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

Reply via email to