Robert Myers (rmyers@rustuck.com) on 2/19/08 wrote:
---------------------------

>No more whompti-flops computers needed. No more ad hoc languages. What's needed
>is the kind of work the US doesn't currently fund: basic research without an immediate
>obvious payoff. Mathematicians welcome. Bureaucrats and computer "scientists" please go away.

You can have the fanciest algorithms around, but you still have to move bits, onto the monitor, on and off the disk, and, many times, to paper. What dismays me in commercial computing is how little "processing" actually takes place. Most of the data is just slightly gussied up alphanumeric strings, sometimes rearranged, sorted, and glommed together. Literally, just shuffled around! Maybe we need the mathematicians to invent even *more* sorting and pattern matching algorithms. I don't think that would interest them much.

IMO, the fundamental measure of processing speed is how many transistors can be flipped in a given instant. Improving integer processing and branch traversal/prediction seems to be the best way to do this.