| Commit message (Collapse) | Author | Age |
|
|
|
|
|
| |
BUG=skia:
Review URL: https://codereview.chromium.org/1212613005
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
SSE speeds up about 4.5x over existing integer SSE,
NEON speeds up about 3x over serial integer code.
We expect 1-2 bit component diffs in the usual GMs.
Still guarded by SK_SUPPORT_LEGACY_XFERMODES,
which I'll now try to lift in Chrome.
BUG=skia:
Review URL: https://codereview.chromium.org/1221493002
|
|
|
|
|
|
| |
BUG=485243
Review URL: https://codereview.chromium.org/1210303003
|
|
|
|
|
|
|
| |
TBR=bsalomon@google.com
BUG=skia:
Review URL: https://codereview.chromium.org/1217843002
|
|
|
|
|
|
|
|
|
| |
Automatic commit by the RecreateSKPs bot.
TBR=
NO_MERGE_BUILDS
Review URL: https://codereview.chromium.org/1218683003
|
|
|
|
|
|
| |
BUG=skia:
Review URL: https://codereview.chromium.org/1216663002
|
|
|
|
|
|
|
|
|
| |
Changes verbose mode to print both the table and the individual sample
values. No need to hold back information in verbose mode.
BUG=skia:
Review URL: https://codereview.chromium.org/1208763003
|
|
|
|
|
|
| |
BUG=skia:
Review URL: https://codereview.chromium.org/1202383006
|
|
|
|
|
|
| |
BUG=skia:3984,skia:3934
Review URL: https://codereview.chromium.org/1211413003
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
It's been outclassed by Valgrind and leak sanitizer,
and it seems to be causing problems for external folks building Skia.
I'm not sure why our own builds seem unaffected.
Latest thread:
https://groups.google.com/forum/#!topic/skia-discuss/oj9FsQwwSF0
BUG=skia:
Review URL: https://codereview.chromium.org/1217573002
|
|
|
|
|
|
|
|
| |
It's too random to be helpful.
BUG=skia:
Review URL: https://codereview.chromium.org/1215703005
|
|
|
|
|
|
| |
BUG=chromium:496224
Review URL: https://codereview.chromium.org/1211363006
|
|
|
|
|
|
|
|
|
|
|
|
| |
These structs are always implemented as
struct uintNNxMx4_t {
uintNNxM val[4];
};
So, the first set of braces is for the struct, the second for val.
BUG=skia:
Review URL: https://codereview.chromium.org/1221453002
|
|
|
|
| |
Review URL: https://codereview.chromium.org/1217443004
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Both 25-35% faster with SSE.
With NEON, Burn measures as a ~10% regression, Dodge a huge 2.9x improvement.
The Burn regression is somewhat artificial: we're drawing random colored rects onto an opaque white dst, so we're heavily biased toward the (d==da) fast path in the serial code. In the vector code there's no short-circuiting and we always pay a fixed cost for ColorBurn regardless of src or dst content.
Dodge's fast paths, in contrast, only trigger when (s==sa) or (d==0), neither of which happens any more than randomly in our benchmark. I don't think (d==0) should happen at all. Similarly, the (s==0) Burn fast path is really only going to happen as often as SkRandom allows.
In practice, the existing Burn benchmark is hitting its fast path 100% of the time. So I actually feel really great that this only dings the benchmark by 10%.
Chrome's still guarded by SK_SUPPORT_LEGACY_XFERMODES, which I'll lift after finishing the last xfermode, SoftLight.
BUG=skia:
Review URL: https://codereview.chromium.org/1214443002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
of https://codereview.chromium.org/1203983003/)
Reason for revert:
fixes have landed in android
Original issue's description:
> Revert of remove SK_SUPPORT_LEGACY_PATHOP_ENUMS (patchset #1 id:1 of https://codereview.chromium.org/1200323005/)
>
> Reason for revert:
> Breaking the Android build.
>
> Original issue's description:
> > remove SK_SUPPORT_LEGACY_PATHOP_ENUMS
> >
> > BUG=skia:
> > TBR=
> >
> > Committed: https://skia.googlesource.com/skia/+/8bcc7a00febd737f7e82513bd5e4a697526626de
>
> TBR=reed@google.com
> NOPRESUBMIT=true
> NOTREECHECKS=true
> NOTRY=true
> BUG=skia:
>
> Committed: https://skia.googlesource.com/skia/+/ba9a4aa8550c982c480d03cb6ba2cabaf6209b41
TBR=scroggo@google.com
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Review URL: https://codereview.chromium.org/1218523002
|
|
|
|
|
|
| |
BUG=skia:
Review URL: https://codereview.chromium.org/1214703002
|
|
|
|
|
|
| |
BUG=499499
Review URL: https://codereview.chromium.org/1210053003
|
|
|
|
|
|
|
| |
BUG=skia:
TBR=
Review URL: https://codereview.chromium.org/1212393002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
GrAALinearizingConvexPathRenderer (patchset #1 id:1 of https://codereview.chromium.org/1212833002/)
Reason for revert:
Manual roll is in: https://codereview.chromium.org/1212373002
Let's re-land this.
Original issue's description:
> Revert of added stroking support to GrAALinearizingConvexPathRenderer (patchset #6 id:100001 of https://codereview.chromium.org/1180903006/)
>
> Reason for revert:
> speculative revert to try to fix DEPS roll (layouttests)
>
> Original issue's description:
> > added stroking support to GrAALinearizingConvexPathRenderer
> >
> > BUG=skia:
> >
> > Committed: https://skia.googlesource.com/skia/+/2436f191e6602953b32a51cf50f2d7a4e2af90fd
>
> TBR=bsalomon@google.com,robertphillips@google.com,ethannicholas@google.com
> NOPRESUBMIT=true
> NOTREECHECKS=true
> NOTRY=true
> BUG=skia:
>
> Committed: https://skia.googlesource.com/skia/+/9730f4a663534009d216c2f6d834bd534dd44a3d
TBR=bsalomon@google.com,robertphillips@google.com,ethannicholas@google.com,reed@chromium.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Review URL: https://codereview.chromium.org/1209003004
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(patchset #6 id:100001 of https://codereview.chromium.org/1180903006/)
Reason for revert:
speculative revert to try to fix DEPS roll (layouttests)
Original issue's description:
> added stroking support to GrAALinearizingConvexPathRenderer
>
> BUG=skia:
>
> Committed: https://skia.googlesource.com/skia/+/2436f191e6602953b32a51cf50f2d7a4e2af90fd
TBR=bsalomon@google.com,robertphillips@google.com,ethannicholas@google.com
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Review URL: https://codereview.chromium.org/1212833002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
of https://codereview.chromium.org/1211123004/)
Reason for revert:
un-referting, did not help DEPS roll
Original issue's description:
> Revert of Return GrGLContext from GrTestTarget (patchset #3 id:40001 of https://codereview.chromium.org/1207393002/)
>
> Reason for revert:
> speculative revert to unblock DEPS roll (layout-tests)
>
> Original issue's description:
> > Return GrGLContext from GrTestTarget
> >
> > BUG=skia:
> >
> > Committed: https://skia.googlesource.com/skia/+/b6d93ea428ca5d13641c35faca7d0380980a3a17
>
> TBR=bsalomon@google.com,joshualitt@google.com,joshualitt@chromium.org
> NOPRESUBMIT=true
> NOTREECHECKS=true
> NOTRY=true
> BUG=skia:
>
> Committed: https://skia.googlesource.com/skia/+/1852ec2b46a2a0efbb3550ff4d8b640f56a810e9
TBR=bsalomon@google.com,joshualitt@google.com,joshualitt@chromium.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Review URL: https://codereview.chromium.org/1215593002
|
|
|
|
|
|
|
|
|
| |
Adds a nanobench mode that takes samples for a fixed amount of time,
rather than taking a fixed amount of samples.
BUG=skia:
Review URL: https://codereview.chromium.org/1204153002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
https://codereview.chromium.org/1207393002/)
Reason for revert:
speculative revert to unblock DEPS roll (layout-tests)
Original issue's description:
> Return GrGLContext from GrTestTarget
>
> BUG=skia:
>
> Committed: https://skia.googlesource.com/skia/+/b6d93ea428ca5d13641c35faca7d0380980a3a17
TBR=bsalomon@google.com,joshualitt@google.com,joshualitt@chromium.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Review URL: https://codereview.chromium.org/1211123004
|
|
|
|
|
|
| |
BUG=skia:
Review URL: https://codereview.chromium.org/1216433002
|
|
|
|
|
|
| |
BUG=skia:
Review URL: https://codereview.chromium.org/1207393002
|
|
|
|
|
|
| |
BUG=skia:
Review URL: https://codereview.chromium.org/1180903006
|
|
|
|
|
|
| |
BUG=skia:
Review URL: https://codereview.chromium.org/1210283002
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
|
|
| |
Adds a loopSKP flag that forces SKPBenches to draw with only 1 loop.
BUG=skia:
Review URL: https://codereview.chromium.org/1203193002
|
|
|
|
|
|
|
|
|
| |
vcvt_n_f32_u32 and _u32_f32 work in power-of-2 fixed point, so (...,8)
meant 'please multiply or divide by 256'. We need to use 255. :(
BUG=skia:
Review URL: https://codereview.chromium.org/1204363002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Now that Sk4px exists, there's a lot less sense in eeking out every
cycle of speed from SkPMFloat: if we need to go _really_ fast, we
should use Sk4px. SkPMFloat's going to be used for things that are
already slow: large-range intermediates, divides, sqrts, etc.
A [0,1] range is easier to work with, and can even be faster if we
eliminate enough *255 and *1/255 steps. This is particularly true
on ARM, where NEON can do the *255 and /255 steps for us while
converting float<->int.
We have lots of experimental SkPMFloat <-> SkPMColor APIs that
I'm now removing. Of the existing APIs, roundClamp() is the sanest,
so I've kept only that, now called round(). The 4-at-a-time APIs
never panned out, so they're gone.
There will be small diffs on:
colormatrix coloremoji colorfilterimagefilter fadefilter imagefilters_xfermodes imagefilterscropexpand imagefiltersgraph tileimagefilter
BUG=skia:
Review URL: https://codereview.chromium.org/1201343004
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
https://codereview.chromium.org/1177243004/)
Reason for revert:
Broke the GPU SAN bots: https://build.chromium.org/p/client.skia/builders/Test-Ubuntu-GCC-Golo-GPU-GT610-x86_64-Debug-ASAN/builds/779/steps/dm/logs/stdio
Original issue's description:
> Cleanup legacy NVPR-related definitions
>
> Fixed-function NVPR codepaths were removed a while ago. Only NVPR API
> version 1.3 (PathFragmentInputGen) was left working. Remove
> backwards-compatibility code that was left behind.
>
> Remove some NVPR API function typedefs that were left from initial
> commits.
>
> Remove PathCoords function pointer from GrGLInterface, it has
> never been called and causes problems in the future, since it will
> not be implemented in the Chromium pseudo extension.
>
> Committed: https://skia.googlesource.com/skia/+/fb8d6884e0e01d0c2f8596adf5af1efb0d08de7e
TBR=joshualitt@google.com,cdalton@nvidia.com,bsalomon@google.com,kkinnunen@nvidia.com
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
Review URL: https://codereview.chromium.org/1206333003
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
I'm getting this error, which is fixed by this change:
[75/76] LINK skpdiff
FAILED: c++ -m64 -pie -Wl,-rpath=\$ORIGIN/lib/ -Wl,-rpath-link=lib/ -o skpdiff -Wl,--start-group obj/tools/skpdiff/skpdiff.skpdiff_main.o obj/tools/skpdiff/skpdiff.SkDiffContext.o obj/tools/skpdiff/skpdiff.SkImageDiffer.o obj/tools/skpdiff/skpdiff.SkPMetric.o obj/tools/skpdiff/skpdiff.skpdiff_util.o obj/tools/skpdiff/skpdiff.SkDifferentPixelsMetric_cpu.o obj/gyp/libflags.a obj/gyp/libpicture_utils.a -Wl,--end-group lib/libskia.so -lrt -lz
/usr/bin/ld: obj/tools/skpdiff/skpdiff.SkDiffContext.o: undefined reference to symbol 'pthread_mutexattr_settype@@GLIBC_2.2.5'
//lib/x86_64-linux-gnu/libpthread.so.0: error adding symbols: DSO missing from command line
collect2: error: ld returned 1 exit status
BUG=skia:
Review URL: https://codereview.chromium.org/1206333002
|
|
|
|
|
|
| |
BUG=skia:3840
Review URL: https://codereview.chromium.org/1204283002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Fixed-function NVPR codepaths were removed a while ago. Only NVPR API
version 1.3 (PathFragmentInputGen) was left working. Remove
backwards-compatibility code that was left behind.
Remove some NVPR API function typedefs that were left from initial
commits.
Remove PathCoords function pointer from GrGLInterface, it has
never been called and causes problems in the future, since it will
not be implemented in the Chromium pseudo extension.
Review URL: https://codereview.chromium.org/1177243004
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
HardLight, Overlay, Darken, and Lighten are all
~2x faster with SSE, ~25% faster with NEON.
This covers all previously-implemented NEON xfermodes.
3 previous SSE xfermodes remain. Those need division
and sqrt, so I'm planning on using SkPMFloat for them.
It'll help the readability and NEON speed if I move that
into [0,1] space first.
The main new concept here is c.thenElse(t,e), which behaves like
(c ? t : e) except, of course, both t and e are evaluated. This allows
us to emulate conditionals with vectors.
This also removes the concept of SkNb. Instead of a standalone bool
vector, each SkNi or SkNf will just return their own types for
comparisons. Turns out to be a lot more manageable this way.
BUG=skia:
Committed: https://skia.googlesource.com/skia/+/b9d4163bebab0f5639f9c5928bb5fc15f472dddc
CQ_EXTRA_TRYBOTS=client.skia.compile:Build-Ubuntu-GCC-Arm64-Debug-Android-Trybot
Review URL: https://codereview.chromium.org/1196713004
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
https://codereview.chromium.org/1180983002/)
Reason for revert:
https://uberchromegw.corp.google.com/i/client.skia.compile/builders/Build-Ubuntu-GCC-MipsDSP2-Debug-Android/builds/1136/steps/build%20most/logs/stdio
Original issue's description:
> Add libjpeg-turbo library (depends on yasm)
> Mangle external function names to avoid conflict with libjpeg
> Take advantage of direct color conversion (RGBA, BGRA, 565)
> Prepare to use jpeg_skip_scanlines (when it is upstreamed)
>
> BUG=skia:
>
> Committed: https://skia.googlesource.com/skia/+/b60c3f8291529303299262dba19b1a896060bd2d
TBR=scroggo@google.com,djsollen@google.com,emmaleer@google.com,msarett@google.com
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Review URL: https://codereview.chromium.org/1199253006
|
|
|
|
|
|
|
|
|
|
| |
Mangle external function names to avoid conflict with libjpeg
Take advantage of direct color conversion (RGBA, BGRA, 565)
Prepare to use jpeg_skip_scanlines (when it is upstreamed)
BUG=skia:
Review URL: https://codereview.chromium.org/1180983002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
id:1 of https://codereview.chromium.org/1207003002/)
Reason for revert:
users are still on dx9 angle :(
Original issue's description:
> remove workaround for dx9 angle slow rgba pixel ops
>
> TBR=robertphillips@google.com
>
> Committed: https://skia.googlesource.com/skia/+/1e1adc33ba1acb9a2ad41c0a5a9b6166ee9d7a2a
TBR=robertphillips@google.com
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
Review URL: https://codereview.chromium.org/1205183002
|
|
|
|
|
|
|
|
|
| |
It's possible this rarely breaks, but I do write ARMv8 code frequently
enough that it'll help prevent broken trees.
BUG=skia:
Review URL: https://codereview.chromium.org/1209763003
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
of https://codereview.chromium.org/1196713004/)
Reason for revert:
64-bit ARM build failures.
Original issue's description:
> Implement four more xfermodes with Sk4px.
>
> HardLight, Overlay, Darken, and Lighten are all
> ~2x faster with SSE, ~25% faster with NEON.
>
> This covers all previously-implemented NEON xfermodes.
> 3 previous SSE xfermodes remain. Those need division
> and sqrt, so I'm planning on using SkPMFloat for them.
> It'll help the readability and NEON speed if I move that
> into [0,1] space first.
>
> The main new concept here is c.thenElse(t,e), which behaves like
> (c ? t : e) except, of course, both t and e are evaluated. This allows
> us to emulate conditionals with vectors.
>
> This also removes the concept of SkNb. Instead of a standalone bool
> vector, each SkNi or SkNf will just return their own types for
> comparisons. Turns out to be a lot more manageable this way.
>
> BUG=skia:
>
> Committed: https://skia.googlesource.com/skia/+/b9d4163bebab0f5639f9c5928bb5fc15f472dddc
TBR=reed@google.com,mtklein@chromium.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Review URL: https://codereview.chromium.org/1205703008
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
HardLight, Overlay, Darken, and Lighten are all
~2x faster with SSE, ~25% faster with NEON.
This covers all previously-implemented NEON xfermodes.
3 previous SSE xfermodes remain. Those need division
and sqrt, so I'm planning on using SkPMFloat for them.
It'll help the readability and NEON speed if I move that
into [0,1] space first.
The main new concept here is c.thenElse(t,e), which behaves like
(c ? t : e) except, of course, both t and e are evaluated. This allows
us to emulate conditionals with vectors.
This also removes the concept of SkNb. Instead of a standalone bool
vector, each SkNi or SkNf will just return their own types for
comparisons. Turns out to be a lot more manageable this way.
BUG=skia:
Review URL: https://codereview.chromium.org/1196713004
|
|
|
|
|
|
| |
TBR=robertphillips@google.com
Review URL: https://codereview.chromium.org/1207003002
|
|
|
|
|
|
|
|
|
|
|
| |
Modern processors support flush-to-zero and denormalized-are-zero
for floating point operations (with ARM NEON unable to disable them).
However, iOS on ARM is the only current system which defaults
processes to using both all the time. However, this is only iOS on
ARM, iOS on x86 (the simulator) does not. Correctly defining this
allows the math tests to run error free in the simulator.
Review URL: https://codereview.chromium.org/1203533003
|
|
|
|
|
|
|
| |
This should be a whitespace only change.
BUG=skia:
Review URL: https://codereview.chromium.org/1194423004
|
|
|
|
| |
Review URL: https://codereview.chromium.org/1203153002
|
|
|
|
|
|
| |
BUG=skia:
Review URL: https://codereview.chromium.org/1181913003
|
|
|
|
|
|
| |
TBR=bsalomon@google.com
Review URL: https://codereview.chromium.org/1205933002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
On the n5 there seems to be an issue where negating a variable at the start
of an equation doesn't work. Moving the negated variable to a subtract at the
end works around the issue (as would multiplying by -1.0).
The main bug was caused by the -DaCub in the else if block, but I also
adjusted the else block to make sure the same issue doesn't appear there
at some later date.
BUG=chromium:502434
Review URL: https://codereview.chromium.org/1210573002
|