On Thu, 2013-05-16 at 15:44 -0400, Adam Jackson wrote: > These were mostly just a waste of memory and cache pressure, and were > really only used for debugging. > > This change reduces instruction count (as measured by callgrind's Ir > event) of gnome-shell-perf-tool on Ivybridge by 3.5% ± 0.015% (n=20).
These numbers are somewhat spurious, since it appears what I actually recorded was the execution of the python harness and not of gnome-shell itself. Still the correlation is strong with this one, so I suspect the improvement is real even if the numbers are unrelated. I'll get better data, sorry about that. - ajax _______________________________________________ mesa-dev mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/mesa-dev
