Chris Wilson <ch...@chris-wilson.co.uk> writes:
> These are often used inplace of a solid-fill gradient, with the
> expectation that have similar performance and hit the same fast paths.
> One exception is the identification of the 1x1R <-> solid-fill
> equivalence in general_composite_rect(). By adding the special case to
> _pixman_bits_image_src_iter_init, we can recover the lost performance:
This issue is also fixed by the patch here:
http://lists.freedesktop.org/archives/pixman/2012-December/002444.html
which I will push shortly (with an updated commit message that includes
similar performance numbers to those you posted).
Doing it in the noop implementation is better because it avoids the
question of, say, a repeating SSE2 iterator potentially getting picked
before the one in pixman-bits-image.c.
Søren
_______________________________________________
Pixman mailing list
Pixman@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/pixman
