On Mon, Sep 28, 2009 at 5:49 PM, <Casper.Dik at sun.com> wrote: > > >>> I would suggest that that is not a proper benchmark for cksum. >> >>Why? Roland said Sun uses the same kind of loop to evaluate the >>performance of cksum and other tools. >> > > How often do you run cksum on the same file?
I do 100x, 1000x, 10000x. I don't know how Sun or Roland do their tests. > > I'd prefer to run cksum on a lot of different files, not just one. > > I'm just wondering that the measurement doesn't actually measure anything > seen in a real application. I don't see a problem for cksum. The algorithm has no branches or and treats each machine word identically. -- Jennifer Pioch, Uni Frankfurt
