Port S32A_opaque blit row to SkOpts.

Port S32A_opaque blit row to SkOpts.

This should be a pixel-for-pixel (i.e. bug-for-bug) port.

BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&issue=1820313002
CQ_EXTRA_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot

Committed: https://skia.googlesource.com/skia/+/b4a7dc99b1a01cdd5c0cd5913b630436ca696210

[mtklein_C, 2016-03-22 15:32:32]

Description was changed from

==========
Port S32A_opaque blit row to SkOpts.

BUG=skia:
==========

to

==========
Port S32A_opaque blit row to SkOpts.

BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...
CQ_EXTRA_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
==========

[mtklein, 2016-03-22 15:32:54]

Description was changed from

==========
Port S32A_opaque blit row to SkOpts.

BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...
CQ_EXTRA_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
==========

to

==========
Port S32A_opaque blit row to SkOpts.

This should be a pixel-for-pixel (i.e. bug-for-bug) port.

BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...
CQ_EXTRA_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
==========

[mtklein, 2016-03-22 15:43:07]

The CQ bit was checked by mtklein@google.com to run a CQ dry run

[commit-bot: I haz the power, 2016-03-22 15:43:18]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1820313002/40001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1820313002/40001

[mtklein_C, 2016-03-22 15:48:33]

mtklein@chromium.org changed reviewers:
+ djsollen@google.com
- mtklein@google.com

[mtklein_C, 2016-03-22 15:48:33]

The CQ bit was checked by mtklein@chromium.org

[mtklein_C, 2016-03-22 15:48:33]

This shouldn't have the same problem that the old code had.
On Android builds without SSE4.1, the "SSE4.1" code will just fall back to SSE2.

[commit-bot: I haz the power, 2016-03-22 15:48:40]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1820313002/60001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1820313002/60001

[commit-bot: I haz the power, 2016-03-22 15:48:41]

Note for Reviewers:
The CQ is waiting for an approval.
If you believe that the CL is not ready yet, or if you would like to L-G-T-M
with comments then please uncheck the CQ checkbox.

Waiting for LGTM from valid reviewer(s) till 2016-03-22 21:48 UTC

[mtklein, 2016-03-22 16:27:44]

The CQ bit was unchecked by mtklein@google.com

[djsollen, 2016-03-22 17:12:42]

https://codereview.chromium.org/1820313002/diff/60001/src/opts/SkOpts_sse41.cpp
File src/opts/SkOpts_sse41.cpp (right):

https://codereview.chromium.org/1820313002/diff/60001/src/opts/SkOpts_sse41.c...
src/opts/SkOpts_sse41.cpp:16: namespace sk_sse41_new {
why do we need to add _new?

[mtklein, 2016-03-22 17:39:27]

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

[mtklein, 2016-03-22 17:39:28]

https://codereview.chromium.org/1820313002/diff/60001/src/opts/SkOpts_sse41.cpp
File src/opts/SkOpts_sse41.cpp (right):

https://codereview.chromium.org/1820313002/diff/60001/src/opts/SkOpts_sse41.c...
src/opts/SkOpts_sse41.cpp:16: namespace sk_sse41_new {
On 2016/03/22 17:12:42, djsollen wrote:
> why do we need to add _new?

This is sort of dumb.

You know how the new SkBlitRow_opts.h code has a lot of
   // TODO: this math is bad and you should feel bad.
?  I started trying to fix some of those math problems a few months ago, and
that's the code here in this file.  The blit_row_color32 and blit_mask_d32_a8 in
this file should have correct math.

SkBlitRow_opts.h also has an older blit_row_color32.  Now that I'm mixing the
two files, I end up with two sk_sse41::blit_row_color32 functions, one older,
slower and incorrect, one newer faster and correct.  I've been dragging my heels
a little to rebase Blink and remove the old code.

[mtklein_C, 2016-03-22 21:57:01]

Looks like Gold agrees there are no diffs.

[djsollen, 2016-03-23 12:48:13]

lgtm

[mtklein, 2016-03-23 13:28:04]

The CQ bit was checked by mtklein@google.com

[commit-bot: I haz the power, 2016-03-23 13:28:16]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1820313002/60001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1820313002/60001

[commit-bot: I haz the power, 2016-03-23 13:29:14]

Description was changed from

==========
Port S32A_opaque blit row to SkOpts.

This should be a pixel-for-pixel (i.e. bug-for-bug) port.

BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...
CQ_EXTRA_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
==========

to

==========
Port S32A_opaque blit row to SkOpts.

This should be a pixel-for-pixel (i.e. bug-for-bug) port.

BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...
CQ_EXTRA_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot

Committed:
https://skia.googlesource.com/skia/+/b4a7dc99b1a01cdd5c0cd5913b630436ca696210
==========

[commit-bot: I haz the power, 2016-03-23 13:29:15]

Committed patchset #4 (id:60001) as
https://skia.googlesource.com/skia/+/b4a7dc99b1a01cdd5c0cd5913b630436ca696210