Main Site Documentation

Fez Supercomputer?


#1

I just stumbled across this supercomputer made from BasicStamps.

http://www.robotinfo.net/penguin/supercomp.html

I was wondering if anyone ever thought about making one with Fez Minis or Fez Pandas?

Hopefully if someone did make one, it wouldn’t be the rats nest of wires that this guy had. :wink:

-Eric


#2

I love the “Portable” and “Field operable” comments

I would’t dare pick t up

Cheers Ian


#3

Very cool. The good news is that a single FEZ has a lot more power that all 12 basic stamps …a LOT more.

So, a supercomputer using FEZ would be just awesome :smiley:


#4

OMG how funny is the video. You must have some serious spare time.

I thought I was watching a motion picture.


#5

has anyone tried a Fez supercomputer yet?


#6

Buying a bunch of MCUs and tying the I2C lines (or whatever) does not a supercomputer make. Regardless of how many there are.

Large parallel-processing supercomputers have lots of memory, high speed interconnects, shared high-speed storage, and software frameworks that manage node availability and work partitioning. The fact that some guy hooked 12 stamps together and got them talking doesn’t justify the label of “supercomputer” or even “parallel processor”.


#7

That’s what I thought! So then how does one “make” a super computer like system (in that they talk and communicate like a supercomputer) with the Fezes?


#8

Step one would be to design and implement a high speed interconnect. You want this as wide (meaning, as many data lines) as possible, and you want it to be as fast as possible.

Step two would be to design a high speed shared storage architecture. You want the different nodes to be able to talk to this storage simultaneously, so you have to manage read and write locks, and handle deadlock conditions, etc.

Step three would be to design the software system that will manage the task of dividing up work to the different nodes, and managing the nodes themselves (bringing them online, taking them offline, handling hardware and software failures).

If you ever read Slashdot during the heyday of the “imagine a Beowulf cluster of these!” meme/joke, then you might know that the gist of the joke is that just because something has a lot of processing power, that doesn’t mean that 1) it’s suitable for massively-parallel computing, or that 2) it’s easy to slap a bunch of computing devices together into an HPC cluster.

I’m not an HPC/supercomputer expert, but I did have a friend that worked for the company responsible for some of the largest clusters available at the time, and I can say, a LOT of work went into the “tying them together” pieces of the puzzle.


#9

I would like to know more. Is he still your friend?


#10

Yes, he is, but I don’t think he would be able to tell you anything you wouldn’t learn better elsewhere. He did hardware troubleshooting for them, he didn’t design or implement any of the interesting stuff :frowning:

I did get some neato tours of the facility while they were assembling some 1k+ node machines, though. I’ll tell you, that many machines make a LOT of noise :slight_smile:

If you want to learn more, look into this: