Why is XRenderAddTraps preferred over XRenderCompositeTrapezoids?

[Clemens Eisserer]

Hi,

1.) It seems cairo plans since some time to switch from
XRenderCompositeTrapezoids to XRenderAddTraps to render their traps.
What are the advantages of XRenderAddTraps compared to
XRenderCompositeTrapezoids?

2.) A thing which struggles me is I have to composite many one-pixel
high lines (scanlines).
For now I simply call XRenderComposite for each line, but performance
is of course suboptimal ( I guess because gpu-setup overhead is high).

Would it help to use XRenderCompositeTrapezoids instead, as far as I
know the mask is generated by the CPU, so per-primitive overhead
should not matter that much.
Or will uploading the generated mask be slower than the
per-primitive-overhead I experience?

3.) Is one call to XRenderFillRectangles with 100 rects much faster
than 100 calls to XRenderFillRectangle?
Is it just protocol related, or is there also a difference how those
rects are processed by the driver/gpu?

Thank you in advance, lg Clemens