I was a Handspring Visor owner, and got hooked on entering my billable hours as appointments in the calendar. I moved to a Teo 650, and loved it bar I had to buy some software and customize my firmware (to "see" the 4GB SD) to use it as a real music player (Audiogateway for Bluetooth, pTunes as a player). That phone was stolen (by some thieving motherfxxxx may he/she rot in hell forever). I replaced it with a Centro (and didn't have to replace my firmware - but still needed the software).
I love the Centro now. It has one or two issues, but for what I actually use it for, it is the best phone on the market (and pretty cheap in the US, I hear).
It seems everyone has read only one line of my question. For those of you who know who you are, Once Again: I suspect a 5 GHz CPU in a current system will not be twice as fast as a 2.5 GHz system. In fact, my own experience is that even in CPU intensive stuff, one will be lucky to get a 15% increase in performance. And for most jobs, this will not be noticeable. For some jobs, for sure, a fster CPU will always help. But better software would help all jobs.
WHAT I AM SAYING IS THAT THE BIGGER BENEFIT WILL COME FROM THE ADDRESS SPACE of 64 bits. In fact, 32 bit CPUs will probably be faster than 64 bit CPUs for many tasks, but 64 bit CPUs will lead to more reliable software.
Hhmmm, I had no idea GPU power has so eclipsed DSPs. However, this is still beside the point, since it is not established that 64 bit inherantly provides much more raw performance in a direct way, and even more speculative is whether current architecture and OS can deliver significantly more real performance with a 64 bit system. I am simply stating that 64 bit may be providing a much more general improvement than simply a performance one. For the performance boosts for your application, multiple servers such as in a Beowulf cluster seem like a logical choice, once one runs into the ceiling of what any single CPU system can handle.
I can build 4 1.6 GHz systems for the price of one 64 bit system today. They can have gigabit networking, a good cluster OS, and probably beat the pants off the 64 bit system in crunching those RF DSP algorithms.
I am arguing that the bigger gain from 64 bit computing may lie in the vast simplification of device handling now that the theoretical address space can dwarf the achievable addressable size of devices.
I don't think "very wrong" is on the mark. I was perhaps over generalizing, as are you if you think that most people need the raw horsepower you need. I was thinking about folks that use word processors, browse the web, send e-mail, play games: you know, about 99% of CPU users. So for 1% of users, I am "very wrong" in my intentionally controversial opening statement.
My main point (which you appear to have overlooked in your zeal to shoot me down) is that the 64 bit architecture offers something else other than (or instead of) raw performance. If you consider that also "very wrong", would you post your argument concerning that point also?
Also, for your application are there not some useful DSP add-in boards that can supply an order of magnitude increase in performance for DSP? At the price of the high end GPUs one could surely buy a DSP or two and have change left over.
Sorry, but I am not actually answering your question directly, but it is perhaps appropriate because your question begs a bigger question.
I don't think anyone needs more speed than the best 32 bit CPUs provide today. The bigger problem today is bugs. Memory leaks, security flaws, memory protection errors, you name them. If I understand him correctly, Linus Torvals has weighed in to say that 64 bit architecture will allow a new way of addressing devices: 1:1 mapping. This will eliminate a huge amount of paging and cacheing code in OSs. If I read Linus correctly, he is saying that 64 bits is enough to map any entire hard drive space directly into memory. This brings me to the comments of another luminary: Donald Knuth. Knuth has written and demonstrated ways of writing very low bug count software, and created a seminal work, the practical, non-trivial application LaTeX, which I use daily. Knuth has proved that a large complex application with strong change management can achieve a very low bug count and still have enough features to have no real competition in its field.
So what I am getting to is another question: is 64 bits enough, now and forever? I mean will we ever need more address space for anything? So can we write or change our OS so direct mapping of everything is the norm, and thus eliminate half the cleverness and most of the bugs in the OS? And expect that this will be "the last re-write". That all that will be needed in the future is new device drivers and re-compiles for new CPUs?
No, they have an agenda. They have a belief that they feel strongly about, and they want others to either believe it too, or at least be held to the constraints that those beliefs create. This is every bit as greedy has having that "belief" be that my bank account should be the biggest or that Globex-MegaCorp's belief that their balance sheet is the most important thing in the world. Remember, having what one thinks in ones brain is a "good" motive does not justify acts that potentially harm (physically, financially, or otherwise) others.
Having a belief that my bank account should be the biggest is clearly of no great help to others in general. Having a belief that it is important to keep the air clean and the climate within bounds is clearly of benefit to others. You need to work on your definition of good.
On the issue of the cure being worse than the illness: in order to maintain the US dependancy on fossil fuels, americans are dying daily in Iraq. The Great Lakes are being poisoned by midwest power stations (an adult can only safely eat 6 annual portions of fish from some great lakes). Is it really worthwhile to push for the economy the economy the economy when real people are getting
sick?
Funny you say that when the article mentions NOTHING about any business being involved in the contradicting studies. As far as I can see, YOU'RE the only one even mentioning business or the profit motive into this equation. I would say that anyone completely believing in EITHER side is just as bad as anyone completely believing in the OTHER side.
Note that the two report authors are: an economist, and a statistic expert working in the minig industry. These are unbiased people?
And from the US Today article:
It remains to be seen whether the McKitrick and McIntyre study will withstand the ''outside scrutiny'' they have asked for and will no doubt receive. But given the implications of the errors and problems they apparently have unearthed within the Mann study, the two researchers have done a tremendous service to science and the public, which should rely on facts to make informed public policy decisions.
Ridiculous: how can we credit a "tremendous service" before the data is evaluated. If it is bogus, won't these people have performed a tremendous disservice?
My own observation has been that soccer moms tend to be unselfish types who drive older minivans (and need them for the soccer kids and their gear). It is the DINKS who drive the Stupid Ugly Vehicles (guzzlers): frequently techies.
The syslogd in Unix has been doing this for more than 10 years: Supplying an error string for _any_ level of problem: info, warning, error, fatal, and sending to a place specified in an external config file, (including uucp (telephone)) destinations, and specifying quite complex error info, such as the program, the authority it was executing under, the actual problem, and in many cases, the correction is implied in the message (such as could not write to device, ID=0, ID required=12, or: no space left on device, etc etc.
As an older (40+) music lover, I would pay for recordings that are "out of print", or otherwise unavailable. Anyone who could distribute that kind of material could have my $5 per CD worth anyday.
The way to make money has always been to implement a sound method and improve it over time. The point being made is that it has never proven neccesary or useful in the past to allow folks to have exclusive access to a method for decades in order for people to benefit from new ideas. Fortunately for the USA, Henry Ford did not patent the assembly line.
Additionally, it could be argued that housewives and farmers had been using assembly line techniques in day to day chores for millenia. That is one of the key problems with many business patents today: prior art almost always exists, it is just too damned expensive to fight it. One click purchasing indeed. Fume Fume. That sounds to me like patenting a goal, not a method, and a universal goal at that.
Slashdot Mirror
Actually, it did.
I was a Handspring Visor owner, and got hooked on entering my billable hours as appointments in the calendar. I moved to a Teo 650, and loved it bar I had to buy some software and customize my firmware (to "see" the 4GB SD) to use it as a real music player (Audiogateway for Bluetooth, pTunes as a player). That phone was stolen (by some thieving motherfxxxx may he/she rot in hell forever). I replaced it with a Centro (and didn't have to replace my firmware - but still needed the software). I love the Centro now. It has one or two issues, but for what I actually use it for, it is the best phone on the market (and pretty cheap in the US, I hear).
It seems everyone has read only one line of my question. For those of you who know who you are, Once Again: I suspect a 5 GHz CPU in a current system will not be twice as fast as a 2.5 GHz system. In fact, my own experience is that even in CPU intensive stuff, one will be lucky to get a 15% increase in performance. And for most jobs, this will not be noticeable. For some jobs, for sure, a fster CPU will always help. But better software would help all jobs.
WHAT I AM SAYING IS THAT THE BIGGER BENEFIT WILL COME FROM THE ADDRESS SPACE of 64 bits. In fact, 32 bit CPUs will probably be faster than 64 bit CPUs for many tasks, but 64 bit CPUs will lead to more reliable software.
Hhmmm, I had no idea GPU power has so eclipsed DSPs. However, this is still beside the point, since it is not established that 64 bit inherantly provides much more raw performance in a direct way, and even more speculative is whether current architecture and OS can deliver significantly more real performance with a 64 bit system. I am simply stating that 64 bit may be providing a much more general improvement than simply a performance one. For the performance boosts for your application, multiple servers such as in a Beowulf cluster seem like a logical choice, once one runs into the ceiling of what any single CPU system can handle.
I can build 4 1.6 GHz systems for the price of one 64 bit system today. They can have gigabit networking, a good cluster OS, and probably beat the pants off the 64 bit system in crunching those RF DSP algorithms.
I am arguing that the bigger gain from 64 bit computing may lie in the vast simplification of device handling now that the theoretical address space can dwarf the achievable addressable size of devices.
I don't think "very wrong" is on the mark. I was perhaps over generalizing, as are you if you think that most people need the raw horsepower you need. I was thinking about folks that use word processors, browse the web, send e-mail, play games: you know, about 99% of CPU users. So for 1% of users, I am "very wrong" in my intentionally controversial opening statement.
My main point (which you appear to have overlooked in your zeal to shoot me down) is that the 64 bit architecture offers something else other than (or instead of) raw performance. If you consider that also "very wrong", would you post your argument concerning that point also?
Also, for your application are there not some useful DSP add-in boards that can supply an order of magnitude increase in performance for DSP? At the price of the high end GPUs one could surely buy a DSP or two and have change left over.
Sorry, but I am not actually answering your question directly, but it is perhaps appropriate because your question begs a bigger question.
I don't think anyone needs more speed than the best 32 bit CPUs provide today. The bigger problem today is bugs. Memory leaks, security flaws, memory protection errors, you name them. If I understand him correctly, Linus Torvals has weighed in to say that 64 bit architecture will allow a new way of addressing devices: 1:1 mapping. This will eliminate a huge amount of paging and cacheing code in OSs. If I read Linus correctly, he is saying that 64 bits is enough to map any entire hard drive space directly into memory. This brings me to the comments of another luminary: Donald Knuth. Knuth has written and demonstrated ways of writing very low bug count software, and created a seminal work, the practical, non-trivial application LaTeX, which I use daily. Knuth has proved that a large complex application with strong change management can achieve a very low bug count and still have enough features to have no real competition in its field.
So what I am getting to is another question: is 64 bits enough, now and forever? I mean will we ever need more address space for anything? So can we write or change our OS so direct mapping of everything is the norm, and thus eliminate half the cleverness and most of the bugs in the OS? And expect that this will be "the last re-write". That all that will be needed in the future is new device drivers and re-compiles for new CPUs?
No, they have an agenda. They have a belief that they feel strongly about, and they want others to either believe it too, or at least be held to the constraints that those beliefs create. This is every bit as greedy has having that "belief" be that my bank account should be the biggest or that Globex-MegaCorp's belief that their balance sheet is the most important thing in the world. Remember, having what one thinks in ones brain is a "good" motive does not justify acts that potentially harm (physically, financially, or otherwise) others. Having a belief that my bank account should be the biggest is clearly of no great help to others in general. Having a belief that it is important to keep the air clean and the climate within bounds is clearly of benefit to others. You need to work on your definition of good. On the issue of the cure being worse than the illness: in order to maintain the US dependancy on fossil fuels, americans are dying daily in Iraq. The Great Lakes are being poisoned by midwest power stations (an adult can only safely eat 6 annual portions of fish from some great lakes). Is it really worthwhile to push for the economy the economy the economy when real people are getting sick? Funny you say that when the article mentions NOTHING about any business being involved in the contradicting studies. As far as I can see, YOU'RE the only one even mentioning business or the profit motive into this equation. I would say that anyone completely believing in EITHER side is just as bad as anyone completely believing in the OTHER side. Note that the two report authors are: an economist, and a statistic expert working in the minig industry. These are unbiased people? And from the US Today article: It remains to be seen whether the McKitrick and McIntyre study will withstand the ''outside scrutiny'' they have asked for and will no doubt receive. But given the implications of the errors and problems they apparently have unearthed within the Mann study, the two researchers have done a tremendous service to science and the public, which should rely on facts to make informed public policy decisions. Ridiculous: how can we credit a "tremendous service" before the data is evaluated. If it is bogus, won't these people have performed a tremendous disservice?
My own observation has been that soccer moms tend to be unselfish types who drive older minivans (and need them for the soccer kids and their gear). It is the DINKS who drive the Stupid Ugly Vehicles (guzzlers): frequently techies.
The syslogd in Unix has been doing this for more than 10 years: Supplying an error string for _any_ level of problem: info, warning, error, fatal, and sending to a place specified in an external config file, (including uucp (telephone)) destinations, and specifying quite complex error info, such as the program, the authority it was executing under, the actual problem, and in many cases, the correction is implied in the message (such as could not write to device, ID=0, ID required=12, or: no space left on device, etc etc.
As an older (40+) music lover, I would pay for recordings that are "out of print", or otherwise unavailable. Anyone who could distribute that kind of material could have my $5 per CD worth anyday.
The way to make money has always been to implement a sound method and improve it over time. The point being made is that it has never proven neccesary or useful in the past to allow folks to have exclusive access to a method for decades in order for people to benefit from new ideas. Fortunately for the USA, Henry Ford did not patent the assembly line. Additionally, it could be argued that housewives and farmers had been using assembly line techniques in day to day chores for millenia. That is one of the key problems with many business patents today: prior art almost always exists, it is just too damned expensive to fight it. One click purchasing indeed. Fume Fume. That sounds to me like patenting a goal, not a method, and a universal goal at that.