Now I want my 10Ghz 45nm PPC 999 with 4 Cores and VMX2 and SMT on each core. Final Cut Pro 7 takes a whole lot of processing tossing around that Hidef Video of mine.
This doesn't mean anything. 200 engineers to "speed up" development of the process? Feh. What, will the laws of physics change once the engineering payroll total hits a magic number?
All this means is that IBM and partners will agree on a certain process for their chips -- which is good in terms of getting support for the process in the industry (tends to keep fab costs down) but means nothing in terms of when we will actually see any PPC processors at that process size.
In January, IBM entered into an agreement with Advanced Micro Devices Inc. to do similar work on 65-nm and 45-nm chips at IBM's Semiconductor Research and Development Center.
just another announcement of an agreement to do x or y in the future.
somewhat headbending to those who remember computers the size of rooms, true.
Kickaha and Amorph couldn't moderate themselves out of a paper bag. Abdicate responsibility and succumb to idiocy. Two years of letting a member make personal attacks against others, then stepping aside when someone won't put up with it. Not only that but go ahead and shut down my posting priviledges but not the one making the attacks. Not even the common decency to abide by their warning (afer three days of absorbing personal attacks with no mods in sight), just shut my posting down and then say it might happen later if a certian line is crossed. Bullshit flag is flying, I won't abide by lying and coddling of liars who go off-site, create accounts differing in a single letter from my handle with the express purpose to decieve and then claim here that I did it. Everyone be warned, kim kap sol is a lying, deceitful poster.
Now I guess they should have banned me rather than just shut off posting priviledges, because kickaha and Amorph definitely aren't going to like being called to task when they thought they had it all ignored *cough* *cough* I mean under control. Just a couple o' tools.
Don't worry, as soon as my work resetting my posts is done I'll disappear forever.
Kickaha and Amorph couldn't moderate themselves out of a paper bag. Abdicate responsibility and succumb to idiocy. Two years of letting a member make personal attacks against others, then stepping aside when someone won't put up with it. Not only that but go ahead and shut down my posting priviledges but not the one making the attacks. Not even the common decency to abide by their warning (afer three days of absorbing personal attacks with no mods in sight), just shut my posting down and then say it might happen later if a certian line is crossed. Bullshit flag is flying, I won't abide by lying and coddling of liars who go off-site, create accounts differing in a single letter from my handle with the express purpose to decieve and then claim here that I did it. Everyone be warned, kim kap sol is a lying, deceitful poster.
Now I guess they should have banned me rather than just shut off posting priviledges, because kickaha and Amorph definitely aren't going to like being called to task when they thought they had it all ignored *cough* *cough* I mean under control. Just a couple o' tools.
Don't worry, as soon as my work resetting my posts is done I'll disappear forever.
Crolles is also designed to go to 65nm and lower, and its progress is not determined by Motorola alone. STM, the largest contract fabricator in Europe and therefor a direct competitor with IBM's Fishkill initiative, has every incentive to keep up.
To those who understand all this processor stuff, how small can they get, in terms of whatever the 130nm, 90nm, etc stuff is called?
"Nanotechnology can best be described as manipulation, placement, measurement, and modeling, resulting in the creation of sub-100 nanometer matter. In human dimensions, one nanometer is 75,000 times smaller than the width of a human hair. In more scientific terms, a nanometer is one billionth of a meter, or about the width of 10 hydrogen atoms placed side by side."
so 75nm is 1000th the size of a human hair and 90nm is 900 hydrogen atoms laying side by side, hydrogen being the smallest of the atoms.
This doesn't mean anything. 200 engineers to "speed up" development of the process? Feh. What, will the laws of physics change once the engineering payroll total hits a magic number?
No, but it means that many more people working to understand what we can actually do. Scientific progress works by two clocks: macro and micro. Macro is the general level of scientific knowlege at any given time and allows for a wide range, and is usually limited by whatever overarching thoeries dominate a specific field; micro is the knowledge of a specific problem. A company/institution/government can invest a small amount of money (which equals a small amount of manpower) and progress gradually, or it can invest a large amount (which equals a large amount of manpower) and progress rapidly. The "law" of diminishing returns applies here since the macro level of scientific knowledge presents something of a ceiling, beyond which theories have to be revised, so manpower (=time=money) must be devoted to challenging those theories.
Therefore, there is also a dialectiacal relationship between the micro and macro levels in which changes in the former can lead to changes in the latter, allowing much more rapid advancement of the former in return.
Just some basic philosophy of science. But devoting more resources to a problem will result in quicker results within a given framework (macro level). If progressing requires creating a new framework, progress will depend on how quickly the old framework can be disposed of and replaced.
Having said all that, you might want to keep in mind that A) I didn't bother to read the article in the link; and I'm very drunk.
"Nanotechnology can best be described as manipulation, placement, measurement, and modeling, resulting in the creation of sub-100 nanometer matter. In human dimensions, one nanometer is 75,000 times smaller than the width of a human hair. In more scientific terms, a nanometer is one billionth of a meter, or about the width of 10 hydrogen atoms placed side by side."
so 75nm is 1000th the size of a human hair and 90nm is 900 hydrogen atoms laying side by side, hydrogen being the smallest of the atoms.
It all seems great, but what I'm missing is some kind of roadmap. When are they planning to take the new 65 nm fab into production? Are wa talking 2005 here, or 2008?
65 nm is 1/10th of the fab of witch the original PowerPC 601 was manufactured. In the same area that one 601 was manufactured, one hundred 601 could be manufactured in the new 65 nm process. The new 300 mm wafers yields 2.5 times as many chips as the old ones. One 300 mm wafer fabbed at 65 nm would produce 250 times more 601-processors if they were to manufacture them in this fashion. Quite an accomplishement in 12-15 years I think.
This doesn't mean anything. 200 engineers to "speed up" development of the process? Feh. What, will the laws of physics change once the engineering payroll total hits a magic number.
It DOES mean something! It means that IBM is comitted to development!
If this was Moto.. THere was one single guy on the job, in his spare time, whithout payment...
This doesn't mean anything. 200 engineers to "speed up" development of the process? Feh. What, will the laws of physics change once the engineering payroll total hits a magic number?
All this means is that IBM and partners will agree on a certain process for their chips -- which is good in terms of getting support for the process in the industry (tends to keep fab costs down) but means nothing in terms of when we will actually see any PPC processors at that process size.
Where it is generally a truism that more engineers does not mean that a project makes it go faster, it is also common sense that fewer engineers on a project doesn't make it go faster.
More engineers means that IBM is taking die shrinks to heart and putting some serious resources into the effort. This is a good sign.
It DOES mean something! It means that IBM is comitted to development!
If this was Moto.. THere was one single guy on the job, in his spare time, whithout payment...
Actually it was quite a few guys paid pretty well, but they just didn't care enough to make their processes highly manufacturable.
Quote:
It all seems great, but what I'm missing is some kind of roadmap. When are they planning to take the new 65 nm fab into production? Are wa talking 2005 here, or 2008?
To those who understand all this processor stuff, how small can they get, in terms of whatever the 130nm, 90nm, etc stuff is called?
Even teh people who understand all this stuff can't give you a definate answer on that. In terms of what we today can envision being manufacturable its about 32nm. Theoretically it's much smaller than that. The challenge we are constantly faced with is making reality approach theory in a cost-effective manner.
Even teh people who understand all this stuff can't give you a definate answer on that. In terms of what we today can envision being manufacturable its about 32nm. Theoretically it's much smaller than that. The challenge we are constantly faced with is making reality approach theory in a cost-effective manner.
Comments
Originally posted by *l++
http://www.eweek.com/article2/0,3959,1211744,00.asp
IBM = GOOD
MOTOROLA = BAD
Great!
Now I want my 10Ghz 45nm PPC 999 with 4 Cores and VMX2 and SMT on each core. Final Cut Pro 7 takes a whole lot of processing tossing around that Hidef Video of mine.
All this means is that IBM and partners will agree on a certain process for their chips -- which is good in terms of getting support for the process in the industry (tends to keep fab costs down) but means nothing in terms of when we will actually see any PPC processors at that process size.
In January, IBM entered into an agreement with Advanced Micro Devices Inc. to do similar work on 65-nm and 45-nm chips at IBM's Semiconductor Research and Development Center.
just another announcement of an agreement to do x or y in the future.
somewhat headbending to those who remember computers the size of rooms, true.
but product ship dates would be better.
IBM=
Moto=
Now I guess they should have banned me rather than just shut off posting priviledges, because kickaha and Amorph definitely aren't going to like being called to task when they thought they had it all ignored *cough* *cough* I mean under control. Just a couple o' tools.
Don't worry, as soon as my work resetting my posts is done I'll disappear forever.
Now I guess they should have banned me rather than just shut off posting priviledges, because kickaha and Amorph definitely aren't going to like being called to task when they thought they had it all ignored *cough* *cough* I mean under control. Just a couple o' tools.
Don't worry, as soon as my work resetting my posts is done I'll disappear forever.
Originally posted by *l++
http://www.eweek.com/article2/0,3959,1211744,00.asp
IBM = GOOD
MOTOROLA = BAD
Crolles is also designed to go to 65nm and lower, and its progress is not determined by Motorola alone. STM, the largest contract fabricator in Europe and therefor a direct competitor with IBM's Fishkill initiative, has every incentive to keep up.
Originally posted by CubeDude
To those who understand all this processor stuff, how small can they get, in terms of whatever the 130nm, 90nm, etc stuff is called?
"Nanotechnology can best be described as manipulation, placement, measurement, and modeling, resulting in the creation of sub-100 nanometer matter. In human dimensions, one nanometer is 75,000 times smaller than the width of a human hair. In more scientific terms, a nanometer is one billionth of a meter, or about the width of 10 hydrogen atoms placed side by side."
so 75nm is 1000th the size of a human hair and 90nm is 900 hydrogen atoms laying side by side, hydrogen being the smallest of the atoms.
Originally posted by Tomb of the Unknown
This doesn't mean anything. 200 engineers to "speed up" development of the process? Feh. What, will the laws of physics change once the engineering payroll total hits a magic number?
No, but it means that many more people working to understand what we can actually do. Scientific progress works by two clocks: macro and micro. Macro is the general level of scientific knowlege at any given time and allows for a wide range, and is usually limited by whatever overarching thoeries dominate a specific field; micro is the knowledge of a specific problem. A company/institution/government can invest a small amount of money (which equals a small amount of manpower) and progress gradually, or it can invest a large amount (which equals a large amount of manpower) and progress rapidly. The "law" of diminishing returns applies here since the macro level of scientific knowledge presents something of a ceiling, beyond which theories have to be revised, so manpower (=time=money) must be devoted to challenging those theories.
Therefore, there is also a dialectiacal relationship between the micro and macro levels in which changes in the former can lead to changes in the latter, allowing much more rapid advancement of the former in return.
Just some basic philosophy of science. But devoting more resources to a problem will result in quicker results within a given framework (macro level). If progressing requires creating a new framework, progress will depend on how quickly the old framework can be disposed of and replaced.
Having said all that, you might want to keep in mind that A) I didn't bother to read the article in the link; and I'm very drunk.
-DCQ
Originally posted by Bigc
"Nanotechnology can best be described as manipulation, placement, measurement, and modeling, resulting in the creation of sub-100 nanometer matter. In human dimensions, one nanometer is 75,000 times smaller than the width of a human hair. In more scientific terms, a nanometer is one billionth of a meter, or about the width of 10 hydrogen atoms placed side by side."
so 75nm is 1000th the size of a human hair and 90nm is 900 hydrogen atoms laying side by side, hydrogen being the smallest of the atoms.
You've just confused me more.
65 nm is 1/10th of the fab of witch the original PowerPC 601 was manufactured. In the same area that one 601 was manufactured, one hundred 601 could be manufactured in the new 65 nm process. The new 300 mm wafers yields 2.5 times as many chips as the old ones. One 300 mm wafer fabbed at 65 nm would produce 250 times more 601-processors if they were to manufacture them in this fashion. Quite an accomplishement in 12-15 years I think.
Originally posted by Tomb of the Unknown
This doesn't mean anything. 200 engineers to "speed up" development of the process? Feh. What, will the laws of physics change once the engineering payroll total hits a magic number.
It DOES mean something! It means that IBM is comitted to development!
If this was Moto.. THere was one single guy on the job, in his spare time, whithout payment...
Good example 'pixie dust' used in their HDs, layer of 3 atoms thick material separating magnetic layers.
3 atoms thick....
read more
Originally posted by Tomb of the Unknown
This doesn't mean anything. 200 engineers to "speed up" development of the process? Feh. What, will the laws of physics change once the engineering payroll total hits a magic number?
All this means is that IBM and partners will agree on a certain process for their chips -- which is good in terms of getting support for the process in the industry (tends to keep fab costs down) but means nothing in terms of when we will actually see any PPC processors at that process size.
Where it is generally a truism that more engineers does not mean that a project makes it go faster, it is also common sense that fewer engineers on a project doesn't make it go faster.
More engineers means that IBM is taking die shrinks to heart and putting some serious resources into the effort. This is a good sign.
Originally posted by DCQ
Having said all that, you might want to keep in mind that A) I didn't bother to read the article in the link; and I'm very drunk.
That's quite a caveat!
Originally posted by T'hain Esh Kelch
It DOES mean something! It means that IBM is comitted to development!
If this was Moto.. THere was one single guy on the job, in his spare time, whithout payment...
Actually it was quite a few guys paid pretty well, but they just didn't care enough to make their processes highly manufacturable.
It all seems great, but what I'm missing is some kind of roadmap. When are they planning to take the new 65 nm fab into production? Are wa talking 2005 here, or 2008?
Roadmap
2007 most likely.
To those who understand all this processor stuff, how small can they get, in terms of whatever the 130nm, 90nm, etc stuff is called?
Even teh people who understand all this stuff can't give you a definate answer on that. In terms of what we today can envision being manufacturable its about 32nm. Theoretically it's much smaller than that. The challenge we are constantly faced with is making reality approach theory in a cost-effective manner.
Originally posted by Eskimo
Even teh people who understand all this stuff can't give you a definate answer on that. In terms of what we today can envision being manufacturable its about 32nm. Theoretically it's much smaller than that. The challenge we are constantly faced with is making reality approach theory in a cost-effective manner.
Thank You. Now I'm less confused than before.
Moronola =
Originally posted by Leonis
IBM =
Moronola =
a little spare time lately, eh.