A lot of very tallented mathematicians go down a dark road in their 20s, trying to prove the impossible, giving up prime years to fail at something and a few actually do prove something important and then are spent. Godel was nuts to start with and the work he did in his 20s pushed over the top.
The 601 had extra instructions for compatibility with POWER. It was part of the architecture to remove some instructions, planned and agreed to by Apple, IBM and Motorola before the 601 was made.
All do respect, but I know how they make chips. They use software to do it and that's why they are so reliable, a human doesn't put each gate in to place. It's also designed with test in mind and there are whole industries and standards surrounding that. Try to name something remotely close to a JTAG interface for software. I believe it's more reliable than software but that's really becuase once you etch a piece of silicon it's pretty damn hard to fix it. Don't get me wrong though, I trust the chip a lot more than the software in most cases, I expect a compiler bug long before I expect to have stumbled on to the magic code stream that doesn't compute correctly and I expect my own errors before that.
This kind of bug is a little different though, we're not talking about a stuck gate that only gets tickled during a single ALU operation or retiring an instruction too early or bigfooting a register too early or anything like that. We're talking about clocking issues and fundamental timing issues in Intel's "server grade" platform. There are accepted standards and practices for how aggressive to be, some vendors can tell you with amazing detail how reliable their chips are, in what conditions, etc.. With clocks in particular some vendors can be picky, I've seen hard hitters scope up boxes and refuse to support hardware they sold because it was clocked out of spec (think about the edge of a clock and clock quality.. a 1.2 Ghz clock isn't enough, it has to actually achieve the level of the clock before it switches back and it takes time for the clock to transition..) it sounds like Intel is either ignoring them or trying to write their own book or the IA64 is a bigger disaster than any one there wants to even hint at. There are a fairly limited class of errors where underclocking the chip fixes the problem and most of those errors are related to the chip being aggressively clocked to begin with. It's ironic, on IBM's POWER4 line of processors they added extra cache room for parity (at the expense of potential performance) and made the leads more beefy (again at the expense of higher clock speeds) because the platform is a server platform that places reliability at a premium. It sounds like Intel has been making PC chips too long and isn't ready for server grade chips.
Their party line has been that they will keep working at it until it's ready, they aren't expecting it to move a lot of chips, etc. etc.. Right now they have walked down a road where they have invested billions? (at least hundreds of millions) in an unproven technology. They have crossed the line to the point that there won't be $1500 IA64 products for years and years. They have piped it as a server grade platform. And it underachieves in every area and has't taken the world by storm nearly as much as they said. So bad is it that HP, their blood brother in that mess has continued the PA-RISC and Alpha lines past the point they claimed when they originally adopted the IA64. The only reason I could imagine them to aggressively clock it like that have would be because that's the only way to make it perform remotely like they have claimed it would. I'm not going to guess about Intel's dirty laundry but I'd guess the stakes are little higher than it would look on the surface for the IA64, either that or there are some incompetants running the show.
Never mind that fact that they offered a seemless transition over the years from 68000 to PowerPC, from MacOS Classic to MacOS X.
If you invested in Apple 15 years ago, they still honor your investment. I can't say that the same is true of MS where different versions of Office don't even like to talk to each other and they are constantly pushing for their customers to spend more money.
What about taking a project that has been a failure in every way and forcing it in to practice and the absolute billions of dollars and the lives it has cost?
The shuttle was supposed to be a cheap way to get in to space, it's by far the most expensive way right now and it's got a reliability problem.
The failure is that NASA was never accountable for the claims made about the shuttle that never were true and they have kept with the program, spending billions of dollars building new shuttles.
Several people on the kernel list have always been against this
stuff. I remember seeing some messages by a few people working on
implementing Forth in kernel space. Sun uses forth for their
firmware, it is a great step above assembly language that is tiny and
easy to implement. I'm not sure how practical it is to expect scheme
drivers but forth drivers are very realistic. http://www.dedasys.com/freesoftware/files/kpforth- 21.tgz>here is
one link. I'm not sure if it's a good idea or not, there is a
certain CS geek appeal that makes it feel more extensible or easier to
patch or something, of course you've got the full code. With a good
forth or scheme interpreter it might be possible to hot patch things
in the kernel while it's live, that's cool in some environments; of
course all of the places where that's cool for HA reasons, it's also
bloody dangerous and the risk offsets the cool factor.
Now with something like scheme, if it could perform well enough and
get robust and polished enough (I looked at schemix, it's still very
primitive, no way you'll see it in Alan or Linus's kernel any time
soon) but if it matures I could almost see that being used for
some scheduling and some other tasks where you want sophisticated
logic that it's complex to do in C and not always safe. Of course,
that's assuming that some folks in the kernel would ever acutally
agree to it.
What's this mean for.dotgnu and mono? Anything, I think they are
getting their own runtimes in order and won't need anything from MS
but in the meantime... I've bounced a couple of times on mono, I
think copying MS is foolish. I think developing a free high
performance rapid programming language and environment is a great
idea. Not so sure about C#. I like what they are doing though. Mono
is looking really good. It seems like if we could agree as a
community more on scripting languages and they weren't as religious we
could do some really killer stuff with python or ruby instead of c#,
but such is life. I digress.
The fact that they are fucking the community isn't too surprising to
me, I don't think MS cares too much for Fox Pro. The more
fascinating thing is that the community itself is actively trying to
get away from the MS platform. That's very interesting. These custom
app environments have always scared the hell out of me as a developer
but they never die. People are still doing clipper and fox pro and
paradox. This old fox pro cat chose to start making VFP run under
WINE rather than change his platform. Sounds like a hellova business
to either reimplement legacy custom systems on Linux (maybe even
OpenSource) or to court some of the few non-MS companies that own some
of that software and port it for them. I don't know if it's ever
been approached like that, most people would rather do new stuff.
The Loki guys showed us how fast they could port games though, taking
a few developers only a few weeks to a few months to get them going.
Maybe I'm optimistic but a few years ago, if you could have produced a
Linux verions of Wordstar there would be users of it today, there are
people who still have the Lotus 1-2-3 slash programmed in to their
fingers and the Wordstar control-D. Autodesk are still dragging their
feet with regard to Linux, Pro/E has been demoed on Linux but they
aren't pushing it yet. There are a lot of apps that could be ported
if someone was willing to do the work. Probably doesn't do a lot of
good for these poor FoxPro guys but how many more Foxpros are out
there? Remember Ashton Tate? dBase? Clipper?
They won't use the fab solely for this product. Sony isn't stupid and they make a ton of different chips and ICs. The fab will have capabilities to build the cell but it will also be able to fab parts for camcorders and DVD players, PS2s and such.
That is correct. I'm not sure it's a good thing though. RMS and the FSF have generally been of the stand point that anything that restricts freedom is bad, even if it restricts the restrictors.
We could start an FS black list though and have the FSF revoke the rights through copyright to use GPLed software that they own the copyright to. That includes trademarks, documentation, etc..
These "language discussions" are always flawed. There are zealots who like one hammer for every nail and then there are these other zealots that are so far from the actual problems that their ideas are kind of hoaky.
Heirarchy will continue to exist. It's the only concept the human brain has to deal with complexity, call it what you will but you classify and associate things in to hierarchy whether you're aware of it or not. I see no reason to believe right now that processors will have more advanced instructions than they currently do now; they may be very different (like optmisitic registers that know values before they have been calculated or something) but they will be on the same order of complexity. The atomic operations will probably remain at the same order of complexity in biological processors, quantum, or SI/GAAS/whatever based transistor processors. I don't see how sort a list will be done without some sort of operations to look at elements in it, compare them, and then change their ordering. Even with quantum computers you have to set up those operations to happen and cause results. That being said there will always be an assembly language.
On top of that there will always be a C like language, if it's not C, that will be a portable assembly language. Then there will be "application" languages built at a higher level still. That won't change, for good reasons, it's just too complex to push the protection and error checking and everything down a level. I'll give examples if you want them. The easiest one that comes to mind is something like Java garbage collection and how programmers assume that it has mystical powers and are shocked when they fire up a profiler and see leftovers sitting around, it's a very complex piece of software and you expect it to go down to a lower level? The lower levels have their own problems keeping up with Dr. Moore.
I think the other biggest area is that reliability needs to go up by several orders. Linux, BSD, Win2000 and WinXP are pretty reliable but they aren't amazing. I've seen all of them crash at one point or another, I may have had hand in making it happen and so might have hardware; either way it did. To really start to solve the issues and problems of humanity better we need to have more trust for our computers, that requires more reliable computers and that require different methods of engineering. The biggest thing going on in programming languages now to deal with that is Functional Programming. In 50 years I could see some kind of concept like an algorithm broker that has the 1700+ "core algorithms" (Knuth suspects that there are about 1700 core algorithms in CS) implemented in an ML or Haskell like language, proven for correctness, in a proven runtime environment being the used in conjunction with some kind of easy to use scripting glue. And critical low level programming will be proven automatically by an interpreter at compile time, they are already making automatic provers for ML.
Sweet dump the old BIOS, replace it with a new one. Doesn't change the fact that your Pentium IV still boots up in 64k real mode just like an 8086.
Now there isn't anything really wrong with that except that fact that booting a PC isn't the most documented procedure out there. I don't know why, I think it has something to do with BIOS Engineers trying to keep a strangle hold on their jobs.. If you've done any modern assembly programming and then try to write a BIOS it's like a different world. It's totally retro, kind of freaky in ways.. Can't even map a modern flash or eeprom in to memory the way the chip comes out of reset, not enough addressability.
From time to time if feels like google is getting stagnant. I'm not sure if that's because I'm behind a computer all day or what though. I kind of liked it back in the heyday when there was infoseek, altavista, nothernlight, and then the indexes and they all kind of had a different flavor. I remember doing searches, switching engines and suddenly my vague 3 word search term rendered the pages I want.
I'm a little dumbfounded as to how MS sees them as a competitor though, they haven't really made much of a move in to "portal space." Is this just another case of a company being too powerful and good at what they do for MS's liking?
Java isn't open. Which isn't really that bad, I'd feel better of ISO, ANSI or ECMA had a draft Java spec but Sun hasn't screwed us yet.
What happens if they start charging for the JDK? Or just stop developing it? I know there are projects like Kaffe and GCJ and IBM's JDK but it's just a derivative of Sun's. Not to be alarmist but Sun's not positioned well right now and should they replace the CEO or something rash like that (how many losses to you take before bringing in new blood?) The new guy will look at what Sun does, look at the strengths, look at the weaknesses, look at the costs, and I don't see how free JDK wins, I don't see how java wins at all
What are the advantages though? Seriously? The end user won't understand them.
As a developer, I'm amped for 64bit, there are lot's of cool things
you can do. I'm thinking about non-relocatable dynamically linked
libraries and mmaped harddrives and cool stuff. The end user will see
two things, cost and speed. So far there hasn't been a 64bit chip
that delivers the speed at the cost to entertain consumers (I dismiss
the 21164 and embedded chips like the r5900 because they don't run
windows, we're talking about desktop computers)
The IA64 chip, Itanium 2, is a very speedy processor but it costs
$3000 for the processor alone. We'll see how the Opteron and Athlon64
do, if AMD is smart they will fit them in with their current pricing
scheme and force Intel's hand if they can hang with Pentium4
performance and start convincing people to do x86-64. Only problem is
they are losing money with their current pricing scheme and I don't
expect to see a 3Ghz opteron this year and Intel will start pushing
4Ghz pentium4s...
If they price it right they could make x86-64 the Linux platform of choice pretty easily though.
Well, to distill it down to the basics, SCO is masochistic. It would appear that they like it rough and hard and through the, how do you put this?, they like it hard through the "back oriface"
So how do you satisfy such a desire? You pick on the biggest, toughest, guy you can see.
Ironic that they are trying to stop AIX sales, IBM makes more money on AIX sales each year than SCO has grossed since their beginning. AIX sales simply won't be stopped. And then to accuse IBM, of all companies, of misappropriating SCO source and technology? There are some very talented lawyers in IBM's employ, SCO might be trying to get bought it's a real possibility but that stuff doesn't happen like that to IBM. They can play really dirty when you try to bully them and they don't lose very often. The question could become "is it cheaper to pay to convert SCOs customers to Linux and let them die or buy them"
It's a lot older than that. There were the 8086, 8088, and 80186 before the 80286. Depending on how you measure things, some people trace the x86 (IA32) lineage back to the 8008 and 4004.
Slashdot Mirror
A lot of very tallented mathematicians go down a dark road in their 20s, trying to prove the impossible, giving up prime years to fail at something and a few actually do prove something important and then are spent. Godel was nuts to start with and the work he did in his 20s pushed over the top.
The 601 had extra instructions for compatibility with POWER. It was part of the architecture to remove some instructions, planned and agreed to by Apple, IBM and Motorola before the 601 was made.
I really meant that all the people DO respect Intel.. ;-)
This kind of bug is a little different though, we're not talking about a stuck gate that only gets tickled during a single ALU operation or retiring an instruction too early or bigfooting a register too early or anything like that. We're talking about clocking issues and fundamental timing issues in Intel's "server grade" platform. There are accepted standards and practices for how aggressive to be, some vendors can tell you with amazing detail how reliable their chips are, in what conditions, etc.. With clocks in particular some vendors can be picky, I've seen hard hitters scope up boxes and refuse to support hardware they sold because it was clocked out of spec (think about the edge of a clock and clock quality.. a 1.2 Ghz clock isn't enough, it has to actually achieve the level of the clock before it switches back and it takes time for the clock to transition..) it sounds like Intel is either ignoring them or trying to write their own book or the IA64 is a bigger disaster than any one there wants to even hint at. There are a fairly limited class of errors where underclocking the chip fixes the problem and most of those errors are related to the chip being aggressively clocked to begin with. It's ironic, on IBM's POWER4 line of processors they added extra cache room for parity (at the expense of potential performance) and made the leads more beefy (again at the expense of higher clock speeds) because the platform is a server platform that places reliability at a premium. It sounds like Intel has been making PC chips too long and isn't ready for server grade chips.
Their party line has been that they will keep working at it until it's ready, they aren't expecting it to move a lot of chips, etc. etc.. Right now they have walked down a road where they have invested billions? (at least hundreds of millions) in an unproven technology. They have crossed the line to the point that there won't be $1500 IA64 products for years and years. They have piped it as a server grade platform. And it underachieves in every area and has't taken the world by storm nearly as much as they said. So bad is it that HP, their blood brother in that mess has continued the PA-RISC and Alpha lines past the point they claimed when they originally adopted the IA64. The only reason I could imagine them to aggressively clock it like that have would be because that's the only way to make it perform remotely like they have claimed it would. I'm not going to guess about Intel's dirty laundry but I'd guess the stakes are little higher than it would look on the surface for the IA64, either that or there are some incompetants running the show.
If you invested in Apple 15 years ago, they still honor your investment. I can't say that the same is true of MS where different versions of Office don't even like to talk to each other and they are constantly pushing for their customers to spend more money.
The shuttle was supposed to be a cheap way to get in to space, it's by far the most expensive way right now and it's got a reliability problem.
The failure is that NASA was never accountable for the claims made about the shuttle that never were true and they have kept with the program, spending billions of dollars building new shuttles.
Now with something like scheme, if it could perform well enough and get robust and polished enough (I looked at schemix, it's still very primitive, no way you'll see it in Alan or Linus's kernel any time soon) but if it matures I could almost see that being used for some scheduling and some other tasks where you want sophisticated logic that it's complex to do in C and not always safe. Of course, that's assuming that some folks in the kernel would ever acutally agree to it.
The fact that they are fucking the community isn't too surprising to me, I don't think MS cares too much for Fox Pro. The more fascinating thing is that the community itself is actively trying to get away from the MS platform. That's very interesting. These custom app environments have always scared the hell out of me as a developer but they never die. People are still doing clipper and fox pro and paradox. This old fox pro cat chose to start making VFP run under WINE rather than change his platform. Sounds like a hellova business to either reimplement legacy custom systems on Linux (maybe even OpenSource) or to court some of the few non-MS companies that own some of that software and port it for them. I don't know if it's ever been approached like that, most people would rather do new stuff. The Loki guys showed us how fast they could port games though, taking a few developers only a few weeks to a few months to get them going.
Maybe I'm optimistic but a few years ago, if you could have produced a Linux verions of Wordstar there would be users of it today, there are people who still have the Lotus 1-2-3 slash programmed in to their fingers and the Wordstar control-D. Autodesk are still dragging their feet with regard to Linux, Pro/E has been demoed on Linux but they aren't pushing it yet. There are a lot of apps that could be ported if someone was willing to do the work. Probably doesn't do a lot of good for these poor FoxPro guys but how many more Foxpros are out there? Remember Ashton Tate? dBase? Clipper?
I don't believe trusted solaris has been b2 certified. It has passed a similar criteria evaluation though.
They won't use the fab solely for this product. Sony isn't stupid and they make a ton of different chips and ICs. The fab will have capabilities to build the cell but it will also be able to fab parts for camcorders and DVD players, PS2s and such.
There won't be a cache difference either, the 64bit chips are word aligned to 64bits. They are optimized for that.
Generally no differnece at all between 64 and 32bit processors, as demonstrated by sparc and POWER/PowerPC.
We could start an FS black list though and have the FSF revoke the rights through copyright to use GPLed software that they own the copyright to. That includes trademarks, documentation, etc..
Heirarchy will continue to exist. It's the only concept the human brain has to deal with complexity, call it what you will but you classify and associate things in to hierarchy whether you're aware of it or not. I see no reason to believe right now that processors will have more advanced instructions than they currently do now; they may be very different (like optmisitic registers that know values before they have been calculated or something) but they will be on the same order of complexity. The atomic operations will probably remain at the same order of complexity in biological processors, quantum, or SI/GAAS/whatever based transistor processors. I don't see how sort a list will be done without some sort of operations to look at elements in it, compare them, and then change their ordering. Even with quantum computers you have to set up those operations to happen and cause results. That being said there will always be an assembly language.
On top of that there will always be a C like language, if it's not C, that will be a portable assembly language. Then there will be "application" languages built at a higher level still. That won't change, for good reasons, it's just too complex to push the protection and error checking and everything down a level. I'll give examples if you want them. The easiest one that comes to mind is something like Java garbage collection and how programmers assume that it has mystical powers and are shocked when they fire up a profiler and see leftovers sitting around, it's a very complex piece of software and you expect it to go down to a lower level? The lower levels have their own problems keeping up with Dr. Moore.
I think the other biggest area is that reliability needs to go up by several orders. Linux, BSD, Win2000 and WinXP are pretty reliable but they aren't amazing. I've seen all of them crash at one point or another, I may have had hand in making it happen and so might have hardware; either way it did. To really start to solve the issues and problems of humanity better we need to have more trust for our computers, that requires more reliable computers and that require different methods of engineering. The biggest thing going on in programming languages now to deal with that is Functional Programming. In 50 years I could see some kind of concept like an algorithm broker that has the 1700+ "core algorithms" (Knuth suspects that there are about 1700 core algorithms in CS) implemented in an ML or Haskell like language, proven for correctness, in a proven runtime environment being the used in conjunction with some kind of easy to use scripting glue. And critical low level programming will be proven automatically by an interpreter at compile time, they are already making automatic provers for ML.
Now there isn't anything really wrong with that except that fact that booting a PC isn't the most documented procedure out there. I don't know why, I think it has something to do with BIOS Engineers trying to keep a strangle hold on their jobs.. If you've done any modern assembly programming and then try to write a BIOS it's like a different world. It's totally retro, kind of freaky in ways.. Can't even map a modern flash or eeprom in to memory the way the chip comes out of reset, not enough addressability.
I'm a little dumbfounded as to how MS sees them as a competitor though, they haven't really made much of a move in to "portal space." Is this just another case of a company being too powerful and good at what they do for MS's liking?
It's the 21st century for crying out loud!
What happens if they start charging for the JDK? Or just stop developing it? I know there are projects like Kaffe and GCJ and IBM's JDK but it's just a derivative of Sun's. Not to be alarmist but Sun's not positioned well right now and should they replace the CEO or something rash like that (how many losses to you take before bringing in new blood?) The new guy will look at what Sun does, look at the strengths, look at the weaknesses, look at the costs, and I don't see how free JDK wins, I don't see how java wins at all
I can't wait. Have you seen the OO bonobo demo? It's wickedly sweet.
As a developer, I'm amped for 64bit, there are lot's of cool things you can do. I'm thinking about non-relocatable dynamically linked libraries and mmaped harddrives and cool stuff. The end user will see two things, cost and speed. So far there hasn't been a 64bit chip that delivers the speed at the cost to entertain consumers (I dismiss the 21164 and embedded chips like the r5900 because they don't run windows, we're talking about desktop computers)
The IA64 chip, Itanium 2, is a very speedy processor but it costs $3000 for the processor alone. We'll see how the Opteron and Athlon64 do, if AMD is smart they will fit them in with their current pricing scheme and force Intel's hand if they can hang with Pentium4 performance and start convincing people to do x86-64. Only problem is they are losing money with their current pricing scheme and I don't expect to see a 3Ghz opteron this year and Intel will start pushing 4Ghz pentium4s...
If they price it right they could make x86-64 the Linux platform of choice pretty easily though.
There is a solution. Mailers that only propagate mail if it is signed by a trusted key.
Stealing code was a paramount concern. It's accounted for.
Ironic that they are trying to stop AIX sales, IBM makes more money on AIX sales each year than SCO has grossed since their beginning. AIX sales simply won't be stopped. And then to accuse IBM, of all companies, of misappropriating SCO source and technology? There are some very talented lawyers in IBM's employ, SCO might be trying to get bought it's a real possibility but that stuff doesn't happen like that to IBM. They can play really dirty when you try to bully them and they don't lose very often. The question could become "is it cheaper to pay to convert SCOs customers to Linux and let them die or buy them"
Those kinds of people are very rare. They alone could have brought the public sector up to par with the NSA.
Not to mention it was a good day because it killed off all those nasty lizard beasts!
It's a lot older than that. There were the 8086, 8088, and 80186 before the 80286. Depending on how you measure things, some people trace the x86 (IA32) lineage back to the 8008 and 4004.