https://bugzilla.novell.com/show_bug.cgi?id=666245
https://bugzilla.novell.com/show_bug.cgi?id=666245#c3 --- Comment #3 from Alexander Stohr <[email protected]> 2011-03-27 11:41:19 UTC --- the current/old design is this: for (pixel 0...999) { get_pixel() put_pixel() } the updated design is this: if (optimisation_is_applicable) { memcpy(dst, src, 999*pixel_size) } else { /* use current/old design */ } as you can see the current/old code is doing two function calls per loop cycle. this is definitely a performance kill on even the best application processor. its hard to say how much worser it will hit the performance on sub-optimal processor designs. in get_pixel and put_pixel there is further a bunch of if/else sequences hidden that is much worser than the one-time check (optimisation_is_applicable). lets hope you got it why you really dont need a benchmark to see its a sure improvement for overall cases. -- Configure bugmail: https://bugzilla.novell.com/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are the QA contact for the bug. You are the assignee for the bug. _______________________________________________ mono-bugs maillist - [email protected] http://lists.ximian.com/mailman/listinfo/mono-bugs
