[quote]Originally posted by Transcendental Octothorpe:
<strong>Well, I have not info from Apple. Just IBM and Mot.
All I know is when Apple is supposed to get chips, and how long they've had to design with them.
It is my opinion (seriously, all my info could be wrong or change) that the next PM update will include a 970, and that it will happen before fall.
Maybe my judgement is clouded, as I (like the rest of us) really want a 970 PM. See my sig. It the one thing that will finally make me drop the couple grand.</strong><hr></blockquote>
I know what you mean. The 970 will really give me a reason to get a powermac. I can't imagine what os x would be like on that computer not to mention the render times for 3d graphics.
Yea, I had a little inside info a while back, and I can tell you everything I heard on the subject. But you guys already know it all. The 970 is coming this year and it will kick Intel's little fat ass all the way to china town! hehe Any doubters can shove it.
<strong>Yea, I had a little inside info a while back, and I can tell you everything I heard on the subject. But you guys already know it all. The 970 is coming this year and it will kick Intel's little fat ass all the way to china town! hehe Any doubters can shove it.
The minute I see PPC970 on apple's site is the minute I hit BUY NOW. I'm just wondering if I should go the the 23" one 20 inch LCD. I can't wait much longer COME ON APPLE!!!
You know it would be funny if apple just did a quite update over night and added the 970 to the Powermacs and didn't say a word. We would all be trying to figure out what was going on. lol!
So your new news says to me that the 970 has successfully reached sampling and the first samples have gone into testing and everything is looking good. Really good. Remember that IBM estimated SPECmarks for the 970. They can't bump the clock rate too much without increasing the power consumption and forcing the bus speeds higher (which could limit how much Apple could get out of the higher speeds), but at the specified clock rates the performance could turn out to be higher than the predictions. The timing is about right for this kind of info to start surfacing.
March production ramp plus time to accumulate enough stock and put the new PowerMacs into production says to me that an August - September timeframe is still just about right. I'll bet that we see a developer preview at WWDC and perhaps the rollout of the 64-bit version of MacOS X.
Well Programmer is most likely right about not seeing the 970 till september. Well my birthday is in September so that would be fine. I'll get myself a nice present ( about time someone did).
But if apple has been working closely with IBM could we not see a 970 in June? I really hope we do.
Well Programmer is most likely right about not seeing the 970 till september. Well my birthday is in September so that would be fine. I'll get myself a nice present ( about time someone did).
But if apple has been working closely with IBM could we not see a 970 in June? I really hope we do.</strong><hr></blockquote>
You can hope for whatever you want, but that doesn't make it any more likely.
<strong>Well Programmer is most likely right about not seeing the 970 till september. Well my birthday is in September so that would be fine. I'll get myself a nice present ( about time someone did).
But if apple has been working closely with IBM could we not see a 970 in June? I really hope we do.</strong><hr></blockquote>
Knowing what is a lot easier than knowing when. Even engineers working on such projects don't know exactly when they'll be done.
<strong>You know it would be funny if apple just did a quite update over night and added the 970 to the Powermacs and didn't say a word. We would all be trying to figure out what was going on. lol!</strong><hr></blockquote>
there is no over night on the internet. the world is bigger than the north american continent. for instance in europe are more people connected to the internet than in america. so most people will know about this and you are the last one to know because you were sleeping. and that would be very bad
there is no over night on the internet. the world is bigger than the north american continent. for instance in europe are more people connected to the internet than in america. so most people will know about this and you are the last one to know because you were sleeping. and that would be very bad</strong><hr></blockquote>
Depends on how it is architected; the way the dual cores work in the Power4, they appear as one processor.</strong><hr></blockquote>
Do you have an technical URL references about this technology, Moki? I'm very curious at what level these "appear as one processor".
[EDIT] Nevermind I went and looked at the Wind River stuff. Careful what talking about how it makes "thing look like a single processor". According to my definition of what a single processor looks like, it does not do this. To take advantage of multiple processors the application must still be written as multiple threads or tasks. This means it doesn't look at more like a single processor than the current Apple duals, except that resource sharing between the processors might be somewhat improved. As I read it the intention of this system is to support NUMA systems and clusters, making them seem like they are traditional SMP designs. Multiple processors still can't speed up a single thread, but multiple threads can be spread across disparate processors.
Do you have an technical URL references about this technology, Moki? I'm very curious at what level these "appear as one processor".</strong><hr></blockquote>
Back in August or September, moki said Apple got a shipment of 1.4Ghz CPUs from Motorola. It took 4 months for those processors to actually show up in new computers. With that in mind, I would expect it to take between 2 and 6 months after "March" for there to be PPC 970 Macs available. So between May and September sounds realistic to me. October or November are even feasible, since this is all new so it may take more time to test and refine such machines.
I wouldn't be surprised if there was a minor PowerMac bump in the spring that puts the 7457 into at least the high end power mac and drops variants of the current mid and high models down to low and mid.
When the 970 does become available, I don't expect there to be some PowerMacs using the 970 and some using the G4 at the same time. Once the 970 is in PowerMacs, I think the G4 will be used solely in laptops and consumer products like the iMac.
<strong>So your new news says to me that the 970 has successfully reached sampling and the first samples have gone into testing and everything is looking good. Really good. Remember that IBM estimated SPECmarks for the 970. They can't bump the clock rate too much without increasing the power consumption and forcing the bus speeds higher (which could limit how much Apple could get out of the higher speeds), but at the specified clock rates the performance could turn out to be higher than the predictions. The timing is about right for this kind of info to start surfacing.
March production ramp plus time to accumulate enough stock and put the new PowerMacs into production says to me that an August - September timeframe is still just about right. I'll bet that we see a developer preview at WWDC and perhaps the rollout of the 64-bit version of MacOS X.</strong><hr></blockquote>
You don't think there is a variable that can allow for 3x and 4x ratios in bus speed? Maybe even half integer increments of 2.5 and 3.5? I fand it hard to believe they would limit the bus to a static ratio. I could be wrong. By "could be" I mean "probably am".
<strong>You don't think there is a variable that can allow for 3x and 4x ratios in bus speed? Maybe even half integer increments of 2.5 and 3.5? I fand it hard to believe they would limit the bus to a static ratio. I could be wrong. By "could be" I mean "probably am". </strong><hr></blockquote>
I don't know... the IBM presentation was pretty clear that the bus speed is half the processor speed. Period. The other documents I've seen do nothing to dissuade me from this notion. Its also a significantly different bus design than MPX, and the emphasis is clearly on high bandwidth. Since there is no L3 cache support my suspicion is that they aren't interested in being able to cripple the processor's FSB.
Its worth pointing out that the FSB is just a connection from processor(s) to the companion chip, and this will likely be a tightly controlled link of minimal length. Combined with its high clock rate this would tend to make me think that the companion chip will sit on a high quality daughtercard with the processor(s). It remains to be seen where the memory sits, and how the connection to the southbridge on the motherboard is done. In this kind of a setup Apple might be able to support very high clock rates on the FSB (i.e. >1 GHz).
...Combined with its high clock rate this would tend to make me think that the companion chip will sit on a high quality daughtercard with the processor(s)processor's FSB....</strong><hr></blockquote>
Yes, from the looks of everything on the new companion chip (can anyone guess the name?), I would think it would have to be extreamly close.
BTW, I think we'll all be pleasently suprised when we see this new chip.
Comments
<strong>Well, I have not info from Apple. Just IBM and Mot.
All I know is when Apple is supposed to get chips, and how long they've had to design with them.
It is my opinion (seriously, all my info could be wrong or change) that the next PM update will include a 970, and that it will happen before fall.
Maybe my judgement is clouded, as I (like the rest of us) really want a 970 PM. See my sig. It the one thing that will finally make me drop the couple grand.</strong><hr></blockquote>
I know what you mean. The 970 will really give me a reason to get a powermac. I can't imagine what os x would be like on that computer not to mention the render times for 3d graphics.
[ 01-31-2003: Message edited by: Algol ]</p>
<strong>Yea, I had a little inside info a while back, and I can tell you everything I heard on the subject. But you guys already know it all. The 970 is coming this year and it will kick Intel's little fat ass all the way to china town! hehe
[ 01-31-2003: Message edited by: Algol ]</strong><hr></blockquote>
Heres to hoping apple actually comes through with our expectations.
You know it would be funny if apple just did a quite update over night and added the 970 to the Powermacs and didn't say a word. We would all be trying to figure out what was going on. lol!
March production ramp plus time to accumulate enough stock and put the new PowerMacs into production says to me that an August - September timeframe is still just about right. I'll bet that we see a developer preview at WWDC and perhaps the rollout of the 64-bit version of MacOS X.
Well Programmer is most likely right about not seeing the 970 till september. Well my birthday is in September so that would be fine. I'll get myself a nice present ( about time someone did).
But if apple has been working closely with IBM could we not see a 970 in June? I really hope we do.
<strong>I WANT ONE NOW!
Well Programmer is most likely right about not seeing the 970 till september. Well my birthday is in September so that would be fine. I'll get myself a nice present ( about time someone did).
But if apple has been working closely with IBM could we not see a 970 in June? I really hope we do.</strong><hr></blockquote>
You can hope for whatever you want, but that doesn't make it any more likely.
<strong>Hm, would multiple cores "act" much like multiple processors? Hm...</strong><hr></blockquote>
Depends on how it is architected; the way the dual cores work in the Power4, they appear as one processor.
<strong>Well Programmer is most likely right about not seeing the 970 till september. Well my birthday is in September so that would be fine. I'll get myself a nice present ( about time someone did).
But if apple has been working closely with IBM could we not see a 970 in June? I really hope we do.</strong><hr></blockquote>
Knowing what is a lot easier than knowing when. Even engineers working on such projects don't know exactly when they'll be done.
<strong>You know it would be funny if apple just did a quite update over night and added the 970 to the Powermacs and didn't say a word. We would all be trying to figure out what was going on. lol!</strong><hr></blockquote>
there is no over night on the internet. the world is bigger than the north american continent. for instance in europe are more people connected to the internet than in america. so most people will know about this and you are the last one to know because you were sleeping. and that would be very bad
<strong>
there is no over night on the internet. the world is bigger than the north american continent. for instance in europe are more people connected to the internet than in america. so most people will know about this and you are the last one to know because you were sleeping. and that would be very bad</strong><hr></blockquote>
For broadband, at least, this is not true:
<a href="http://cyberatlas.internet.com/markets/broadband/article/0,,10099_783401,00.html"; target="_blank">http://cyberatlas.internet.com/markets/broadband/article/0,,10099_783401,00.html</a>;
...do you have any stats on how many people are online in the EU?
<strong>
Depends on how it is architected; the way the dual cores work in the Power4, they appear as one processor.</strong><hr></blockquote>
Do you have an technical URL references about this technology, Moki? I'm very curious at what level these "appear as one processor".
[EDIT] Nevermind I went and looked at the Wind River stuff. Careful what talking about how it makes "thing look like a single processor". According to my definition of what a single processor looks like, it does not do this. To take advantage of multiple processors the application must still be written as multiple threads or tasks. This means it doesn't look at more like a single processor than the current Apple duals, except that resource sharing between the processors might be somewhat improved. As I read it the intention of this system is to support NUMA systems and clusters, making them seem like they are traditional SMP designs. Multiple processors still can't speed up a single thread, but multiple threads can be spread across disparate processors.
[ 02-02-2003: Message edited by: Programmer ]</p>
<strong>
Do you have an technical URL references about this technology, Moki? I'm very curious at what level these "appear as one processor".</strong><hr></blockquote>
This is good for a start, I think: <a href="http://www.digit-life.com/articles/ibmpower4/"; target="_blank">http://www.digit-life.com/articles/ibmpower4/</a>;
<strong>
This is good for a start, I think: <a href="http://www.digit-life.com/articles/ibmpower4/"; target="_blank">http://www.digit-life.com/articles/ibmpower4/</a></strong><hr></blockquote>;
Interesting article, albeit a little old. Almost the last line, however, is quite interesting:
[quote]
Will SMT be integrated into personal POWER4 processors?
<hr></blockquote>
Yes, I've been wondering that too.
[ 02-02-2003: Message edited by: Programmer ]</p>
Back in August or September, moki said Apple got a shipment of 1.4Ghz CPUs from Motorola. It took 4 months for those processors to actually show up in new computers. With that in mind, I would expect it to take between 2 and 6 months after "March" for there to be PPC 970 Macs available. So between May and September sounds realistic to me. October or November are even feasible, since this is all new so it may take more time to test and refine such machines.
I wouldn't be surprised if there was a minor PowerMac bump in the spring that puts the 7457 into at least the high end power mac and drops variants of the current mid and high models down to low and mid.
When the 970 does become available, I don't expect there to be some PowerMacs using the 970 and some using the G4 at the same time. Once the 970 is in PowerMacs, I think the G4 will be used solely in laptops and consumer products like the iMac.
<strong>...I think the G4 will be used solely in laptops and consumer products like the iMac.</strong><hr></blockquote>
If Motorola ever produces a cpu on the 0.13µm process.
<strong>So your new news says to me that the 970 has successfully reached sampling and the first samples have gone into testing and everything is looking good. Really good. Remember that IBM estimated SPECmarks for the 970. They can't bump the clock rate too much without increasing the power consumption and forcing the bus speeds higher (which could limit how much Apple could get out of the higher speeds), but at the specified clock rates the performance could turn out to be higher than the predictions. The timing is about right for this kind of info to start surfacing.
March production ramp plus time to accumulate enough stock and put the new PowerMacs into production says to me that an August - September timeframe is still just about right. I'll bet that we see a developer preview at WWDC and perhaps the rollout of the 64-bit version of MacOS X.</strong><hr></blockquote>
You don't think there is a variable that can allow for 3x and 4x ratios in bus speed? Maybe even half integer increments of 2.5 and 3.5? I fand it hard to believe they would limit the bus to a static ratio. I could be wrong. By "could be" I mean "probably am".
<strong>You don't think there is a variable that can allow for 3x and 4x ratios in bus speed? Maybe even half integer increments of 2.5 and 3.5? I fand it hard to believe they would limit the bus to a static ratio. I could be wrong. By "could be" I mean "probably am".
I don't know... the IBM presentation was pretty clear that the bus speed is half the processor speed. Period. The other documents I've seen do nothing to dissuade me from this notion. Its also a significantly different bus design than MPX, and the emphasis is clearly on high bandwidth. Since there is no L3 cache support my suspicion is that they aren't interested in being able to cripple the processor's FSB.
Its worth pointing out that the FSB is just a connection from processor(s) to the companion chip, and this will likely be a tightly controlled link of minimal length. Combined with its high clock rate this would tend to make me think that the companion chip will sit on a high quality daughtercard with the processor(s). It remains to be seen where the memory sits, and how the connection to the southbridge on the motherboard is done. In this kind of a setup Apple might be able to support very high clock rates on the FSB (i.e. >1 GHz).
<strong>
...Combined with its high clock rate this would tend to make me think that the companion chip will sit on a high quality daughtercard with the processor(s)processor's FSB....</strong><hr></blockquote>
Yes, from the looks of everything on the new companion chip (can anyone guess the name?), I would think it would have to be extreamly close.
BTW, I think we'll all be pleasently suprised when we see this new chip.