SkPx: new approach to fixed-point SIMD

SkPx: new approach to fixed-point SIMD

SkPx is like Sk4px, except each platform implementation of SkPx can declare
a different sweet spot of N pixels, with extra loads and stores to handle the 
ragged edge of 0<n<N pixels.

In this case, _sse's sweet spot remains 4 pixels.   _neon jumps up to 8 so
we can now use NEON's transposing loads and stores, and _none is just 1.
This makes operations involving alpha considerably more efficient on NEON,
as alpha is its own distinct 8x8 bit plane that's easy to toss around.

This incorporates a few other improvements I've been wanting:
  - no requirement that we're dealing with SkPMColor.  SkColor works too.
  - no anonymous namespace hack to differentiate implementations.

Codegen and perf look good on Clang/x86-64 and GCC/ARMv7.
The NEON code looks very similar to the old NEON code, as intended.
No .skp or GM diffs on my laptop.  Don't expect any.

I intend this to replace Sk4px.  Plan after landing:
  - port SkXfermode_opts.h
  - port Color32 in SkBlitRow_D32.cpp (and move to SkBlitRow_opts.h like other
    SkOpts code)
  - delete all Sk4px-related code
  - clean up evolutionary dead ends in SkNx (Sk16b, Sk16h, Sk4i, Sk4d, etc.)
    leaving Sk2f, Sk4f (and Sk2s, Sk4s).
  - find a machine with AVX2 to work on, write SkPx_avx2.h handling 8 pixels
    at a time.

In the end we'll have Sk4f for float pixels, SkPx for fixed-point pixels.

BUG=skia:4117
Committed: https://skia.googlesource.com/skia/+/82c93b45ed6ac0b628adb8375389c202d1f586f9

CQ_EXTRA_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot;client.skia.compile:Build-Mac10.8-Clang-Arm7-Debug-Android-Trybot

Committed: https://skia.googlesource.com/skia/+/a7627dc5cc2bf5d9a95d883d20c40d477ecadadf

Committed: https://skia.googlesource.com/skia/+/e8e17cf23d2a036f9b3050bedeb9d3a544221f4c

[mtklein, 2015-09-07 20:35:02]

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

[commit-bot: I haz the power, 2015-09-07 20:35:04]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1317233005/140001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1317233005/140001

[commit-bot: I haz the power, 2015-09-07 20:35:45]

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

[commit-bot: I haz the power, 2015-09-07 20:35:45]

Dry run: Try jobs failed on following builders:
  Build-Ubuntu-Clang-x86_64-Debug-Trybot on client.skia.compile (JOB_FAILED,
http://build.chromium.org/p/client.skia.compile/builders/Build-Ubuntu-Clang-x...)

[mtklein, 2015-09-07 20:44:38]

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

[commit-bot: I haz the power, 2015-09-07 20:44:44]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1317233005/160001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1317233005/160001

[commit-bot: I haz the power, 2015-09-07 20:49:55]

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

[commit-bot: I haz the power, 2015-09-07 20:49:55]

Dry run: This issue passed the CQ dry run.

[mtklein_C, 2015-09-07 21:25:25]

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

[msarett, 2015-09-08 15:33:12]

In general, I like the concept of allowing NEON and SSE implementations to be
more independent.

lgtm

https://codereview.chromium.org/1317233005/diff/160001/src/opts/SkBlitMask_op...
File src/opts/SkBlitMask_opts.h (right):

https://codereview.chromium.org/1317233005/diff/160001/src/opts/SkBlitMask_op...
src/opts/SkBlitMask_opts.h:40: if (color == SK_ColorBLACK) {
You use different functions for different special cases because BLACK and opaque
are much easier than default blits?

This is really clever!

[mtklein, 2015-09-08 15:45:27]

https://codereview.chromium.org/1317233005/diff/160001/src/opts/SkBlitMask_op...
File src/opts/SkBlitMask_opts.h (right):

https://codereview.chromium.org/1317233005/diff/160001/src/opts/SkBlitMask_op...
src/opts/SkBlitMask_opts.h:40: if (color == SK_ColorBLACK) {
On 2015/09/08 15:33:12, msarett wrote:
> You use different functions for different special cases because BLACK and
opaque
> are much easier than default blits?
> 
> This is really clever!

Yep.  It is clever.  Sadly, not my cleverness, but still, very clever!

My only claim to cleverness here is in the general case, where I noticed (1 -
sa*aa) is actually just left.alpha().inv().

[mtklein, 2015-09-14 19:37:11]

The CQ bit was checked by mtklein@google.com

[commit-bot: I haz the power, 2015-09-14 19:37:25]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1317233005/160001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1317233005/160001

[commit-bot: I haz the power, 2015-09-14 19:43:25]

Committed patchset #9 (id:160001) as
https://skia.googlesource.com/skia/+/82c93b45ed6ac0b628adb8375389c202d1f586f9

[mtklein_C, 2015-09-14 20:14:08]

A revert of this CL (patchset #9 id:160001) has been created in
https://codereview.chromium.org/1336423002/ by mtklein@chromium.org.

The reason for reverting is:
http://build.chromium.org/p/client.skia.compile/builders/Build-Mac10.8-Clang-....

[mtklein, 2015-11-06 16:20:47]

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

[commit-bot: I haz the power, 2015-11-06 16:20:53]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1317233005/160001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1317233005/160001

[commit-bot: I haz the power, 2015-11-06 16:22:24]

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

[commit-bot: I haz the power, 2015-11-06 16:22:25]

Dry run: Try jobs failed on following builders:
  Build-Mac10.8-Clang-Arm7-Debug-Android-Trybot on client.skia.compile
(JOB_FAILED,
http://build.chromium.org/p/client.skia.compile/builders/Build-Mac10.8-Clang-...)

[mtklein, 2015-11-06 16:38:45]

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

[commit-bot: I haz the power, 2015-11-06 16:38:55]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1317233005/180001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1317233005/180001

[commit-bot: I haz the power, 2015-11-06 16:40:04]

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

[commit-bot: I haz the power, 2015-11-06 16:40:04]

Dry run: Try jobs failed on following builders:
  Build-Mac10.8-Clang-Arm7-Debug-Android-Trybot on client.skia.compile
(JOB_FAILED,
http://build.chromium.org/p/client.skia.compile/builders/Build-Mac10.8-Clang-...)

[mtklein, 2015-11-06 16:49:39]

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

[commit-bot: I haz the power, 2015-11-06 16:49:50]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1317233005/200001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1317233005/200001

[commit-bot: I haz the power, 2015-11-06 16:50:49]

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

[commit-bot: I haz the power, 2015-11-06 16:50:50]

Dry run: Try jobs failed on following builders:
  Build-Mac10.8-Clang-Arm7-Debug-Android-Trybot on client.skia.compile
(JOB_FAILED,
http://build.chromium.org/p/client.skia.compile/builders/Build-Mac10.8-Clang-...)

[mtklein, 2015-11-06 16:57:52]

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

[commit-bot: I haz the power, 2015-11-06 16:57:57]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1317233005/220001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1317233005/220001

[commit-bot: I haz the power, 2015-11-06 17:10:10]

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

[commit-bot: I haz the power, 2015-11-06 17:10:11]

Dry run: This issue passed the CQ dry run.

[mtklein, 2015-11-06 17:18:10]

The CQ bit was checked by mtklein@google.com

[mtklein, 2015-11-06 17:18:10]

The patchset sent to the CQ was uploaded after l-g-t-m from msarett@google.com
Link to the patchset: https://codereview.chromium.org/1317233005/#ps220001
(title: "<<16 is not allowed")

[commit-bot: I haz the power, 2015-11-06 17:18:21]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1317233005/220001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1317233005/220001

[commit-bot: I haz the power, 2015-11-06 17:19:00]

Committed patchset #12 (id:220001) as
https://skia.googlesource.com/skia/+/a7627dc5cc2bf5d9a95d883d20c40d477ecadadf

[mtklein, 2015-11-06 19:33:57]

A revert of this CL (patchset #12 id:220001) has been created in
https://codereview.chromium.org/1409843005/ by mtklein@google.com.

The reason for reverting is: master-skia unhappy:
https://android-build.storage.googleapis.com/builds/git_master-skia-linux-vol....

[mtklein, 2015-11-06 20:00:38]

The CQ bit was checked by mtklein@google.com

[mtklein, 2015-11-06 20:00:39]

The patchset sent to the CQ was uploaded after l-g-t-m from msarett@google.com
Link to the patchset: https://codereview.chromium.org/1317233005/#ps240001
(title: "shl,shr")

[commit-bot: I haz the power, 2015-11-06 20:19:21]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1317233005/240001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1317233005/240001

[commit-bot: I haz the power, 2015-11-06 22:10:51]

Committed patchset #13 (id:240001) as
https://skia.googlesource.com/skia/+/e8e17cf23d2a036f9b3050bedeb9d3a544221f4c