The Blue Gene Lite system by IBM is actually running even cooler (article).
The 440PPC processor being used is designed for embedded computing, so each node (2 processors and 4 FPUs) uses only 15 watts per node. That means that the 1024 processor system (512 nodes in normal configuration), now at #73 in top500, only uses about 7.7kW of power. At 240 processors or 120 nodes, power consumption would only be 1.8kW. This is far better than the Transmeta numbers.
I recently started working at IBM doing iSeries Linux work, when I mentioned to someone that I had taken an MPI class in college. I found out later that he was doing BGL work and needed help, so now I work on this!
IBM Research BGL Home
There are 65536 (2^16) compute nodes (CNs) on the system running a very small, from-scratch OS. There are also 1024 (2^10) I/O nodes on the system running a full Linux system (ZDnet article). The custom CN kernel is designed to look like linux, but is much smaller and written for a very singular purpose.
The system has a number of networks that link all the nodes together. The first is the 3-D Torus network, the point-to-point node connection topology. The asteroids game is a 2-D torus because the top connects to the bottom and the sides connect; a 2-D torus looks like a donut when connected together. A 3-D torus looks like a cube (3-D Mesh), but the sides are directly connected to the opposite end (it really requires 4 Euclidean dimension to draw well). This network only connects the 2^16 CNs.
The I/O nodes (running Linux) are connected by ethernet and then each linked to 64 CNs by the tree network. Unsurprisingly, it looks like a tree (for the people who actually know what a plant called a tree looks like, it is not like that).
About 7 years ago, I played football (American) in High School (BTW, do I belong here?). Anyway, our coach pushed creatine for the better players so that they could bulk up. I do not recall an body odor issues, but there was concern over other effects.
About that time, a wrestler from Wisconsin (I believe) died while using creatine (the very high dosage and many hours in a wet suit on an exercise bike with no water while trying to make weight probably added to the issue).
Creatine is simplistically a way to get anaerobic (no oxygen) energy without the lactic acid build-up. This is because the aerobic (with oxygen) stuff happens before the activity, and the energy is then stored on the creatine amino acid in a semi-stable form.
Anyway, there was a lot of worry that nothing was/is known about the long term effects. It is known to occur naturally, even more so in fish, and swimmers have a high natural presence (holding their breath and all).
A quick google shows a lot of pro-creatine info on body-building sites. They indicate that serious side-effects are known, but IIRC the lack of possible side effects in not generally considered to be "proven" (to the extent that you can ever prove that sort of thing).
I recently pulled out the documentation on the IBM drive that I bought some years back. It contains a lot of similar things saying that IBM will cover the user if every sued over use of the product for any reason, they will handle all legal issues, and generally hold the user blameless. They also promised that, in the event that the product was found to be infringing on the IP rights of others, IBM would replace the device with a functional equivalent or allow the user to continue with the infrigment.
I imagine that a lot of the products from IBM are covered in the same manner!
I doubt that one would get arrested if the server admins removed PERL and the server started kicking the source to you. Everyone visiting the site would end up in jail.
What if removing the file name gave you a directory listing? This might have happened to a friend in college, and (s)he might have gotten all the answers to the semester's homework. Should this be illegal? Is this illegal?
In the case of Brian West, the server was wide open and required few tools. This is almost the same as the above issue, but Brian got arrested. Obviously he should not have started to modify the source, but his initial intrusion sounds almost accidental.
It just goes back to the blame game: who gets the blame for a bad server. Joe Sixpack cannot be accountable if the server is just spitting out the scripts, and the admin cannot always be accountable for another obscure WIN2K hole. Somewhere in the middle, it is very easy to get in, and seems to be very easy to get arrested.
The Association of American Publishers, however, continues to hail the government's action, saying Sklyarov's software "facilitates theft, and makes it less likely that e-books will soon become a popular reading format."
I think history shows that the opposite is true: free things become popular much faster than stuff that you have to pay to get (if they are very simple and equal in quality). How would MP3's have become so popular if we always had to pay? IE was the same: M$ gave it away, while Netscape still charged for their browser.
eBooks are very unlikely to cause a change until people can get them without hassle: free (as in free beer), and without copy protection (as in free speech). All the specialized hardware/software turns a lot of people off--a portable eBook has a much high initial investment than an old paperback.
I do want the computer to return to the previous state. I like the memory and the processor to get cleared when I reboot the computer. If they did not, my Windows uptime would soon go from 6 hours to 6 microseconds.
About a year ago, when they were last adding new TLDs, somebody tried to get.kids. Obviously, they did not like it then, so I see no reason it would be better now.
The Blue Gene Lite system by IBM is actually running even cooler (article).
The 440PPC processor being used is designed for embedded computing, so each node (2 processors and 4 FPUs) uses only 15 watts per node. That means that the 1024 processor system (512 nodes in normal configuration), now at #73 in top500, only uses about 7.7kW of power. At 240 processors or 120 nodes, power consumption would only be 1.8kW. This is far better than the Transmeta numbers.
I recently started working at IBM doing iSeries Linux work, when I mentioned to someone that I had taken an MPI class in college. I found out later that he was doing BGL work and needed help, so now I work on this! IBM Research BGL Home
There are 65536 (2^16) compute nodes (CNs) on the system running a very small, from-scratch OS. There are also 1024 (2^10) I/O nodes on the system running a full Linux system (ZDnet article). The custom CN kernel is designed to look like linux, but is much smaller and written for a very singular purpose.
The system has a number of networks that link all the nodes together. The first is the 3-D Torus network, the point-to-point node connection topology. The asteroids game is a 2-D torus because the top connects to the bottom and the sides connect; a 2-D torus looks like a donut when connected together. A 3-D torus looks like a cube (3-D Mesh), but the sides are directly connected to the opposite end (it really requires 4 Euclidean dimension to draw well). This network only connects the 2^16 CNs.
The I/O nodes (running Linux) are connected by ethernet and then each linked to 64 CNs by the tree network. Unsurprisingly, it looks like a tree (for the people who actually know what a plant called a tree looks like, it is not like that).
Summary PDF
About 7 years ago, I played football (American) in High School (BTW, do I belong here?). Anyway, our coach pushed creatine for the better players so that they could bulk up. I do not recall an body odor issues, but there was concern over other effects.
About that time, a wrestler from Wisconsin (I believe) died while using creatine (the very high dosage and many hours in a wet suit on an exercise bike with no water while trying to make weight probably added to the issue).
Creatine is simplistically a way to get anaerobic (no oxygen) energy without the lactic acid build-up. This is because the aerobic (with oxygen) stuff happens before the activity, and the energy is then stored on the creatine amino acid in a semi-stable form.
Anyway, there was a lot of worry that nothing was/is known about the long term effects. It is known to occur naturally, even more so in fish, and swimmers have a high natural presence (holding their breath and all).
A quick google shows a lot of pro-creatine info on body-building sites. They indicate that serious side-effects are known, but IIRC the lack of possible side effects in not generally considered to be "proven" (to the extent that you can ever prove that sort of thing).
I recently pulled out the documentation on the IBM drive that I bought some years back. It contains a lot of similar things saying that IBM will cover the user if every sued over use of the product for any reason, they will handle all legal issues, and generally hold the user blameless. They also promised that, in the event that the product was found to be infringing on the IP rights of others, IBM would replace the device with a functional equivalent or allow the user to continue with the infrigment.
I imagine that a lot of the products from IBM are covered in the same manner!
This is a very interesting problem.
I doubt that one would get arrested if the server admins removed PERL and the server started kicking the source to you. Everyone visiting the site would end up in jail.
What if removing the file name gave you a directory listing? This might have happened to a friend in college, and (s)he might have gotten all the answers to the semester's homework. Should this be illegal? Is this illegal?
In the case of Brian West, the server was wide open and required few tools. This is almost the same as the above issue, but Brian got arrested. Obviously he should not have started to modify the source, but his initial intrusion sounds almost accidental.
It just goes back to the blame game: who gets the blame for a bad server. Joe Sixpack cannot be accountable if the server is just spitting out the scripts, and the admin cannot always be accountable for another obscure WIN2K hole. Somewhere in the middle, it is very easy to get in, and seems to be very easy to get arrested.
The Association of American Publishers, however, continues to hail the government's action, saying Sklyarov's software "facilitates theft, and makes it less likely that e-books will soon become a popular reading format."
I think history shows that the opposite is true: free things become popular much faster than stuff that you have to pay to get (if they are very simple and equal in quality). How would MP3's have become so popular if we always had to pay? IE was the same: M$ gave it away, while Netscape still charged for their browser.
eBooks are very unlikely to cause a change until people can get them without hassle: free (as in free beer), and without copy protection (as in free speech). All the specialized hardware/software turns a lot of people off--a portable eBook has a much high initial investment than an old paperback.
I do want the computer to return to the previous state. I like the memory and the processor to get cleared when I reboot the computer. If they did not, my Windows uptime would soon go from 6 hours to 6 microseconds.
About a year ago, when they were last adding new TLDs, somebody tried to get .kids. Obviously, they did not like it then, so I see no reason it would be better now.