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

[John Skaller]

On Mon, 2005-05-23 at 17:26 +0300, Einar Karttunen wrote:

> If we measure per-benchmark startup times then it will be likely that
> either A or B will be punished. Thus the best way seems to be using hello
> for the startup time.

The 'best way(tm)' is to include the startup time in the result.
For low n, this will punish some systems (eg Java). For high
n it will reward some systems (eg Java) when the startup costs
bear fruit (eg Java JIT operation).

The real problem is that CRAPS concentrates on the times for
high n -- the hello test being the exception. Perhaps it should
have a higher weight :)

-- 
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