Server Fault is a question and answer site for system and network administrators. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

Some pictures regarding the Texas Advanced Computing Center (one I am currently interested in) here:

If you see the two supercomputers they have, Lonestar and Ranger, they are not like the normal computers you and I would see every day. Nor do they even resemble anything like it despite the difference in scale.

I was just wondering why these "supercomputers" look the way they do (giant rectangular boxes packed together across a room). In any case, each rectangular box looks like its own individual unit, so wouldn't a "supercomputer" pictured here actually be multiple computers (or whatever these boxes are) working in tandem, rather than one giant "computer"?

*edit: possibly a better visual depiction of the 'boxes' and their properties I am referring to:

share|improve this question

closed as not constructive by Ben Pilbrow, Shane Madden, Sven, Zoredache, Alex Oct 9 '11 at 23:41

As it currently stands, this question is not a good fit for our Q&A format. We expect answers to be supported by facts, references, or expertise, but this question will likely solicit debate, arguments, polling, or extended discussion. If you feel that this question can be improved and possibly reopened, visit the help center for guidance.If this question can be reworded to fit the rules in the help center, please edit the question.

Where is the line between "one giant computer" and "multiple computers working in tandem"? Is it the chassis? The rack? The network? – jscott Oct 9 '11 at 22:35
Note the word "Cluster", and the node counts in the thousands. – Shane Madden Oct 9 '11 at 22:36
So each "node" in itself could be a standalone computer? with memory&cpu? or each node is a processor? I'm not sure where the line is drawn and how the terms should be interpreted in this situation... – Dark Templar Oct 9 '11 at 22:51
@Dark Templar: These kind of questions (as your prior one) isn't a good fit on this site. Please read our faq. – Sven Oct 9 '11 at 22:54
because a regular mainframe takes at least two racks and those have "super" in their name so they have to be bigger</joke> – Hubert Kario Oct 9 '11 at 23:21
up vote 2 down vote accepted

The idea of a Supercomputer isn't one box with all the resources as that would be difficult to do. The idea is instead to share the load across hundreds/thousands of nodes with Hi-speed networks for transfer between them.

share|improve this answer
Ah, so a supercomputer is more like a computer network then? – Dark Templar Oct 9 '11 at 22:52
Yes that is exactly what it is. – Jacob Oct 9 '11 at 23:04
there were single-node custom designed supercomputers using single CPU in the early 90's, they were slower and more expensive. Redesigning the software to be massively parallel is just much easier and less expensive. – Hubert Kario Oct 9 '11 at 23:17
The term has evolved; Jacob's essentially right in that supercomputers are more like highly niche parallel processing computers networked together with custom software to take advantage of the network of systems. But that kind of refers to clusters. There are computers that are basically multiple computers within a computer; then those are internetworked. See the old Cray's. Those were specially built with cooling systems and custom processors. – Bart Silverstrim Oct 10 '11 at 1:13
Ever see the movie "Sneakers?" That bench they sit in to talk is actually a Cray supercomputer. It had it's own cooling room because the heat from the core could burn your skin off. At least, that's my recollection. – Bart Silverstrim Oct 10 '11 at 1:14

Not the answer you're looking for? Browse other questions tagged or ask your own question.