[Shootout-list] Many tests cheat
Isaac Gouy
igouy2@yahoo.com
Tue, 2 Nov 2004 07:31:58 -0800 (PST)
--- skaller <skaller@users.sourceforge.net> wrote:
> > > For example, there is a limit on how much buffering
> > > is allowed in some tests that do I/O (4K).
> >
> > This would shift many benchmarks to "how optimized is the default
> > IO solution".
> The benchmark obviously must be changed so the IO speed isn't
> relevant -- right now several benchmarks measure nothing
> else.
IO speed isn't relevant because...?
__________________________________
Do you Yahoo!?
Check out the new Yahoo! Front Page.
www.yahoo.com