Eliminate static initializers in SkColor_SSE2.h.

Eliminate static initializers in SkColor_SSE2.h.

Chrome hates static initializers.

Two global masks can become a single local mask instead.  Perf looks like a no-op:

$ c --match bitmaprect_80 bitmap_RGBA --config 8888
                              bitmap_RGBA_8888_scale	13.7us -> 14.1us	1.03x
                    bitmap_RGBA_8888_update_volatile	4.53us ->  4.6us	1.02x
                                    bitmap_RGBA_8888	4.55us -> 4.61us	1.01x
                             bitmap_RGBA_8888_update	4.64us -> 4.67us	1.01x
             bitmap_RGBA_8888_A_source_stripes_three	9.66us -> 9.71us	1.01x
                       bitmaprect_80_filter_identity	10.6us -> 10.5us	0.99x
                     bitmaprect_80_nofilter_identity	10.5us -> 10.4us	0.99x

TBR=reed@google.com
BUG=skia:

Committed: https://skia.googlesource.com/skia/+/785982ed80ce43653f64640d04dae7eaf5e2f809

[mtklein, 2014-11-25 17:55:16]

mtklein@google.com changed reviewers:
+ mtklein@google.com, reed@google.com

[mtklein, 2014-11-25 17:55:16]

The CQ bit was checked by mtklein@google.com

[mtklein, 2014-11-25 17:55:16]

lgtm

[commit-bot: I haz the power, 2014-11-25 17:56:10]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/762453002/1

[commit-bot: I haz the power, 2014-11-25 18:05:47]

Committed patchset #1 (id:1) as
https://skia.googlesource.com/skia/+/785982ed80ce43653f64640d04dae7eaf5e2f809

[qiankun1, 2014-11-26 07:40:18]

qkmiao@gmail.com changed reviewers:
+ qkmiao@gmail.com

[qiankun1, 2014-11-26 07:40:18]

Is there a tool to generate the data in your format? And where to find some skp
files to testing?

[mtklein, 2014-11-26 14:46:41]

On 2014/11/26 07:40:18, qiankun1 wrote:
> Is there a tool to generate the data in your format? And where to find some
skp
> files to testing?

Yes, skia/bin contains 'c' and 'compare' now.  If you sync to head and add
skia/bin to your path, you should be able to run that command literally.  Note
that compare is a Python script that depends on scipy for its implementation of
the Mann-Whitney U test.

We cannot redistribute .skp files, but you can use the directions here to
capture some of your own:
 
http://www.chromium.org/developers/how-tos/trace-event-profiling-tool/saving-...

Those directions look a little dated, but should work fine.  I think you really
only need to pass --enable-skia-benchmarking now.