This is my actual problem. As you say, Mips, Flops and so on only
measure CPU power, and that's not that important. From my point of view
the best measure would be one which said something like "if you run
your bunch of software in our cluster instead of your computer you'll
do X times faster. Obviously the best (and maybe only) way to do this
is actually running the software.
I've been told to look for a standard of this kind of measure, but I've
found nothing. I can simulate it by running LINPACK-like benchmarks
both in local and sending it to the cluster a number of times, but I'd
like to know if there's something better. I've read about SPEChpc2002
, but it's not free...
Any of you know any other cluster benchmark?