Actually, Kickfire are the guys with the cool “non-Von-Neumann” super-parallel chip.

Best,

CAM

That said, there is still room for some kind of special processing hardware today. The Azul Java machine is an interesting example. The use of GPGPU’s is very promising because they’re made in such quantity, and their speed and quality and price are all being driven by the ever-growing digital game industry.

However, a GPGPU is not promising for database systems, at least not in any very obvious way. It’s good when you have a relatively small amount of data that needs a relatively large amount of computation. Database systems, on the other hand, spend a lot of their effort on moving data around. So at this point I don’t particularly expect GPGPU technology to apply to database systems in any conventional way (although I could imaging special-purpose DBMS’s, that embed a lot of numerics inside the DB, perhaps).

In any case, I think extrapolating forward from the failure of, say, the old Britton-Lee database machine is not a good idea. The balances between components of hardware change rapidly, and as they do, the tradeoffs between what to do in hardware and what to do in software can change just as radically as the tradeoffs between what to do locally (on a client) and what to do remotely (on a server).

It’s a new world out there, since then, and it’s too early to judge simply the concept of “special hardware” per se. It depends on what special hardware, how you’re using it, and so on.

Of course I wish InfoBright the best of success.