ok. i also added some profiling with oprofile. it shows the cpu-usage while resizing the frames inside sylpheed-claws. it seems that all cpu goes into memcpy operations. the same action with fglrx doesn't cause this.
the evas_benchmark file shows the performance differences between software- and xrender-rendering with radeon and fglrx. though the differences here are not so big that they could be the reason for the sluggish gtk and qt(it's also slow as hell) performance
ok. i also added some profiling with oprofile. it shows the cpu-usage while resizing the frames inside sylpheed-claws. it seems that all cpu goes into memcpy operations. the same action with fglrx doesn't cause this.
the evas_benchmark file shows the performance differences between software- and xrender-rendering with radeon and fglrx. though the differences here are not so big that they could be the reason for the sluggish gtk and qt(it's also slow as hell) performance