[cairo] ANN: "Caskbench" performance benchmark

[Chris Wilson]

On Fri, Sep 26, 2014 at 09:38:16PM +0100, Chris Wilson wrote:
> On Fri, Sep 26, 2014 at 01:01:25PM -0700, Bryce Harrington wrote:
> > Apart from the stars test, cairo-gl did better all-around than cairo
> > image.  And for gradients and image manipulation it's profoundly faster.
> > Now, I haven't tested against GLX but this makes me wonder if this would
> > translate into significantly better performance for, say, Inkscape?  If
> > so, should we maybe be advocating cairo-gl/cairo-egl more heavily here?
> 
> I notice you don't actually synchronise the rendering pipeline before
> measuring the throughput performance. That would be worth checking.

To illustrate that point:

=0 ickle:/usr/src/caskbench$ ./src/caskbench -t egl
cairo-animation      100    PASS  100  9999
cairo-bubbles        100    PASS  100  9999  0.00%
cairo-circle         100    PASS  100  9999
cairo-clip           100    PASS  100  9999  0.00%
cairo-cubic          100    PASS  100  9999
cairo-curves         100    PASS  100  2791  0.00%
cairo-fill           100    PASS  100  9999
...
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre