Actually, returning the data in 1,3,2 order would be the older ATA "tagged command queueing" way of doing things, where commands had to complete in-order. In SCSI TCQ and the new non-brain-damaged ATA NCQ the drive would return the data in the 1,2,3 order, which is different from the order that the OS requestd them in, but minimizes the amount of time an application must wait for its data. SCSI TCQ and ATA NCQ are about out-or-order COMPLETION, not just out-of-order EXECUTION.
Well, I was cautiously optomistic until I saw it was from BYU. Now I think it's just B.S. Sorry, but they are not known for being smart about this sort of thing.
Then we agree: random does not mean orderless. Evolution depends on random mutation events that are constrained by natural selection to filter out bad adaptations/mutations. Therefore the argument that evolution can't be corrent because it is random can only be made by people who don't understand randomness does not mean white noise or 50-50 coin tosses.
Look at the graduate level math of engineering random processes, and you'll see that the majority of random processes that engineers deal with are NOT dominated by randomness, they have some order despite having a random nature. An example is the sound made by a flute when you first blow into it, it starts out as noise, but with each soscilation it becomes more and more pure in tone, unitl you get a clean sounding note. That is an example of a random process, that is not completely nondeterministic. If you argue that it's not random it just indicates you have a crappy understanding of what random means. Not every random process is a coin toss or white noise.
In a nutshell: old-style IDE TCQ is totally brain damaged and allows out of order execution, but only in-order completion, in other words the disk may have the data ready for your nth request, but can't give them to you until it gets the data for the first, second, third,.....(n-1)th requests. So the seeking may go faster, but you still have to wait longer than with SCSI TCQ, which leads to the question of why even bother?
There are better algorithms than elevator, especially since the disk knows it's rotational position and elevator doesn't even use that info.
The specific algorithm used to makes a group of outstanding requests complete the fastest is up to the disk, some will have good algorithms others will not. The point is that without having command queueing in the protocol you can't use ANY algorithm, and are stuck with in-order seeking.
What about this is news? Well for years I have been telling people that SCSI drives are not just overpriced IDE drives with a different connector, and that the speed difference is due to the protocol, not the raw transfer rate, and I've heard people with their egos bruised by not having the fastest computer parts tell me "no it's not, look at these crappy single-user benchmark scores, the IDE drives with 16 MB of write-back cache turned on by default outperform the scsi disk that are actually writing the data to disk by 1%". All of a sudden they will all say "command queueing is so great!" now that their computers support it. Kinda like mac people said PPC was SO much better until apple switched to intel.
So the news is the the IDE vs SCSI flamewar will switch from "SCSI is better... no it's not" to "now that SATA caught up 10 years later SCSI was never better........ yes it was"
1) I said questions about bush's actions are more important than questions about kerry's character, so your objection is misplaced.
2) treason is giving aid to the enemy, as in getting your own guys killed so that the other guys can win. If speaking out against a unnecessary war qualifies as wanting the other side to win, or qualifies as killing your own guys, then lots of us are guilty of treason, and some may argue that being treacherous (by your definition) is morally obligated, making those of us who are not traitors the bad guys.
In summary, hatred of kerry, whether rational or irrational doesn't change the fact that the bush administration is too closed for many people's likings. For instance Why are the names of the people on Cheney's energy task force secret? Why on earth should that be a secret? Hating kerry doesn't fill the void left by those nagging questions.
Anyway slashdot must be broken for us to be having this discussion between the 2 of us.
All wonderfull questions, and all besides the point that I wish the bush administration was more open.
As for Kerry's discharge, I seem to remember a guy by the name of Nixon who tried to have kerry ruined for his testimony before the senate against the war. Who knows what tricks he might have played via command pressure? not me. I also don't know what tricks bush played regarding his service. Seeing as Bush is president (not kerry), and bush started a war (not kerry) I think the questions about Bush ACTIONS are more important than questions about kerrys character.
Hey guys, I used to work in the phone industry. I think that they should never have allowed phones without 911 in the first place, but it is ineveitable that people will die "beacause of this" if it isn't fixed simply because your 911 service is not there to save only your own ass. If your neighbor comes pounding on your door saying their houses in on fire, and your 911 is broken then their lives are in danger, even if they didn't chose to have some braind-damaged non-911 phone service.
911 is NOT all about YOU and YOUR SAFETY. It's about te safety of anyone who happens to be near your phone.
I am not a psychologist, but feel qualified to say that the morons who think they can place autistic spectral disorders into a place on the GENDER scale are idiots, and that is what people call "poop psychology" when it gets printed in popular pschyology magazines.
Women are from venus, men are from mars, autists are from jupiter is just the most simple-minded non-scientific bullshit. Just because "women are more in touch with other people's feelings" doesn't mean that autists are the extreme of masculinity any more than "Slackware users tend to tweak their systems by hand with vi" means an emacs user is a Suse extremist. What's next? Pepole prone to panic attacks are just extremely feminine?
The energy per photon is just too low to break covalent bonds, so there is no way microwave energy could break DNA directly, unless you pump in enough energy to cook it.
You don't have to break the DNA molecule to cause damage, you only have to change its chemistry long enough for it to react with some other chemical in its surroundings, which is how the real damage from "ionizing" radiation happens.
BUT ionization is only one possible result of exciting a DNA molecule. Basically if you start with a molecule in the ground state, and hit it with a photon its electrons can be raised to a higher energy level, and if the photon has enough energy it can rip the electron right out of the molecule, thus altering its chemistry significantly. Microwaves are non-ionizing: they can't rip the electron completely away, but they CAN raise it to an excited state, and those excited states have different chemistry than the ground state molecule. Also a photon can raise the molecule into an non-electronic excited state, say a vibrational or rotationally excited state, which can also change the chemistry of the molecule.
In summary:
Ionizing radiation is dangerous. and Microwaves are non-ionizing radiation.
therefore microwaves are not dangerous via the ionization mechanism, but may be dangerous via some other mechanism.
Actually sir, if the indians had been given a deadly disease like measles, and ONLY measles their population would have bounced back in a generation or two with disease resistance. Instead the were finished off by europeans while they were in a weakened state. If every white guy had been a quaker the indians would NOT have all been killed off while in their weakened state, and therefore they WERE NOT "basically doomed to die", as people of questionable moral intent might put it.
Your analysis of this chapter of history is so poor that it makes everything else you say suspect.
You are a fuckng pompus ass... no wait, sorry, you hit one of my buttons.
ECC codes CAN and DO cover packet loss if you interleave the ECC information accross packets, instead of just generating it for a single packet. In this scenario lost packets are called "Erasures", and their coding is "rateless erasure coding". It will work just fine.
No, multiple modules will never be faster -- a mulit-channel controller will be the same with one or two modules; slower with more than two (which is possible.)
you seem to be confusing the concept of "multi" with the concept of "dual". My computer has quad memory channels. In my computer of course 4 will be faster than 2, not in latency, but in data transfer rate ("bandwidth").You need BOTH, I guess some riced-out overclockers might have missed the fact that MHz isn't everything.
Re:Dangers of using ATA or SATA for Raid
on
SATA vs ATA?
·
· Score: 2, Interesting
Actually I just had a 120GB maxtor drive that i used to replace a 60GB one that had failed give me kernel messages to the effect off "flush cache command failed", meaning the disk refused to obey when the kernel told it to flush the write-back cache (probably to make windows benchmarks look better). Why should I trust this drive when I tell it to disable to write-back cache entirely?
Furthermore, if I am using a hardware raid how do I use hdparm? And finally, ATA drives have write-back ON by default, SCSI drives have it OFF by default.
more registers sure as hell makes things easier, and it will speed up execution even with all those "advanced optimizations" you mentioned. Even with register renaming you still have a load/store every 5th instruction or so, and even if those load/stores execute instantly you have a bunch of useless instructions clogging your datapath. With more program-visible registers fewer spills occur, leaving more room for real instructions in the piepline.
You see, you CAN have PRIVATE news servers with PRIVATE newsgroups using exsisting usenet technology. You just have to not specify any news peers, and require login/passwords.
TV's don't have anti-comb filters, they have COMB filters. A comb filter picks up several equaly spaced frequency ranges, and has a frequency response that looks like a comb turned bristle-side-up. This is needed to seperate the Y and C channels, since the C channel is made up of harmonics riding on the color subcarrier, that sit in the middle of the Y signal's frequency spectrum.
Some of your points make me question weather you understand the concepts here.
FPGA's can't handle the complexity for the programs we write today for general computer use
Sure they can! You can implement a general purpose CPU inside an FPGA; it would be slow and expensive compared to a real CPU, but it would be able to run any general purpose algorithm you can think of. There is no fundamental reason why you can't do anything with an FPGA, it all comes down to the PARTICULAR task at hand, and how best to accomplish it.
FPGA's are much more expensive in terms of power and cost than an equivilant processor/ASIC/specific purpose chip
This is only true if you think of an FPGA as a replacement for a regular CPU, running regular software. But there are 2 easy examples of tasks where and FPGA is cheaper, and more powerful. The first is when you have several programs or ASICS that are only used one at a time, which you can replace by a single FPGA that switches configuration as needed. The second is for specialized software tasks that are rarely used, so they're not worth optimizing a general purpose CPU for, but used a lot in certain situations. An example is high volume cryptography -- you can buy a fixed function card that does the work for you, but what if a new algorithm comes out? You have to buy a new card! with an FPGA approach you can just update the functionality, and re-use the silicon to perform other tasks when you're not doing cryptography!
Another thing to keep in mind is that ASICS are only cheaper than FPGAs if you get into high volumes... In many cases off the shelf FPGAs are cheaper than ASICs until your product starts to sell in high volumes.
FPGA's are exceedingly slow.
BULLSHIT!!! My 89 corvette is exceedingly slow too, I guess. I don't know where you get this idea from. The speed you get out of an FPGA is entirely a function of how you choose to design the circuit inside it. The bigger the design the greater the potential speed. FPGAs can run moderate designs in the hundreds of MHz, and not CPU-like single operation at a time MHz, more like completely pipelined, one datachunk fully processed per clock MHz.
In order to make them worthwhile, the hardware algorithm they contain must be massively parallel, or not require speeds that modern processors can attain - which leads back to the FPGA's cannot represent extrememly complex systems yet.
Actually, FPGAs do better on tasks that are pipelinable and not just parallel, which basically includes all kinds of number cruching, and bit twidling.
You need to better define what you mean by complex systems. Nobody is advocating implementing powerpoint in an FPGA, researchers are trying to offload tasks that usually require specialized hardware to programable hardware, not replace cheap CPUs with expensive FPGAs for no reason.
Those people who have an interest in both software and hardware tend to lean to one side or the other, and end up writing drivers for embedded systems, or designing hardware for embedded systems, very few actually participate in the whole enchillada because of the complexity fo the complete system
My intrest in this area comes from the fact that when the hardware arrives, the software team and hardware team spend a few months blaming each other while the bugs are worked out. If they worked together they would have a competitive advantage by getting to market sooner.
There's still a metric ton and many years of research work to be done behind the idea of a language that can be translated into both hardware and software
And it's a metric ton of high paying, fun work, and I don't see anything wrong with that.
LaTeX Project Public License. The LaTeX Project Public License (LPPL) has previously been considered non-free under the terms of the Debian Free Software Guidelines (DFSG). Jeff Licquia has now posted a new revision of the LPPL, which he believes satisfies the DFSG. There was general agreement that the new license is DFSG-free and after a year of work and perhaps 1,500 emails in total, the issue should hopefully be resolved.
Slashdot Mirror
Actually, returning the data in 1,3,2 order would be the older ATA "tagged command queueing" way of doing things, where commands had to complete in-order. In SCSI TCQ and the new non-brain-damaged ATA NCQ the drive would return the data in the 1,2,3 order, which is different from the order that the OS requestd them in, but minimizes the amount of time an application must wait for its data. SCSI TCQ and ATA NCQ are about out-or-order COMPLETION, not just out-of-order EXECUTION.
Well, I was cautiously optomistic until I saw it was from BYU. Now I think it's just B.S. Sorry, but they are not known for being smart about this sort of thing.
Then we agree: random does not mean orderless. Evolution depends on random mutation events that are constrained by natural selection to filter out bad adaptations/mutations. Therefore the argument that evolution can't be corrent because it is random can only be made by people who don't understand randomness does not mean white noise or 50-50 coin tosses.
Look at the graduate level math of engineering random processes, and you'll see that the majority of random processes that engineers deal with are NOT dominated by randomness, they have some order despite having a random nature. An example is the sound made by a flute when you first blow into it, it starts out as noise, but with each soscilation it becomes more and more pure in tone, unitl you get a clean sounding note. That is an example of a random process, that is not completely nondeterministic. If you argue that it's not random it just indicates you have a crappy understanding of what random means. Not every random process is a coin toss or white noise.
The number of heads doesn't matter because they can't move independently.
In a nutshell: old-style IDE TCQ is totally brain damaged and allows out of order execution, but only in-order completion, in other words the disk may have the data ready for your nth request, but can't give them to you until it gets the data for the first, second, third, .... .(n-1)th requests. So the seeking may go faster, but you still have to wait longer than with SCSI TCQ, which leads to the question of why even bother?
NCQ allows out-of-order completion.
There are better algorithms than elevator, especially since the disk knows it's rotational position and elevator doesn't even use that info.
The specific algorithm used to makes a group of outstanding requests complete the fastest is up to the disk, some will have good algorithms others will not. The point is that without having command queueing in the protocol you can't use ANY algorithm, and are stuck with in-order seeking.
What about this is news? Well for years I have been telling people that SCSI drives are not just overpriced IDE drives with a different connector, and that the speed difference is due to the protocol, not the raw transfer rate, and I've heard people with their egos bruised by not having the fastest computer parts tell me "no it's not, look at these crappy single-user benchmark scores, the IDE drives with 16 MB of write-back cache turned on by default outperform the scsi disk that are actually writing the data to disk by 1%". All of a sudden they will all say "command queueing is so great!" now that their computers support it. Kinda like mac people said PPC was SO much better until apple switched to intel.
... no it's not" to "now that SATA caught up 10 years later SCSI was never better ........ yes it was"
So the news is the the IDE vs SCSI flamewar will switch from "SCSI is better
how can I?
two ways:
1) I said questions about bush's actions are more important than questions about kerry's character, so your objection is misplaced.
2) treason is giving aid to the enemy, as in getting your own guys killed so that the other guys can win. If speaking out against a unnecessary war qualifies as wanting the other side to win, or qualifies as killing your own guys, then lots of us are guilty of treason, and some may argue that being treacherous (by your definition) is morally obligated, making those of us who are not traitors the bad guys.
In summary, hatred of kerry, whether rational or irrational doesn't change the fact that the bush administration is too closed for many people's likings. For instance Why are the names of the people on Cheney's energy task force secret? Why on earth should that be a secret? Hating kerry doesn't fill the void left by those nagging questions.
Anyway slashdot must be broken for us to be having this discussion between the 2 of us.
All wonderfull questions, and all besides the point that I wish the bush administration was more open.
As for Kerry's discharge, I seem to remember a guy by the name of Nixon who tried to have kerry ruined for his testimony before the senate against the war. Who knows what tricks he might have played via command pressure? not me. I also don't know what tricks bush played regarding his service. Seeing as Bush is president (not kerry), and bush started a war (not kerry) I think the questions about Bush ACTIONS are more important than questions about kerrys character.
here you go:
of course you may have to use the wayback machine on those URLs
http://www.awolbush.com/kerry-vs-bush.asp
if only the bush administration was this open.
Hey guys, I used to work in the phone industry. I think that they should never have allowed phones without 911 in the first place, but it is ineveitable that people will die "beacause of this" if it isn't fixed simply because your 911 service is not there to save only your own ass. If your neighbor comes pounding on your door saying their houses in on fire, and your 911 is broken then their lives are in danger, even if they didn't chose to have some braind-damaged non-911 phone service.
911 is NOT all about YOU and YOUR SAFETY. It's about te safety of anyone who happens to be near your phone.
I am not a psychologist, but feel qualified to say that the morons who think they can place autistic spectral disorders into a place on the GENDER scale are idiots, and that is what people call "poop psychology" when it gets printed in popular pschyology magazines.
Women are from venus, men are from mars, autists are from jupiter is just the most simple-minded non-scientific bullshit. Just because "women are more in touch with other people's feelings" doesn't mean that autists are the extreme of masculinity any more than "Slackware users tend to tweak their systems by hand with vi" means an emacs user is a Suse extremist. What's next? Pepole prone to panic attacks are just extremely feminine?
Here's a very off-topic answer
There is MORE THAN ONE political party that calls themselves "The green party" Make sure you are reading the platform of the correct party.
You don't have to break the DNA molecule to cause damage, you only have to change its chemistry long enough for it to react with some other chemical in its surroundings, which is how the real damage from "ionizing" radiation happens.
BUT ionization is only one possible result of exciting a DNA molecule. Basically if you start with a molecule in the ground state, and hit it with a photon its electrons can be raised to a higher energy level, and if the photon has enough energy it can rip the electron right out of the molecule, thus altering its chemistry significantly. Microwaves are non-ionizing: they can't rip the electron completely away, but they CAN raise it to an excited state, and those excited states have different chemistry than the ground state molecule. Also a photon can raise the molecule into an non-electronic excited state, say a vibrational or rotationally excited state, which can also change the chemistry of the molecule.
In summary:
Ionizing radiation is dangerous.
and
Microwaves are non-ionizing radiation.
therefore microwaves are not dangerous via the ionization mechanism, but may be dangerous via some other mechanism.
Actually sir, if the indians had been given a deadly disease like measles, and ONLY measles their population would have bounced back in a generation or two with disease resistance. Instead the were finished off by europeans while they were in a weakened state. If every white guy had been a quaker the indians would NOT have all been killed off while in their weakened state, and therefore they WERE NOT "basically doomed to die", as people of questionable moral intent might put it.
Your analysis of this chapter of history is so poor that it makes everything else you say suspect.
You are a fuckng pompus ass...
no wait, sorry, you hit one of my buttons.
ECC codes CAN and DO cover packet loss if you interleave the ECC information accross packets, instead of just generating it for a single packet. In this scenario lost packets are called "Erasures", and their coding is "rateless erasure coding". It will work just fine.
No, multiple modules will never be faster -- a mulit-channel controller will be the same with one or two modules; slower with more than two (which is possible.)
you seem to be confusing the concept of "multi" with the concept of "dual". My computer has quad memory channels. In my computer of course 4 will be faster than 2, not in latency, but in data transfer rate ("bandwidth").You need BOTH, I guess some riced-out overclockers might have missed the fact that MHz isn't everything.
Actually I just had a 120GB maxtor drive that i used to replace a 60GB one that had failed give me kernel messages to the effect off "flush cache command failed", meaning the disk refused to obey when the kernel told it to flush the write-back cache (probably to make windows benchmarks look better). Why should I trust this drive when I tell it to disable to write-back cache entirely?
Furthermore, if I am using a hardware raid how do I use hdparm? And finally, ATA drives have write-back ON by default, SCSI drives have it OFF by default.
more registers sure as hell makes things easier, and it will speed up execution even with all those "advanced optimizations" you mentioned. Even with register renaming you still have a load/store every 5th instruction or so, and even if those load/stores execute instantly you have a bunch of useless instructions clogging your datapath. With more program-visible registers fewer spills occur, leaving more room for real instructions in the piepline.
Actually it is STILL just usenet.
You see, you CAN have PRIVATE news servers with PRIVATE newsgroups using exsisting usenet technology. You just have to not specify any news peers, and require login/passwords.
I did this years ago.
TV's don't have anti-comb filters, they have COMB filters. A comb filter picks up several equaly spaced frequency ranges, and has a frequency response that looks like a comb turned bristle-side-up. This is needed to seperate the Y and C channels, since the C channel is made up of harmonics riding on the color subcarrier, that sit in the middle of the Y signal's frequency spectrum.
Sure they can! You can implement a general purpose CPU inside an FPGA; it would be slow and expensive compared to a real CPU, but it would be able to run any general purpose algorithm you can think of. There is no fundamental reason why you can't do anything with an FPGA, it all comes down to the PARTICULAR task at hand, and how best to accomplish it.
This is only true if you think of an FPGA as a replacement for a regular CPU, running regular software. But there are 2 easy examples of tasks where and FPGA is cheaper, and more powerful. The first is when you have several programs or ASICS that are only used one at a time, which you can replace by a single FPGA that switches configuration as needed. The second is for specialized software tasks that are rarely used, so they're not worth optimizing a general purpose CPU for, but used a lot in certain situations. An example is high volume cryptography -- you can buy a fixed function card that does the work for you, but what if a new algorithm comes out? You have to buy a new card! with an FPGA approach you can just update the functionality, and re-use the silicon to perform other tasks when you're not doing cryptography!
Another thing to keep in mind is that ASICS are only cheaper than FPGAs if you get into high volumes... In many cases off the shelf FPGAs are cheaper than ASICs until your product starts to sell in high volumes.
BULLSHIT!!! My 89 corvette is exceedingly slow too, I guess. I don't know where you get this idea from. The speed you get out of an FPGA is entirely a function of how you choose to design the circuit inside it. The bigger the design the greater the potential speed. FPGAs can run moderate designs in the hundreds of MHz, and not CPU-like single operation at a time MHz, more like completely pipelined, one datachunk fully processed per clock MHz.
Actually, FPGAs do better on tasks that are pipelinable and not just parallel, which basically includes all kinds of number cruching, and bit twidling.
You need to better define what you mean by complex systems. Nobody is advocating implementing powerpoint in an FPGA, researchers are trying to offload tasks that usually require specialized hardware to programable hardware, not replace cheap CPUs with expensive FPGAs for no reason.
My intrest in this area comes from the fact that when the hardware arrives, the software team and hardware team spend a few months blaming each other while the bugs are worked out. If they worked together they would have a competitive advantage by getting to market sooner.
And it's a metric ton of high paying, fun work, and I don't see anything wrong with that.
from the current issue f debian weekly news:
LaTeX Project Public License. The LaTeX Project Public License (LPPL) has previously been considered non-free under the terms of the Debian Free Software Guidelines (DFSG). Jeff Licquia has now posted a new revision of the LPPL, which he believes satisfies the DFSG. There was general agreement that the new license is DFSG-free and after a year of work and perhaps 1,500 emails in total, the issue should hopefully be resolved.