Reason for revert:
Who wants to land forever?
Original issue's description:
> update memset16/32 inlining heuristics
>
> I spent some time looking at perf.skia.org and it looks like we can do better.
>
> It is weird, weird, weird that on x86, we see three completely different behaviors:
> - x86 Android: inlining better for small N, custom better for large N;
> - Windows: inlining better for large N, custom better for small N;
> - other x86: inlining generally better
>
> BUG=skia:4316,chromium:516426
>
> (Temporary, plan to revert.)
> TBR=reed@google.com
>
> Committed: https://skia.googlesource.com/skia/+/b68fa409fc00ce2f38e2a0fd6f9dc2379b372481TBR=reed@google.com,jcgregorio@google.com,mtklein@chromium.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:4316,chromium:516426
Review URL: https://codereview.chromium.org/1358793002
I spent some time looking at perf.skia.org and it looks like we can do better.
It is weird, weird, weird that on x86, we see three completely different behaviors:
- x86 Android: inlining better for small N, custom better for large N;
- Windows: inlining better for large N, custom better for small N;
- other x86: inlining generally better
BUG=skia:4316,chromium:516426
(Temporary, plan to revert.)
TBR=reed@google.com
Review URL: https://codereview.chromium.org/1357193002
Remove some bogus tests on the cache, as they are not thread-reliable. Running w/ discardable these are racy.
BUG=532981
Review URL: https://codereview.chromium.org/1351453004
The new FP is used to implement SkXM::Mode color filters and SkXM::Mode image filters. Also, these now support all advanced SkXM::Mode xfermodes.
Review URL: https://codereview.chromium.org/1334293003
This makes the blurcircles bench go from ~33us to ~8us on Windows desktop.
It will require layout test suppressions
Review URL: https://codereview.chromium.org/1311583005
Possible follow-up changes to consider
1. Roll SkImage_Raster and _Gpu into _Generator, where the generator (or cacherator) is backed by a pre-existing texture or raster.
2. Evolve SkImageUsageType into a verb requiring stretching, and have the caller (common code) digest the caps() and usage, so that subclasses are just told what to do (stretch or not)
3. Common code/utility to convert an unstretched texture into a stretch one (and cache it) if the generator can only make an unstretched one.
BUG=skia:
Review URL: https://codereview.chromium.org/1282363002
This was a pre-SkOpts attempt that we can bring under its wing now.
This should be a perf no-op, deo volente.
BUG=skia:4117
Review URL: https://codereview.chromium.org/1314863006
SkOncePtr<T[]> is identical to SkOncePtr<T> except we'll default to delete[]
for cleanup.
CQ_EXTRA_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Debug-ASAN-Trybot
BUG=skia:
No public API changes.
TBR=reed@google.com
Review URL: https://codereview.chromium.org/1311893010
Reason for revert:
Breaks Chrome roll.
obj/skia/ext/skia_chrome.skia_memory_dump_provider.o
does not have -I include/private on its include path, but transitively includes SkMessageBus.h.
Original issue's description:
> Port uses of SkLazyPtr to SkOncePtr.
>
> This gives SkOncePtr a non-trivial destructor that uses std::default_delete
> by default. This is overrideable, as seen in SkColorTable.
>
> SK_DECLARE_STATIC_ONCE_PTR still just leaves its pointers hanging at EOP.
>
> BUG=skia:
>
> No public API changes.
> TBR=reed@google.com
>
> Committed: https://skia.googlesource.com/skia/+/a1254acdb344174e761f5061c820559dab64a74cTBR=herb@google.com,mtklein@chromium.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Review URL: https://codereview.chromium.org/1334523002
This gives SkOncePtr a non-trivial destructor that uses std::default_delete
by default. This is overrideable, as seen in SkColorTable.
SK_DECLARE_STATIC_ONCE_PTR still just leaves its pointers hanging at EOP.
BUG=skia:
No public API changes.
TBR=reed@google.com
Review URL: https://codereview.chromium.org/1322933005
Image encoding may fail during serialization, resulting in zero-length
encoded data in the SKP.
Instead of invalidating the stream (and preventing deserialization of
the whole picture) we can instantiate placeholder images.
BUG=skia:4285
R=reed@google.com,robertphillips@google.com
Review URL: https://codereview.chromium.org/1308273011
It is easy to think in some cases that SkString::resize(int) is not
destructive, since optimizations mean that most of the time the data
is still there after a resize. However, in the general case, the
original string's data is lost and the new SkString contains garbage.
Review URL: https://codereview.chromium.org/1304833004
The million SKPs generated require >5T of storage. A good deal
of that are copies of system fonts.
Chrome built with
#DEFINE SK_WHITELIST_SERIALIZED_TYPEFACES
will omit the font data if the font matches a precomputed
checksum.
The captured SKP prepends sk_ to the names of fonts that
have their data omitted. The SKP consumer can either add
renamed fonts from the recording machine, or add
gDeserializeTypefaceDelegate = WhitelistDeserializeTypeface;
which strips the sk_ prefix when deserializing typefaces.
whitelist_typefaces --check
Computes the checksums of fallback
fonts and returns 0 if the checksums match the checked-in
file SkWhitelistChecksum.cpp.
whitelist_typefaces --generate
Writes an updated version of SkWhitelistChecksum.cpp.
(Added Mike since this modifies a public header)
R=bungeman@google.com,rmistry@google.com,reed@google.com
Review URL: https://codereview.chromium.org/1317913005
Dump the memory statistics of resource cache and glyph cache using the
SkTraceMemoryDump interface.
BUG=chromium:503168
Review URL: https://codereview.chromium.org/1313793004
Re-land; layout tests are suppressed and gm differences are understood.
A merge conflict prevented a automatic reland.
If the endcap is not butt, draw the endcaps even when the line
has zero length.
If the dash length is zero, generate a zero length line segment.
Treat a move followed by a close as a move followed by a zero-length
line.
TBR=reed@google.com
BUG=422974
Review URL: https://codereview.chromium.org/1314213002
Unfortunately, immintrin.h (which is also included by SkTypes)
includes xmmintrin.h which includes mm_malloc.h which includes
stdlib.h for malloc even though, from the implementation, it is
difficult to see why.
Fortunately, arm_neon.h does not seem to be involved in such
shenanigans, so building for Android will keep things sane.
TBR=reed@google.com
Doesn't change Skia API, just moves an include.
Review URL: https://codereview.chromium.org/1313203003
The motivation for this was to remove SK_OFFSETOF from SkTypes, but
this CL is mostly about cleaning up our use of offsetof generally.
SK_OFFSETOF is removed to SkTypes and added to the two places it is
actually used (for the non standard behavior of finding the offset of
fields in types which are not standard layout).
Older versions of gcc required POD for offsetof to be used without
warning. Newer versions require the more relaxed standard layout.
Now that we no longer build on older versions of gcc, remove the
old warning suppressions.
PODMatrix is renamed to AggregateMatrix. SkMatrix is already POD
(trivial and standard layout). The PODMatrix name implies that the
POD-ness is needed for the offsetof, but it is actually the aggregate
attribute which is needed for compile time constant initialization.
This makes it more obvious that this can be revisited after we can
rely on constexpr constructors.
This also adds skstd::declval since this allows removal of existing
awkward code which casts a constant to a pointer to find the size of
a field.
TBR=reed@google.com
No API change, only removes unused macro.
Review URL: https://codereview.chromium.org/1309523003
Looks like the -Wmicrosoft warnings in the bug are coming up specificically
because many the effects in SkLightingImageFilter are defined inside an
anonymous namespace (spanning, I think, lines 33-702 today).
BUG=skia:4091
No public API changes.
TBR=reed@google.com
Review URL: https://codereview.chromium.org/1311783004
CL (1 of 3) adds empty lists in our .gypi,
and builds the files in those empty lists with the appropriate flags.
CL (2 of 3) will have Chrome's GYP and GN files read these lists,
and build them with the appropriate flags.
CL (3 of 3) will add runtime detection and stub files to the lists
with empty Init_sse42(), Init_avx(), Init_avx2() methods.
After that, we should be able to use SSE 4.2, AVX, and AVX2 if desired.
Some motivation:
- SSE 4.2 adds some sweet string-oriented methods that
can help us write fast high quality 32-bit hashes.
- AVX is SSE doubled, e.g. 8 floats or two SkPMFloat at a time.
- AVX2 is SSE2 doubled, e.g. 8 pixels at a time.
BUG=skia:4117
Review URL: https://codereview.chromium.org/1290423007
Reason for revert:
More GMs changed than I expected. Will probably affect layout tests as well; reverting until I can verify that the changes are correct.
Original issue's description:
> experiment with zero-length round capped line segments
>
> If the endcap is not butt, draw the endcaps even when the line
> has zero length.
>
> If the dash length is zero, generate a zero length line segment.
>
> Treat a move followed by a close as a move followed by a zero-length
> line.
>
> R=reed@google.com,schenney@google.com
> BUG=422974
>
> Committed: https://skia.googlesource.com/skia/+/dd3c165828fffb369d0f4b13b48381169a0249a9TBR=reed@google.com,schenney@google.com,schenney@chromium.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=422974
Review URL: https://codereview.chromium.org/1304163008
If the endcap is not butt, draw the endcaps even when the line
has zero length.
If the dash length is zero, generate a zero length line segment.
Treat a move followed by a close as a move followed by a zero-length
line.
R=reed@google.com,schenney@google.com
BUG=422974
Review URL: https://codereview.chromium.org/1309753002
Reason for revert:
This causes a syntax error.
http://build.chromium.org/p/tryserver.chromium.mac/builders/mac_chromium_compile_dbg_ng/builds/87819/steps/compile%20%28with%20patch%29/logs/stdio
Original issue's description:
> Implement canComputeFastBounds() for image filters.
>
> Image filters have never implemented this check, which means that
> filters which affect transparent black falsely claim they can compute
> their bounds.
>
> Implemented an affectsTransparentBlack() virtual for image
> filters, and a similar helper function for color filters.
>
> This will affect the following GMs: imagefiltersscaled
> (lighting, perlin noise now filter to clip),
> colorfilterimagefilter (new test case), imagefiltersclipped
> (perlin noise now filters to clip).
>
> Note: I de-inlined SkPaint::canComputeFastBounds() to avoid adding
> a dependency from SkPaint.h to SkImageFilter.h.h. Skia benches show
> no impact from this change, but will watch the perf bots carefully.
>
> BUG=4212
>
> Committed: https://skia.googlesource.com/skia/+/915881fe743f9a789037695f543bc6ea189cd0cbTBR=reed@google.com,senorblanco@chromium.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=4212
Review URL: https://codereview.chromium.org/1300403003
Image filters have never implemented this check, which means that
filters which affect transparent black falsely claim they can compute
their bounds.
Implemented an affectsTransparentBlack() virtual for image
filters, and a similar helper function for color filters.
This will affect the following GMs: imagefiltersscaled
(lighting, perlin noise now filter to clip),
colorfilterimagefilter (new test case), imagefiltersclipped
(perlin noise now filters to clip).
Note: I de-inlined SkPaint::canComputeFastBounds() to avoid adding
a dependency from SkPaint.h to SkImageFilter.h.h. Skia benches show
no impact from this change, but will watch the perf bots carefully.
BUG=4212
Review URL: https://codereview.chromium.org/1296943002
SkTemplates.h contains a number of Skia specific utilities which are
not designed for external use. In addition to reducing the external
support burden, this will allow Skia to freely refactor this file.
Review URL: https://codereview.chromium.org/1272293004
By adding a cast to SK_ARRAY_COUNT, the compiler treats the
compile-time value as if it were a const int, and like regular
numbers, permits it to be compared to signed and unsigned
numbers freely.
R=reed@google.com
Review URL: https://codereview.chromium.org/1299943002
Old flow to serialize a picture:
1) serialize picture ops
2) serialize all sub pictures recursively
3) flatten the rest of this picture into a buffer, deduping flattenable factories and typefaces as we go
4) serialize the factories and typefaces
5) serialize the bytes from 3)
This allows the data in step 5) to refer to the deduplicated factories and typefaces from step 4). But, each sub picture in step 2) is completely siloed, so they can't dedup with the parent picture or each other.
New flow:
1) serialize picture ops
2) flatten the rest of this picture into a buffer, deduping flattenable factories and typefaces as we go
3) dummy-serialize sub pictures into /dev/null, with the effect of adding any new typefaces to our dedup set
4) serialize the factories and typefaces
5) serialize the bytes from 2)
6) serialize all sub pictures recursively, with perfect deduplication because of step 3).
Now all typefaces in the top-level picture and all sub pictures recursively should end up deduplicated in the top-level typeface set.
Decoding changes are similar: we just thread through the top-level typefaces to the sub pictures. What's convenient / surprising is that this new code correctly reads old pictures if we just have each picture prefer its local typeface set over the top-level one: old pictures always just use their own typefaces, and new pictures always use the top-level ones.
BUG=skia:4092
Review URL: https://codereview.chromium.org/1233953004
To do this, create SkImageCacherator, which wraps a generator and provides an
interface to get a cached answer for either the raster or texture output of
the generator.
BUG=skia:
Review URL: https://codereview.chromium.org/1291803002
This allows removal the difficult to use (and so currently unused)
placement new and related macros to allow any constructor of T to
be used to initilize the storage of SkTLazy. This also properly
aligns the SkTLazy storage.
Review URL: https://codereview.chromium.org/1283183003
Paths are cached as tessellated triangle meshes in vertex buffers on the GPU. Stroked paths are not (yet) cached.
Paths containing no curved segments (linear paths) are reused at all scales. Paths containing curved segments are reused within a scale tolerance threshold.
In order to invalidate the cache when an SkPath is changed or deleted,
this required implementing genID change notification in SkPath. This is
modelled almost exactly on SkPixelRef::GenIDChangeListener.
However, It does not currently implement the check for unique genIDs,
so notifiers will fire when the first instance of an SkPathRef
using a given genID is destroyed.
Another caveat is that you cannot successfully add a change notifier
to an empty path, since it uses the "canonical" empty path which is
never modified or destroyed. For this reason, we prevent adding
listeners to it.
BUG=skia:4121,skia:4122, 497403
DOCS_PREVIEW= https://skia.org/?cl=1114353004
Committed: https://skia.googlesource.com/skia/+/468dfa72eb6694145487be17876804dfca3b7adb
Review URL: https://codereview.chromium.org/1114353004
Does not try to cache calls to readPixels at the moment:
- not triggered by drawing
- not clear if we want to perform any pixel transformations (that readPixels allows) on the GPU or CPU
Can consider that another time.
BUG=513695
Review URL: https://codereview.chromium.org/1262923003
Paths are cached as tessellated triangle meshes in vertex buffers on the GPU. Stroked paths are not (yet) cached.
Paths containing no curved segments (linear paths) are reused at all scales. Paths containing curved segments are reused within a scale tolerance threshold.
In order to invalidate the cache when an SkPath is changed or deleted,
this required implementing genID change notification in SkPath. This is
modelled almost exactly on SkPixelRef::GenIDChangeListener.
However, It does not currently implement the check for unique genIDs,
so notifiers will fire when the first instance of an SkPathRef
using a given genID is destroyed.
Another caveat is that you cannot successfully add a change notifier
to an empty path, since it uses the "canonical" empty path which is
never modified or destroyed. For this reason, we prevent adding
listeners to it.
BUG=skia:4121,skia:4122, 497403
DOCS_PREVIEW= https://skia.org/?cl=1114353004
Review URL: https://codereview.chromium.org/1114353004
Renames Sk4pxXfermode.h to SkXfermode_opts.h,
and refactors it a tiny bit internally.
This moves xfermode optimization from being "compile-time everywhere but NEON"
to simply "runtime everywhere". I don't anticipate any effect on perf or
correctness.
BUG=skia:4117
Review URL: https://codereview.chromium.org/1264543006
With this new arrangement, the benefits of inlining sk_memset16/32 have changed.
On x86, they're not significantly different, except for small N<=10 where the inlined code is significantly slower.
On ARMv7 with NEON, our custom code is still significantly faster for N>10 (up to 2x faster). For small N<=10 inlining is still significantly faster.
On ARMv7 without NEON, our custom code is still ridiculously faster (up to 10x) than inlining for N>10, though for small N<=10 inlining is still a little faster.
We were not using the NEON memset16 and memset32 procs on ARMv8. At first blush, that seems to be an oversight, but if so it's an extremely lucky one. The ARMv8 code generation for our memset16/32 procs is total garbage, leaving those methods ~8x slower than just inlining the memset, using the compiler's autovectorization.
So, no need to inline any more on x86, and still inline for N<=10 on ARMv7. Always inline for ARMv8.
BUG=skia:4117
Review URL: https://codereview.chromium.org/1270573002
This enables the NEON sk_float_rsqrt() code for configurations that have NEON at run-time but not compile-time.
These devices will see about a 2x (1.26 -> 2.33) slowdown in sk_float_rsqrt(), but it should be more precise than our portable fallback.
(When inlined, the portable fallback and the NEON code are almost identical in speed. The only difference is precision. Going through a function pointer is causing all this slowdown. This is a good example of a place where Skia really benefits from compile-time NEON.)
BUG=skia:4117,skia:4114
No public API changes.
TBR=reed@google.com
Review URL: https://codereview.chromium.org/1264893002
SDL isn't an OS anyway, it's just a library views can use. Remaining
support for Brew was removed some time ago, and there are currently
no uses of SK_BUILD_FOR_PALM.
Review URL: https://codereview.chromium.org/1268573002
This hasn't been tested for years, and no one currently knows when it
last worked (if ever). It is doubtful that any of the remaining logic
would even make sense with a modern version of Embedded Compact 2013.
Review URL: https://codereview.chromium.org/1260453008
The current include-what-you-use with current clang is much less
noisy and more useful than it has been in the past. This change
introduces a few IWYU directives (which are helpful documentation for
humans as well) and fixes a few sets of includes.
Review URL: https://codereview.chromium.org/1207893002
To make this work, we tag their pixelrefs as temporarily immutable, allowing
ourselves to restore the pixels to mutability only when the image drops away.
This should allow us to wobble back and forth between writing to the Surface
and reading from the Image without a COW, with the Surface seeing mutable
pixels and the Image seeing immutable pixels.
The big idea is, Image doesn't need forever-immutable pixels, it just needs
pixels that are immutable as long as it's alive.
BUG=skia:
patch from issue 804523002 at patchset 40001 (http://crrev.com/804523002#ps40001)
Review URL: https://codereview.chromium.org/1254383006
This reverts commit d12e6ffa5c.
Our Chrome roll canaries are failing with the dreaded
Ninja-says-there's-more-work-to-do message. I will break this up
smaller (if possible) and try again tomorrow.
BUG=skia:4126
Review URL: https://codereview.chromium.org/1258293004 .
This is a contract change for SkPath::getBounds(), which formally was defined to return 0,0,0,0 for a 1-point path, regardless of the coordinates of that point. This seems wacky/inconsistent, and was causing other bugs (incorrect bounds) when this was unioned with other rects.
Does anyone remember why we defined it this way?
BUG=513799
Review URL: https://codereview.chromium.org/1261773002
SkSurface_Raster snapshots do not lock their backing bitmaps when the
pixel ref is shared - they only lock on deep-copy.
But since for raster surfaces the pixels are always in memory, I think
it would be OK to also lock in the former case.
This allows for optimized (zero-copy) reads of raster surface snapshot
data.
R=reed@google.com
Review URL: https://codereview.chromium.org/1256993002
Improves max relative error from 0.00175126 to 0.000650197.
Also add unit tests to check error bounds.
BUG=chromium:511458
Review URL: https://codereview.chromium.org/1251423002
Tidy up a little while I'm in here:
1) SIMD headers are now included by SkTypes.h as appropriate.
2) _mm_cvtss_f32() is pithier and generates the same code.
Looks like this is the only code checking for SSE wrong. After this CL:
~/skia (sse) $ git grep __SSE
include/core/SkPreConfig.h: #if defined(__SSE4_2__)
include/core/SkPreConfig.h: #elif defined(__SSE4_1__)
include/core/SkPreConfig.h: #elif defined(__SSE3__)
include/core/SkPreConfig.h: #elif defined(__SSE2__)
every other check is in SkPreConfig.h where it belongs.
This is going to affect some GMs subtly on Windows.
BUG=chromium:511458
No public API changes.
TBR=reed@google.com
Review URL: https://codereview.chromium.org/1248503004
This is split off of https://codereview.chromium.org/1225923010/ (Start tightening correspondence betweeen GrDrawContext and GrRenderTarget). It:
fixes some style nits
replaces some passing of GrContext with GrTextureProvider & GrDrawContext
does a bit of the finer grained creation of GrDrawContexts
Review URL: https://codereview.chromium.org/1245183002
Visual Studio 2015 has additional warnings around noexcept and
disabling exceptions, which can be worked around with the
(undocumented) _HAS_EXCEPTIONS macro.
Visual Studio 2013 and 2015 have roundf in math.h, so use it to
avoid extra work and casts.
We avoid using cmath, as it undefs isfinite on gcc, but Visual Studio
2015 no longer provides overloads of copysign from math.h (which is
actually correct). As a result, use copysignf (which is available in
math.h in 2013 and 2015) directly.
Review URL: https://codereview.chromium.org/1244173005
This deduplicates a few pieces of code:
- we end up with one copy of each xfer32() driver loop instead of one per xfermode;
- we end up with two* copies of each xfermode implementation instead of ten**.
* For a given Mode: Mode() itself and xfer_aa<Mode>().
** From unrolling: twice at a stride of 8, once at 4, once at 2, and once at 1, then all again for when we have AA.
This decreases the size of SkXfermode.o from 1.5M to 620K on x86-64 and from 1.3M to 680K on ARMv7+NEON.
If we wanted to, we could eliminate the xfer_aa<Mode>() copy by tagging each Mode() function as __attribute__((noinline)) or its equivalent. This would result in another ~100K space savings.
Performance is affected in proportion to the original xfermode speed:
fast modes like Plus take the largest proportional hit, and slow modes
like HardLight or SoftLight see essentially no hit at all.
This adds SK_VECTORCALL to help keep this code fast on ARMv7 and Windows. I've looked at the ARMv7 generated code... it looks good, even pretty.
For compatibility with SK_VECTORCALL, we now pass the vector-sized arguments by value instead of by reference. Some refactoring now allows us to declare each mode as just a static function instead of a struct, which simplifies things.
TBR=reed@google.com
No public API changes.
BUG=skia:
Committed: https://skia.googlesource.com/skia/+/e617e1525916d7ee684142728c0905828caf49da
CQ_EXTRA_TRYBOTS=client.skia.compile:Build-Ubuntu-GCC-Arm7-Debug-Android_NoNeon-Trybot
Review URL: https://codereview.chromium.org/1242743004
Reason for revert:
http://build.chromium.org/p/client.skia.compile/builders/Build-Ubuntu-GCC-Arm7-Debug-Android_NoNeon/builds/1168/steps/build%20most/logs/stdio
Original issue's description:
> De-templatize Sk4pxXfermode code a bit.
>
> This deduplicates a few pieces of code:
> - we end up with one copy of each xfer32() driver loop instead of one per xfermode;
> - we end up with two* copies of each xfermode implementation instead of ten**.
>
> * For a given Mode: Mode() itself and xfer_aa<Mode>().
> ** From unrolling: twice at a stride of 8, once at 4, once at 2, and once at 1, then all again for when we have AA.
>
> This decreases the size of SkXfermode.o from 1.5M to 620K on x86-64 and from 1.3M to 680K on ARMv7+NEON.
>
> If we wanted to, we could eliminate the xfer_aa<Mode>() copy by tagging each Mode() function as __attribute__((noinline)) or its equivalent. This would result in another ~100K space savings.
>
> Performance is affected in proportion to the original xfermode speed:
> fast modes like Plus take the largest proportional hit, and slow modes
> like HardLight or SoftLight see essentially no hit at all.
>
> This adds SK_VECTORCALL to help keep this code fast on ARMv7 and Windows. I've looked at the ARMv7 generated code... it looks good, even pretty.
>
> For compatibility with SK_VECTORCALL, we now pass the vector-sized arguments by value instead of by reference. Some refactoring now allows us to declare each mode as just a static function instead of a struct, which simplifies things.
>
> TBR=reed@google.com
> No public API changes.
>
> BUG=skia:
>
> Committed: https://skia.googlesource.com/skia/+/e617e1525916d7ee684142728c0905828caf49daTBR=msarett@google.com,mtklein@chromium.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Review URL: https://codereview.chromium.org/1245273005
This deduplicates a few pieces of code:
- we end up with one copy of each xfer32() driver loop instead of one per xfermode;
- we end up with two* copies of each xfermode implementation instead of ten**.
* For a given Mode: Mode() itself and xfer_aa<Mode>().
** From unrolling: twice at a stride of 8, once at 4, once at 2, and once at 1, then all again for when we have AA.
This decreases the size of SkXfermode.o from 1.5M to 620K on x86-64 and from 1.3M to 680K on ARMv7+NEON.
If we wanted to, we could eliminate the xfer_aa<Mode>() copy by tagging each Mode() function as __attribute__((noinline)) or its equivalent. This would result in another ~100K space savings.
Performance is affected in proportion to the original xfermode speed:
fast modes like Plus take the largest proportional hit, and slow modes
like HardLight or SoftLight see essentially no hit at all.
This adds SK_VECTORCALL to help keep this code fast on ARMv7 and Windows. I've looked at the ARMv7 generated code... it looks good, even pretty.
For compatibility with SK_VECTORCALL, we now pass the vector-sized arguments by value instead of by reference. Some refactoring now allows us to declare each mode as just a static function instead of a struct, which simplifies things.
TBR=reed@google.com
No public API changes.
BUG=skia:
Review URL: https://codereview.chromium.org/1242743004
This change is motivated by a recent switch in how chromium handles
<video> color spaces, making rec709 more commonly used. This will
allow video -> canvas copies to take the fast GPU path when we're using
709, just as we do with 601 and jpeg.
Chromium-side change: https://codereview.chromium.org/1236313002
Review URL: https://codereview.chromium.org/1241723005
Motivation:
- perf win for clients that overwrite the surface after a snapshot.
- may allow us to eliminate SkDeferredCanvas, as this was its primary advantage.
BUG=skia:
Review URL: https://codereview.chromium.org/1236023004
The new test is disabled by default, as it's quite slow.
We can run it if we suspect problems by passing -x to DM.
This test would have been failing before the bug fix, and now is passing.
Assuming the Priv on the end means it's not considered public API...
TBR=reed@google.com
BUG=skia:4052
Review URL: https://codereview.chromium.org/1228333003
and are treated as convex when they are not.
Allow the SkPath::Iter to leave degenerate path
segments unmolested by passing an additional exact
bool to next().
Treat any non-zero length as significant in addPt().
R=reed@google.com,robertphillips@google.com
BUG=493450
Review URL: https://codereview.chromium.org/1228383002
The error log is as follows:
../../third_party/skia/include/core/SkSpinlock.h:24: error: undefined reference to 'SkPODSpinlock::contendedAcquire()'
collect2: error: ld returned 1 exit status
[mtklein added below here]
Despite the presence in include/ and the added SK_API, this file is not part of Skia's public API... it's just used by files which are.
TBR=reed@google.com
Review URL: https://codereview.chromium.org/1229003004
The proportion of time spent doing useful work is well over 99% in acquire(),
so outlining it doesn't hurt speed at all, and makes it much easier to pick out
on a profile.
It'd be about 50/50 work/overhead if we outlined the extremely-cheap release().
I also tried outlining some SkRefCnt methods with similar mixed results.
BUG=skia:
No public API changes.
TBR=reed@google.com
Review URL: https://codereview.chromium.org/1212253013
Follow up to the split between SkImageGenerator and SkCodec. Now that
SkCodec does not inherit from SkImageGenerator, SkImageGenerator no
longer needs Options or Result, which were added for SkCodec. Remove
them, but keep them behind a flag, since Chromium has its own
subclasses of SkImageGenerator which assume the old signature for
onGetPixels.
Review URL: https://codereview.chromium.org/1226023003
For some users of SkPictureRecorder, the cull rect is more efficiently
determined while drawing is in progress, rather than when recording starts.
The existing API requires the cull rect at start time, even though the
information is not used for any culling purpose until the end of recording.
This patch provides a means to reset the cull rect when recording ends,
allowing users to update the rect based on information learned during
drawing and for the new rect to be used as the culling bound. A valid
bound is still required on the beginRecording call because
it sizes the underlying canvas and sets the aspect ratio for any bounding
box hierarchy. The bounding box factory can also be specified and parameters
that control SkPicture creation.
R=mtklein, reed1
BUG=skia:3919
Review URL: https://codereview.chromium.org/1178673007
Some of this is transitive, like SkRecords.h used by SkMiniRecorder.h
used by (public) SkPictureRecorder.h.
BUG=skia:
Review URL: https://codereview.chromium.org/1217293004
This makes nanobench picture recording benchmarks somewhat useful again,
as opposed to all taking about 5us to run no matter the content.
ATTN Sheriff: this will probably trigger perf.skia.org alerts.
BUG=skia:
Review URL: https://codereview.chromium.org/1219873002
this also exposes nine-patch drawing directly to devices, and creates a shared iterator for unrolling a nine-patch into single rect->rect draws.
BUG=skia:
Review URL: https://codereview.chromium.org/1211583003
This CL continues cleaning up Skia's usage of SkSurfaceProps. It:
Removes the duplicate SkSurfaceProps object from SkImageFilter::Proxy.
Removes a dispreferred ctor from SkCanvas
Removes the initForRootLayer entry point from SkDevice (since the root device and the canvas should always have the same pixel geometry now).
Review URL: https://codereview.chromium.org/1201983006
This CL starts the process of pushing kLegacyFontHost_InitType-type SkSurfaceProps up the call stack and out of Skia. It:
Gets rid of the default SkBaseDevice ctor. This means everyone has to always hand an explicit SkSurfaceProps to it.
It makes public the SkBitmapDevice creation methods that require SkSurfaceProps.
Removes (in Skia's code base) all SkBitmapDevice ctor calls w/o SkSurfaceProps.
Makes the "recording" canvases (e.g., pdf, svg, xps) explicitly not use kLegacyFontHost_InitType.
Replicates the creating canvas/device's flags on saveLayer devices
BUG=skia:3934
Review URL: https://codereview.chromium.org/1204433002
sk_inv_determinant has a guard that the determinant can't get too big so this CL only checks if the determinant gets too small.
BUG=492263
Review URL: https://codereview.chromium.org/1188433011
