Commit Graph

1718 Commits

Author SHA1 Message Date
Mike Klein
5d5cc3cb22 Temporarily restore colorcube bench and GM files.
Just the usual... we don't generate .bp for DM or nanobench yet.

See https://skia-review.googlesource.com/c/7363/ and
https://googleplex-android-review.git.corp.google.com/#/c/1819530/-1..1

Change-Id: If0098ed8a71a170d5efa773495d5bbf02a1e13fc
Reviewed-on: https://skia-review.googlesource.com/7427
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reviewed-by: Mike Klein <mtklein@chromium.org>
2017-01-24 02:17:30 +00:00
Mike Klein
319ba3d3a1 Move shader register setup to SkRasterPipelineBlitter.
We've been seeding the initial values of our registers to x+0.5,y+0.5,
1,0, 0,0,0,0 (useful values for shaders to start with) in all pipelines.
This CL changes that to do so only when blitting, and only when we have
a shader.

The nicest part of this change is that SkRasterPipeline itself no longer
needs to have a concept of y, or what x means.  It just marches x
through [x,x+n), and the blitter handles y and layers the meaning of
"dst x coordinate" onto x.

This ought to make SkSplicer a little easier to work with too.

dm --src gm --config f16 srgb 565 all draws the same.

Change-Id: I69d8c1cc14a06e5dfdd6a7493364f43a18f8dec5
Reviewed-on: https://skia-review.googlesource.com/7353
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
2017-01-23 20:00:23 +00:00
Mike Reed
918e144408 change clip-bounds getters to always return the rect
(actually fixes undefined result in getClipBounds)

future CLs
- update all callers to new apis
- move/rename virtuals

BUG=skia:

DOCS_PREVIEW= https://skia.org/?cl=7400

Change-Id: I45b93014e915c0d1c36d97d948c9ac8931f23258
Reviewed-on: https://skia-review.googlesource.com/7400
Reviewed-by: Brian Salomon <bsalomon@google.com>
Reviewed-by: Cary Clark <caryclark@google.com>
Commit-Queue: Mike Reed <reed@google.com>
2017-01-23 17:14:53 +00:00
Mike Klein
efaad3cd53 Remove SkColorCubeFilter. It is unused.
Change-Id: Iec5fc759e331de24caea1347f9510917260d379b
Reviewed-on: https://skia-review.googlesource.com/7363
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
2017-01-21 15:09:31 +00:00
Mike Klein
d8ee67c381 Add -Release ASAN bots.
These may be better at -fsanitize=object-size.

No need to loop more than once in nanobench for these bots.

CQ_INCLUDE_TRYBOTS=skia.primary:Build-Ubuntu-Clang-x86_64-Release-ASAN,Perf-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Release-ASAN,Perf-Ubuntu-Clang-Golo-GPU-GT610-x86_64-Release-ASAN,Test-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Release-ASAN,Test-Ubuntu-Clang-Golo-GPU-GT610-x86_64-Release-ASAN

Change-Id: If89e94390d473434717cfe28de6be9055b68d8d4
Reviewed-on: https://skia-review.googlesource.com/7278
Reviewed-by: Herb Derby <herb@google.com>
Reviewed-by: Eric Boren <borenet@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
2017-01-19 20:29:59 +00:00
Mike Klein
f76885694d Add a bench to exercise legacy-mode SkRasterPipeline behavior.
No fancy f16 or sRGB here... just good old legacy 8888.

Change-Id: I21eb7c0d8e2c7a7d92e9d8a8bae9d318c4daa7e5
Reviewed-on: https://skia-review.googlesource.com/7109
Reviewed-by: Mike Klein <mtklein@chromium.org>
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
2017-01-17 15:56:11 +00:00
Herb Derby
ac04fef619 Remove SkFallbackAlloc and SkFixedAlloc.
CQ_INCLUDE_TRYBOTS=skia.primary:Test-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Debug-ASAN;skia.primary:Test-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Debug-MSAN

TBR=reed@google.com

Change-Id: I1000dc9ed8ad65b249798759d9af99f47fc237d2
Reviewed-on: https://skia-review.googlesource.com/6809
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Herb Derby <herb@google.com>
2017-01-16 17:01:57 +00:00
Herb Derby
0497f088bb Introduce SkArenaAlloc - should be fast for POD types and RAII for types with dtors.
- Implementation.
- Use in SkLinearPipeline.

TBR=mtklein@google.com

Change-Id: Ie014184469b217132b0307b5a9ae40c0c60e5fc9
Reviewed-on: https://skia-review.googlesource.com/6921
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Herb Derby <herb@google.com>
2017-01-13 18:45:19 +00:00
Yuqian Li
550148ba57 Reland https://skia-review.googlesource.com/c/6091/
The only difference is that we now also put the guard flag
SK_SUPPORT_LEGACY_AAA in SkUserConfig.h. Previously, SkAnalyticEdge.cpp doesn't
get that flag from SkScan.h and that caused many problems.

BUG=skia:
TBR=reed@google.com,caryclark@google.com

Change-Id: I134bb76cebd6fffa712f438076668765321bba3b
Reviewed-on: https://skia-review.googlesource.com/6992
Reviewed-by: Yuqian Li <liyuqian@google.com>
Commit-Queue: Yuqian Li <liyuqian@google.com>
2017-01-13 16:07:48 +00:00
Mike Klein
e71b167dbd Attempt 3: SkRasterPipelineBlitter: support A8
Now that SkOpts_hsw.cpp no longer hooks in SkRasterPipeline_opts,
it should be safe to try this again.

This reverts commit 86d55b312a.

Change-Id: I2d495600ca9d3a0f49c2e02fbaaae349cefac3a1
Reviewed-on: https://skia-review.googlesource.com/6985
Reviewed-by: Mike Klein <mtklein@chromium.org>
2017-01-13 13:25:28 +00:00
Yuqian Li
aeef5610d7 Revert "Reland https://skia-review.googlesource.com/c/6091/"
This reverts commit b46fff60bc.

Reason for revert: possible chromium cc unit tests failure

Change-Id: Ie174c55e4d0fc3ae45854b5897ba26b7ad5a9c13
Reviewed-on: https://skia-review.googlesource.com/6981
Commit-Queue: Yuqian Li <liyuqian@google.com>
Reviewed-by: Yuqian Li <liyuqian@google.com>
2017-01-13 00:37:20 +00:00
Yuqian Li
b46fff60bc Reland https://skia-review.googlesource.com/c/6091/
The only difference is that we now put the guard flag SK_SUPPORT_LEGACY_AAA in
SkUserConfig.h instead of SkScan.h. Previously, SkAnalyticEdge.cpp doesn't get
that flag from SkScan.h and that caused many problems.

BUG=skia:
TBR=reed@google.com,caryclark@google.com

Change-Id: I7b89d3cb64ad71715101d2a5e8e77be3a8a6fa16
Reviewed-on: https://skia-review.googlesource.com/6972
Reviewed-by: Yuqian Li <liyuqian@google.com>
Commit-Queue: Yuqian Li <liyuqian@google.com>
2017-01-12 21:13:20 +00:00
Yuqian Li
90ee03b0d1 Revert "Implement Analytic AA for General Paths (with Guard against Chrome)"
This reverts commit 89a0e72287.

Reason for revert: <INSERT REASONING HERE>

Original change's description:
> Implement Analytic AA for General Paths (with Guard against Chrome)
> 
> I've set up a SK_SUPPORT_LEGACY_AAA flag to guard against Chromium layout tests. I also set that flag in this CL so theoretically this CL won't trigger any GM changes. I'll use this to verify my guard, and remove that flag and actually enables concave AAA in a future CL.
> 
> When enabled, for most simple concave paths (e.g., rectangle stroke, rrect stroke, sawtooth, stars...), the Analytic AA achieves 1.3x-2x speedup, and they look much prettier. And they probably are the majority in our use cases by number. But they probably are not the majority by time cost; a single complicated path may cost 10x-100x more time to render than a rectangle stroke... For those complicated paths, we fall back to supersampling by default as we're likely to be 1.1-1.2x slower and the quality improvement is not visually significant. However, one can use gSkForceAnalyticAA to disable that fallback.
> 
> BUG=skia:
> 
> Change-Id: If9549a3acc4a187cfaf7eb51890c148da3083d31
> Reviewed-on: https://skia-review.googlesource.com/6091
> Reviewed-by: Mike Reed <reed@google.com>
> Commit-Queue: Yuqian Li <liyuqian@google.com>
> 

TBR=caryclark@google.com,liyuqian@google.com,reed@google.com
BUG=skia:
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true

Change-Id: I13c05aaa1bcb14956bd0fe01bb404e41be75af22
Reviewed-on: https://skia-review.googlesource.com/6961
Commit-Queue: Yuqian Li <liyuqian@google.com>
Reviewed-by: Yuqian Li <liyuqian@google.com>
2017-01-12 18:13:02 +00:00
Yuqian Li
89a0e72287 Implement Analytic AA for General Paths (with Guard against Chrome)
I've set up a SK_SUPPORT_LEGACY_AAA flag to guard against Chromium layout tests. I also set that flag in this CL so theoretically this CL won't trigger any GM changes. I'll use this to verify my guard, and remove that flag and actually enables concave AAA in a future CL.

When enabled, for most simple concave paths (e.g., rectangle stroke, rrect stroke, sawtooth, stars...), the Analytic AA achieves 1.3x-2x speedup, and they look much prettier. And they probably are the majority in our use cases by number. But they probably are not the majority by time cost; a single complicated path may cost 10x-100x more time to render than a rectangle stroke... For those complicated paths, we fall back to supersampling by default as we're likely to be 1.1-1.2x slower and the quality improvement is not visually significant. However, one can use gSkForceAnalyticAA to disable that fallback.

BUG=skia:

Change-Id: If9549a3acc4a187cfaf7eb51890c148da3083d31
Reviewed-on: https://skia-review.googlesource.com/6091
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Yuqian Li <liyuqian@google.com>
2017-01-12 17:17:32 +00:00
Mike Reed
693fdbd6b8 refFoo variant for getters that naturally have a sk_sp
BUG=skia:

Change-Id: I13afa1b81e8a72d93e45fb4d37228be196b0f388
Reviewed-on: https://skia-review.googlesource.com/6923
Reviewed-by: Florin Malita <fmalita@chromium.org>
Reviewed-by: Robert Phillips <robertphillips@google.com>
Commit-Queue: Mike Reed <reed@google.com>
2017-01-12 16:38:34 +00:00
Herb Derby
8d80bb5f20 Revert "Introduce SkArenaAlloc - should be fast for POD types and RAII for types with dtors."
This reverts commit 6ff51aedda.

Reason for revert: breaks win2k8 and PDFium

Change-Id: Ib1e2db8e523d5d321836ce00e3773def3db8be2f
Reviewed-on: https://skia-review.googlesource.com/6898
Commit-Queue: Herb Derby <herb@google.com>
Reviewed-by: Herb Derby <herb@google.com>
2017-01-11 21:47:44 +00:00
Herb Derby
6ff51aedda Introduce SkArenaAlloc - should be fast for POD types and RAII for types with dtors.
- Implementation.
- Use in SkLinearPipeline.
 
TBR=mtklein@google.com
Change-Id: Ia8efd09b2f3139a57182889ba84d1610eae92749
Reviewed-on: https://skia-review.googlesource.com/6352
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Herb Derby <herb@google.com>
2017-01-11 20:43:22 +00:00
Mike Reed
ab273facbf move SkTRegister.h into tools
BUG=skia:

Change-Id: Ie7d4fac3024b361a281f456fec2b3a837e2bfe43
Reviewed-on: https://skia-review.googlesource.com/6881
Commit-Queue: Mike Reed <reed@google.com>
Reviewed-by: Mike Klein <mtklein@chromium.org>
2017-01-11 19:53:36 +00:00
Hal Canary
95e3c058ef SkTypes.h : move SkAutoMalloc into SkAutoMalloc.h
* SkAutoFree moved to SkTemplates.h (now implmented with unique_ptr).

  * SkAutoMalloc and SkAutoSMalloc moved to SkAutoMalloc.h

  * "SkAutoFree X(sk_malloc_throw(N));" --> "SkAutoMalloc X(N);"

Revert "Revert 'SkTypes.h : move SkAutoMalloc into SkAutoMalloc.h'"
This reverts commit c456b73fef.

Change-Id: Ie2c1a17c20134b8ceab85a68b3ae3e61c24fbaab
Reviewed-on: https://skia-review.googlesource.com/6886
Reviewed-by: Hal Canary <halcanary@google.com>
Commit-Queue: Hal Canary <halcanary@google.com>
2017-01-11 18:55:34 +00:00
Kevin Lubick
c456b73fef Revert "SkTypes.h : move SkAutoMalloc into SkAutoMalloc.h"
This reverts commit a5494f1170.

Reason for revert: Broke Google3

Original change's description:
> SkTypes.h : move SkAutoMalloc into SkAutoMalloc.h
> 
>   * SkAutoFree moved to SkTemplates.h (now implmented with unique_ptr).
> 
>   * SkAutoMalloc and SkAutoSMalloc moved to SkAutoMalloc.h
> 
>   * "SkAutoFree X(sk_malloc_throw(N));" --> "SkAutoMalloc X(N);"
> 
> Change-Id: Idacd86ca09e22bf092422228599ae0d9bedded88
> Reviewed-on: https://skia-review.googlesource.com/4543
> Reviewed-by: Ben Wagner <bungeman@google.com>
> Reviewed-by: Mike Reed <reed@google.com>
> Commit-Queue: Hal Canary <halcanary@google.com>
> 

TBR=halcanary@google.com,bungeman@google.com,reed@google.com,reviews@skia.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true

Change-Id: Ie8bd176121c3ee83c110d66c0d0ac65e09bfc9c5
Reviewed-on: https://skia-review.googlesource.com/6884
Commit-Queue: Kevin Lubick <kjlubick@google.com>
Reviewed-by: Kevin Lubick <kjlubick@google.com>
2017-01-11 17:22:12 +00:00
Hal Canary
a5494f1170 SkTypes.h : move SkAutoMalloc into SkAutoMalloc.h
* SkAutoFree moved to SkTemplates.h (now implmented with unique_ptr).

  * SkAutoMalloc and SkAutoSMalloc moved to SkAutoMalloc.h

  * "SkAutoFree X(sk_malloc_throw(N));" --> "SkAutoMalloc X(N);"

Change-Id: Idacd86ca09e22bf092422228599ae0d9bedded88
Reviewed-on: https://skia-review.googlesource.com/4543
Reviewed-by: Ben Wagner <bungeman@google.com>
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Hal Canary <halcanary@google.com>
2017-01-11 15:36:45 +00:00
Yuqian Li
8eedbfc9ac Revert "Revert "Improve quad edges' smoothness in non-AA cases""
This reverts commit 1e74cad9b4.

Reason for revert: the guard flag has now been confirmed to be landed on chromium/src. We should now be able to pass the layout tests.

Original change's description:
> Revert "Improve quad edges' smoothness in non-AA cases"
> 
> This reverts commit d4ed326d6f.
> 
> Reason for revert: reverting temporarily to get us rolling into Chrome again.
> 
> Must be this CL right?
> https://storage.googleapis.com/chromium-layout-test-archives/linux_trusty_blink_rel/3364/layout-test-results/results.html
> 
> Original change's description:
> > Improve quad edges' smoothness in non-AA cases
> > 
> > Previously, non-AA quad edges only have an accuracy about 1/2 pixel
> > (while the AA quad edges have an accuracy about 1/8 pixel).  Now, we
> > increase non-AA quad edges' accuracy to 1/8 pixel as well.
> > 
> > The difference is very significant for rotating non-AA filled circles.
> > For example, run `./out/Debug/SampleApp --slide GM:fillcircle` with AA
> > turned off (by pressing b).
> > 
> > The benchmark added reveals that increasing quad accuracy from 1/2 to
> > 1/8 doesn't affect the performance significantly. The following is the
> > 1/2-accuracy performance versus 1/8-accuracy performance:
> > 
> > curr/maxrss     loops   min     median  mean    max     stddev  samples
> > config  bench
> > 7/17  MB        19      2.43µs  2.57µs  2.81µs  10.5µs  22%     16119
> > 8888    path_fill_big_nonaacircle
> > 7/17  MB        17      1.38µs  1.42µs  1.52µs  13µs    20%     21409
> > 8888    path_fill_small_nonaacircle
> > 
> > curr/maxrss     loops   min     median  mean    max     stddev  samples
> > config  bench
> > 7/17  MB        71      2.52µs  2.59µs  2.79µs  7.67µs  19%     7557
> > 8888    path_fill_big_nonaacircle
> > 7/17  MB        64      1.45µs  1.49µs  1.51µs  2.39µs  5%      12704
> > 8888    path_fill_small_nonaacircle
> > 
> > 
> > BUG=skia:
> > 
> > Change-Id: I3482098aeafcc6f2ec9aa3382977c0dc1b650964
> > Reviewed-on: https://skia-review.googlesource.com/6699
> > Reviewed-by: Mike Reed <reed@google.com>
> > Commit-Queue: Yuqian Li <liyuqian@google.com>
> > 
> 
> TBR=caryclark@google.com,liyuqian@google.com,reed@google.com,djsollen@google.com,bungeman@google.com,reviews@skia.org,fmalita@chromium.org
> BUG=skia:
> NOPRESUBMIT=true
> NOTREECHECKS=true
> NOTRY=true
> 
> Change-Id: I5bc4596ab506f6f61ac2da91a07cf51d61114f31
> Reviewed-on: https://skia-review.googlesource.com/6829
> Commit-Queue: Mike Klein <mtklein@google.com>
> Reviewed-by: Mike Klein <mtklein@google.com>
> 

TBR=djsollen@google.com,mtklein@google.com,bungeman@google.com,reviews@skia.org,caryclark@google.com,fmalita@chromium.org,liyuqian@google.com,reed@google.com
BUG=skia:
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true

Change-Id: I0ec2ea8dc0c6ad0ebdcb48878fb301c32443a09e
Reviewed-on: https://skia-review.googlesource.com/6858
Commit-Queue: Yuqian Li <liyuqian@google.com>
Reviewed-by: Yuqian Li <liyuqian@google.com>
2017-01-11 13:56:05 +00:00
Mike Klein
c0a7a08359 remove xbyak experiment
SkSplicer is better.

CQ_INCLUDE_TRYBOTS=skia.primary:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD

Change-Id: I014ec0e9fb00a8a4694d442e672c65402621dc67
Reviewed-on: https://skia-review.googlesource.com/6830
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
2017-01-10 16:25:10 +00:00
Mike Klein
1e74cad9b4 Revert "Improve quad edges' smoothness in non-AA cases"
This reverts commit d4ed326d6f.

Reason for revert: reverting temporarily to get us rolling into Chrome again.

Must be this CL right?
https://storage.googleapis.com/chromium-layout-test-archives/linux_trusty_blink_rel/3364/layout-test-results/results.html

Original change's description:
> Improve quad edges' smoothness in non-AA cases
> 
> Previously, non-AA quad edges only have an accuracy about 1/2 pixel
> (while the AA quad edges have an accuracy about 1/8 pixel).  Now, we
> increase non-AA quad edges' accuracy to 1/8 pixel as well.
> 
> The difference is very significant for rotating non-AA filled circles.
> For example, run `./out/Debug/SampleApp --slide GM:fillcircle` with AA
> turned off (by pressing b).
> 
> The benchmark added reveals that increasing quad accuracy from 1/2 to
> 1/8 doesn't affect the performance significantly. The following is the
> 1/2-accuracy performance versus 1/8-accuracy performance:
> 
> curr/maxrss     loops   min     median  mean    max     stddev  samples
> config  bench
> 7/17  MB        19      2.43µs  2.57µs  2.81µs  10.5µs  22%     16119
> 8888    path_fill_big_nonaacircle
> 7/17  MB        17      1.38µs  1.42µs  1.52µs  13µs    20%     21409
> 8888    path_fill_small_nonaacircle
> 
> curr/maxrss     loops   min     median  mean    max     stddev  samples
> config  bench
> 7/17  MB        71      2.52µs  2.59µs  2.79µs  7.67µs  19%     7557
> 8888    path_fill_big_nonaacircle
> 7/17  MB        64      1.45µs  1.49µs  1.51µs  2.39µs  5%      12704
> 8888    path_fill_small_nonaacircle
> 
> 
> BUG=skia:
> 
> Change-Id: I3482098aeafcc6f2ec9aa3382977c0dc1b650964
> Reviewed-on: https://skia-review.googlesource.com/6699
> Reviewed-by: Mike Reed <reed@google.com>
> Commit-Queue: Yuqian Li <liyuqian@google.com>
> 

TBR=caryclark@google.com,liyuqian@google.com,reed@google.com,djsollen@google.com,bungeman@google.com,reviews@skia.org,fmalita@chromium.org
BUG=skia:
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true

Change-Id: I5bc4596ab506f6f61ac2da91a07cf51d61114f31
Reviewed-on: https://skia-review.googlesource.com/6829
Commit-Queue: Mike Klein <mtklein@google.com>
Reviewed-by: Mike Klein <mtklein@google.com>
2017-01-10 14:21:30 +00:00
Yuqian Li
d4ed326d6f Improve quad edges' smoothness in non-AA cases
Previously, non-AA quad edges only have an accuracy about 1/2 pixel
(while the AA quad edges have an accuracy about 1/8 pixel).  Now, we
increase non-AA quad edges' accuracy to 1/8 pixel as well.

The difference is very significant for rotating non-AA filled circles.
For example, run `./out/Debug/SampleApp --slide GM:fillcircle` with AA
turned off (by pressing b).

The benchmark added reveals that increasing quad accuracy from 1/2 to
1/8 doesn't affect the performance significantly. The following is the
1/2-accuracy performance versus 1/8-accuracy performance:

curr/maxrss     loops   min     median  mean    max     stddev  samples
config  bench
7/17  MB        19      2.43µs  2.57µs  2.81µs  10.5µs  22%     16119
8888    path_fill_big_nonaacircle
7/17  MB        17      1.38µs  1.42µs  1.52µs  13µs    20%     21409
8888    path_fill_small_nonaacircle

curr/maxrss     loops   min     median  mean    max     stddev  samples
config  bench
7/17  MB        71      2.52µs  2.59µs  2.79µs  7.67µs  19%     7557
8888    path_fill_big_nonaacircle
7/17  MB        64      1.45µs  1.49µs  1.51µs  2.39µs  5%      12704
8888    path_fill_small_nonaacircle


BUG=skia:

Change-Id: I3482098aeafcc6f2ec9aa3382977c0dc1b650964
Reviewed-on: https://skia-review.googlesource.com/6699
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Yuqian Li <liyuqian@google.com>
2017-01-09 18:53:06 +00:00
Mike Klein
86d55b312a Revert "Retry "SkRasterPipelineBlitter: support A8"..."
This reverts commit f55ea6a1de.

Reason for revert: crbug.com/679147

Original change's description:
> Retry "SkRasterPipelineBlitter: support A8"...
> 
>     ...preferring SkA8_Coverage_Blitter over SkRasterPipelineBlitter.
> 
> I think we could make this work with SkRasterPipelineBlitter (tell it, draw white in Src mode with this mask), but the existing blitter is pretty hard to beat in efficiency and correctness.
> 
> CQ_INCLUDE_TRYBOTS=skia.primary:Perf-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Debug-MSAN,Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD
> 
> 
> Change-Id: I72df9995c63f3334d8111c59711818cb5ed1e63c
> Reviewed-on: https://skia-review.googlesource.com/6627
> Reviewed-by: Mike Klein <mtklein@chromium.org>
> Commit-Queue: Mike Klein <mtklein@chromium.org>
> 

TBR=mtklein@chromium.org,brianosman@google.com,reed@google.com,reviews@skia.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true

Change-Id: I6a36b4c087a52e54f4d591ded40e6a202fb77068
Reviewed-on: https://skia-review.googlesource.com/6760
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reviewed-by: Mike Klein <mtklein@chromium.org>
2017-01-07 22:05:05 +00:00
Mike Klein
058e747ee2 zero fBuf in new SkXbyakBench
MSAN's keeping me honest...

CQ_INCLUDE_TRYBOTS=skia.primary:Perf-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Debug-MSAN

Change-Id: If61f75ec919a2b5ae0e973db05760f88588fe18f
Reviewed-on: https://skia-review.googlesource.com/6702
Reviewed-by: Mike Klein <mtklein@chromium.org>
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
2017-01-06 22:02:25 +00:00
Mike Klein
83f532e9b5 Add a real SkXbyak bench, implement enough to run it.
CQ_INCLUDE_TRYBOTS=skia.primary:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD

SkXbyak_…
9320  …JITCompiled 1x  …Interpreted 1.24x  …HandWritten 2.5x

Change-Id: I37d2d255ff32dcce73d29081d506e2d67477af97
Reviewed-on: https://skia-review.googlesource.com/6697
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reviewed-by: Herb Derby <herb@google.com>
2017-01-06 21:02:18 +00:00
Mike Klein
f55ea6a1de Retry "SkRasterPipelineBlitter: support A8"...
...preferring SkA8_Coverage_Blitter over SkRasterPipelineBlitter.

I think we could make this work with SkRasterPipelineBlitter (tell it, draw white in Src mode with this mask), but the existing blitter is pretty hard to beat in efficiency and correctness.

CQ_INCLUDE_TRYBOTS=skia.primary:Perf-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Debug-MSAN,Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD


Change-Id: I72df9995c63f3334d8111c59711818cb5ed1e63c
Reviewed-on: https://skia-review.googlesource.com/6627
Reviewed-by: Mike Klein <mtklein@chromium.org>
Commit-Queue: Mike Klein <mtklein@chromium.org>
2017-01-06 17:32:03 +00:00
Mike Klein
8c8cb5bfc5 simplify by removing _d stages
CQ_INCLUDE_TRYBOTS=skia.primary:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD

Change-Id: I75e232faee6ad48f65bac5b119a461280b27bbc8
Reviewed-on: https://skia-review.googlesource.com/6661
Reviewed-by: Mike Klein <mtklein@chromium.org>
Commit-Queue: Mike Klein <mtklein@chromium.org>
2017-01-06 16:14:00 +00:00
Mike Klein
a2d25ec0ef Use stack instead of malloc() for most calls to SkRasterPipeline::run().
Also split bench into run/compile variants to measure the effect:
 Before …f16_compile 1x  …f16_run 1.02x  …srgb_compile 1.56x  …srgb_run 1.61x
 After  …f16_run 1x  …f16_compile 1.01x  …srgb_compile 1.58x  …srgb_run 1.59x

CQ_INCLUDE_TRYBOTS=skia.primary:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD

Change-Id: I8e65fb2acdbb05ccc0b3894f16d7646603c3e74d
Reviewed-on: https://skia-review.googlesource.com/6621
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
2017-01-05 20:41:43 +00:00
Hal Canary
55325b7c59 clean up non-ASCII comments
Change-Id: I07ad00133f6a938de70a94024a0ebe36c6c542bb
Reviewed-on: https://skia-review.googlesource.com/6524
Commit-Queue: Hal Canary <halcanary@google.com>
Reviewed-by: Hal Canary <halcanary@google.com>
2017-01-03 16:29:37 +00:00
Hal Canary
43fb7a014b BUILD.gn: skia_enable_pdf
BUG=skia:

Change-Id: Icf616bec73e81aad97815b519566ff5b9db611e3
Reviewed-on: https://skia-review.googlesource.com/6495
Commit-Queue: Hal Canary <halcanary@google.com>
Reviewed-by: Mike Klein <mtklein@chromium.org>
2017-01-03 14:25:12 +00:00
Brian Salomon
09d994ecb3 Misc batch->op cleanup Part 1 of 2
Change-Id: I80f951976558a284e55386e0a368f08bd835d8ca
Reviewed-on: https://skia-review.googlesource.com/6359
Commit-Queue: Brian Salomon <bsalomon@google.com>
Reviewed-by: Brian Osman <brianosman@google.com>
2016-12-21 16:45:40 +00:00
Mike Reed
9c457ad27b speedup dynamicwstream
- move bytesWritten calculation to query the tail, allowing write() to be faster since it doesn't have to update anything extra per-write.
- enforce that all blocks are multiple-of-4 bytes big
- update the minimum block size to 4K

Before: 30ms
After:  23ms for non-4-bytes writes
        13ms for 4-bytes writes

BUG=skia:

Change-Id: Id06ecad3b9fe426747e02accf1393595e3356ce3
Reviewed-on: https://skia-review.googlesource.com/6087
Reviewed-by: Mike Klein <mtklein@chromium.org>
Commit-Queue: Mike Reed <reed@google.com>
2016-12-15 19:49:31 +00:00
Yuqian Li
ba62b4ae86 Change FLAGS_analyticAA's default to true
BUG=skia:

Change-Id: I1abf2284ed9dfaa69110c4fe86325c8e4ee43317
Reviewed-on: https://skia-review.googlesource.com/5767
Reviewed-by: Derek Sollenberger <djsollen@google.com>
Commit-Queue: Yuqian Li <liyuqian@google.com>
2016-12-14 19:53:43 +00:00
Mike Reed
49282296b6 add tests/bench for dynamicwstream
BUG=skia:

Change-Id: I5a995b63b1a2975cce8101717777eaa6fc12af21
Reviewed-on: https://skia-review.googlesource.com/6035
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Mike Reed <reed@google.com>
2016-12-14 18:34:30 +00:00
Mike Klein
d37d5d9649 Revert "Revert "clamp to premul when reading premul sRGB""
This reverts commit 2e018f548d.

Reason for revert: doesn't appear to have been the roll problem.

Original change's description:
> Revert "clamp to premul when reading premul sRGB"
> 
> This reverts commit 04e10da836.
> 
> Reason for revert: roll?
> 
> Change-Id: Id0a8dcd62763bd6eddde120c513ca97e098a4268
> Reviewed-on: https://skia-review.googlesource.com/6022
> Commit-Queue: Mike Klein <mtklein@chromium.org>
> Reviewed-by: Mike Klein <mtklein@chromium.org>
> 

TBR=mtklein@chromium.org,reviews@skia.org,brianosman@google.com
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true

Change-Id: I399ca5e728ce6766c6707682c4c6b685681ffdeb
Reviewed-on: https://skia-review.googlesource.com/6025
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reviewed-by: Mike Klein <mtklein@chromium.org>
2016-12-14 13:38:41 +00:00
Mike Klein
2e018f548d Revert "clamp to premul when reading premul sRGB"
This reverts commit 04e10da836.

Reason for revert: roll?

Change-Id: Id0a8dcd62763bd6eddde120c513ca97e098a4268
Reviewed-on: https://skia-review.googlesource.com/6022
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reviewed-by: Mike Klein <mtklein@chromium.org>
2016-12-14 04:24:08 +00:00
Mike Klein
04e10da836 clamp to premul when reading premul sRGB
It's pretty easy to start with sound premultiplied linear floats, pack those to sRGB encoded bytes, then read them back to linear floats and find them not quite premultiplied, with a color channel just a smidge greater than the alpha channel.  This can happen basically any time we have different transfer functions for alpha and colors... sRGB being the only one we draw into.

This is an annoying problem with no known good solution.  So apply the clamp hammer.

These new calls on SkRasterPipeline should make it impossible to get wrong.

CQ_INCLUDE_TRYBOTS=skia.primary:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD

Change-Id: I4c974f4a7b151f3f684946f1e83d06b1b288fd01
Reviewed-on: https://skia-review.googlesource.com/5945
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
2016-12-13 22:09:57 +00:00
Ethan Nicholas
941e7e2c95 re-land of added sk_FragCoord support to skslc
BUG=skia:

Change-Id: Ifac1aa39839058787ad1794200c3dbb93c147a69
Reviewed-on: https://skia-review.googlesource.com/5850
Reviewed-by: Ethan Nicholas <ethannicholas@google.com>
Commit-Queue: Ethan Nicholas <ethannicholas@google.com>
2016-12-13 14:28:53 +00:00
Yuqian Li
131c1fb963 Add GMs and benchs for concave Analytic AA
BUG=skia:

Change-Id: I2ed6e2c4f81dc9d5c53b07332c0063f42c6b3c79
Reviewed-on: https://skia-review.googlesource.com/5771
Reviewed-by: Cary Clark <caryclark@google.com>
Commit-Queue: Yuqian Li <liyuqian@google.com>
2016-12-12 22:08:38 +00:00
Greg Daniel
e8e4a3e678 Revert "added sk_FragCoord support to skslc"
This reverts commit ce33f10677.

Reason for revert: Breaking many gpu bots

Change-Id: I94c813ed6a9311458c872f74bb1b0792f46ff414
Reviewed-on: https://skia-review.googlesource.com/5737
Commit-Queue: Greg Daniel <egdaniel@google.com>
Reviewed-by: Greg Daniel <egdaniel@google.com>
2016-12-12 17:22:28 +00:00
Ethan Nicholas
ce33f10677 added sk_FragCoord support to skslc
BUG=skia:

Change-Id: If78a4d08121699f87659f0d2e35f3edbf1867401
Reviewed-on: https://skia-review.googlesource.com/5408
Reviewed-by: Greg Daniel <egdaniel@google.com>
Commit-Queue: Ethan Nicholas <ethannicholas@google.com>
2016-12-12 16:42:34 +00:00
Mike Reed
ebfce6d9b4 change SkClipOp to a class enum
BUG=skia:

Change-Id: I25dbe6d6b8666a2a0a7be7bdd2ae0b067868d14e
Reviewed-on: https://skia-review.googlesource.com/5718
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Mike Reed <reed@google.com>
2016-12-12 15:38:31 +00:00
Brian Osman
61624f0c71 Plumb dst color space in many places, rather than "mode"
This is less to type in most cases, and gives us more information
(for things like picture-backed images, where we need to know all
about the destination surface).

Additionally, strip out the plumbing entirely for bitmap sources,
where we don't need to know anything.

BUG=skia:

Change-Id: I4deff6c7c345fcf62eb08b2aff0560adae4313da
Reviewed-on: https://skia-review.googlesource.com/5748
Reviewed-by: Mike Klein <mtklein@chromium.org>
Reviewed-by: Brian Salomon <bsalomon@google.com>
Commit-Queue: Brian Osman <brianosman@google.com>
2016-12-09 20:31:23 +00:00
Mike Reed
c1f7774e8d Revert[2] "remove SK_SUPPORT_LEGACY_CLIP_REGIONOPS"
This reverts commit a129dfef2a.

BUG=skia:

Change-Id: I717de6e5fcd4516aa684b014b1414b0f82ac2b91
Reviewed-on: https://skia-review.googlesource.com/5722
Commit-Queue: Mike Reed <reed@google.com>
Reviewed-by: Derek Sollenberger <djsollen@google.com>
2016-12-09 14:33:41 +00:00
Mike Reed
a129dfef2a Revert "remove SK_SUPPORT_LEGACY_CLIP_REGIONOPS"
This reverts commit 8e7432b7f9.

Reason for revert: <INSERT REASONING HERE>

external/skia/bench/../tools/android/SkAndroidSDKCanvas.h:103:36: error: C++ requires a type specifier for all declarations
    void onClipRect(const SkRect&, ClipOp, ClipEdgeStyle) override;

Original change's description:
> remove SK_SUPPORT_LEGACY_CLIP_REGIONOPS
> 
> 
> switch over to SkClipOps now that SK_SUPPORT_LEGACY_CLIP_REGIONOPS is gone
> 
> BUG=skia:
> 
> Change-Id: Ifdc8b3746d508348a40cc009a4e529a1cb3c405d
> Reviewed-on: https://skia-review.googlesource.com/5714
> Commit-Queue: Mike Reed <reed@google.com>
> Reviewed-by: Mike Reed <reed@google.com>
> 

TBR=reed@google.com,reviews@skia.org
BUG=skia:
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true

Change-Id: If26ea91d7464615e43c1d3d2f726e337ff56b55c
Reviewed-on: https://skia-review.googlesource.com/5721
Commit-Queue: Mike Reed <reed@google.com>
Reviewed-by: Mike Reed <reed@google.com>
2016-12-09 13:14:41 +00:00
Mike Reed
8e7432b7f9 remove SK_SUPPORT_LEGACY_CLIP_REGIONOPS
switch over to SkClipOps now that SK_SUPPORT_LEGACY_CLIP_REGIONOPS is gone

BUG=skia:

Change-Id: Ifdc8b3746d508348a40cc009a4e529a1cb3c405d
Reviewed-on: https://skia-review.googlesource.com/5714
Commit-Queue: Mike Reed <reed@google.com>
Reviewed-by: Mike Reed <reed@google.com>
2016-12-08 21:45:27 +00:00
George Burgess IV
75b5718d20 nanobench: Add per-run time reporting.
This patch adds per-benchmark-iteration times to our JSON output. Given that we
already collect these statistics, giving them to the user would be nice.

No unit-test provided, since `rgrep -i json tests` yielded nothing. Happy to add
one if someone wants.

BUG=None.
TEST=nanobench now writes per-run timinings with the output JSON.

Change-Id: I910f1d97fd3e0ee69fc8e78e011e67b9c866f18d
Reviewed-on: https://skia-review.googlesource.com/5617
Reviewed-by: Mike Klein <mtklein@chromium.org>
Commit-Queue: Ravi Mistry <rmistry@google.com>
2016-12-06 21:48:42 +00:00