SSE4 opaque blend using intrinsics instead of assembly.

SSE4 opaque blend using intrinsics instead of assembly.

Since we had such a hard time with the assembly versions of this blit (to the
point that we have them completely disabled everywhere), I thought I'd take
a shot at writing a version of the blit using intrinsics.

The key feature of SSE4 we're exploiting is that we can use ptest (_mm_test*)
to skip the blend when the 16 src pixels we consider each loop are all opaque
or all transparent.  _mm_shuffle_epi8 from SSSE3 also lends a hand to extract
all those alphas.

It's worth looking to see if we can backport this type of logic to SSE2 using
_mm_movemask_epi8, or up to 32 pixels at a time using AVX.

My local performance testing doesn't show this to be an unambiguous win
(there are probably microbenchmarks and SKPs where we'd be better off just
powering through the blend rather than looking at alphas), but the potential
does seem tantalizing enough to let skiaperf vet it on the bots.  (< 1.0x is a win.)

DM says it draws pixel perfect compare to the old code.

Microbenchmarks:
               bitmap_RGBA_8888_A_source_stripes_two	  14us -> 14.4us	1.03x
             bitmap_RGBA_8888_A_source_stripes_three	14.3us -> 14.5us	1.01x
                       bitmap_RGBA_8888_scale_bilerp	61.9us -> 62.2us	1.01x
bitmap_RGBA_8888_update_volatile_scale_rotate_bilerp	 102us ->  101us	0.99x
                bitmap_RGBA_8888_scale_rotate_bilerp	 103us ->  101us	0.99x
                              bitmap_RGBA_8888_scale	18.4us -> 18.2us	0.99x
             bitmap_RGBA_8888_A_scale_rotate_bicubic	  71us ->   70us	0.99x
         bitmap_RGBA_8888_update_scale_rotate_bilerp	 103us ->  101us	0.99x
              bitmap_RGBA_8888_A_scale_rotate_bilerp	 112us ->  109us	0.98x
                    bitmap_RGBA_8888_update_volatile	5.72us -> 5.58us	0.98x
                                    bitmap_RGBA_8888	5.73us -> 5.58us	0.97x
                             bitmap_RGBA_8888_update	5.78us ->  5.6us	0.97x
                     bitmap_RGBA_8888_A_scale_bilerp	70.7us ->   68us	0.96x
                    bitmap_RGBA_8888_A_scale_bicubic	23.7us -> 21.8us	0.92x
                                  bitmap_RGBA_8888_A	13.9us -> 10.9us	0.78x
                    bitmap_RGBA_8888_A_source_opaque	  14us -> 6.29us	0.45x
               bitmap_RGBA_8888_A_source_transparent	  14us -> 3.65us	0.26x

Running over our ~70 SKP web page captures, this looks like we spend 0.7x
the time in S32A_Opaque_BlitRow compared to the SSE2 version, which should
be a decent predictor of real-world impact.

BUG=chromium:399842
Committed: https://skia.googlesource.com/skia/+/04bc91b972417038fecfa87c484771eac2b9b785

CQ_EXTRA_TRYBOTS=client.skia:Test-Mac10.6-MacMini4.1-GeForce320M-x86_64-Release-Trybot

Committed: https://skia.googlesource.com/skia/+/6dbfb21a6c88af6d94e8c823c3ad559f1a41b493

[mtklein_C, 2015-01-25 16:53:38]

mtklein@chromium.org changed reviewers:
+ henrik.smiding@intel.com

[mtklein_C, 2015-01-25 16:53:39]

Hi Henrik, since you were the author of
https://codereview.chromium.org/289473009, and this is sort of my take on the
same thing, I thought you might like to review this.  If not, no problem, just
let me know!

[mtklein, 2015-01-25 16:55:18]

The CQ bit was checked by mtklein@google.com

[commit-bot: I haz the power, 2015-01-25 16:56:07]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/874863002/140001

[commit-bot: I haz the power, 2015-01-25 16:56:08]

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 2015-01-25 22:56 UTC

[commit-bot: I haz the power, 2015-01-25 16:59:47]

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

[commit-bot: I haz the power, 2015-01-25 16:59:48]

Try jobs failed on following builders:
  Build-Win-VS2013-x86-Debug-Trybot on client.skia.compile
(http://build.chromium.org/p/client.skia.compile/builders/Build-Win-VS2013-x86...)

[mtklein, 2015-01-25 17:03:19]

The CQ bit was checked by mtklein@google.com

[commit-bot: I haz the power, 2015-01-25 17:04:08]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/874863002/160001

[commit-bot: I haz the power, 2015-01-25 17:04:09]

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 2015-01-25 23:04 UTC

[commit-bot: I haz the power, 2015-01-25 23:04:17]

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

[commit-bot: I haz the power, 2015-01-25 23:04:18]

No LGTM from a valid reviewer yet. Please ask for an LGTM from a
full Skia committer from
https://skia.googlesource.com/skia/+/master/CQ_COMMITTERS

[mtklein, 2015-01-26 19:37:25]

The CQ bit was checked by mtklein@google.com

[commit-bot: I haz the power, 2015-01-26 19:38:34]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/874863002/200001

[commit-bot: I haz the power, 2015-01-26 19:38:34]

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 2015-01-27 01:38 UTC

[mtklein, 2015-01-26 20:15:09]

The CQ bit was unchecked by mtklein@google.com

[mtklein_C, 2015-01-26 21:40:24]

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

[mtklein_C, 2015-01-26 21:40:24]

+Herb, who's been working on this with me this afternoon.

[mtklein_C, 2015-01-26 21:44:33]

The CQ bit was checked by mtklein@chromium.org

[commit-bot: I haz the power, 2015-01-26 21:45:29]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/874863002/220001

[commit-bot: I haz the power, 2015-01-26 21:45:29]

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 2015-01-27 03:45 UTC

[commit-bot: I haz the power, 2015-01-26 21:49:38]

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

[commit-bot: I haz the power, 2015-01-26 21:49:39]

Try jobs failed on following builders:
  Build-Win-VS2013-x86-Debug-Trybot on client.skia.compile
(http://build.chromium.org/p/client.skia.compile/builders/Build-Win-VS2013-x86...)

[mtklein, 2015-01-26 21:52:10]

The CQ bit was checked by mtklein@google.com

[commit-bot: I haz the power, 2015-01-26 21:52:38]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/874863002/240001

[commit-bot: I haz the power, 2015-01-26 21:52:39]

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 2015-01-27 03:52 UTC

[mtklein, 2015-01-26 21:59:55]

The CQ bit was checked by mtklein@google.com

[commit-bot: I haz the power, 2015-01-26 21:59:59]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/874863002/260001

[commit-bot: I haz the power, 2015-01-26 22:00:00]

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 2015-01-27 03:59 UTC

[reed1, 2015-01-26 22:04:31]

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

[reed1, 2015-01-26 22:04:32]

hurray for deleting code! (and speeding things up)
lgtm

[commit-bot: I haz the power, 2015-01-26 22:06:46]

Committed patchset #14 (id:260001) as
https://skia.googlesource.com/skia/+/04bc91b972417038fecfa87c484771eac2b9b785

[Nico, 2015-01-26 22:23:01]

thakis@chromium.org changed reviewers:
+ thakis@chromium.org

[Nico, 2015-01-26 22:23:02]

https://codereview.chromium.org/874863002/diff/260001/gyp/opts.gyp
File gyp/opts.gyp (right):

https://codereview.chromium.org/874863002/diff/260001/gyp/opts.gyp#newcode210
gyp/opts.gyp:210: 'target_name': 'opts_sse4',
You probably need something like https://codereview.chromium.org/475273002 for
this target, else clang-cl will likely be unhappy about this.

[bungeman-skia, 2015-01-26 22:31:42]

A revert of this CL (patchset #14 id:260001) has been created in
https://codereview.chromium.org/874033004/ by bungeman@google.com.

The reason for reverting is: This kills Mac 10.6 bots.

FAILED: c++ -MMD -MF obj/src/opts/opts_sse4.SkBlitRow_opts_SSE4.o.d
-DSK_INTERNAL -DSK_GAMMA_SRGB -DSK_GAMMA_APPLY_TO_A8
-DSK_SCALAR_TO_FLOAT_EXCLUDED -DSK_ALLOW_STATIC_GLOBAL_INITIALIZERS=1
-DSK_SUPPORT_GPU=1 -DSK_SUPPORT_OPENCL=0 -DSK_FORCE_DISTANCE_FIELD_TEXT=0
-DSK_BUILD_FOR_MAC -DSK_CRASH_HANDLER -DSK_DEVELOPER=1 -I../../src/core
-I../../src/utils -I../../include/c -I../../include/config -I../../include/core
-I../../include/pathops -I../../include/pipe -I../../include/utils/mac
-I../../include/effects -O0 -gdwarf-2 -mmacosx-version-min=10.6 -arch x86_64
-mssse3 -Wall -Wextra -Winit-self -Wpointer-arith -Wsign-compare
-Wno-unused-parameter -Wno-invalid-offsetof -msse4.1  -c
../../src/opts/SkBlitRow_opts_SSE4.cpp -o
obj/src/opts/opts_sse4.SkBlitRow_opts_SSE4.o
../../src/opts/SkBlitRow_opts_SSE4.cpp:15:27: warning: x86intrin.h: No such file
or directory
../../src/opts/SkBlitRow_opts_SSE4.cpp: In function 'void
S32A_Opaque_BlitRow32_SSE4(SkPMColor*, const SkPMColor*, int, U8CPU)':
../../src/opts/SkBlitRow_opts_SSE4.cpp:40: error: '_mm_testz_si128' was not
declared in this scope
../../src/opts/SkBlitRow_opts_SSE4.cpp:45: error: '_mm_testc_si128' was not
declared in this scope.

[Nico, 2015-01-26 22:37:45]

On 2015/01/26 22:31:42, bungeman1 wrote:
> A revert of this CL (patchset #14 id:260001) has been created in
> https://codereview.chromium.org/874033004/ by mailto:bungeman@google.com.
> 
> The reason for reverting is: This kills Mac 10.6 bots.
> 
> FAILED: c++ -MMD -MF obj/src/opts/opts_sse4.SkBlitRow_opts_SSE4.o.d
> -DSK_INTERNAL -DSK_GAMMA_SRGB -DSK_GAMMA_APPLY_TO_A8
> -DSK_SCALAR_TO_FLOAT_EXCLUDED -DSK_ALLOW_STATIC_GLOBAL_INITIALIZERS=1
> -DSK_SUPPORT_GPU=1 -DSK_SUPPORT_OPENCL=0 -DSK_FORCE_DISTANCE_FIELD_TEXT=0
> -DSK_BUILD_FOR_MAC -DSK_CRASH_HANDLER -DSK_DEVELOPER=1 -I../../src/core
> -I../../src/utils -I../../include/c -I../../include/config
-I../../include/core
> -I../../include/pathops -I../../include/pipe -I../../include/utils/mac
> -I../../include/effects -O0 -gdwarf-2 -mmacosx-version-min=10.6 -arch x86_64
> -mssse3 -Wall -Wextra -Winit-self -Wpointer-arith -Wsign-compare
> -Wno-unused-parameter -Wno-invalid-offsetof -msse4.1  -c
> ../../src/opts/SkBlitRow_opts_SSE4.cpp -o
> obj/src/opts/opts_sse4.SkBlitRow_opts_SSE4.o
> ../../src/opts/SkBlitRow_opts_SSE4.cpp:15:27: warning: x86intrin.h: No such
file
> or directory
> ../../src/opts/SkBlitRow_opts_SSE4.cpp: In function 'void
> S32A_Opaque_BlitRow32_SSE4(SkPMColor*, const SkPMColor*, int, U8CPU)':
> ../../src/opts/SkBlitRow_opts_SSE4.cpp:40: error: '_mm_testz_si128' was not
> declared in this scope
> ../../src/opts/SkBlitRow_opts_SSE4.cpp:45: error: '_mm_testc_si128' was not
> declared in this scope.

This might be a config problem with your 10.6 bots. On a chromium 10.6 bot:

hrome-bot@vm9-a1 bash$ cat test.cc
#include <x86intrin.h>
chrome-bot@vm9-a1 bash$ clang -c test.cc -H
. /usr/bin/../lib/clang/3.0/include/x86intrin.h
.. /usr/bin/../lib/clang/3.0/include/immintrin.h

[mtklein, 2015-01-26 23:08:02]

> This might be a config problem with your 10.6 bots. On a chromium 10.6 bot:

Very well could be.  Looks like including emmintrin and smmintrin is the easy
way out.

[mtklein, 2015-01-27 22:18:56]

The CQ bit was checked by mtklein@google.com

[commit-bot: I haz the power, 2015-01-27 22:19:20]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/874863002/300001

[commit-bot: I haz the power, 2015-01-27 22:35:24]

Committed patchset #16 (id:300001) as
https://skia.googlesource.com/skia/+/6dbfb21a6c88af6d94e8c823c3ad559f1a41b493

[fmalita_google_do_not_use, 2015-01-29 05:04:13]

On 2015/01/27 22:35:24, I haz the power (commit-bot) wrote:
> Committed patchset #16 (id:300001) as
> https://skia.googlesource.com/skia/+/6dbfb21a6c88af6d94e8c823c3ad559f1a41b493

I just noticed a ~5% linux/key_mobile_sites_smooth rasterization time
improvement which seems attributable to this CL - nice job!

https://chromeperf.appspot.com/report?masters=ChromiumPerf&bots=linux-release...

[mtklein, 2015-01-29 14:38:21]

> I just noticed a ~5% linux/key_mobile_sites_smooth rasterization time
> improvement which seems attributable to this CL - nice job!
> 
>
https://chromeperf.appspot.com/report?masters=ChromiumPerf&bots=linux-release...

Ooh, nice.  You can really tell which sites are image-heavy just from whether or
not they improved here.

[stephana, 2015-02-02 17:52:00]

A revert of this CL (patchset #16 id:300001) has been created in
https://codereview.chromium.org/873553003/ by stephana@google.com.

The reason for reverting is: This causes a bug on the 'hittestpath' GM on
MacMini 4,1 

See: 

https://gold.skia.org/#/triage/hittestpath?head=0 

for details. .