On Mon, Jul 16, 2018 at 12:06 PM, Michel Dänzer <mic...@daenzer.net> wrote: > On 2018-07-13 08:35 PM, Marek Olšák wrote: >> https://pastebin.com/raw/itNDpPv0 >> >> Cleanups only: +10.85% >> Total: +11.8% > > Thanks, that's more useful. > > If you pass all 3 data files to a single ministat -s invocation, it > combines all of them in a single graph, and prints information about > whether or not a difference was detected, and if yes, the interval in > which the difference lies at 95% confidence. > > > It might be even better to compare the total number of frames rendered > in a fixed amount of time, with multiple runs for each test > configuration, in case there is systemic variance between runs (e.g. due > to ASLR).
While further comparison would be interesting to have, we don't have the manpower to do further testing (and that includes testing the effect of the noimport flag). We at least know there is "some" improvement, so let's move onto something else. Marek _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev