Sk4x4f: NEON impl.

Sk4x4f: NEON impl.

Notable tricks:
  - v{ld,st}4q_f32 handle transposing loads and stores of floats in one step
  - vcvtq_n_{f32_u32,u32_f32} let us do conversion to and from floats without shifts


BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&issue=1828613002

Committed: https://skia.googlesource.com/skia/+/1fd50acbaa1e26f892ad810a67cb3fa90b039c85

[mtklein_C, 2016-03-23 03:14:03]

Description was changed from

==========
start on neon



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

to

==========
start on neon



BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...
==========

[mtklein_C, 2016-03-23 23:01:03]

Description was changed from

==========
start on neon



BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...
==========

to

==========
Sk4x4f: NEON impl.

Notable tricks:
  - v{ld,st}4q_f32 handle transposing loads and stores of floats in one step
  - vcvtq_n_{f32_u32,u32_f32} let us do fixed point conversion to and from
floats


BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...
==========

[mtklein_C, 2016-03-23 23:04:43]

The CQ bit was checked by mtklein@chromium.org to run a CQ dry run

[commit-bot: I haz the power, 2016-03-23 23:04:48]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1828613002/40001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1828613002/40001

[mtklein_C, 2016-03-23 23:16:16]

mtklein@chromium.org changed reviewers:
+ herb@google.com

[mtklein_C, 2016-03-23 23:16:17]

I know you're eager to learn NEON.  Want to have a look here?

I can give you some pointers if you're looking for docs:
 
http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.dui0489e/CJAJIIGG...
 
http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.dui0472j/chr13591...

[commit-bot: I haz the power, 2016-03-23 23:16:18]

The CQ bit was unchecked by commit-bot@chromium.org

[commit-bot: I haz the power, 2016-03-23 23:16:19]

Dry run: This issue passed the CQ dry run.

[mtklein_C, 2016-03-24 02:03:30]

mtklein@chromium.org changed reviewers:
+ msarett@google.com

[mtklein_C, 2016-03-24 02:03:31]

+Matt, who may be interested to see that we've finally found a use for
vcvtq_n_f32_u32.

[mtklein_C, 2016-03-24 02:03:54]

Description was changed from

==========
Sk4x4f: NEON impl.

Notable tricks:
  - v{ld,st}4q_f32 handle transposing loads and stores of floats in one step
  - vcvtq_n_{f32_u32,u32_f32} let us do fixed point conversion to and from
floats


BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...
==========

to

==========
Sk4x4f: NEON impl.

Notable tricks:
  - v{ld,st}4q_f32 handle transposing loads and stores of floats in one step
  - vcvtq_n_{f32_u32,u32_f32} let us do conversion to and from floats without
shifts


BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...
==========

[msarett, 2016-03-24 17:00:50]

lgtm in case you need one of those :)

https://codereview.chromium.org/1828613002/diff/40001/src/core/Sk4x4f.h
File src/core/Sk4x4f.h (right):

https://codereview.chromium.org/1828613002/diff/40001/src/core/Sk4x4f.h#newco...
src/core/Sk4x4f.h:91: auto r =  
vcvtq_f32_u32(vandq_u32(vdupq_n_u32(0x000000FF), b16)    ),
Woohoo this is cool!

[mtklein, 2016-03-24 17:11:26]

The CQ bit was checked by mtklein@google.com

[commit-bot: I haz the power, 2016-03-24 17:11:46]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1828613002/40001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1828613002/40001

[commit-bot: I haz the power, 2016-03-24 17:12:43]

Description was changed from

==========
Sk4x4f: NEON impl.

Notable tricks:
  - v{ld,st}4q_f32 handle transposing loads and stores of floats in one step
  - vcvtq_n_{f32_u32,u32_f32} let us do conversion to and from floats without
shifts


BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...
==========

to

==========
Sk4x4f: NEON impl.

Notable tricks:
  - v{ld,st}4q_f32 handle transposing loads and stores of floats in one step
  - vcvtq_n_{f32_u32,u32_f32} let us do conversion to and from floats without
shifts


BUG=skia:
GOLD_TRYBOT_URL=
https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&is...

Committed:
https://skia.googlesource.com/skia/+/1fd50acbaa1e26f892ad810a67cb3fa90b039c85
==========

[commit-bot: I haz the power, 2016-03-24 17:12:44]

Committed patchset #3 (id:40001) as
https://skia.googlesource.com/skia/+/1fd50acbaa1e26f892ad810a67cb3fa90b039c85