[Pixman] [PATCH] sse2: Add a fast path for add_n_8888

[Siarhei Siamashka]

On Wed, 02 Jan 2013 19:40:58 +0100
sandmann at cs.au.dk (Søren Sandmann) wrote:

> Chris Wilson <chris at chris-wilson.co.uk> writes:
> 
> > This path is being exercised by inplace compositing of trapezoids, for
> > instance as used in the firefox-asteroids cairo-trace.
> >
> > core2 @ 2.66GHz,
> >
> > reference memcpy speed = 4898.2MB/s (1224.6MP/s for 32bpp fills)
> >
> > before: add_n_8888 = L1:   4.36  L2:   4.27  M:  1.61 (  0.13%)  HT:
> > 1.65  VT:  1.63  R:  1.63  RT:  1.59 (  21Kops/s)
> >
> > after:  add_n_8888 = L1:2969.09  L2:3926.11  M:603.30 ( 49.27%)  HT:524.69
> > VT:401.01  R:407.59  RT:210.34 ( 804Kops/s)
> 
> Just two brief comments, and then I'll disappear again (until the 11th
> or so):
> 
> - It looks like this function will work for abgr destinations as well as
>   argb.
> 
> - I'm surprised that the new function is _that_ much better. The current
>   code should hit an SSE2 combiner and noop iterators for both source
>   and destination, so while I'd expect a solid improvement from a
>   dedicated fast path, it is hard to believe that it would be 919 times
>   faster than the old. If these numbers are real, there has to be
>   something wrong with either the benchmark or the current code.

The "sse2_combine_add_u" combiner does not have a special path for zero
mask and this could be improved. But indeed, the difference is still
quite unexpectedly large.

-- 
Best regards,
Siarhei Siamashka