When adjusting the CTM for filter use, we were subtracting off the
destination coordinates of the drawDevice() or drawSprite(). This is
not quite correct: we should subtract off the coordinates relative to
the device origin instead. This occurs when one filtered saveLayer() is
drawn inside another saveLayer(), both with non-zero origin.
This fixes layout test svg/batik/text/smallFonts.svg in Blink, and is
exercised by the provided unit test.
BUG=skia:
R=bsalomon@google.com
Review URL: https://codereview.chromium.org/222723002
git-svn-id: http://skia.googlecode.com/svn/trunk@14029 2bbb7eff-a529-9590-31e7-b0007b416f81
Aarch64 support
This change contains the necessary modifications to have Skia build and
run properly on an ARMv8 processor in aarch64 execution state.
Here's a list of the changes:
- add an arm64 target to the build system + SK_CPU_ARM64 flag
- MatrixTest was failing when built in Release mode. Fused MAC
instructions were generated which made some intermediate results
more accurate. As the test relies on result comparison, the more
precise results when compared to others led to a gap bigger than
what was tolerated. As I don't know if some actual skia code relies
on results being comparable, I've disabled fused MAC instruction
with -ffp-contract=off for arm64.
- Modify include/core/SkOnce.h to have barriers work.
- SK_CPU_ARM64 implies SK_ARM_NEON_MODE_ALWAYS.
- use existing Xfermode optimisations with modifications that can be
removed in the future when toolchains are ready. Also save a few
instructions is two Xfermodes (will apply to ARM too).
- use existing SkBoxBlur and SkMorphology optimisations.
- use existing SkBlitMask optimisations
- use existing BitmapProcState and Convolution optimisations.
Future changes will include:
- Blitters (only partialy merged upstream)
- SkUtils (there's little value in sending asm optimisations without
having them benchmarked on real hardware).
Signed-off-by: Kevin PETIT <kevin.petit@arm.com>
BUG=skia:
Committed: http://code.google.com/p/skia/source/detail?r=13980R=djsollen@google.com, reed@google.com, mtklein@google.com, halcanary@google.com
Author: kevin.petit@arm.com
Review URL: https://codereview.chromium.org/143423004
git-svn-id: http://skia.googlecode.com/svn/trunk@14025 2bbb7eff-a529-9590-31e7-b0007b416f81
If one of inputs to SkXfermodeImageFilter draws nothing, either due to
it being cropped out upstream, or within the filter itself, the filter
should still draw the other input, since otherwise the result will be incorrect.
For the GPU path, since we can't detect this case in
canFilterImageGPU() without recursing, we'll just drop to
the generic path if either input is empty, since we can't use the effect in that case anyway.
While we're at it, let's drop to the generic path if the
xfermode can't be expressed as an effect, since the code
here was doing a 2-pass render in that case anyway, which
is equivalent to what the (xfermode == NULL) case was doing
anyway.
R=bsalomon@google.com, sugoi@chromium.org
Review URL: https://codereview.chromium.org/220723007
git-svn-id: http://skia.googlecode.com/svn/trunk@14016 2bbb7eff-a529-9590-31e7-b0007b416f81
Record performance as measured by bench_record (out/Release/bench_record --skr) improves by at least 1.9x, at most 6.7x, arithmetic mean 2.6x, geometric mean 3.0x. So, good.
Correctness as measured by DM (out/Debug/dm --skr) is ~ok. One GM (shadertext2) fails because we're assuming all paint effects are immutable, but SkShaders are still mutable.
To do after this CL:
- measure playback speed
- catch up feature-wise to SkPicture
- match today's playback speed
BUG=skia:
R=robertphillips@google.com, bsalomon@google.com, reed@google.com, mtklein@google.com
Author: mtklein@chromium.org
Review URL: https://codereview.chromium.org/206313003
git-svn-id: http://skia.googlecode.com/svn/trunk@14010 2bbb7eff-a529-9590-31e7-b0007b416f81
This patch implements basics for Xfermode SSE optimization. Based on
these basics, SSE2 implementation of multiply_modeproc is provided. SSE2
implementation for other modes will come in future. With this patch
performance of Xfermode_Multiply will improve about 45%. Here are the
data on desktop i7-3770.
before:
Xfermode_Multiply 8888: cmsecs = 33.30 565: cmsecs = 45.65
after:
Xfermode_Multiply 8888: cmsecs = 17.18 565: cmsecs = 24.87
BUG=
R=mtklein@google.com
Author: qiankun.miao@intel.com
Review URL: https://codereview.chromium.org/202903004
git-svn-id: http://skia.googlecode.com/svn/trunk@14006 2bbb7eff-a529-9590-31e7-b0007b416f81
Reason for revert:
GYP's failing on most (all?) bots.
Original issue's description:
> ARM Skia NEON patches - 35 - First AArch64 support
>
> Aarch64 support
>
> This change contains the necessary modifications to have Skia build and
> run properly on an ARMv8 processor in aarch64 execution state.
>
> Here's a list of the changes:
>
> - add an arm64 target to the build system + SK_CPU_ARM64 flag
>
> - MatrixTest was failing when built in Release mode. Fused MAC
> instructions were generated which made some intermediate results
> more accurate. As the test relies on result comparison, the more
> precise results when compared to others led to a gap bigger than
> what was tolerated. As I don't know if some actual skia code relies
> on results being comparable, I've disabled fused MAC instruction
> with -ffp-contract=off for arm64.
>
> - Modify include/core/SkOnce.h to have barriers work.
>
> - SK_CPU_ARM64 implies SK_ARM_NEON_MODE_ALWAYS.
>
> - use existing Xfermode optimisations with modifications that can be
> removed in the future when toolchains are ready. Also save a few
> instructions is two Xfermodes (will apply to ARM too).
>
> - use existing SkBoxBlur and SkMorphology optimisations.
>
> - use existing SkBlitMask optimisations
>
> - use existing BitmapProcState and Convolution optimisations.
>
> Future changes will include:
>
> - Blitters (only partialy merged upstream)
>
> - SkUtils (there's little value in sending asm optimisations without
> having them benchmarked on real hardware).
>
> Signed-off-by: Kevin PETIT <kevin.petit@arm.com>
>
> BUG=skia:
>
> Committed: http://code.google.com/p/skia/source/detail?r=13980R=djsollen@google.com, reed@google.com, halcanary@google.com, kevin.petit@arm.comTBR=djsollen@google.com, halcanary@google.com, kevin.petit@arm.com, reed@google.com
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Author: mtklein@google.com
Review URL: https://codereview.chromium.org/216113005
git-svn-id: http://skia.googlecode.com/svn/trunk@13983 2bbb7eff-a529-9590-31e7-b0007b416f81
Aarch64 support
This change contains the necessary modifications to have Skia build and
run properly on an ARMv8 processor in aarch64 execution state.
Here's a list of the changes:
- add an arm64 target to the build system + SK_CPU_ARM64 flag
- MatrixTest was failing when built in Release mode. Fused MAC
instructions were generated which made some intermediate results
more accurate. As the test relies on result comparison, the more
precise results when compared to others led to a gap bigger than
what was tolerated. As I don't know if some actual skia code relies
on results being comparable, I've disabled fused MAC instruction
with -ffp-contract=off for arm64.
- Modify include/core/SkOnce.h to have barriers work.
- SK_CPU_ARM64 implies SK_ARM_NEON_MODE_ALWAYS.
- use existing Xfermode optimisations with modifications that can be
removed in the future when toolchains are ready. Also save a few
instructions is two Xfermodes (will apply to ARM too).
- use existing SkBoxBlur and SkMorphology optimisations.
- use existing SkBlitMask optimisations
- use existing BitmapProcState and Convolution optimisations.
Future changes will include:
- Blitters (only partialy merged upstream)
- SkUtils (there's little value in sending asm optimisations without
having them benchmarked on real hardware).
Signed-off-by: Kevin PETIT <kevin.petit@arm.com>
BUG=skia:
R=djsollen@google.com, reed@google.com, mtklein@google.com, halcanary@google.com
Author: kevin.petit@arm.com
Review URL: https://codereview.chromium.org/143423004
git-svn-id: http://skia.googlecode.com/svn/trunk@13980 2bbb7eff-a529-9590-31e7-b0007b416f81
Valgrind's whining about m.setConcat(m, I). That special cases into m =
m, which compiles into memcpy(&m, &m, sizeof(m)), and then Valgrind
decides that's not kosher because &m and &m overlap. (memmove would
have been fine, but this is compiler generated code; not much we can do.)
preConcat gets us the same thing with an early can-we-noop check for I,
sidestepping the whole problem.
BUG=skia:
R=bsalomon@google.com, mtklein@google.com
Author: mtklein@chromium.org
Review URL: https://codereview.chromium.org/214823003
git-svn-id: http://skia.googlecode.com/svn/trunk@13972 2bbb7eff-a529-9590-31e7-b0007b416f81
Use path rendering to render the text from outlines if supported by the
GPU. Implement this in GrStencilAndCoverTextContext by copying large
chunks of code from GrBitmapTextContext (drawText) and
GrDistanceFieldTextContext (drawPosText).
The drawing is implemented with "instanced" path drawing
functions.
Moves the creation of the "main" text context from SkGpuDevice to the
GrContext::createTextContext. This is done because the decision of which
text renderer is optimal can be made only with the internal
implementation-specific information of the context.
R=jvanverth@google.com, bsalomon@google.com
Author: kkinnunen@nvidia.com
Review URL: https://codereview.chromium.org/196133014
git-svn-id: http://skia.googlecode.com/svn/trunk@13962 2bbb7eff-a529-9590-31e7-b0007b416f81
