There is good science to suggest that the conservation of energy is real. This has been tested repeatedly. There is also good science to suggest that the theory of relativity is real, every day in particle accelerators across the world it's used to make predictions that turn out. The combination of conservation of energy, and relativity suggests that on any largish scale, there can be no teleportation.
In the 19th century, there was "good science to suggest" that, given a strong enough rocket engine, objects can be accelerated to speeds bigger than 300000km/s. There was also "good science" that suggested that the space is flat and euclidian.
What i'm saying is, your argument boils down to "our present knowledge is perfect, thereby anything contradicting it cannot exist."
I am not saying that said teleportation project is sound and sane. I am saying that one should look at whatever paradigm he/she adheres to with caution. Too often i see people otherwise rational that seem to imply that psychic phenomena are made impossible by the simple fact that a million newagers believe in them ("if a pothead believes in X, then X does not exist"). A million newagers may have an irrational belief, yet that does not make certain things impossible.
Again, i am not implying anything, i just don't like it when people take a transitory scientific paradigm as dogma.
These rather wasteful supercomputers are getting less and less impressive. You know what would be impressive? Published results!
The results are already "published", just not explicitly.
The gas price is twice smaller than it could be? That's because supercomputers such as those made by SGI are used to do simulations related to oil drilling and stuff.
The car prices are smaller than they could be? That's because car crashes are simulated on supercomputers instead of performed actually during the design process.
Nuclear weapons are more powerful than they could be? That's because... oh, wait.:-)
What the [expletive deleted] do you DO with all those terabytes or high-speed RAM?
Simulations. Everything from nuclear processes, to space shuttles re-entering atmosphere, to cars crashing into walls, to oil drilling, to... whatever. That's what the SGI systems are used for.
What's wrong with you people? "Itanium is bad" is an urban myth. Yes it's expensive. Yes, Itanium 1 was indeed bad. But this is Itanium2. It might still be expensive, but it's currently the best CPU for large supercomputers - machines which run hundreds of CPU in parallel, which is exactly what SGI does.
SGI is using the best tool for the job. When (or rather IF) AMD comes up with a better CPU for this kind of workload, they'll probably migrate to that.
Don't get me wrong, i'm using AMD on all my PCs, but a massively parallel supercomputer is a different thing.
The Big Mac is just like any other commodity cluster. It's just a bunch of machines tied together in a closed network. The SGI supercomputers keep all CPUs in a single machine, sharing all the memory over extremely fast, proprietary interconnects. In such a system, the CPUs talk to each other as fast (if not faster) as the CPUs in a dual-CPU server.
Assuming the total CPU power is the same, the SGI supercomputer is faster than any cluster (Big Mac included) for all problems that are not 100% parallelizable. For those few problems whose algorhitms are 100% parallel, a SGI system and a cluster will probably be equal.
Then you're assuming each machine has just one CPU. That is not correct, and it's the biggest difference between SGI supercomputers and commodity clusters. An SGI system has hundreds, if not thousands of CPUs per machine.
SGI has a layered approach to the max number of CPUs in a supercomputer. I guess 256 is what they call "ultrastable" - kinda like the Linux kernel 2.2. But the NASA monster already has 512 CPU machines, and who knows what the japanese system has.
Apparently, SGI sells bigger systems to customers who "know what they are doing" and who work closer with SGI. If you want something that 100% no-frills, then probably the 256 CPU is the current absolutely stable limit.
almost any processor except an Itanium would be even faster
I am sorry to say you're terribly misinformed. Itanium still is better that anything else at large-scale supercomputers. I am not sure what are the details, and i can't find the URL i'm looking for, but anyway that's precisely why it is used in the Altix systems. It may not be the absolute fastest in single-CPU machines, but it outperforms everything else in systems with hundreds of CPUs. It was not chosen blindly for the Altix. It was a "we want the absolute best for this system, money no issue" decision.
Itanium in general has been a horrendously expensive fiasco for Intel
That's because it has a horrendous price/performance ratio. But that does not matter in the case of a system such as the Columbia supercomputer (the CPUs are a small fraction of the total cost).
"Itanium is slow" is an urban myth. It is not suited for commodity computers, but the processor itself is very good (if you forget the price tag and the problems it had with the earlier versions).
NASA loves the SGI supercomputers. The US government loves NASA. If Microsoft touches NASA, i betcha Uncle Sam will finally do the right thing (i.e. slam Microsoft).
Yeah, that's the explanation. The Altix is not a commodity cluster. It's high-performance proprietary architecture. And by the way, each node of the Columbia cluster is a supercomputer itself (512 CPUs running a single OS image). That's totally different from a beige PC cluster. Just one detail, instead of your off-the-shelf network infrastructure that you use in the beige PC cluster, the Altix has this fast NUMA interconnect which links together the CPUs directly (no PCI bus / network card / network cables overhead). Much more performance, therefore more complexity, therefore it takes more time to install. Obvious.
In actual truth, faster machines allow to perform more iterations of the same algorithm in the same time. Each new iteration adds more precision to the prediction. So, faster computers do enable better predictions.
I think someone at NASA got really scared / pissed off / whatever by the shuttle failure. Probably lots of money are pumped now to make Triple Sure that It Ain't Gonna Happen Again. Of course, once you have that much computing power under control, you can do all kinds of other interesting things with it. If they're successful with predicting weather with greater accuracy and stuff like that, i betcha quite a few Rich Entities will buy Altix supercomputers in a hurry.
Sun, can hold up to 106 processers in its Sunfire 15K product, or 72 dual-core processors in the E25K. SGI's Origin systems are equally large I believe.
Actually, SGI makes 1024-CPU systems using the older MIPS/Irix architecture (the Origin and Onyx platforms), and 512-CPU systems using the newer Intel/Linux (the Altix machines). And that's what they make on a regular basis. Experimental systems are even bigger. Also, the Intel/Linux SGI systems are still very young and likely to grow a lot more. That's one order of magnitude above Sun.
SGI is leading the single-OS-image market in terms of the size of systems.
Well, if it wasn't for Intel, it would be AMD, or whoever else makes the fastest CPUs. Also, if it wasn't for Linux, it would be FreeBSD or whatever.
The thing with these systems is the interconnect architecture, the hardware "glue" that holds together hundreds (nay, soon thousands) of CPUs running one single OS image. That's what SGI did and that's what is pretty unique. That's why they deserve the pat on the shoulder.
Yeah, Irix is cool. The trouble is, SGI resisted the hardware change. They kept on betting on the wrong horse (MIPS). At the same time, Intel and AMD were beating the crap out of all other CPUs. So, it's not the OS change they resisted, it's the hardware.
Fortunately, they made the right decision eventually.
produce liquid carbon dioxide, which could be sequestered underground
That is the most idiotic thing i've heard in a long time. "Zero-emission"... yeah, right, let's bury all emission underground, so it's zero. Oh, wait...:-)
Is there a way to buy just the fanless power supply, not the whole case? I'm very interested in fanless power supplies for VIA mobos, but only the supplies, because i already have the cases.
Awesome! Can you provide any details on how to strip down Firefox? A URL to documentation or something? (If you prefer, you can reply by email instead of Slashdot - see my address above) Thanks!
But i thought the Linksys is locked to Vonage or some kind of service like that? Are you aware of any Linksys devices that are not locked? If yes, where can i find them?
Slashdot Mirror
There is good science to suggest that the conservation of energy is real. This has been tested repeatedly.
There is also good science to suggest that the theory of relativity is real, every day in particle accelerators across the world it's used to make predictions that turn out.
The combination of conservation of energy, and relativity suggests that on any largish scale, there can be no teleportation.
In the 19th century, there was "good science to suggest" that, given a strong enough rocket engine, objects can be accelerated to speeds bigger than 300000km/s. There was also "good science" that suggested that the space is flat and euclidian.
What i'm saying is, your argument boils down to "our present knowledge is perfect, thereby anything contradicting it cannot exist."
I am not saying that said teleportation project is sound and sane. I am saying that one should look at whatever paradigm he/she adheres to with caution.
Too often i see people otherwise rational that seem to imply that psychic phenomena are made impossible by the simple fact that a million newagers believe in them ("if a pothead believes in X, then X does not exist"). A million newagers may have an irrational belief, yet that does not make certain things impossible.
Again, i am not implying anything, i just don't like it when people take a transitory scientific paradigm as dogma.
The thing is... it doesn't.
;-)
So far.
It's a single-OS-image supercomputer.
:-)
But yeah, nice joke.
These rather wasteful supercomputers are getting less and less impressive.
:-)
You know what would be impressive? Published results!
The results are already "published", just not explicitly.
The gas price is twice smaller than it could be? That's because supercomputers such as those made by SGI are used to do simulations related to oil drilling and stuff.
The car prices are smaller than they could be? That's because car crashes are simulated on supercomputers instead of performed actually during the design process.
Nuclear weapons are more powerful than they could be? That's because... oh, wait.
What the [expletive deleted] do you DO with all those terabytes or high-speed RAM?
Simulations. Everything from nuclear processes, to space shuttles re-entering atmosphere, to cars crashing into walls, to oil drilling, to... whatever. That's what the SGI systems are used for.
What's wrong with you people? "Itanium is bad" is an urban myth. Yes it's expensive. Yes, Itanium 1 was indeed bad. But this is Itanium2. It might still be expensive, but it's currently the best CPU for large supercomputers - machines which run hundreds of CPU in parallel, which is exactly what SGI does.
SGI is using the best tool for the job. When (or rather IF) AMD comes up with a better CPU for this kind of workload, they'll probably migrate to that.
Don't get me wrong, i'm using AMD on all my PCs, but a massively parallel supercomputer is a different thing.
is this thing faster than the Big Mac?
Yes it is.
The Big Mac is just like any other commodity cluster. It's just a bunch of machines tied together in a closed network.
The SGI supercomputers keep all CPUs in a single machine, sharing all the memory over extremely fast, proprietary interconnects. In such a system, the CPUs talk to each other as fast (if not faster) as the CPUs in a dual-CPU server.
Assuming the total CPU power is the same, the SGI supercomputer is faster than any cluster (Big Mac included) for all problems that are not 100% parallelizable. For those few problems whose algorhitms are 100% parallel, a SGI system and a cluster will probably be equal.
0.000634765625 TB's per machine
Then you're assuming each machine has just one CPU. That is not correct, and it's the biggest difference between SGI supercomputers and commodity clusters.
An SGI system has hundreds, if not thousands of CPUs per machine.
SGI has a layered approach to the max number of CPUs in a supercomputer.
I guess 256 is what they call "ultrastable" - kinda like the Linux kernel 2.2.
But the NASA monster already has 512 CPU machines, and who knows what the japanese system has.
Apparently, SGI sells bigger systems to customers who "know what they are doing" and who work closer with SGI. If you want something that 100% no-frills, then probably the 256 CPU is the current absolutely stable limit.
almost any processor except an Itanium would be even faster
I am sorry to say you're terribly misinformed. Itanium still is better that anything else at large-scale supercomputers. I am not sure what are the details, and i can't find the URL i'm looking for, but anyway that's precisely why it is used in the Altix systems. It may not be the absolute fastest in single-CPU machines, but it outperforms everything else in systems with hundreds of CPUs.
It was not chosen blindly for the Altix. It was a "we want the absolute best for this system, money no issue" decision.
Itanium in general has been a horrendously expensive fiasco for Intel
That's because it has a horrendous price/performance ratio. But that does not matter in the case of a system such as the Columbia supercomputer (the CPUs are a small fraction of the total cost).
"Itanium is slow" is an urban myth. It is not suited for commodity computers, but the processor itself is very good (if you forget the price tag and the problems it had with the earlier versions).
NASA loves the SGI supercomputers. The US government loves NASA.
If Microsoft touches NASA, i betcha Uncle Sam will finally do the right thing (i.e. slam Microsoft).
I don't build supercomputers
Yeah, that's the explanation.
The Altix is not a commodity cluster. It's high-performance proprietary architecture. And by the way, each node of the Columbia cluster is a supercomputer itself (512 CPUs running a single OS image). That's totally different from a beige PC cluster.
Just one detail, instead of your off-the-shelf network infrastructure that you use in the beige PC cluster, the Altix has this fast NUMA interconnect which links together the CPUs directly (no PCI bus / network card / network cables overhead).
Much more performance, therefore more complexity, therefore it takes more time to install. Obvious.
In actual truth, faster machines allow to perform more iterations of the same algorithm in the same time. Each new iteration adds more precision to the prediction. So, faster computers do enable better predictions.
:-)
But yeah, nice joke.
I think someone at NASA got really scared / pissed off / whatever by the shuttle failure. Probably lots of money are pumped now to make Triple Sure that It Ain't Gonna Happen Again.
Of course, once you have that much computing power under control, you can do all kinds of other interesting things with it. If they're successful with predicting weather with greater accuracy and stuff like that, i betcha quite a few Rich Entities will buy Altix supercomputers in a hurry.
Sun, can hold up to 106 processers in its Sunfire 15K product, or 72 dual-core processors in the E25K. SGI's Origin systems are equally large I believe.
Actually, SGI makes 1024-CPU systems using the older MIPS/Irix architecture (the Origin and Onyx platforms), and 512-CPU systems using the newer Intel/Linux (the Altix machines). And that's what they make on a regular basis. Experimental systems are even bigger. Also, the Intel/Linux SGI systems are still very young and likely to grow a lot more.
That's one order of magnitude above Sun.
SGI is leading the single-OS-image market in terms of the size of systems.
Well, if it wasn't for Intel, it would be AMD, or whoever else makes the fastest CPUs.
Also, if it wasn't for Linux, it would be FreeBSD or whatever.
The thing with these systems is the interconnect architecture, the hardware "glue" that holds together hundreds (nay, soon thousands) of CPUs running one single OS image. That's what SGI did and that's what is pretty unique. That's why they deserve the pat on the shoulder.
Yeah, Irix is cool. The trouble is, SGI resisted the hardware change. They kept on betting on the wrong horse (MIPS). At the same time, Intel and AMD were beating the crap out of all other CPUs.
So, it's not the OS change they resisted, it's the hardware.
Fortunately, they made the right decision eventually.
So, if i only get one IP address, that means i cannot run my own H.323 or SIP server or anything like that.
It sucks. No thanks.
produce liquid carbon dioxide, which could be sequestered underground
:-)
That is the most idiotic thing i've heard in a long time. "Zero-emission"... yeah, right, let's bury all emission underground, so it's zero.
Oh, wait...
Is there a way to buy just the fanless power supply, not the whole case?
I'm very interested in fanless power supplies for VIA mobos, but only the supplies, because i already have the cases.
Awesome!
Can you provide any details on how to strip down Firefox? A URL to documentation or something?
(If you prefer, you can reply by email instead of Slashdot - see my address above)
Thanks!
Wow, really?
Was it the 600MHz EPIA, or the 1GHz thing?
Could you encode video real-time on that mobo?
I'm extremely interested in this issue. Could you please reply to my email address instead of Slashdot? (see address above)
Thanks!
My "friend" is not playing games anymore. Too much time wasted. Period.
That's what i thougth.
But then i read the article and, lo and behold! it was actually interesting.
Not all advertising is evil.
But i thought the Linksys is locked to Vonage or some kind of service like that?
Are you aware of any Linksys devices that are not locked? If yes, where can i find them?