[Shootout-list] fannkuch

[John Skaller]

On Fri, 2005-05-20 at 11:55 +0200, Bengt Kleberg wrote:
> On 2005-05-19 22:23, Brent Fulgham wrote:
> ...deleted
> > 
> > This measurement limit is based on the resolution of
> > the timers available.  We found that anything below
> > about 0.01 second was not reliable.
> 
> thank you. this was the information i was looking for.
> 
> if 0.009 is not reliable, does that not mean that 0.01 seconds is 50% 
> reliable? and that we need 0.1 seconds to reach 90% reliable?

I have just run some benchmarks on my AMD64 which are specifically
run for about 5 seconds. On an otherwise unloaded machine, variations
of 5% still occur in runs. 


John Skaller, skaller at users.sf.net
PO Box 401 Glebe, NSW 2037, Australia Ph:61-2-96600850 
Download Felix here: http://felix.sf.net