XO-1(.75)

[Yioryos Asprobounitis]

> 

> Interesting, thanks.   An explanation was asked for, so here's one:
> 
> This script uses CPU time accounting to measure the time the process
> and children spend scheduled on the CPU.
> 


I actually think that combining the two can give some interesting results.
In a fast screen was interesting than in distance for example all the increase was CPU related, while in speak, scratch and fototoon  was all outside CPU.
Ofcourse would be good to do the test on the same machine and with or without caching and preexisting or not journal entries.
It would appear however that although there is a considerable slowdown can not be attributed to Gtk3 only and may be other components and even activity-specific cases that need to be looked up at the individual activity level.