 2+GHz G4 on a 90nm process 2Q '03?
Just some thoughts. Any opinions on it?
[QB]Forgive me if this has been asked and answered, but what is the shortest time between upgrades that Apple has ever done?
[QB]<hr></blockquote>
I think that the PM G4 came only three months or so of the BW PM G3. <a href="http://www.apple-history.com"; target="_blank">www.apple-history.com</a> is slower than dirt right now, or I'd check for sure.
[quote] It'll also have a DMA engine and perhaps the DSP-like features that were talked about last year. We can hope for a direct AGP 8x port as well. Is this what you are refering to TO? <hr></blockquote>
Well, those wouldn't be suprises, would they? Well, maybe the DSP.
[quote]Originally posted by mooseman:
<strong>...seems iteresting that while the 970 is garnering the lion's share of attention, the fact that a 1.42GHz G4 came out on a 180nm process has escaped mention.
Additonally, just last summer, Philips, Motorola, and STMicroelecronics announced they were preparing a facility capable of churning out 90 nanometer microprocessors on 300mm silicon....by the end of 2002. So if preproduction silicon is coming out by the end of 2002, whats keeping Moto from introducing a 2+GHz G4 on a 90nm process 2Q '03?
Just some thoughts. Any opinions on it?</strong><hr></blockquote>
I've been talking about that for a while now.
If Mot actually pulls this off this year, they'll suddenly have an attractive little chip. Perfect for iBooks.
But this line of discussion is more appropriate for the 7447/7457 thread next door.
[ 02-04-2003: Message edited by: Amorph ]</p>
Apple (and, therefore, we) have nothing to lose.
[ 02-04-2003: Message edited by: Bigc ]</p>
<strong>...seems iteresting that while the 970 is garnering the lion's share of attention, the fact that a 1.42GHz G4 came out on a 180nm process has escaped mention.
Additonally, just last summer, Philips, Motorola, and STMicroelecronics announced they were preparing a facility capable of churning out 90 nanometer microprocessors on 300mm silicon....by the end of 2002. So if preproduction silicon is coming out by the end of 2002, whats keeping Moto from introducing a 2+GHz G4 on a 90nm process 2Q '03?
Just some thoughts. Any opinions on it?</strong><hr></blockquote>
Make it 1.6, 1.8, 2.0, 500 GHz...
if they don't change the FSB, who cares.
[ 02-04-2003: Message edited by: boots ]</p>
<strong>
Make it 1.6, 1.8, 2.0, 500 GHz...
if they don't change the FSB, who cares.
</strong><hr></blockquote>
You're saying you wouldn't take a 5 watt 1.5 GHz G4+ w/ 512K L2 cache? The FSB is important folks, but its not everything. And the 7457-RM is always a possibility for early 2004 according to Moto's roadmap.
<strong>
You're saying you wouldn't take a 5 watt 1.5 GHz G4+ w/ 512K L2 cache? The FSB is important folks, but its not everything. And the 7457-RM is always a possibility for early 2004 according to Moto's roadmap.</strong><hr></blockquote>
I don't know about boots, but I wouldn't. Really, the CPU has been fast enough for me for a while now. What I can't stand is the overall system architecture. slow disks, slow FSB, slow memory, slow PCI, slow AGP, mediocre built-in sound.
I'm a big fan of fast and wide.
having said that I don't think my B&W can hold out much longer. As soon as the 9700 Pro becomes available I'll pick up a new machine and then sell it when something I like comes out.
...Additonally, just last summer, Philips, Motorola, and STMicroelecronics announced they were preparing a facility capable of churning out 90 nanometer microprocessors on 300mm silicon....by the end of 2002. So if preproduction silicon is coming out by the end of 2002, whats keeping Moto from introducing a 2+GHz G4 on a 90nm process 2Q '03?
...Any opinions on it?<hr></blockquote>
I remember those press releases. I personally got excited. They mentioned something like high end processors ?? manufactured by the end of 2002.
My opinion now, press release bologna. Suprise me Motorola, let's have another press release announcing ANYTHING is being manufactured using a 0.09µm process - ANYTHING AT ALL.
edit: originally wrote 0.9µm process above. Ha, I actually showed Motorola going backwards.
[ 02-07-2003: Message edited by: rickag ]</p>
I think that we are not seeing the real performane of the current processors because of the bottlekneck caused by the FSB. If we can get a decent FSB then the performance on current machines and processors will leap.
I doubt that Moto would make the current processors on the 0.09 process, I am sure they are fully aware of the shortcommings too. Any move to 0.09 would be accompanied with a revised FSB.
<strong>It's clear that next year the whole range will be unrecognisable in terms of performance, and these boards will go quite quiet. However in the mean time...
</strong><hr></blockquote>
Are you saying that we won't find anything to bitch about? Is that some sort of challenge?
<strong>
Are you saying that we won't find anything to bitch about? Is that some sort of challenge?
Well what's wrong with being an optimist.
I for one am quite eager to see what pops up next but in the meantime I may just have to get the wifey one of those new 17" iMacs to replace her old reliable Rev. A iMac.
That mantra about that slow bus speed throttling the G4 is everywere but were is the evidence for this?
Can anyone show that a dual 1.2 GHz G4 on a G4/400 (with a 100 MHz bus) is much slower CPU wise than a dual 1.25 with a halfway DDR bus at 167 MHz?
According to xlr8yourmac test of dual 1GHz CPUs with 133 and DDR167 the differecen between them is 10% or less even if the DDR is at least 25% faster in the bus speed.
I would guess that a dual 1.42 GHz G4 could saturate the 30 MHz bus on a PM 6100. However, I have yet to see any evidence that the main problem of the G4 is slow bus speed. The fact that that it is a common opinion does not make it true <img src="graemlins/oyvey.gif" border="0" alt="[oyvey]" />
<strong>The aluring siren songs about the bus speed.
That mantra about that slow bus speed throttling the G4 is everywere but were is the evidence for this?....The fact that that it is a common opinion does not make it true <img src="graemlins/oyvey.gif" border="0" alt="[oyvey]" /> </strong><hr></blockquote>
There's a variety of computationally-bound programs designed to take full advantage of multiprocessing that see a miserable speedup going from a single 1GHz G4 to a dual 1GHz G4. That in itself doesn't prove anything - but when the same program sees almost the complete doubling when going from a 500MHz G4 to a dual 500MHz dual.... Strongly indicates that the second G4 isn't doing so much _in_some_cases.
A second important note is that the two G4's share a single bus -> there's conflict there. And it makes a Quad insane. There wouldn't be any screaming about price/performance if there was a real bus + quads available (on the high end, there'd still be millions screaming for a $500 box).
You can calculate the 'max' data consumption rate, it is something like 10x the FSB max throughput, way out of whack. It isn't crippling... in an _single_ CPU situation.
<strong>
A second important note is that the two G4's share a single bus -> there's conflict there.</strong><hr></blockquote>
Please forgive my ignorance, but this brings up a question for me. How are the duals connected to the FSB? As I understand it, they are connected in such a way that the FSB is part of Motos fab, and Apple cannot change the bus. This led me to assume the FSB was part of the G4 cpu, and that Duals would have two busses? And, if the FSB is not on the cpu but rather on the chipset, what about the design has made, altering it too expensive?
"They are working on software so that 2 processors will work seamlessly like 1." If that is true, then why wouldn't they have just asked IBM to make an actual (dual core) Power4 with the Altivec unit???
What is the probability that they will even debut with ANY dualies? I realize their are some gains by using multiple processors, but I would think prices will be fairly high in the beginning when yields of this new processor are low.
Those 2 issues alone make me doubt a lot of the talk that is going on about the 970. Especially when people start spouting off saying "I know a guy who knows a guy that was working on x, y, and z for the dual 970 ..."
I would love something that resembles a fact about the whole situation, but until I see it otherwise I will assume any 970 based mac debuts as a single processor. And I would think that is a tricky situation when you debut a "best" system with a single 1.8 Ghz 970 system next to a dual 1.42 Ghz G4 at "better". At least for the marketing department.
[QB
Additonally, just last summer, Philips, Motorola, and STMicroelecronics announced they were preparing a facility capable of churning out 90 nanometer microprocessors on 300mm silicon....by the end of 2002. So if preproduction silicon is coming out by the end of 2002, whats keeping Moto from introducing a 2+GHz G4 on a 90nm process 2Q '03?
Just some thoughts. Any opinions on it?[/QB]<hr></blockquote>
Yeah, here's my thoughts, no way. First off Crolles, the facility you speak of is a R&D center first and foremost. It has limited production capabilities and is more of a pilot line for development work on 90nm and sub 90nm processes.
As for your time frame there is little chance that anyone will beat Intel, IBM, or AMD to 90nm for high performance complex CMOS production. Even they are shooting for 90nm production in Q4 '03 at best. There have been a number of issues that have arisen trying to get 90nm going and now a good segment of the industry has pushed out adoption to late '04 or early '05. It is becoming paramount for designers to take into account the production challenges present at 130nm and below. This means simple scaling is no longer as feasible for a design intended for an older technology like .18um.