No, they really aren't. I work on a top 20 machine, and can tell you that attaching this via a high-latency interconnect (read: the web) would completely kill the purpose of using this machine. And no, you cannot just "compensate by using more nodes." Amdahl's law kills that idea right out.
I've worked in both "cloud computing" (back when it was known as "grid computing") and HPC or High-Performance Computing. While they are similar in some ways, they are designed to fulfill different purposes and are best suited to different job types. The codes being run by Cycle for this project are EP codes, ones that would not necessarily benefit from the top 50 machines in the world. These machines are better suited for MPP work, which depends more on low-latency, high-speed interconnects.
Cloud computing and the Top500 computers are comparing different things. Generally, "Clouds" cannot efficiently run codes you would run on a Top500 machine, and vice-versa. They are large machines serving different purposes.
"Shell In A Box implements a web server that can export arbitrary command line tools to a web based terminal emulator. This emulator is accessible to any JavaScript and CSS enabled web browser and does not require any additional browser plugins. Most typically, login shells would be exported this way:"
No thank you! As a network/linux admin, you're seriously going to trust your root prompt to a web service?!?! Please, stay off my machines.
Seriously though, as an admin, it's very difficult to see moving all of this stuff to the web. What happens when the border routers to my site go down? I don't have any way to bring them up, because my OS keeps telling me "Page not found"?
Why do you get to decide what's a "justifiable use"? I like to use my iPad as a browser on the couch, and to check email. I find that if I'm sitting in front of the TV, I'd rather not sit with my laptop all the time. I also find my iPhone a little too small for viewing when I have the option of a larger screen.
As for an e-reader, I prefer the iPad because I'm not locked into a single store for books; I can buy from the Kindle, Nook, Borders, and Apple stores, among others.
I do have a "wider variety of devices" but the tablet fits certain use cases that I have. Don't think that "justifiable uses" fit everyone.
The reason you can get such good performance from a Cray is the way the filesystem is connected to the machine. Many machines use an external Lustre solution, requiring slower InfiniBand connections to the entire Lustre "appliance". With a machine like a Cray, you can use internal Lustre where the disks and controllers are connected to IO nodes, and IO nodes are connected to all the compute nodes via the low-latency, high-speed interconnect internal to the system.
It doesn't include its own special tools for anything, so you are forced to do everything the "standard Linux way," which is the way that works on every distro (with some special exceptions, like DSL).
That's just it, there is no "standard Linux way" unless you're referring to the kernel itself. I came from a RedHat shop and went to a SuSE environment. Things are in different places, a fact you have to deal with anytime you change distros. They all have quirks, even between the RPM distros.
And as others have said elsewhere, if you would like to come convince Purdue's Board of Trustees along with our CIO to give us that money, we would be happy to. The reality is that everyone wants better computers, but can't afford a new facility. If you're interested in making a large donation...:)
Well if we had the space, we would have. Unfortunately, our data center is rather small and fairly stressed on cooling and power. This was the only way possible to fit the new cluster in.
Slashdot Mirror
No, they really aren't. I work on a top 20 machine, and can tell you that attaching this via a high-latency interconnect (read: the web) would completely kill the purpose of using this machine. And no, you cannot just "compensate by using more nodes." Amdahl's law kills that idea right out. I've worked in both "cloud computing" (back when it was known as "grid computing") and HPC or High-Performance Computing. While they are similar in some ways, they are designed to fulfill different purposes and are best suited to different job types. The codes being run by Cycle for this project are EP codes, ones that would not necessarily benefit from the top 50 machines in the world. These machines are better suited for MPP work, which depends more on low-latency, high-speed interconnects.
Cloud computing and the Top500 computers are comparing different things. Generally, "Clouds" cannot efficiently run codes you would run on a Top500 machine, and vice-versa. They are large machines serving different purposes.
Tell that to someone who works 2nd or 3rd shift. They like to sleep too.
"Shell In A Box implements a web server that can export arbitrary command line tools to a web based terminal emulator. This emulator is accessible to any JavaScript and CSS enabled web browser and does not require any additional browser plugins. Most typically, login shells would be exported this way:" No thank you! As a network/linux admin, you're seriously going to trust your root prompt to a web service?!?! Please, stay off my machines. Seriously though, as an admin, it's very difficult to see moving all of this stuff to the web. What happens when the border routers to my site go down? I don't have any way to bring them up, because my OS keeps telling me "Page not found"?
Why do you get to decide what's a "justifiable use"? I like to use my iPad as a browser on the couch, and to check email. I find that if I'm sitting in front of the TV, I'd rather not sit with my laptop all the time. I also find my iPhone a little too small for viewing when I have the option of a larger screen. As for an e-reader, I prefer the iPad because I'm not locked into a single store for books; I can buy from the Kindle, Nook, Borders, and Apple stores, among others. I do have a "wider variety of devices" but the tablet fits certain use cases that I have. Don't think that "justifiable uses" fit everyone.
"Jigawatt" is a correct pronunciation of "gigawatt." You can use a hard and soft 'g' interchangeably in this case.
The reason you can get such good performance from a Cray is the way the filesystem is connected to the machine. Many machines use an external Lustre solution, requiring slower InfiniBand connections to the entire Lustre "appliance". With a machine like a Cray, you can use internal Lustre where the disks and controllers are connected to IO nodes, and IO nodes are connected to all the compute nodes via the low-latency, high-speed interconnect internal to the system.
It doesn't include its own special tools for anything, so you are forced to do everything the "standard Linux way," which is the way that works on every distro (with some special exceptions, like DSL).
That's just it, there is no "standard Linux way" unless you're referring to the kernel itself. I came from a RedHat shop and went to a SuSE environment. Things are in different places, a fact you have to deal with anytime you change distros. They all have quirks, even between the RPM distros.
And as others have said elsewhere, if you would like to come convince Purdue's Board of Trustees along with our CIO to give us that money, we would be happy to. The reality is that everyone wants better computers, but can't afford a new facility. If you're interested in making a large donation... :)
Well if we had the space, we would have. Unfortunately, our data center is rather small and fairly stressed on cooling and power. This was the only way possible to fit the new cluster in.