[Shootout-list] fannkuch (timer resolution; HZ=1000?)

[Jon Harrop]

On Monday 23 May 2005 10:39, Bengt Kleberg wrote:
> On 2005-05-21 11:31, Jon Harrop wrote:
> > On Saturday 21 May 2005 07:55, Pascal Obry wrote:
> >>One car argue that the JVM and the CLR are part of the design. It's not
> >> the fault of compiled programs if loading the CPU cache is fast!
> >
> > True, but that only justifies having one benchmark concentrate on
> > measuring the startup time, not having half of the benchmarks measuring
> > the startup time.
>
> if all bechmarks contained one measurement of the startup (for that
> benchmark) and the posssibility to subtract that value from the other
> measurments, then we would have a good comproimise. imho.

Alas you can't do this because the startup time for each benchmark is likely 
to be quite different (at least for some languages) because different 
benchmarks will exercise different parts of the run-time which may incur 
their own startup.

Otherwise, yes, we could just have subtracted the startup time.

A better solution would be to study the results for various "n".

-- 
Dr Jon D Harrop, Flying Frog Consultancy Ltd.
Objective CAML for Scientists
http://www.ffconsultancy.com/products/ocaml_for_scientists