The KeyContext is used in the addToKey methods but must appear in the
AddToKey methods bc the latter can call the former.
Bug: skia:12701
Change-Id: I3143afec8337b1e3e12f1c3cc198714009ca6930
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/520539
Reviewed-by: Jim Van Verth <jvanverth@google.com>
Commit-Queue: Robert Phillips <robertphillips@google.com>
SkPipelineData is evolving into a big deal - it deserves it owns files.
Bug: skia:12701
Change-Id: I78b4100f1b90fa10f2b264e6d13fca6f15bba39b
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/516157
Reviewed-by: Jim Van Verth <jvanverth@google.com>
Commit-Queue: Robert Phillips <robertphillips@google.com>
This is a reland of 0596094b81
Original change's description:
> Remove skstd::optional entirely.
>
> Change-Id: Id9862712ea3e769797abd654922879ce6bc4487c
> Reviewed-on: https://skia-review.googlesource.com/c/skia/+/504976
> Reviewed-by: Ben Wagner <bungeman@google.com>
> Reviewed-by: Brian Osman <brianosman@google.com>
> Commit-Queue: John Stiles <johnstiles@google.com>
Change-Id: Ie5bae44de729aabe50c4e51ad3c7cc476fbc5dc6
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/512358
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: John Stiles <johnstiles@google.com>
There is no need for these headers to be in include/private:
SkPaintParamsKey.h
SkShaderCodeDictionary.h
Added the new header:
src/core/SkBuiltInCodeSnippetID.h
Bug: skia:12701
Change-Id: I413e9a21bc26d5df48765d16dd7390e324006368
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/505197
Reviewed-by: Michael Ludwig <michaelludwig@google.com>
Commit-Queue: Robert Phillips <robertphillips@google.com>
This reverts commit 0596094b81.
Reason for revert: Flutter somehow still references skstd::optional
flutter_engine in google3 still has old code:
http://screen/BHDrjqwzchdFVfQ
Original change's description:
> Remove skstd::optional entirely.
>
> Change-Id: Id9862712ea3e769797abd654922879ce6bc4487c
> Reviewed-on: https://skia-review.googlesource.com/c/skia/+/504976
> Reviewed-by: Ben Wagner <bungeman@google.com>
> Reviewed-by: Brian Osman <brianosman@google.com>
> Commit-Queue: John Stiles <johnstiles@google.com>
Change-Id: Idea391399c2e11b83d5a130023adb340d40cadcb
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/505396
Auto-Submit: John Stiles <johnstiles@google.com>
Bot-Commit: Rubber Stamper <rubber-stamper@appspot.gserviceaccount.com>
Reviewed-by: Heather Miller <hcm@google.com>
Commit-Queue: Heather Miller <hcm@google.com>
Change-Id: Id9862712ea3e769797abd654922879ce6bc4487c
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/504976
Reviewed-by: Ben Wagner <bungeman@google.com>
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: John Stiles <johnstiles@google.com>
We now use std::string_view throughout. SkStringView.h has been moved to
include/private/ and is only used for our C++20/23 compatibility methods
(starts_with/ends_with/contains).
Change-Id: I961842c6778256a03868e7602d48add34f420763
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/502306
Reviewed-by: Ben Wagner <bungeman@google.com>
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: John Stiles <johnstiles@google.com>
Auto-Submit: John Stiles <johnstiles@google.com>
This reverts commit 17d0fc087c.
Reason for revert: flutter still uses the skstd class
Original change's description:
> Remove skstd::optional entirely.
>
> Skia now uses C++17's std::optional.
>
> Change-Id: I387069589baaefadd25e25bcec3f4cc6ee6fd090
> Reviewed-on: https://skia-review.googlesource.com/c/skia/+/501477
> Reviewed-by: Ben Wagner <bungeman@google.com>
> Reviewed-by: Brian Osman <brianosman@google.com>
> Commit-Queue: John Stiles <johnstiles@google.com>
> Auto-Submit: John Stiles <johnstiles@google.com>
Change-Id: I2c001588007640ac7b8c9f0760038b46c220a07e
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/502702
Auto-Submit: John Stiles <johnstiles@google.com>
Bot-Commit: Rubber Stamper <rubber-stamper@appspot.gserviceaccount.com>
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Brian Osman <brianosman@google.com>
This is a reland of 64c971350e
Original change's description:
> Use native std::string_view.
>
> We also used some string_view functionality from C++20/23. These have
> been replaced with free functions with the same name.
>
> Change-Id: I3bf40f99aeb500495f344fd8c6872619267d42be
> Reviewed-on: https://skia-review.googlesource.com/c/skia/+/500897
> Reviewed-by: Herb Derby <herb@google.com>
> Auto-Submit: John Stiles <johnstiles@google.com>
> Reviewed-by: Brian Osman <brianosman@google.com>
> Commit-Queue: John Stiles <johnstiles@google.com>
Change-Id: I4ff237381c16179f716ecde1929154fdd4ad3442
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/501480
Reviewed-by: Brian Osman <brianosman@google.com>
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: John Stiles <johnstiles@google.com>
Skia now uses C++17's std::optional.
Change-Id: I387069589baaefadd25e25bcec3f4cc6ee6fd090
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/501477
Reviewed-by: Ben Wagner <bungeman@google.com>
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: John Stiles <johnstiles@google.com>
Auto-Submit: John Stiles <johnstiles@google.com>
This reverts commit 64c971350e.
Reason for revert: breaks
Housekeeper-PerCommit-CreateDockerImage_Skia_Release
https://status.skia.org/logs/7PAT8xw23VsUyx4oJgZZ/1327ba91-d03a-4e98-b1dd-0dedb401333b
"<string_view> not found"
Original change's description:
> Use native std::string_view.
>
> We also used some string_view functionality from C++20/23. These have
> been replaced with free functions with the same name.
>
> Change-Id: I3bf40f99aeb500495f344fd8c6872619267d42be
> Reviewed-on: https://skia-review.googlesource.com/c/skia/+/500897
> Reviewed-by: Herb Derby <herb@google.com>
> Auto-Submit: John Stiles <johnstiles@google.com>
> Reviewed-by: Brian Osman <brianosman@google.com>
> Commit-Queue: John Stiles <johnstiles@google.com>
Change-Id: I3712eddc8ad49ad38d31ca5bf008260e251bdbd7
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/501396
Auto-Submit: John Stiles <johnstiles@google.com>
Bot-Commit: Rubber Stamper <rubber-stamper@appspot.gserviceaccount.com>
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Brian Osman <brianosman@google.com>
We also used some string_view functionality from C++20/23. These have
been replaced with free functions with the same name.
Change-Id: I3bf40f99aeb500495f344fd8c6872619267d42be
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/500897
Reviewed-by: Herb Derby <herb@google.com>
Auto-Submit: John Stiles <johnstiles@google.com>
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: John Stiles <johnstiles@google.com>
Presumably, SkVM will also need a way to represent the data passed to its programs
This CL attempts to be as mechanical as possible.
Bug: skia:12701
Change-Id: I7fb2c06d645809bf5422a25b8b537cf6c249fede
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/497136
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Robert Phillips <robertphillips@google.com>
Since the SkShaders, etc will need access to SkPaintParamKeys and the SkShaderCodeDictionary they can't be buried in the skgpu namespace.
The currently planned signature for addToKey is:
void addToKey(SkShaderCodeDictionary*, SkBackend, SkPaintParamsKey*) const;
This CL doesn't modify the classes beyond what is needed to move them.
Bug: skia:12701
Change-Id: I18bbf6d6c3a768427112a3d19a9ccf2d46a23ad2
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/494237
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Robert Phillips <robertphillips@google.com>
SkPaintParamsKey can be variable length and is thus the path forward for encapsulating/representing PaintParams.
Note: SkPaintParamsKey isn't in the skgpu namespace bc, ultimately, the individual SkShaders, etc will be responsible for adding their own information to the key.
Bug: skia:12701
Change-Id: I7472dc00706a4548bc3ffb4e287a941a2b8ffcae
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/492405
Reviewed-by: Michael Ludwig <michaelludwig@google.com>
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Robert Phillips <robertphillips@google.com>
This is to be used in the PaintParamKey's block dumping methods.
Bug: skia:12701
Change-Id: I14de21d2d8b30e0fa69ac2e33fa975dc20f6656c
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/493217
Reviewed-by: Michael Ludwig <michaelludwig@google.com>
Commit-Queue: Robert Phillips <robertphillips@google.com>
This is a reland of e1e1c03229
Original change's description:
> Start on custom mesh API
>
> Bug: skia:12720
> Change-Id: I8ed0555f1c5b8b0e97e73a657635dac2c0df0ccf
> Reviewed-on: https://skia-review.googlesource.com/c/skia/+/482457
> Reviewed-by: Brian Osman <brianosman@google.com>
> Commit-Queue: Brian Salomon <bsalomon@google.com>
Bug: skia:12720
Change-Id: I5c54f37949d8bd45ea606264c439912b65158b79
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/487220
Commit-Queue: Brian Salomon <bsalomon@google.com>
Auto-Submit: Brian Salomon <bsalomon@google.com>
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Brian Osman <brianosman@google.com>
Bug: skia:12720
Change-Id: I8ed0555f1c5b8b0e97e73a657635dac2c0df0ccf
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/482457
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Brian Salomon <bsalomon@google.com>
Chromium has been using the remote glyph cache for a few years now.
It's time to give it a proper home.
This is an intermediate CL. The old .h file includes the new .h file.
After I change the include paths in Chromium, I will delete the old
file.
Change-Id: Iaf00c46aa0698326c0bdec9a0eed218bcc3e334e
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/482700
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Herb Derby <herb@google.com>
This entire API existed, but was unused (no longer connected to
drawVertices or runtime effects).
In theory, we could further simplify some of the matrix providers, but
more importantly - I have serious doubts about the correctness of
localToDeviceHitsPixelsCenters for most of them.
Change-Id: If5af182015dd96e5ed3353a117223e8dbbe17097
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/481683
Reviewed-by: Michael Ludwig <michaelludwig@google.com>
Commit-Queue: Brian Osman <brianosman@google.com>
This will let us use it elsewhere.
Change-Id: I39a5dc0651bee8fbd5fa7302e34a3a79f7efbd3d
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/481736
Commit-Queue: John Stiles <johnstiles@google.com>
Auto-Submit: John Stiles <johnstiles@google.com>
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Brian Osman <brianosman@google.com>
src/gpu/GrBlockAllocator -> src/core/SkBlockAllocator
src/gpu/GrTBlockList -> src/core/SkTBlockList
Tests and references also renamed.
Bug: skia:12330
Change-Id: I5fad05faa3dcecd89a0a478dcf30c090ea7589f5
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/441477
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Michael Ludwig <michaelludwig@google.com>
This reverts commit 14b1d56a2b.
Reason for revert: fix emplace_back() usage
Original change's description:
> Revert "Remove SkTLList"
>
> This reverts commit e1d523d70f.
>
> Reason for revert: breaking old stdlib versions (< c17)
>
> Original change's description:
> > Remove SkTLList
> >
> > Change-Id: I198678b5cb298cf51872fbb8d4fd5d705a6b684e
> > Reviewed-on: https://skia-review.googlesource.com/c/skia/+/437339
> > Reviewed-by: Brian Osman <brianosman@google.com>
> > Commit-Queue: Michael Ludwig <michaelludwig@google.com>
>
> TBR=brianosman@google.com,michaelludwig@google.com,skcq-be@skia-corp.google.com.iam.gserviceaccount.com
>
> Change-Id: I8e02e4cd2f293e7530f842be783de10f69be2ef4
> No-Presubmit: true
> No-Tree-Checks: true
> No-Try: true
> Reviewed-on: https://skia-review.googlesource.com/c/skia/+/438078
> Reviewed-by: Michael Ludwig <michaelludwig@google.com>
> Commit-Queue: Michael Ludwig <michaelludwig@google.com>
# Not skipping CQ checks because this is a reland.
Change-Id: Ied33ce81a8312963ff0713c4660cdb8541a02180
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/438080
Commit-Queue: Michael Ludwig <michaelludwig@google.com>
Reviewed-by: Brian Osman <brianosman@google.com>
This reverts commit e1d523d70f.
Reason for revert: breaking old stdlib versions (< c17)
Original change's description:
> Remove SkTLList
>
> Change-Id: I198678b5cb298cf51872fbb8d4fd5d705a6b684e
> Reviewed-on: https://skia-review.googlesource.com/c/skia/+/437339
> Reviewed-by: Brian Osman <brianosman@google.com>
> Commit-Queue: Michael Ludwig <michaelludwig@google.com>
TBR=brianosman@google.com,michaelludwig@google.com,skcq-be@skia-corp.google.com.iam.gserviceaccount.com
Change-Id: I8e02e4cd2f293e7530f842be783de10f69be2ef4
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/438078
Reviewed-by: Michael Ludwig <michaelludwig@google.com>
Commit-Queue: Michael Ludwig <michaelludwig@google.com>
Change-Id: I198678b5cb298cf51872fbb8d4fd5d705a6b684e
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/437339
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Michael Ludwig <michaelludwig@google.com>
Introduce a new call to SkShaderBase to return an
SkUpdatableShader. An SkUpdatableShader is both a SkShaderBase
and has an update() method.
If the onUpdatableShader call returns !nullptr, then the
shader's specialized updatable shader is used. Otherwise,
the shader is wrapped in a TexCoordShader.
This scheme allows Shaders to have specialized updaters,
but also adds updaters for shaders that don't need
specialization.
orig this bench
771µs 779µs verts_textures_colors
217µs 335µs verts_textures
275µs 380µs verts_textures_persp
Bug=skia:11822
Change-Id: I11ba344eba96188c5631228cd5e91c5d834ea3d6
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/429417
Commit-Queue: Herb Derby <herb@google.com>
Reviewed-by: Mike Reed <reed@google.com>
Bug: skia:11235
Change-Id: Iefa0156f542f217e687299f053768ee5b87f84d7
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/430977
Reviewed-by: Michael Ludwig <michaelludwig@google.com>
Commit-Queue: Mike Reed <reed@google.com>
Change-Id: I71ae924d32dc2268cc4a3db1920c08287533f9ae
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/430697
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Herb Derby <herb@google.com>
This is an SkBlender type which represents a traditional Skia blend mode
(from the SkBlendMode enum).
Change-Id: I7c74395be70584e11a5f1445b7f6cacfff35c532
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/420817
Commit-Queue: Mike Reed <reed@google.com>
Auto-Submit: John Stiles <johnstiles@google.com>
Reviewed-by: Brian Osman <brianosman@google.com>
Reviewed-by: Mike Reed <reed@google.com>
This allows SkM44 and optimize_intrinsic_call to share the same matrix
inversion logic.
Support for 2x2 and 3x3 matrix inversion was also added to
SkMatrixInvert, but is not currently used anywhere in Skia besides
optimize_intrinsic_call. (The perspective case of SkMatrix::ComputeInv
could probably be adapted to use the shared 3x3 code.)
Change-Id: Ie55aab536b4bd0c0a04f2c24527747670ca68fbb
Bug: skia:12054
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/420219
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: John Stiles <johnstiles@google.com>
Auto-Submit: John Stiles <johnstiles@google.com>
Like SkColorFilter, SkShader, etc., this has a public-facing component
(SkBlender) and a private subclass (SkBlenderBase) which can be
obtained via a helper function (as_BB). At present there are no public-
facing methods, but the type needs to be exposed to be usable by the
outside world.
These classes exist for SkRuntimeEffect to subclass. The blender base
provides a `program` method with the parameters that blending will use.
Change-Id: I75c772fd4108a9c21fbda84201a8b23d3750a0df
Bug: skia:12080
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/416916
Auto-Submit: John Stiles <johnstiles@google.com>
Commit-Queue: Brian Osman <brianosman@google.com>
Reviewed-by: Brian Osman <brianosman@google.com>
Change-Id: Id02ed33b4fe60663327cc50d79db2bf876ad6df7
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/415458
Reviewed-by: Brian Osman <brianosman@google.com>
Commit-Queue: Ethan Nicholas <ethannicholas@google.com>
This is needed by the upcoming DSLParser.
Change-Id: I54a0714e55feeb78894df766b14c795970f2c2d4
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/411308
Commit-Queue: Ethan Nicholas <ethannicholas@google.com>
Reviewed-by: John Stiles <johnstiles@google.com>
Fixes CMake build
Cq-Include-Trybots: luci.skia.skia.primary:Build-Debian10-Clang-x86_64-Release-CMake
Change-Id: If4da32306e6735dced70412216e43f0b8bbca48c
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/407357
Commit-Queue: Brian Osman <brianosman@google.com>
Commit-Queue: Robert Phillips <robertphillips@google.com>
Auto-Submit: Brian Osman <brianosman@google.com>
Reviewed-by: Robert Phillips <robertphillips@google.com>
Makes computeFastBounds not part of the public API, it's only accessible
to subclasses of SkPathEffect, GrStyle, and SkPaint. Subclasses can
invoke it other path effects using SkPathEffectPriv::ComputeFastBounds.
Changes the internal function to
bool computeFastBounds(SkRect* bounds) const;
Subclasses of SkPathEffect must implement this, and can choose to return
false when fast bounds aren't computable.
Provides implementations of computeFastBounds() for path effects
bundled with Skia.
Bug: skia:11974
Change-Id: I545ccf99b4e669d3af9df13acfac28573306fab8
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/406140
Commit-Queue: Michael Ludwig <michaelludwig@google.com>
Reviewed-by: Mike Reed <reed@google.com>
This pebble's been in our shoe long enough!
The _Gpu.cpp files have also been moved into separate gpu.gni
file so they're gone.
Formatter also had its way with the file.
Change-Id: Ia9324953725f070c1a7b250bcb68311168560a29
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/373816
Reviewed-by: Robert Phillips <robertphillips@google.com>
Commit-Queue: Robert Phillips <robertphillips@google.com>
Commit-Queue: Adlai Holler <adlai@google.com>
Auto-Submit: Adlai Holler <adlai@google.com>
Bug: skia:10632
Change-Id: If4dd7779b0856f6d0b441381bf7f2f51527cdb9d
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/352497
Reviewed-by: Jim Van Verth <jvanverth@google.com>
Commit-Queue: Brian Salomon <bsalomon@google.com>
This is a reland of 26ad8ccdec
... now with MSAN support.
Original change's description:
> add ERMS (enhanced rep mov/sto) SkOpts slice
>
> Intel's got two CPUID bits indicating the speed of rep mov/sto
> (memcpy/memset),
>
> - ERMS, Enhanced Rep Mov/Sto, older, large copies are fast?
> - FSRM, Fast Short Rep Mov, newer, small copies are fast?
>
> ERMS has been around a long time on Intel, but is relatively recent on
> Ryzen, and FSRM is new across the board. The startup cost for
> ERMS-but-not-FSRM copies really is noticeable, so we cut over to the
> previous SSE/AVX routines when N is small.
>
> I've left the memset benchmarks as I found them most useful when
> tuning the small/large cutoff in this CL.
>
> Change-Id: I3ac4e3f34796aba0ea86aabbe9dda7526919456a
> Reviewed-on: https://skia-review.googlesource.com/c/skia/+/332580
> Reviewed-by: Herb Derby <herb@google.com>
> Commit-Queue: Mike Klein <mtklein@google.com>
Cq-Include-Trybots: luci.skia.skia.primary:Test-Debian10-Clang-GCE-CPU-AVX2-x86_64-Release-All-MSAN
Change-Id: Ia293bba90022c48c884599331ef35aa67644729b
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/334343
Commit-Queue: Mike Klein <mtklein@google.com>
Reviewed-by: Herb Derby <herb@google.com>
This reverts commit 26ad8ccdec.
Reason for revert: gonna need to teach MSAN about this to reland.
Original change's description:
> add ERMS (enhanced rep mov/sto) SkOpts slice
>
> Intel's got two CPUID bits indicating the speed of rep mov/sto
> (memcpy/memset),
>
> - ERMS, Enhanced Rep Mov/Sto, older, large copies are fast?
> - FSRM, Fast Short Rep Mov, newer, small copies are fast?
>
> ERMS has been around a long time on Intel, but is relatively recent on
> Ryzen, and FSRM is new across the board. The startup cost for
> ERMS-but-not-FSRM copies really is noticeable, so we cut over to the
> previous SSE/AVX routines when N is small.
>
> I've left the memset benchmarks as I found them most useful when
> tuning the small/large cutoff in this CL.
>
> Change-Id: I3ac4e3f34796aba0ea86aabbe9dda7526919456a
> Reviewed-on: https://skia-review.googlesource.com/c/skia/+/332580
> Reviewed-by: Herb Derby <herb@google.com>
> Commit-Queue: Mike Klein <mtklein@google.com>
TBR=mtklein@google.com,herb@google.com
Change-Id: I3264af132272dbbaac8fc8b62e139a6a112bbadb
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/334342
Reviewed-by: Mike Klein <mtklein@google.com>
Commit-Queue: Mike Klein <mtklein@google.com>
Intel's got two CPUID bits indicating the speed of rep mov/sto
(memcpy/memset),
- ERMS, Enhanced Rep Mov/Sto, older, large copies are fast?
- FSRM, Fast Short Rep Mov, newer, small copies are fast?
ERMS has been around a long time on Intel, but is relatively recent on
Ryzen, and FSRM is new across the board. The startup cost for
ERMS-but-not-FSRM copies really is noticeable, so we cut over to the
previous SSE/AVX routines when N is small.
I've left the memset benchmarks as I found them most useful when
tuning the small/large cutoff in this CL.
Change-Id: I3ac4e3f34796aba0ea86aabbe9dda7526919456a
Reviewed-on: https://skia-review.googlesource.com/c/skia/+/332580
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Mike Klein <mtklein@google.com>
