Arent Orion something with stars (And a Metallica song) and not a desert?
Orion is a legendary Greek warrior who was turned into a constellation by the gods. Among the "stars" that make up the constellation are the supergiants Rigel and Betelgeuse, and the Orion Nebula.
The change in name might have something to do with the fact that it will mark the end of the G3 as it has existed, and also something to do with the fact that a constellation is a single figure made up of many individual stars.
Quote:
Riiiight. Photoshop already screeeams!
Whether Photoshop screams will be Adobe's problem. It certainly could...
I will have to agree with several other posters...
This is the most exciting stuff in Future Hardware in some time...
Now if we could just get Kormac in here to verify!!!
No, really, I do find the idea of Apple using some derivative of IBM PPC4xx series CPUS in a cell-configuration for future PowerBooks to be VERY exciting!
Rmember the old adage folks; Many hands make light work!
Now if we could get Apple to purchase Alias from SGI...
Exactly my point. Many companies doesnt take the time to optimize their apps properly... And some of them takes years to do it!
And Adobe seems to favor the dark side more and more.. Photoshop 7.0.1 is pretty sluggish at some points..
I think Adobe feels why put the extra work in on the Mac side to optimize for dual processors or altivec or 64-bit or whatever when on the "dark side" they can just throw crap at a 3Ghz+ P4 and have the same or in many cases better results
its a shame but, well, guess in a way it kind of makes sense.
Seems to me the only sure-fire way to get properly optimized software is if Apple actually owns the software in question...
After all, if Apple owned Alias right now, I would bet we would have a fully-optimized version of Maya Unlimited for Mac OS X/G5s already...
As opposed to a less-than-optimized version of Maya Complete...
In a perfect world, Apple would buy Alias, port Unlimited over to OS X, secure RenderMan from Pixar and integrate it as the default renderer in Maya, and then come out with a complete suite of VFX/DCC/3D tools...
The all Apple pipeline, both in hardware AND in software...
MacRonin: I've been aware of this for a long time, and it's actually my main reason for giving him a pretty harsh response initially. I'm convinced this Nr9 is the same Nr9 as on Arstechnica. His posting style is equal, and I found this to be equally ridiculous as his trolling over at Ars. I seriously doubt that Nr9 has any insider information, but we'll just have to wait and see.
This is by far the most interesting discussion here on FH in a long, long time. With that being said, I do hope that this praise isn't given to a thread started by a troll with sinister plans...
I'm convinced this Nr9 is the same Nr9 as on Arstechnica. His posting style is equal...
I agree! His way of writing is very similar. He spells rather poorly, fails to put capital letters when starting new sentences and his grammar is flawed, sometimes leaving out entire words. It's very likely the same guy.
Nope no desire for an expensive ibook. What the ibook had was good battery life and decent (but by no means great) performance. I'm all for anything that can increase battery life and at the same time increase perfromance.
If they avoid the MCM route and where able to implement two SMP SOC processors we could end up with the best of both worlds. Reasonably good processor speed and extended battery life. What would be realy neat would be a controll panel with little switches that allowed you to put one or more of your processors to sleep.
I could see it now, 4 beavers knawing at their trees, click on the beaver (which represents a processor) and the beaver goes to sleep. Like wise a little store house in the Beavers den expands to represent increased battery life. Apple really needs to do this, I'd even sell them the rights cheap.
Dave
Quote:
Originally posted by Barto
Do you want an iBook that costs more than a PowerBook?
Thought not. This is a cool direction, but as with any new direction, expensive initially.
I followed one of the Ars Battlefront threads held up as an example of Nr9's trolling, and it's a claim that Macs are better than PCs because they weigh more, and so they're less likely to fall off desks in earthquakes. Now, I'm almost 100% positive that is trolling, given that it's a brilliant parody of the sorts of claims made in that forum, and the overzealous denizens of the Battlefront bit down hard on it.
I grew up on USENET. Trolling of this kind is an art form and a brutally effective form of parody. If he was in fact trolling the Battlefront, I can't judge him to harshly. It's a profoundly silly forum, not least for being full of overly earnest people who take irrelevant metrics, dubious engineering claims, and debates over platform superiority far too seriously. If he can get them riled up over the merits of engineering cases for their ability to stay upright in southeast Asian earthquakes, more power to him.
That said, how about the PowerBook G5? If he's trolling us, at least we've bettered the Ars crowd insofar as we've turned it into a good discussion. Let's keep that up, shall we?
I followed one of the Ars Battlefront threads held up as an example of Nr9's trolling, and it's a claim that Macs are better than PCs because they weigh more, and so they're less likely to fall off desks in earthquakes. Now, I'm almost 100% positive that is trolling, given that it's a brilliant parody of the sorts of claims made in that forum, and the overzealous denizens of the Battlefront bit down hard on it.
I grew up on USENET. Trolling of this kind is an art form and a brutally effective form of parody. If he was in fact trolling the Battlefront, I can't judge him to harshly. It's a profoundly silly forum, not least for being full of overly earnest people who take irrelevant metrics, dubious engineering claims, and debates over platform superiority far too seriously. If he can get them riled up over the merits of engineering cases for their ability to stay upright in southeast Asian earthquakes, more power to him.
That said, how about the PowerBook G5? If he's trolling us, at least we've bettered the Ars crowd insofar as we've turned it into a good discussion. Let's keep that up, shall we?
While he may have been frequenting the Ars Battlefront simply to post humorous replies and poke some fun at the people there, starting threads like this doesn't really qualify him for a front-row seat in church on sunday.
As much as I am enjoying this thread, I am rather ingorant as to how processors really works. Is there anywhere on the internet that I can visit that explains (in rather laymen-terms) how a processor is constructed and how it works? I suspect that would further enhance my enjoyment of this thread.
I seem to recall something written by John Siracusa over at Ars Technica regarding the G5. Is that a good place to start or are there better sites that explain processor design even simpler?
[EDIT: It wasn't written by John Siracusa but by Jon "Hannibal" Stokes.]
A rumor it is; but the concept is something to think about. If you take a couple of things into consideration, such as Apples commitment to multi threading and the use of vector operations, then you could see where this is a very real possibility. Now this could be a logn term joke who knows but it is none the less completely possible, though as mentioned before I really thing such a machine should be targeted at the low pwoer market and not the PowerBook market.
To keep things truely Symetric they would have to have a vector unit and FPU attached to each processor. So you would never be doing vector operation any greater than was implemented for each processor. You can not think of this a 512 bit vector operations, what you have would be the ability to process four threads of vector operations at a time. This would be absolutely wonderful though it may be a power usage killer.
The nice thing is that it may not reguire a rewrite at all, just about any multithread app that may have more than one thread doing vector operations would benefit. Along with that the syste would have access to vector operations. Yes heavy single thread vector operations would be slow, but do realize that only that app would be slower any other running software would not be impacted.
Why you would want to elimenate multi threading is beyond me. Multithreading is what makes this sort of machine feasable. Sure a CPU bound process will perform poorly but how much software out there is really that bound up. Lets face it the OS would benefit, just about every application written in the last few years would benefit, people who run multiple programs at anyone time will beenfit. The only people who would loose would be those running CPU bound programs that don;t multi thread well and don't make much use of system resources. Sure there are some programs like this but not many.
Alright who really cares about bench marks anyways, this is an Apple forum right. Really Apple has suffered for years with poorly performing machines, when it comes to bench marks, whats to stop this. Plus any reasonable marketing idiot will come up with multi thread benchmarks that show the potential of this machine. Further if marketed towards resonably intelligent customers 4X SMP will be a big draw in and of itself. It would also be reasonable to assume that bandwidth and VMX issues would be addressed so the 700 MHz performance would exceed the current results that come from the 750 series.
Like I said I have alot of reservations about the reality of this machine. On the other hand the concept is sound and would leverage in a very positive manner some of Apple greatest technology advantages. Sitting here in NY I don't know what Apple has up its sleeves, what I do know is that the sensible thing to do would be to introduce a low power 970 in the powerbook. This would be playing it safe for Apple and would satisfy the lust that their customers have for such a machine. One thing is for certain, Apple is about the only manufacture that could pull this off, that is a massive SMP portable.
Thanks
Dave
Quote:
Originally posted by Zapchud
Even though Amorph and Wizard69 did a fair job in getting something remotely credible out of this rumor, I still find this rumor to have way too many unanswered questions about it.
How will they get Altivec to perform acceptably?
Like it's been proposed now, we wind up with 4 Altivec-units. This would be pretty equivalent to a very low-clocked, but flexible 512-bit Altivec.
Even 256-bit Altivec has been doomed into the land of the law of diminishing returns, because it will be very hard to find enough parallelism in the code to exploit this (and it would make the unit itself a transistor monster, but that's not the concern here).
Yes, you could probably get acceptable performance out of these four units, if you're skilled enough as a programmer to manage to split the code onto all the units, but I believe that's pretty hard, and more importantly: It would require a rewrite of all code.
On regular code, optimized for the 970, and old (legacy) AV-code, it would perform at ~30% compared to the 970, because of the low clock-frequency, which is pretty low in my book.
This could be possibly be solved with the technology that would have to be the key to the biggest problem of this design entirely: To make it possible for all the cores to execute on the same thread, i.e. eliminate the need for multithreading. (And don't ask me how to do that, if it's even possible)
Without this, this pseudo-G5 Powerbook would be a terrible machine for all things involving less than 4 threads. A typical example of this is benchmarks. Benchmarks are almost always performed with the benchmark itself as the only running CPU-intensive task. And the typical benchmark (especially the cross-platform ones) is not multithreaded.
So unless some breakthrough is achieved relative to multi/single-threading, this machine would probably stand out as very slow in every aspect of benchmarking, except where they tested multitasking extensively.
I seem to recall something written by John Siracusa over at Ars Technica regarding the G5. Is that a good place to start or are there better sites that explain processor design even simpler?
[EDIT: It wasn't written by John Siracusa but by Jon "Hannibal" Stokes.]
Hannibal's articles on CPU design are excellent. Don't be afraid to follow the links, either. Happy reading.
I suppose that Ars would be ok to start. The problem is that if you have no electronics background at all it may take awhile to digest the material.
Honestly the best way to get started with increasing your knowledge of microprocssors is to get an 8 bit development system or trainer board and crack the books. What you will find is that to really get an understanding of a mircoproccesor requires that you understand both programming and a little electronics. Unfortunately its been so long I really don't know what or whom to suggest as a vendor for such materials. the major suppliers would be a good place to start.
A more modern approach and probally alot cheaper would be to get one of the free microprocessor simulators that float around the internet. I've heard there are good ones out there, maybe someone can pipe in with a suggestion. A simulator and a few good books for the processor being simulated will get you started. The board approach above is nicer if you can afford it, writing programs to blink lights and drive motors can pull you in deep.
There is a bit of a jump from a 8Bit microproccesor to the PPC. The PPC is really close to being a mainframe processor on a chip, thus has its own quirks. In anyevent the concepts transfer without issue.
After writing all of this all I can say is read Hannibal's materials if you like, but without a back ground it may not be usefull. If however your interest is tweaked then you have a couple of ideas to consider above.
DAve
Quote:
Originally posted by KANE
As much as I am enjoying this thread, I am rather ingorant as to how processors really works. Is there anywhere on the internet that I can visit that explains (in rather laymen-terms) how a processor is constructed and how it works? I suspect that would further enhance my enjoyment of this thread.
I seem to recall something written by John Siracusa over at Ars Technica regarding the G5. Is that a good place to start or are there better sites that explain processor design even simpler?
[EDIT: It wasn't written by John Siracusa but by Jon "Hannibal" Stokes.]
Comments
Originally posted by T'hain Esh Kelch
Arent Orion something with stars (And a Metallica song) and not a desert?
Orion is a legendary Greek warrior who was turned into a constellation by the gods. Among the "stars" that make up the constellation are the supergiants Rigel and Betelgeuse, and the Orion Nebula.
The change in name might have something to do with the fact that it will mark the end of the G3 as it has existed, and also something to do with the fact that a constellation is a single figure made up of many individual stars.
Riiiight. Photoshop already screeeams!
Whether Photoshop screams will be Adobe's problem. It certainly could...
This is the most exciting stuff in Future Hardware in some time...
Now if we could just get Kormac in here to verify!!!
No, really, I do find the idea of Apple using some derivative of IBM PPC4xx series CPUS in a cell-configuration for future PowerBooks to be VERY exciting!
Rmember the old adage folks; Many hands make light work!
Now if we could get Apple to purchase Alias from SGI...
Originally posted by MacRonin
Now if we could get Apple to purchase Alias from SGI...
You just never give up, do ya?
Originally posted by Amorph
Whether Photoshop screams will be Adobe's problem. It certainly could...
Exactly my point. Many companies doesnt take the time to optimize their apps properly... And some of them takes years to do it!
And Adobe seems to favor the dark side more and more.. Photoshop 7.0.1 is pretty sluggish at some points..
Originally posted by T'hain Esh Kelch
Exactly my point. Many companies doesnt take the time to optimize their apps properly... And some of them takes years to do it!
And Adobe seems to favor the dark side more and more.. Photoshop 7.0.1 is pretty sluggish at some points..
I think Adobe feels why put the extra work in on the Mac side to optimize for dual processors or altivec or 64-bit or whatever when on the "dark side" they can just throw crap at a 3Ghz+ P4 and have the same or in many cases better results
its a shame but, well, guess in a way it kind of makes sense.
Originally posted by Rhumgod
You just never give up, do ya?
NOPE!
Seems to me the only sure-fire way to get properly optimized software is if Apple actually owns the software in question...
After all, if Apple owned Alias right now, I would bet we would have a fully-optimized version of Maya Unlimited for Mac OS X/G5s already...
As opposed to a less-than-optimized version of Maya Complete...
In a perfect world, Apple would buy Alias, port Unlimited over to OS X, secure RenderMan from Pixar and integrate it as the default renderer in Maya, and then come out with a complete suite of VFX/DCC/3D tools...
The all Apple pipeline, both in hardware AND in software...
Hey! Get that zealot brand away from me!
1. Nr9 was deprived of love as a child... or he really has inside information. Apple legal is perking their ears.
2. The idea of a quad CPU PB before a quad CPU PM is interesting.
http://episteme.arstechnica.com/6/ub...5231&m=7951003
Seems to hold some contention on our friend Nr9, and whether or not he is actually legit, or just another troll...
Here is his posting history over there...
http://episteme.arstechnica.com/6/ub...562&u=57509882
Apparently he has been banned from the arstech forums for excessive trolling...
Wondering if this is the same guy?!?
Comments?
Not trying to start shit, just trying to check the overall spin on this subject...
Originally posted by MacRonin
This same subject has leaped over to the arstech forums...
http://episteme.arstechnica.com/6/ub...5231&m=7951003
Seems to hold some contention on our friend Nr9, and whether or not he is actually legit, or just another troll...
Here is his posting history over there...
http://episteme.arstechnica.com/6/ub...562&u=57509882
Apparently he has been banned from the arstech forums for excessive trolling...
Wondering if this is the same guy?!?
Comments?
Not trying to start shit, just trying to check the overall spin on this subject...
gee, great, always great when the losers over at Ars begin to add their "wisdom" the the discussion.
Just was reading there about an hour before this. they are more pathetic than ever.
Originally posted by Zapchud
I'm convinced this Nr9 is the same Nr9 as on Arstechnica. His posting style is equal...
I agree! His way of writing is very similar. He spells rather poorly, fails to put capital letters when starting new sentences and his grammar is flawed, sometimes leaving out entire words. It's very likely the same guy.
If they avoid the MCM route and where able to implement two SMP SOC processors we could end up with the best of both worlds. Reasonably good processor speed and extended battery life. What would be realy neat would be a controll panel with little switches that allowed you to put one or more of your processors to sleep.
I could see it now, 4 beavers knawing at their trees, click on the beaver (which represents a processor) and the beaver goes to sleep. Like wise a little store house in the Beavers den expands to represent increased battery life. Apple really needs to do this, I'd even sell them the rights cheap.
Dave
Originally posted by Barto
Do you want an iBook that costs more than a PowerBook?
Thought not. This is a cool direction, but as with any new direction, expensive initially.
Barto
I grew up on USENET. Trolling of this kind is an art form and a brutally effective form of parody. If he was in fact trolling the Battlefront, I can't judge him to harshly. It's a profoundly silly forum, not least for being full of overly earnest people who take irrelevant metrics, dubious engineering claims, and debates over platform superiority far too seriously. If he can get them riled up over the merits of engineering cases for their ability to stay upright in southeast Asian earthquakes, more power to him.
That said, how about the PowerBook G5?
Originally posted by Amorph
I followed one of the Ars Battlefront threads held up as an example of Nr9's trolling, and it's a claim that Macs are better than PCs because they weigh more, and so they're less likely to fall off desks in earthquakes. Now, I'm almost 100% positive that is trolling, given that it's a brilliant parody of the sorts of claims made in that forum, and the overzealous denizens of the Battlefront bit down hard on it.
I grew up on USENET. Trolling of this kind is an art form and a brutally effective form of parody. If he was in fact trolling the Battlefront, I can't judge him to harshly. It's a profoundly silly forum, not least for being full of overly earnest people who take irrelevant metrics, dubious engineering claims, and debates over platform superiority far too seriously. If he can get them riled up over the merits of engineering cases for their ability to stay upright in southeast Asian earthquakes, more power to him.
That said, how about the PowerBook G5?
While he may have been frequenting the Ars Battlefront simply to post humorous replies and poke some fun at the people there, starting threads like this doesn't really qualify him for a front-row seat in church on sunday.
Microsoft is Racist
But I agree on your last remark, back to the topic of the Powerbook G5!!
i dont think we need to discuss that
anyway, the processor has no real L2 cache but a 2KB prefetch buffer for L3
I seem to recall something written by John Siracusa over at Ars Technica regarding the G5. Is that a good place to start or are there better sites that explain processor design even simpler?
[EDIT: It wasn't written by John Siracusa but by Jon "Hannibal" Stokes.]
To keep things truely Symetric they would have to have a vector unit and FPU attached to each processor. So you would never be doing vector operation any greater than was implemented for each processor. You can not think of this a 512 bit vector operations, what you have would be the ability to process four threads of vector operations at a time. This would be absolutely wonderful
The nice thing is that it may not reguire a rewrite at all, just about any multithread app that may have more than one thread doing vector operations would benefit. Along with that the syste would have access to vector operations. Yes heavy single thread vector operations would be slow, but do realize that only that app would be slower any other running software would not be impacted.
Why you would want to elimenate multi threading is beyond me. Multithreading is what makes this sort of machine feasable. Sure a CPU bound process will perform poorly but how much software out there is really that bound up. Lets face it the OS would benefit, just about every application written in the last few years would benefit, people who run multiple programs at anyone time will beenfit. The only people who would loose would be those running CPU bound programs that don;t multi thread well and don't make much use of system resources. Sure there are some programs like this but not many.
Alright who really cares about bench marks anyways, this is an Apple forum right. Really Apple has suffered for years with poorly performing machines, when it comes to bench marks, whats to stop this. Plus any reasonable marketing idiot will come up with multi thread benchmarks that show the potential of this machine. Further if marketed towards resonably intelligent customers 4X SMP will be a big draw in and of itself. It would also be reasonable to assume that bandwidth and VMX issues would be addressed so the 700 MHz performance would exceed the current results that come from the 750 series.
Like I said I have alot of reservations about the reality of this machine. On the other hand the concept is sound and would leverage in a very positive manner some of Apple greatest technology advantages. Sitting here in NY I don't know what Apple has up its sleeves, what I do know is that the sensible thing to do would be to introduce a low power 970 in the powerbook. This would be playing it safe for Apple and would satisfy the lust that their customers have for such a machine. One thing is for certain, Apple is about the only manufacture that could pull this off, that is a massive SMP portable.
Thanks
Dave
Originally posted by Zapchud
Even though Amorph and Wizard69 did a fair job in getting something remotely credible out of this rumor, I still find this rumor to have way too many unanswered questions about it.
How will they get Altivec to perform acceptably?
Like it's been proposed now, we wind up with 4 Altivec-units. This would be pretty equivalent to a very low-clocked, but flexible 512-bit Altivec.
Even 256-bit Altivec has been doomed into the land of the law of diminishing returns, because it will be very hard to find enough parallelism in the code to exploit this (and it would make the unit itself a transistor monster, but that's not the concern here).
Yes, you could probably get acceptable performance out of these four units, if you're skilled enough as a programmer to manage to split the code onto all the units, but I believe that's pretty hard, and more importantly: It would require a rewrite of all code.
On regular code, optimized for the 970, and old (legacy) AV-code, it would perform at ~30% compared to the 970, because of the low clock-frequency, which is pretty low in my book.
This could be possibly be solved with the technology that would have to be the key to the biggest problem of this design entirely: To make it possible for all the cores to execute on the same thread, i.e. eliminate the need for multithreading. (And don't ask me how to do that, if it's even possible)
Without this, this pseudo-G5 Powerbook would be a terrible machine for all things involving less than 4 threads. A typical example of this is benchmarks. Benchmarks are almost always performed with the benchmark itself as the only running CPU-intensive task. And the typical benchmark (especially the cross-platform ones) is not multithreaded.
So unless some breakthrough is achieved relative to multi/single-threading, this machine would probably stand out as very slow in every aspect of benchmarking, except where they tested multitasking extensively.
Originally posted by KANE
I seem to recall something written by John Siracusa over at Ars Technica regarding the G5. Is that a good place to start or are there better sites that explain processor design even simpler?
[EDIT: It wasn't written by John Siracusa but by Jon "Hannibal" Stokes.]
Hannibal's articles on CPU design are excellent. Don't be afraid to follow the links, either. Happy reading.
I suppose that Ars would be ok to start. The problem is that if you have no electronics background at all it may take awhile to digest the material.
Honestly the best way to get started with increasing your knowledge of microprocssors is to get an 8 bit development system or trainer board and crack the books. What you will find is that to really get an understanding of a mircoproccesor requires that you understand both programming and a little electronics. Unfortunately its been so long I really don't know what or whom to suggest as a vendor for such materials. the major suppliers would be a good place to start.
A more modern approach and probally alot cheaper would be to get one of the free microprocessor simulators that float around the internet. I've heard there are good ones out there, maybe someone can pipe in with a suggestion. A simulator and a few good books for the processor being simulated will get you started. The board approach above is nicer if you can afford it, writing programs to blink lights and drive motors can pull you in deep.
There is a bit of a jump from a 8Bit microproccesor to the PPC. The PPC is really close to being a mainframe processor on a chip, thus has its own quirks. In anyevent the concepts transfer without issue.
After writing all of this all I can say is read Hannibal's materials if you like, but without a back ground it may not be usefull. If however your interest is tweaked then you have a couple of ideas to consider above.
DAve
Originally posted by KANE
As much as I am enjoying this thread, I am rather ingorant as to how processors really works. Is there anywhere on the internet that I can visit that explains (in rather laymen-terms) how a processor is constructed and how it works? I suspect that would further enhance my enjoyment of this thread.
I seem to recall something written by John Siracusa over at Ars Technica regarding the G5. Is that a good place to start or are there better sites that explain processor design even simpler?
[EDIT: It wasn't written by John Siracusa but by Jon "Hannibal" Stokes.]