> Or even better, use a real application for a benchmark instead of
> something artificial like this. There are many ways that tests like
> this can give misleading results. I have an "old favorite" one of my
> applications that I've tended to use for such purposes for a while.
Even better, use your own application. I remember testing some
self-written applications on various machines. Which machine ran the
fastest depended on the application, i.e. depended on whether it was I/O
intensive or needed a lot of memory or was CPU bound or could be
parallelized or not or could fit inside the cache etc etc. It's also
worth looking into the compiler options and choosing the ones which will
make your application run the fastest, if that is what you are
interested in.
|