Beowulf in a Box

[Simon Thorpe]

>> My feeling is that the main reason that previous specialist hardware system
>> never really took off is that the programming environment was typically too
>> complex and idiosyncratic, and keeping up with microprocessor development
>> was too difficult.
>
>The box you describe also will also have a difficult programming
>environment -- it's a "clump", a cluster of multiprocessors, which can
>be much more challenging than a simple cluster. Hopefully the vendor
>will be able to continue to keep up with microprocessor development,
>but other boards were based on similar processors which suffered from
>technology failures, such as the transputer.

Yeah, but the transputer was really only of any use in specialized parallel
computers (with complicated and idiosyncratic languages like OCCAM).
StrongARM chips are really quite different - they'll be found in things
like set-top boxes and network computers like the one marketed by Corel
http://www.corelcomputer.com/products/linux/netwinder_dm.htm.  And it
really looks like Intel is going to push StrongARM/Linux in the future (see
for example  http://www.theregister.co.uk/980927-000003.html ). That's why
StrongARMs already only cost $29 and are likely to go lower.

Furthemore, by using the CPU daughtercard concept, it should be possible to
produce a design using a new chip very quickly after it's been released (at
least if we can convince Simtec that it's viable...)

Cheers

Simon


__________________
Simon Thorpe
Centre de Recherche Cerveau et Cognition
133, route de Narbonne
31062 Toulouse France
Tel 33 (0)5 62 17 28 03. Fax 33 (0)5 62 17 28 09
http://www.cerco.ups-tlse.fr/private/simon.html
__________________