IIRC, some researchers had succeeded in making cables suitable for data transmission from some plastic. dirt cheap, and quite fast too (of course not as good as single mode fiber, but better than copper).
Bzzt, wrong! More efficient can mean bigger, but it can also mean cleaner (i.e., less fallout) and cheaper. Cleaner is obviously good: a war would kill fewer people in less gruesome ways, and clean bombs are a better deterrent. Cheaper is also good, since all the bombs will have to be rebuilt from scratch in the fairly near future. (Don't give me any garbage about nuclear disarmament. It'll never happen, anybody who thinks it will is deluded.)
Bzzt, wrong! (heard that one before?:)) In real life, bigger does not mean cleaner. Well, yes theoretically it's possible to design a big bomb with relatively smaller fallout than a smaller one (there's a minimum size for the fission trigger which in this hypothetical weapon would be the main cause of fallout). But, in real life the current generation warheads have about 50% of the energy output coming from fission. The reason is that as you said in another paragraph the cost of the delivery vehicles dwarf the cost of the warheads themselves. Making the bomb casing (which needs to be made of a high-Z material anyway) of a fissile material (usually enriched uranium) gets you a bigger bang for the buck. Read the Nuclear Weapons FAQ by Carey Sublette for a more thorough explanation of this.
Talking about cpu reviews, does anyone know if there is some hardware site that does reviews on Linux? While I don't usually bother to follow these hardware sites that closely anymore I think it would be interesting to see how these cpu:s compare under Linux. Say some benchmark like the linpack benchmark using generic compiler options usually found in binary packages and also effects of cpu-specific optimizations gcc can achieve. I read some time ago that gcc could optimize better for intel cpu:s than for athlons, is that still true? At least for me that would be more interesting to know than whatever >200 fps they can achieve in quake 3.
No. perl6 will (hopefully) be a natural upgrade path for perl programmers. Ruby is still just a python clone with some perl-like syntax thrown in which noone uses.
It is a great box but only if you use half of the CPU's. not enough cache to go around on the dual cpu boards so IBM has to disable half of them and sell them as 16 ways. Kinda sad.
And their switch architech for connecting them together is slow and has a relative high latency. But for what they are charging...
It is a SUN killer not a HPTC box. They have been telling their customers for the last two years that this box is for TPC not HPTC. HPTC low margin. TPC high margin. They want the HPTC customers to migrate towards linux.
Thier switch is not even really ready for prime time on these boxes.
Here you can see some benchmarks comparing the 32-way p690 with the 16-way HPC (ie. same machine but with only one cpu per power4 chip). The HPC achieves about 80% of the p690 performance. While this is impressive and suggests that the 2-cpu power4 suffers from L2 cache bandwidth I still think this is a semi-low-end configuration. When you want many cpu:s the internode bandwidth and latency is probably going to be more important. I.e. if you want say 512 cpu:s then 16 32-way p690:s are probably going to be faster than 32 16-way HPC:s, depending on your application of course. Not to mention reduced space, electricity and cooling requirements.
And also IIRC their switch so far supports only 16 nodes, although IBM claims it will support 128 nodes by the end of the year. And I wouldn't call it slow either, speed is 1GB/s (that's gigaBYTES, not gigaBITS), which is about the same as the T3E IIRC.
Finally, I'd say it's very much a HPC box in addition to a SUN killer. Take a look at the top500 list. There's lots of IBM SP:s there at the top isn't it? The p690 is essentially a SP with the 375 MHz power3:s replaced by 1+ GHz power4:s. Same goes for the switch. It's an upgraded version of the SP switch.
Of course all these IBM machines are seriously smoked by this new Japanese earth simulator machine, which is supposed to be 5 times faster than the current top500 #1, the ASCI white (an IBM SP with 8192 cpu:s).
Uh, yes. You're correct. T3:s are all alpha based. Guess it was just some idea I got when I was on a tour of the local supercomputer center a few years ago (they have a T3E with 375MHz CPU:s)...
It's interesting to note that while Vader does know he had a child, it isn't until he reads Luke's mind in ROTJ does he realize he had twin children.
I don't see any inconsistency here. Anakin bangs wife -> wife gets pregnant. Even Anakin should understand that his wife is pregnant even if she wouldn't tell him, no matter how dim-witted he is. And seing how he acted in "Attack of the clones", that is plenty dimwitted indeed. Anyway, so Anakin joins Palpatine (hey, I would too if I'd get that cool black helmet with The-breathing-sound) and leaves Padme. Or maybe Padme dumped Anakin? You know, maybe she wasn't satisified, or she was plain weirded out when Anakin fingered her with that robotic hand (you can see the robot hand at the end of "attack of the clones")?;-D
At least some older T3s used MIPS processors (probably during the time they were owned by silicon graphics). Nowadays they seem to be concentrating on their new SV2 vector supercomputer, which has cray designed processors. I guess developing a successor to the T3E is not really viable any longer as clusters like the IBM system I descibe in the above post or even el cheapo Linux/Intel clusters do essentially the same thing as a T3E type computer at significantly lower cost. In fact, Cray sells Linux clusters these days (iron provided by Dell).
Power4... still competitive in performance but AFAIK to get a high end system you need to give your first born to IBM. And, IMO not really designed for the HPC kind of stuff I'm interested in.
Huh??? What are you smoking?:) The HPC market is one of the primary markets for the power4, the other being big enterprise systems. In fact, CSC, the Finnish national supercomputer center is currently installing their new toy, a power4 machine which will have 512 processors when it's finished in september. FYI, that's 256 power4 chips, as one chip has 2 cpu cores. Anyway, the design consists of 16 fairly standard 32 cpu pSeries 690 refrigerator sized boxes. Currently I think they are connected with gigabit ethernet or something like that, but during the summer a proprietary IBM high speed interconnect will be installed. Total performance is estimated to be about 2.2 teraflops, more than 4 times faster than the old 540 cpu Cray T3E, and placing the computer among the fastest in Europe. Currently I think 6 nodes are operational...
BRAG MODE ON And I have an account on that baby!!! *Drool* Wonder how many fps quake would get?;-) BRAG MODE OFF No seriously, they naturally have a strict policy on what you are allowed to run on it. You have to fill out forms requesting cpu hours with project descriptions etc. etc. Anyway, my plan is to run ab initio calculations on it. Hopefully that is. They're having some serious problems, related to MPI, I think... Which has led to the fact that everyone is submitting the big jobs they planned to run on it to the old T3E, which is rapidly getting overloaded...:(
Actually the LSB says you have to support installing RPM packages, but not that you have to use rpm to do that. From http://www.linuxbase.org/spec/refspecs/LSB_1.1.0/g LSB/swinstall.html I got the following: "Applications should be provided in the RPM packaging format as defined in the appendix of Maximum RPM" and "The LSB does not specify the interface to the tools used to manipulate LSB-conformant packages. Each conforming distribution will provide documentation for installing LSB packages."
Debian supports installing rpm's through the alien program which converts rpm's into deb's (or tgz's for other distro's). I've done this myself several times. It also supports creating LSB-compatible rpm's through the lsb-rpm package. Hence, in this regard, debian is LSB compliant. As far as I know (and I admit it's not my domain of expertise) debian has no problems reaching full LSB compliance, and debian 3.0 will be LSB-compliant. At least that's what they're aiming for.
Good points. But unfortunately debian 3.0 won't be LSB compliant, IIRC. I think the main problem lies in runlevels, and init.d script installation.
PostgreSQL blob api also sucks golfballs through a waterhose, but as of pgSQL 7.1 there is no row lenght limit any longer. So you could stuff an arbitrarily long attatchment as a TEXT or VARCHAR field.
It's all there in the JFS todo list which can be seen here. Extending is apparently going to be implemented RSN, and ACL:s seem to be a longer term project.
Yes exactly! What an evil bait to link the words "hosting nude doctored photos of her. "!!! Would I have clicked the link if I had known it was just a boring press release? NO, NO, NO!!!;-)
Damnit! Now I'm extra proud of being a Finn. Our parliament made the right decision. I'm happy they weren't swayed by all kinds of luddites with absolutely no clue about the issues regarding nuclear power.
No mention of noise, or rather the lack of it, in the article? Pretty important IMHO, unless you're just gonna watch Top Gun over and over again. Those jet eng^D^D^D^D^D^D^D fans make me crazy!
There are no plans to make a microscopic nuclear reactor, according to the article. So there's nothing there going critical. Essentially they were talking about the kind of nuclear batteries that have been in use for a long time already on space craft and such.
Yep, you're right. Way back when I was going to buy a soundcard for my familys 16MHz 386 (which at the time was a really high end machine) there wasn't much choice. There were no soundcard drivers with a unified API in DOS, so every game had to support your particular soundcard. And they all supported Adlib. SoundBlaster was Adlib compatible, and had a joystick port. So in the end it was an easy choice.
Slashdot Mirror
IIRC, some researchers had succeeded in making cables suitable for data transmission from some plastic. dirt cheap, and quite fast too (of course not as good as single mode fiber, but better than copper).
Yes, and myrinet (wulfkit/quadrics/via/whatever) makes Gb ethernet seem dirt cheap by comparison...:(
Like, say, Qt and MySQL... And a lot of other programs using similar schemes.
Bzzt, wrong! More efficient can mean bigger, but it can also mean cleaner (i.e., less fallout) and cheaper. Cleaner is obviously good: a war would kill fewer people in less gruesome ways, and clean bombs are a better deterrent. Cheaper is also good, since all the bombs will have to be rebuilt from scratch in the fairly near future. (Don't give me any garbage about nuclear disarmament. It'll never happen, anybody who thinks it will is deluded.)
Bzzt, wrong! (heard that one before?
Talking about cpu reviews, does anyone know if there is some hardware site that does reviews on Linux? While I don't usually bother to follow these hardware sites that closely anymore I think it would be interesting to see how these cpu:s compare under Linux. Say some benchmark like the linpack benchmark using generic compiler options usually found in binary packages and also effects of cpu-specific optimizations gcc can achieve. I read some time ago that gcc could optimize better for intel cpu:s than for athlons, is that still true? At least for me that would be more interesting to know than whatever >200 fps they can achieve in quake 3.
Well, unless you're running apache 2.x, it ain'tthreaded...
And thttpd is imho a select() based webserver, which generally means high performance.
Of all the nit-picky things that users bitch about, getting rid of one of them is a Good Thing in my book.
So, where do you dispose of your ex-users?
You know, the heat death of the universe isn't exactly imminent...
So I should just drop down my pants and take a dump when and where I feel like it?
No. perl6 will (hopefully) be a natural upgrade path for perl programmers. Ruby is still just a python clone with some perl-like syntax thrown in which noone uses.
...
;-)
And maybe a gift certificate to Blowfish [blowfish.com]
Hey!! There's that funny looking OpenBSD fish!!
And what, dental dams? What kind of retarded idea is that? Sheesh...
It is a great box but only if you use half of the CPU's. not enough cache to go around on the dual cpu boards so IBM has to disable half of them and sell them as 16 ways. Kinda sad.
And their switch architech for connecting them together is slow and has a relative high latency. But for what they are charging...
It is a SUN killer not a HPTC box. They have been telling their customers for the last two years that this box is for TPC not HPTC. HPTC low margin. TPC high margin. They want the HPTC customers to migrate towards linux.
Thier switch is not even really ready for prime time on these boxes.
Here you can see some benchmarks comparing the 32-way p690 with the 16-way HPC (ie. same machine but with only one cpu per power4 chip). The HPC achieves about 80% of the p690 performance. While this is impressive and suggests that the 2-cpu power4 suffers from L2 cache bandwidth I still think this is a semi-low-end configuration. When you want many cpu:s the internode bandwidth and latency is probably going to be more important. I.e. if you want say 512 cpu:s then 16 32-way p690:s are probably going to be faster than 32 16-way HPC:s, depending on your application of course. Not to mention reduced space, electricity and cooling requirements.
And also IIRC their switch so far supports only 16 nodes, although IBM claims it will support 128 nodes by the end of the year. And I wouldn't call it slow either, speed is 1GB/s (that's gigaBYTES, not gigaBITS), which is about the same as the T3E IIRC.
Finally, I'd say it's very much a HPC box in addition to a SUN killer. Take a look at the top500 list. There's lots of IBM SP:s there at the top isn't it? The p690 is essentially a SP with the 375 MHz power3:s replaced by 1+ GHz power4:s. Same goes for the switch. It's an upgraded version of the SP switch.
Of course all these IBM machines are seriously smoked by this new Japanese earth simulator machine, which is supposed to be 5 times faster than the current top500 #1, the ASCI white (an IBM SP with 8192 cpu:s).
Uh, yes. You're correct. T3:s are all alpha based. Guess it was just some idea I got when I was on a tour of the local supercomputer center a few years ago (they have a T3E with 375MHz CPU:s)...
We're getting DEEP into nerdism here
To say the least...
It's interesting to note that while Vader does know he had a child, it isn't until he reads Luke's mind in ROTJ does he realize he had twin children.
I don't see any inconsistency here. Anakin bangs wife -> wife gets pregnant. Even Anakin should understand that his wife is pregnant even if she wouldn't tell him, no matter how dim-witted he is. And seing how he acted in "Attack of the clones", that is plenty dimwitted indeed. Anyway, so Anakin joins Palpatine (hey, I would too if I'd get that cool black helmet with The-breathing-sound) and leaves Padme. Or maybe Padme dumped Anakin? You know, maybe she wasn't satisified, or she was plain weirded out when Anakin fingered her with that robotic hand (you can see the robot hand at the end of "attack of the clones")?
At least some older T3s used MIPS processors (probably during the time they were owned by silicon graphics). Nowadays they seem to be concentrating on their new SV2 vector supercomputer, which has cray designed processors. I guess developing a successor to the T3E is not really viable any longer as clusters like the IBM system I descibe in the above post or even el cheapo Linux/Intel clusters do essentially the same thing as a T3E type computer at significantly lower cost. In fact, Cray sells Linux clusters these days (iron provided by Dell).
Power4
Huh??? What are you smoking?
BRAG MODE ON
And I have an account on that baby!!! *Drool* Wonder how many fps quake would get?
BRAG MODE OFF
No seriously, they naturally have a strict policy on what you are allowed to run on it. You have to fill out forms requesting cpu hours with project descriptions etc. etc. Anyway, my plan is to run ab initio calculations on it. Hopefully that is. They're having some serious problems, related to MPI, I think... Which has led to the fact that everyone is submitting the big jobs they planned to run on it to the old T3E, which is rapidly getting overloaded...:(
Actually the LSB says you have to support installing RPM packages, but not that you have to use rpm to do that. From http://www.linuxbase.org/spec/refspecs/LSB_1.1.0/
"Applications should be provided in the RPM packaging format as defined in the appendix of Maximum RPM"
and
"The LSB does not specify the interface to the tools used to manipulate LSB-conformant packages. Each conforming distribution will provide documentation for installing LSB packages."
Debian supports installing rpm's through the alien program which converts rpm's into deb's (or tgz's for other distro's). I've done this myself several times. It also supports creating LSB-compatible rpm's through the lsb-rpm package. Hence, in this regard, debian is LSB compliant. As far as I know (and I admit it's not my domain of expertise) debian has no problems reaching full LSB compliance, and debian 3.0 will be LSB-compliant. At least that's what they're aiming for.
Good points. But unfortunately debian 3.0 won't be LSB compliant, IIRC. I think the main problem lies in runlevels, and init.d script installation.
PostgreSQL blob api also sucks golfballs through a waterhose, but as of pgSQL 7.1 there is no row lenght limit any longer. So you could stuff an arbitrarily long attatchment as a TEXT or VARCHAR field.
It's all there in the JFS todo list which can be seen
here.
Extending is apparently going to be implemented RSN, and ACL:s seem to be a longer term project.
Yes exactly! What an evil bait to link the words "hosting nude doctored photos of her. "!!! Would I have clicked the link if I had known it was just a boring press release? NO, NO, NO!!! ;-)
Damnit! Now I'm extra proud of being a Finn. Our parliament made the right decision. I'm happy they weren't swayed by all kinds of luddites with absolutely no clue about the issues regarding nuclear power.
No mention of noise, or rather the lack of it, in the article? Pretty important IMHO, unless you're just gonna watch Top Gun over and over again. Those jet eng^D^D^D^D^D^D^D fans make me crazy!
In fact I can. With PostgreSQL and python.
*Dons asbestos kit*
;-)
In an unrelated note, I think gnucash 1.6.x has support for MySQL and PostgreSQL, in case flat files don't cut it.
There are no plans to make a microscopic nuclear reactor, according to the article. So there's nothing there going critical. Essentially they were talking about the kind of nuclear batteries that have been in use for a long time already on space craft and such.
Yep, you're right. Way back when I was going to buy a soundcard for my familys 16MHz 386 (which at the time was a really high end machine) there wasn't much choice. There were no soundcard drivers with a unified API in DOS, so every game had to support your particular soundcard. And they all supported Adlib. SoundBlaster was Adlib compatible, and had a joystick port. So in the end it was an easy choice.