AuroraMiddleware/skia2
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
12,491 Commits 1 Branch 0 Tags 544 MiB
b0b1aa04ed
Commit Graph

12491 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
mtklein
91359bed48 Revert of Clean up Test's resourcePath code. (https://codereview.chromium.org/319473003/) 
Reason for revert:
Some benchmarks are written in a way that makes this change unsafe (e.g. const char* resPath = GetResourcePath().c_str(); in SkipZeroesBench) and Valgrind and ASAN caught that.  We can try again after a more careful cleanup of GetResourcePath().

Original issue's description:
> Clean up resourcePath code.
>
> 1) Make the implementation of SetResourcePath/GetResourcePath of GM and SkBenchmark match with the one in Test.
> 2) Make gResourcePath a static pointer to const char and move it inside the classes.
>
> BUG=None
> TEST=make tests && out/Debug/tests
>      make gm && out/Debug/gm
>      make bench && out/Debug/bench
> R=mtklein@google.com
>
> Committed: https://skia.googlesource.com/skia/+/52e4f413ffe2d281f9e90ff2147db08083ffcba7

R=tfarina@chromium.org
TBR=tfarina@chromium.org
NOTREECHECKS=true
NOTRY=true
BUG=None

Author: mtklein@google.com

Review URL: https://codereview.chromium.org/320733002
 2014-06-08 07:02:47 -07:00
robertphillips
643b8bd661 First pass at splitting out SkPictureRecord from SkPicture 
This patch begins the process of splitting apart SkPicture, SkPicturePlayback and SkPictureRecord.

This is still a bit messy. In a follow up CL I hope to delay the creation of SkPictureRecorder's SkPicture until endRecording time.

R=reed@google.com, mtklein@google.com

Author: robertphillips@google.com

Review URL: https://codereview.chromium.org/318763004
 2014-06-08 05:55:05 -07:00
tfarina
52e4f413ff Clean up resourcePath code. 
1) Make the implementation of SetResourcePath/GetResourcePath of GM and SkBenchmark match with the one in Test.
2) Make gResourcePath a static pointer to const char and move it inside the classes.

BUG=None
TEST=make tests && out/Debug/tests
     make gm && out/Debug/gm
     make bench && out/Debug/bench

R=mtklein@google.com

Author: tfarina@chromium.org

Review URL: https://codereview.chromium.org/319473003
 2014-06-07 20:50:44 -07:00
mtklein
3d06b48660 whitespace to trigger builds 
BUG=skia:

Committed: https://skia.googlesource.com/skia/+/5037fceeab7d29b99a6497bcdf1c97f03e532956

R=mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/314313004
 2014-06-07 20:27:45 -07:00
mtklein
5037fceeab whitespace to trigger builds 
BUG=skia:
R=mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/314313004
 2014-06-07 17:19:04 -07:00
Mike Klein
b77c7ef37f Clean up Skia for Clang's -Wtautological-undefined-compare 
This is blocking Chrome from rolling a new Clang, and me too for our TSAN bots.

BUG=chromium:381910

Review URL: https://codereview.chromium.org/325603002
 2014-06-07 19:15:14 -04:00
mtklein
19cae4fa2c use __atomics in SkBarriers_tsan.h 
I am having a hard time getting TSAN's own atomic hooks to work on our bots,
but __atomic_foo work fine and are understood just fine by TSAN.

BUG=skia:
R=bungeman@google.com, mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/320063003
 2014-06-06 15:11:04 -07:00
djordje.pesut
aaf1df632d MIPS: modified gypi files to support build 
R=teodora.petrovic@gmail.com, djsollen@google.com

Author: djordje.pesut@imgtec.com

Review URL: https://codereview.chromium.org/304903003
 2014-06-06 14:09:12 -07:00
jvanverth
d78a2fac37 Rollback of fe689c46 and all subsequent changes 
BUG=skia:
R=humper@google.com
TBR=humper@google.com
NOTRY=True
NOTREECHECKS=True

Author: jvanverth@google.com

Review URL: https://codereview.chromium.org/324463005
 2014-06-06 13:40:36 -07:00
humper
9ab6c00f6c remove extra debug prints 
BUG=skia:
TBR=jvanverth
NOTRY=True
NOTREECHECKS=True

Author: humper@google.com

Review URL: https://codereview.chromium.org/314423002
 2014-06-06 13:28:04 -07:00
humper
39dd491efe fix 10.6 shader tests 
BUG=skia:
TBR=jvanverth
NOTRY=True
NOTREECHECKS=True

Author: humper@google.com

Review URL: https://codereview.chromium.org/324543002
 2014-06-06 12:55:23 -07:00
humper
e10a4ff45a repair math error introduced by windows build fix 
BUG=skia:
TBR=jvanverth
NOTRY=True
NOTREECHECKS=True

Author: humper@google.com

Review URL: https://codereview.chromium.org/320593003
 2014-06-06 12:21:03 -07:00
jvanverth
a07213ac83 Disable bigblurs GM (for fe689c46a7) 
BUG=skia:
R=humper@google.com
TBR=humper@google.com
NOTRY=True
NOTREECHECKS=True

Author: jvanverth@google.com

Review URL: https://codereview.chromium.org/325453002
 2014-06-06 11:59:26 -07:00
humper
1afc04d877 one channel texture fix for blur shader 
BUG=skia:
R=bsalomon@google.com
TBR=bsalomon
NOTRY=True
NOTREECHECKS=True

Author: humper@google.com

Review URL: https://codereview.chromium.org/319543007
 2014-06-06 11:55:24 -07:00
humper
da1c00914e disable GPU/CPU blur match test (possibly temporary) 
BUG=skia:
TBR=jvanverth
NOTRY=True
NOTREECHECKS=True

Author: humper@google.com

Review URL: https://codereview.chromium.org/322593002
 2014-06-06 11:37:24 -07:00
humper
7bf666a00f fix blur test 
BUG=skia:
TBR=jvanverth
NOTRY=True
NOTREECHECKS=True

Author: humper@google.com

Review URL: https://codereview.chromium.org/323583002
 2014-06-06 11:22:50 -07:00
humper
ede6cfc0f5 Revert of Revert of another GM to ignore for blur rebaseline (https://codereview.chromium.org/319943004/) 
Reason for revert:
Hopefully working now

Original issue's description:
> Revert of another GM to ignore for blur rebaseline (https://codereview.chromium.org/319203002/)
>
> Reason for revert:
> Follow-on to fe689c46a7, which needs to be reverted due to bot failures.
>
> Original issue's description:
> > another GM to ignore for blur rebaseline
> >
> > BUG=skia:
> > TBR=jvanverth
> > NOTRY=True
> > NOTREECHECKS=True
> >
> > Committed: https://skia.googlesource.com/skia/+/f131055929afb9c9671aee3e575c380d48c5ee4d
>
> TBR=humper@google.com
> NOTREECHECKS=true
> NOTRY=true
> BUG=skia:
>
> Committed: https://skia.googlesource.com/skia/+/f255de0fe160e33b340301859be1d9374c5607fe

R=jvanverth@google.com
TBR=jvanverth@google.com
NOTREECHECKS=true
NOTRY=true
BUG=skia:

Author: humper@google.com

Review URL: https://codereview.chromium.org/324453004
 2014-06-06 11:18:17 -07:00
jvanverth
f255de0fe1 Revert of another GM to ignore for blur rebaseline (https://codereview.chromium.org/319203002/) 
Reason for revert:
Follow-on to fe689c46a7, which needs to be reverted due to bot failures.

Original issue's description:
> another GM to ignore for blur rebaseline
>
> BUG=skia:
> TBR=jvanverth
> NOTRY=True
> NOTREECHECKS=True
>
> Committed: https://skia.googlesource.com/skia/+/f131055929afb9c9671aee3e575c380d48c5ee4d

R=humper@google.com
TBR=humper@google.com
NOTREECHECKS=true
NOTRY=true
BUG=skia:

Author: jvanverth@google.com

Review URL: https://codereview.chromium.org/319943004
 2014-06-06 10:59:13 -07:00
humper
f131055929 another GM to ignore for blur rebaseline 
BUG=skia:
TBR=jvanverth
NOTRY=True
NOTREECHECKS=True

Author: humper@google.com

Review URL: https://codereview.chromium.org/319203002
 2014-06-06 10:36:02 -07:00
humper
fe689c46a7 Faster GPU rect blur that doesn't require computing vertical and horizontal 
scanlines on the CPU first.  Should make extremely large drop shadows fast
again.

BUG=skia:
R=bsalomon@google.com

Author: humper@google.com

Review URL: https://codereview.chromium.org/316273004
 2014-06-06 09:48:40 -07:00
mtklein
e4d3e605f7 DM: SKP source / PDF backend 
Removed expectations code for PDF backend for now, given that we don't have any, and refactored a little to make that cleaner.

We can now test .skp -> .pdf -> .png in DM.  Neat eh?

BUG=skia:2598
R=halcanary@google.com, mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/316643003
 2014-06-06 09:28:43 -07:00
reed
d71be5d78b remove SK_SUPPORT_LEGACY_SETCONFIG_INFO and SK_SUPPORT_LEGACY_INSTALLPIXELSPARAMS from chrome 
TBR=
NOTRY=True

Author: reed@google.com

Review URL: https://codereview.chromium.org/320583003
 2014-06-06 09:02:22 -07:00
kevin.petit
ea6b46b6c0 ARM Skia NEON patches - 39 - arm64 565 blitters 
This enables all 565 blitters except S32A_D565_Opaque.

Here are some performance results:

S32_D565_Opaque:
================

+-------+------------+------------+
| count | Cortex-A53 | Cortex-A57 |
+-------+------------+------------+
|     1 |    -18.37% |    -13.04% |
+-------+------------+------------+
|     2 |     -9.90% |    -13.78% |
+-------+------------+------------+
|     4 |     -8.28% |     -6.77% |
+-------+------------+------------+
|     8 |    157.63% |     78.15% |
+-------+------------+------------+
|    16 |     72.67% |     44.81% |
+-------+------------+------------+
|    64 |     76.78% |     40.89% |
+-------+------------+------------+
|   256 |     73.85% |     36.05% |
+-------+------------+------------+
|  1024 |     75.73% |     36.70% |
+-------+------------+------------+

S32_D565_Blend:
===============

+-------+------------+------------+
| count | Cortex-A53 | Cortex-A57 |
+-------+------------+------------+
|     1 |     -9.99% |    -13.79% |
+-------+------------+------------+
|     2 |     -9.17% |     -6.74% |
+-------+------------+------------+
|     4 |     -6.73% |     -4.42% |
+-------+------------+------------+
|     8 |    163.31% |    112.82% |
+-------+------------+------------+
|    16 |     55.21% |     44.68% |
+-------+------------+------------+
|    64 |     54.09% |     41.99% |
+-------+------------+------------+
|   256 |     52.63% |     40.64% |
+-------+------------+------------+
|  1024 |     52.46% |     40.45% |
+-------+------------+------------+

S32A_D565_Blend:
================

+-------+------------+------------+
| count | Cortex-A53 | Cortex-A57 |
+-------+------------+------------+
|     1 |     -5.88% |     -6.06% |
+-------+------------+------------+
|     2 |     -4.74% |     -0.01% |
+-------+------------+------------+
|     4 |     -5.42% |     -3.03% |
+-------+------------+------------+
|     8 |     78.78% |     77.96% |
+-------+------------+------------+
|    16 |     98.19% |     79.61% |
+-------+------------+------------+
|    64 |    111.56% |     72.60% |
+-------+------------+------------+
|   256 |    113.80% |     69.96% |
+-------+------------+------------+
|  1024 |    114.42% |     70.85% |
+-------+------------+------------+

S32_D565_Opaque_Dither:
=======================

+-------+------------+------------+
| count | Cortex-A53 | Cortex-A57 |
+-------+------------+------------+
|     1 |     -4.18% |     -0.93% |
+-------+------------+------------+
|     2 |     -2.43% |     -2.04% |
+-------+------------+------------+
|     4 |     -1.09% |     -1.23% |
+-------+------------+------------+
|     8 |    184.89% |    136.53% |
+-------+------------+------------+
|    16 |    128.64% |     89.11% |
+-------+------------+------------+
|    64 |    132.68% |    100.98% |
+-------+------------+------------+
|   256 |    157.02% |    100.86% |
+-------+------------+------------+
|  1024 |    163.85% |    103.62% |
+-------+------------+------------+

S32_D565_Blend_Dither:
======================

+-------+------------+------------+
| count | Cortex-A53 | Cortex-A57 |
+-------+------------+------------+
|     1 |     -4.87% |      0.01% |
+-------+------------+------------+
|     2 |     -2.71% |      2.97% |
+-------+------------+------------+
|     4 |     -2.20% |      0.28% |
+-------+------------+------------+
|     8 |    149.76% |    146.80% |
+-------+------------+------------+
|    16 |     85.69% |     95.77% |
+-------+------------+------------+
|    64 |     88.81% |    101.39% |
+-------+------------+------------+
|   256 |     97.32% |    107.22% |
+-------+------------+------------+
|  1024 |     98.08% |    115.71% |
+-------+------------+------------+

S32A_D565_Opaque_Dither:
========================

+-------+------------+------------+
| count | Cortex-A53 | Cortex-A57 |
+-------+------------+------------+
|     1 |     -1.86% |      0.02% |
+-------+------------+------------+
|     2 |     -0.58% |     -1.52% |
+-------+------------+------------+
|     4 |     -0.75% |      1.16% |
+-------+------------+------------+
|     8 |    240.74% |    155.16% |
+-------+------------+------------+
|    16 |    181.97% |    132.15% |
+-------+------------+------------+
|    64 |    203.11% |    136.48% |
+-------+------------+------------+
|   256 |    223.45% |    133.05% |
+-------+------------+------------+
|  1024 |    225.96% |    134.05% |
+-------+------------+------------+

Signed-off-by: Kévin PETIT <kevin.petit@arm.com>

BUG=skia:
R=djsollen@google.com, mtklein@google.com

Author: kevin.petit@arm.com

Review URL: https://codereview.chromium.org/317193003
 2014-06-06 08:45:36 -07:00
mtklein
2e44b51b9a Effectively unlimited linking. 
Ninja will still cap concurrency with it's default value (from -j), so we just
need a big number equal or greater than the number of cores in any machine.

BUG=skia:
R=borenet@google.com, mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/319153002
 2014-06-06 08:27:07 -07:00
egdaniel
97724ed4cf Revert of Fix Assert for gpu ConicalTwoPointGradient edgecase to be correct bounds. (https://codereview.chromium.org/311373003/) 
Reason for revert:
changed assert is failing

Original issue's description:
> Fix Assert for gpu ConicalTwoPointGradient edgecase to be correct bounds.
>
> BUG=skia:
>
> Committed: https://skia.googlesource.com/skia/+/be4fd4f7349b97a7c34a4177ec26d8aea9616628

R=bsalomon@google.com
TBR=bsalomon@google.com
NOTREECHECKS=true
NOTRY=true
BUG=skia:

Author: egdaniel@google.com

Review URL: https://codereview.chromium.org/320573002
 2014-06-06 07:47:17 -07:00
mtklein
1a50651524 Pull in GYP_LINK_CONCURRENCY=N support. 
BUG=skia:
R=borenet@google.com, mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/315183003
 2014-06-06 07:37:46 -07:00
egdaniel
be4fd4f734 Fix Assert for gpu ConicalTwoPointGradient edgecase to be correct bounds. 
BUG=skia:
R=bsalomon@google.com

Author: egdaniel@google.com

Review URL: https://codereview.chromium.org/311373003
 2014-06-06 07:26:16 -07:00
sugoi
0951fe1298 Fixing another clusterfuzz issue 
This was introduced by removing SkValidatingReadBuffer::readBitmap in https://codereview.chromium.org/295793002/

Since SkReadBuffer::skip wasn't virtual, it was using the unsafe SkReadBuffer::skip within SkReadBuffer::readBitmap rather than using SkValidatingReadBuffer::skip. I also removed direct uses of fReader within SkReadBuffer::readBitmap so that it can use the virtual readInt / readFixed functions that have a version in SkValidatingReadBuffer.

Also, I changed SkReadBuffer::readPoint so that it uses the virtual readScalar, that way, it becomes redundant with SkValidatingReadBuffer::readPoint, which can then be removed.

BUG=380723
R=reed@google.com, mtklein@google.com, sugoi@google.com

Author: sugoi@chromium.org

Review URL: https://codereview.chromium.org/317003003
 2014-06-06 06:44:17 -07:00
qiankun.miao
5102345029 Fix android_run_skia script running with command line options 
This script cannot recognize command line options when running bench:
e.g. android_run_skia bench --config 8888.

BUG=skia:
R=mtklein@google.com, djsollen@google.com

Author: qiankun.miao@intel.com

Review URL: https://codereview.chromium.org/314903003
 2014-06-06 06:43:46 -07:00
tfarina
f9dae780c2 Remove GrIsPow2 in favor of SkIsPow2. 
Looks like there is no good reason to have two copies of this function
doing the same thing with different name.

BUG=None
TEST=make tests
R=bsalomon@google.com

Author: tfarina@chromium.org

Review URL: https://codereview.chromium.org/318873002
 2014-06-06 06:35:28 -07:00
jcgregorio
659988168a Add metrics reporting to SkFiddle. 
Also update the headers for template.cpp while we're here.

BUG=skia:
R=mtklein@google.com

Author: jcgregorio@google.com

Review URL: https://codereview.chromium.org/312373002
 2014-06-06 06:30:31 -07:00
rmistry
a494a91a1d Whitespace change to test new CQ trybots 
BUG=skia:2203
TBR=

(SkipBuildbotRuns)

Author: rmistry@google.com

Review URL: https://codereview.chromium.org/319123002
 2014-06-06 06:26:59 -07:00
sugoi
56d135c03e Adding kernel offset validation 
Fixing bug found by clusterfuzz in SkMatrixConvolutionImageFilter.

BUG=381244
R=senorblanco@google.com, senorblanco@chromium.org, sugoi@google.com

Author: sugoi@chromium.org

Review URL: https://codereview.chromium.org/319003002
 2014-06-06 06:22:03 -07:00
mtklein
a8928b745a Add SkBarriers_tsan.h. 
Slight counterproposal to crrev.com/310663002.

BUG=skia:

No API changes.

R=bungeman@google.com, mtklein@google.com, reed@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/306373002
 2014-06-06 06:21:49 -07:00
bsalomon
594069f0fe Use vertex attribute for text color in GrBitmapTextContext 
R=jvanverth@google.com

Author: bsalomon@google.com

Review URL: https://codereview.chromium.org/316063002
 2014-06-06 06:16:34 -07:00
krajcevski
c250d2e4ab Initial KTX encoder 
The encoder comes with tests to check that the encoding/decoding
operations between ETC encoded bitmaps and ARGB bitmaps are sane.

R=bsalomon@google.com, robertphillips@google.com

Author: krajcevski@google.com

Review URL: https://codereview.chromium.org/312353003
 2014-06-06 06:16:28 -07:00
Ben Wagner
b0b0feb71f Fix SK_API for DirectWrite port. 
The declaration and definition should have the same calling convention.

TBR=reed@google.com

Review URL: https://codereview.chromium.org/317993002
 2014-06-05 18:03:39 -04:00
Ben Wagner
98875e1abd Rename SkFontHost_win_dw.cpp SkScalerContext. 
This is a continuation of https://codereview.chromium.org/314193002/ .

TBR=reed@google.com

Review URL: https://codereview.chromium.org/315173004
 2014-06-05 16:55:58 -04:00
bungeman
51daa25a2b Split SkFontHost_win_dw. 
Split SkFontHost_win_dw into FontMgr, Typeface, and ScalerContext.
This makes working on these files easier, and moves away from the legacy
FontHost naming.

R=reed@google.com

Author: bungeman@google.com

Review URL: https://codereview.chromium.org/314193002
 2014-06-05 13:38:45 -07:00
fmalita
c3b589a24e SkClipStack::Element tweaks. 
(
This is intended to facilitate efficient kMatrix_SaveFlags emulation
on restore():

  * collect all clip stack elements for the current save count into a
    side clip stack
  * canvas.restore(everything)
  * replay the collected clip ops to restore the initial clip state
  => we restored the matrix but the clip state is unchanged
)

Two main changes:

  * expose the save count for SkClipStack::Element
  * expose a replay method for the same (logic relocated from
    SkCanvas::replayClips)

The SkCanvas::ClipVisitor shuffling is to enable forward decl
in SkClipStack.h (cannot fwdecl a nested class).

R=reed@google.com, robertphillips@google.com
TBR=reed@google.com

Author: fmalita@chromium.org

Review URL: https://codereview.chromium.org/269693003
 2014-06-05 12:40:07 -07:00
bungeman
5d3f9c765f Update gyp for msvs-ninja clean. 
BUG=skia:2439
R=borenet@google.com, epoger@google.com

Author: bungeman@google.com

Review URL: https://codereview.chromium.org/317833005
 2014-06-05 12:14:44 -07:00
scroggo
0187dc2155 Fixes for SkAlphaTypes. 
When using allocPixels to set the info and create a new pixelRef in one
shot, create the pixelRef with the corrected info of the bitmap (i.e.
alphatype).

Simplify the check to determine whether to copy the genID in SkBitmap::
copyTo's same configs/same sizes case. The old logic (only checking the
height and assuming the others must be the same) relied on a deep
(mis?)understanding of the rest of the function, and I cannot convince
myself that it has to be true, given that readPixels may have switched
src to a different SkBitmap. Instead, just compare the SkImageInfos,
which is much clearer. (This also caught a bug where a 565 bitmap had
the wrong alphatype, leading to the allocPixels fixes.)

If readPixels succeeds but the source is unpremultiplied, fail out
of copyTo, since readPixels assumes premultiplied.

When copying from 8888 to 4444 or in the fallback case of drawing,
return false if the alphatype is unpremul, which would have failed
anyway.

BUG=skia:2012
R=reed@google.com, bsalomon@google.com

Author: scroggo@google.com

Review URL: https://codereview.chromium.org/317053003
 2014-06-05 11:18:05 -07:00
epoger
b144271179 reland "rebaseline_server: download actual-results.json files from GCS instead of SVN" 
relands https://codereview.chromium.org/310093003 with modifications.

BUG=skia:2641
R=jcgregorio@google.com

Author: epoger@google.com

Review URL: https://codereview.chromium.org/313343003
 2014-06-05 10:30:37 -07:00
scroggo
9de2fb680f Add mips64 to the makefile. 
Currently we have no optimizations for mips64, so it correctly
contains the various _none.cpps.

Corresponds to https://android-review.googlesource.com/#/c/96536/1

R=halcanary@google.com, djsollen@google.com

Author: scroggo@google.com

Review URL: https://codereview.chromium.org/311163003
 2014-06-05 10:28:36 -07:00
reed
6dd061f138 add SK_SUPPORT_LEGACY_COMPUTE_CONFIG_SIZE 
TBR=scroggo
NOTRY=True

Author: reed@google.com

Review URL: https://codereview.chromium.org/315263002
 2014-06-05 10:00:04 -07:00
mtklein
1b918af0d8 Rename skimage expectations for ASAN bot to match bot renaming. 
BUG=skia:
R=borenet@google.com, mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/316063004
 2014-06-05 08:51:26 -07:00
reed
ddd014e652 remove SkBitmap::allocConfigPixels and update dox 
I see no callers in android

R=scroggo@google.com

Author: reed@google.com

Review URL: https://codereview.chromium.org/310283004
 2014-06-05 08:51:20 -07:00
jvanverth
71804cc303 Revert of Add SSE4 optimization of S32A_Opaque_Blitrow (https://codereview.chromium.org/289473009/) 
Reason for revert:
Buildbot failures on Mac 10.6 and Mac 10.7.

R=reed@google.com, mtklein@google.com, tomhudson@google.com, djsollen@google.com, joakim.landberg@intel.com, henrik.smiding@intel.com
TBR=reed@google.com
NOTRY=True

Original issue's description:
> Add SSE4 optimization of S32A_Opaque_Blitrow
>
> Adds optimization of Skia S32A_Opaque_Blitrow blitter using SSE4.2 SIMD
> instruction set. Special case for when alpha is zero or opaque.
>
> Performance increase of 10%-400% compared to the existing SSE2
> optimization (measured on Silvermont architecture).
> Noticeable in ~25 different skia bench subtests, especially in
> bitmap_8888_*, repeatTile_*, and morph_*.
>
> bitmap_8888_A - 100% faster
> bitmap_8888_A_source_transparent - 250% faster
> bitmap_8888_A_source_opaque - 25% faster
> bitmap_8888_A_scale_bicubic - 75% faster
>
> Signed-off-by: Henrik Smiding <henrik.smiding@intel.com>
>
> Committed: https://skia.googlesource.com/skia/+/e2527b147679b0c43019fae7d59cc3777d2d097e

Author: jvanverth@google.com

Review URL: https://codereview.chromium.org/311053009
 2014-06-05 08:19:23 -07:00
halcanary
5ec3d21714 remove ashmem from skia 
R=scroggo@google.com, djsollen@google.com

Author: halcanary@google.com

Review URL: https://codereview.chromium.org/319533004
 2014-06-05 08:16:34 -07:00
bsalomon
93c2fb02f1 Rebaselines for drrect GM on GPU 
TBR=

Author: bsalomon@google.com

Review URL: https://codereview.chromium.org/318773007
 2014-06-05 07:56:56 -07:00