| Commit message (Collapse) | Author | Age |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Reland of:
https://skia-review.googlesource.com/c/9386/
Desktop (HP z620)
Before:
mipmap_build_2048x2048_0_gamma 10.5 ms
mipmap_build_2048x2048_1_gamma 77.1 ms
After:
mipmap_build_2048x2048_0_gamma 10.5 ms
mipmap_build_2048x2048_1_gamma 41.0 ms
Pixel XL
Before:
mipmap_build_2048x2048_0_gamma 160 ms
mipmap_build_2048x2048_1_gamma 1.5 s
After:
mipmap_build_2048x2048_0_gamma 160 ms
mipmap_build_2048x2048_1_gamma 570 ms
Also provides marginal performance improvements
for other sRGB downsamples.
CQ_INCLUDE_TRYBOTS=skia.primary:Test-Ubuntu-GCC-ShuttleA-GPU-GTX550Ti-x86_64-Release-Valgrind_PreAbandonGpuContext
BUG=skia:
Change-Id: Ia82fc2ef795e1bb63a4a9deac5e38f5fde39f651
Reviewed-on: https://skia-review.googlesource.com/9455
Reviewed-by: Matt Sarett <msarett@google.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This reverts commit 3ea01f72f20d4f58bf0dcd420fa5c2724b67ac8d.
Reason for revert: triggering errors on the MSAN bots
Original change's description:
> Optimize mipmap downsample_2_2 in sRGB mode
>
> Desktop (HP z620)
> Before:
> mipmap_build_2048x2048_0_gamma 10.5 ms
> mipmap_build_2048x2048_1_gamma 77.1 ms
> After:
> mipmap_build_2048x2048_0_gamma 10.5 ms
> mipmap_build_2048x2048_1_gamma 25.1 ms
>
> Pixel XL
> Before:
> mipmap_build_2048x2048_0_gamma 160 ms
> mipmap_build_2048x2048_1_gamma 1.5 s
> After:
> mipmap_build_2048x2048_0_gamma 160 ms
> mipmap_build_2048x2048_1_gamma 313 ms
>
> Also provides marginal performance improvements
> for other sRGB downsamples.
>
> BUG=skia:
>
> Change-Id: Icfcd2ccd69676ccf3822db8042a4698e4464bb71
> Reviewed-on: https://skia-review.googlesource.com/9386
> Commit-Queue: Matt Sarett <msarett@google.com>
> Reviewed-by: Mike Klein <mtklein@chromium.org>
>
TBR=mtklein@chromium.org,mtklein@google.com,msarett@google.com,brianosman@google.com,reed@google.com,reviews@skia.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Change-Id: I06907fb1691077a03daadc0980e86393bc08d9c5
Reviewed-on: https://skia-review.googlesource.com/9450
Reviewed-by: Derek Sollenberger <djsollen@google.com>
Commit-Queue: Derek Sollenberger <djsollen@google.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Desktop (HP z620)
Before:
mipmap_build_2048x2048_0_gamma 10.5 ms
mipmap_build_2048x2048_1_gamma 77.1 ms
After:
mipmap_build_2048x2048_0_gamma 10.5 ms
mipmap_build_2048x2048_1_gamma 25.1 ms
Pixel XL
Before:
mipmap_build_2048x2048_0_gamma 160 ms
mipmap_build_2048x2048_1_gamma 1.5 s
After:
mipmap_build_2048x2048_0_gamma 160 ms
mipmap_build_2048x2048_1_gamma 313 ms
Also provides marginal performance improvements
for other sRGB downsamples.
BUG=skia:
Change-Id: Icfcd2ccd69676ccf3822db8042a4698e4464bb71
Reviewed-on: https://skia-review.googlesource.com/9386
Commit-Queue: Matt Sarett <msarett@google.com>
Reviewed-by: Mike Klein <mtklein@chromium.org>
|
|
|
|
|
|
|
|
|
|
| |
It's awkward today that it can go a little over 1.0f.
This is already slow, so a clamp won't slow it signficantly.
Change-Id: I9f882804e3ee949d72b7a05ad2cbac51731f6311
Reviewed-on: https://skia-review.googlesource.com/6617
Reviewed-by: Matt Sarett <msarett@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This reverts commit d0fdc0f234b8b55cf418f4db9466d3883deadfb1.
Reason for revert: <INSERT REASONING HERE>
Original change's description:
> SkColorSpaceXform bug fixes
>
> (1) Clamp properly!
>
> Finally came to this realization: clamping in the
> store functions (after gamma encoding) is ridiculous.
> It is impossible to know how to clamp premul values
> to alpha when they are already gamma encoded.
>
> I've moved the clamp out of the store function.
> Whew, this actually makes the code look simpler.
>
> And I expect this to fix some buggy images on Gold!
>
> (2) Correctly handle the memcpy() case.
>
> Looks like this only ever worked for RGBA inputs,
> never got updated when we added BGRA inputs.
>
> This probably flew under the radar because the
> clients are smart enough to avoid performing a
> color xform altogether when the color spaces
> match.
>
> BUG=skia:
>
> Change-Id: I4870048105efcbecc70b4bd5f77c39537006363e
> Reviewed-on: https://skia-review.googlesource.com/5389
> Commit-Queue: Mike Klein <mtklein@chromium.org>
> Reviewed-by: Mike Klein <mtklein@chromium.org>
>
TBR=mtklein@chromium.org,mtklein@google.com,msarett@google.com,reviews@skia.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
Change-Id: Id9e4cfdaa7b30a3841e83c4cde16aa7d33acc0f2
Reviewed-on: https://skia-review.googlesource.com/5457
Commit-Queue: Matt Sarett <msarett@google.com>
Reviewed-by: Matt Sarett <msarett@google.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(1) Clamp properly!
Finally came to this realization: clamping in the
store functions (after gamma encoding) is ridiculous.
It is impossible to know how to clamp premul values
to alpha when they are already gamma encoded.
I've moved the clamp out of the store function.
Whew, this actually makes the code look simpler.
And I expect this to fix some buggy images on Gold!
(2) Correctly handle the memcpy() case.
Looks like this only ever worked for RGBA inputs,
never got updated when we added BGRA inputs.
This probably flew under the radar because the
clients are smart enough to avoid performing a
color xform altogether when the color spaces
match.
BUG=skia:
Change-Id: I4870048105efcbecc70b4bd5f77c39537006363e
Reviewed-on: https://skia-review.googlesource.com/5389
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reviewed-by: Mike Klein <mtklein@chromium.org>
|
|
|
|
|
|
|
|
|
|
|
| |
Every sRGB GM changes, none noticeably.
CQ_INCLUDE_TRYBOTS=skia.primary:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD
Change-Id: I632845aea0f40751639cccbcfde8fa270cae0301
Reviewed-on: https://skia-review.googlesource.com/5275
Reviewed-by: Mike Klein <mtklein@chromium.org>
Commit-Queue: Mike Klein <mtklein@chromium.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
It looks like I'm not going to be able to avoid supporting sRGB G8, I8, 565, 4444, 8888.
(A8 and F16 will always be linear.) This fixes 565, and lays out the rest of the accum_*.
I did a little reorganization to keep things in ascending bit depth, just for sanity.
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=5145
CQ_INCLUDE_TRYBOTS=master.client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
Change-Id: Ib0508e5a4ee1bab2044a76bcabc367841d634cd2
Reviewed-on: https://skia-review.googlesource.com/5145
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
We've just re-noticed this can happen:
1) we have a properly premultiplied linear color;
2) we convert that to sRGB;
3) we convert that back to linear;
4) that color does not appear to be premultiplied.
Removing sk_linear_to_srgb_noclamp(), and thus always clamping to [0,1] here in linear space, does not fix this problem. However, it does help keep it from propagating too badly.
Just double-checked: the older Sk4f pipeline (SkXfermode4f, SkPM4fPriv, etc) already use sk_linear_to_srgb() exclusively, so they're already doing this same clamp.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=4314
Change-Id: I6352eb0ba969eb25674e8441e43bb51e1e1c0df3
Reviewed-on: https://skia-review.googlesource.com/4314
Reviewed-by: Yuqian Li <liyuqian@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Original review here: https://skia-review.googlesource.com/c/2990/
Second attempt here: https://skia-review.googlesource.com/c/3064/
This is the same as the second attempt, but with the change to SkOpts_hsw.cpp left out.
That omitted part is the key piece... this just lands the refactoring.
CQ_INCLUDE_TRYBOTS=master.client.skia:Perf-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Debug-ASAN-Trybot,Perf-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Debug-GN,Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot,Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-Fast-Trybot;master.client.skia.compile:Build-Win-MSVC-x86_64-Debug-Trybot
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=3242
Change-Id: Iaafa793a4854c2c9cd7e85cca3701bf871253f71
Reviewed-on: https://skia-review.googlesource.com/3242
Reviewed-by: Mike Klein <mtklein@chromium.org>
Commit-Queue: Mike Klein <mtklein@chromium.org>
|
|
|
|
|
|
|
|
|
|
|
|
| |
This reverts commit Id0ba250037e271a9475fe2f0989d64f0aa909bae.
crbug.com/654213
Looks like Chrome Canary's picking up Haswell code on non-Haswell machines.
Change-Id: I16f976da24db86d5c99636c472ffad56db213a2a
Reviewed-on: https://skia-review.googlesource.com/3108
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reviewed-by: Mike Klein <mtklein@chromium.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Original review here: https://skia-review.googlesource.com/c/2990/
Changes since:
- simpler implementations of load_tail() / store_tail(): slower, but more obviously correct to all compilers
- fleshed out math ops on Sk8i and Sk8u to make unit tests happy on -Fast bot (where we always have AVX2)
- now storing stage functions as void(*)() to avoid undefined behavior and/or linker problems. This restores 32-bit Windows.
- all AVX2 Sk8x methods are marked always-inline, to avoid linking the "wrong" version on Debug builds.
CQ_INCLUDE_TRYBOTS=master.client.skia:Perf-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Debug-ASAN-Trybot,Perf-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Debug-GN,Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot,Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-Fast-Trybot;master.client.skia.compile:Build-Win-MSVC-x86_64-Debug-Trybot
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=3064
Change-Id: Id0ba250037e271a9475fe2f0989d64f0aa909bae
Reviewed-on: https://skia-review.googlesource.com/3064
Reviewed-by: Mike Klein <mtklein@chromium.org>
Commit-Queue: Mike Klein <mtklein@chromium.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This reverts commit I1c82e5755d8e44cc0b9c6673d04b117f85d71a3a.
Reason for revert: lots of failing bots.
TBR=mtklein@chromium.org,msarett@google.com,reviews@skia.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
Change-Id: I653bed3905187f43196504f19424985fa2a765b5
Reviewed-on: https://skia-review.googlesource.com/3063
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reviewed-by: Mike Klein <mtklein@chromium.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bench runtime changes:
sRGB: 7194 -> 3735 = 1.93x faster
F16: 6531 -> 2559 = 2.55x faster
Instead of building 4x and 1-3x pipelines and then maybe 8x and 1-7x, instead build either the short ones or the long ones, but not both. If we just take care to use a compatible run_pipeline(), there's some cross-module type disagreement but everything works out in the end.
Oddly, a few places that looked like they'd be faster using SkNx_fma() or Sk4f_round()/Sk8f_round() are actually faster the long way, e.g. multiply, add 0.5, truncate. Curious! In all the other places you see here that I've used SkNx_fma(), it's been a significant speedup.
This folds in a couple refactors and cleanups that I've been meaning to do. Hope you don't mind... if find the new code considerably easier to read than the old code.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2990
CQ_INCLUDE_TRYBOTS=master.client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
Change-Id: I1c82e5755d8e44cc0b9c6673d04b117f85d71a3a
Reviewed-on: https://skia-review.googlesource.com/2990
Reviewed-by: Matt Sarett <msarett@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Looks great (imperceptibly different) but ~10% slower on both ARMv8 and x86-64. Probably need to hide the table-or-math logic behind Sk4f/Sk8f unless we find faster math.
I do like the new look of the pipeline stages though. A lot clearer.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2880
CQ_INCLUDE_TRYBOTS=master.client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
Change-Id: I44952237d56ba167445b07d4830eb8959c4d47b7
Reviewed-on: https://skia-review.googlesource.com/2880
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reviewed-by: Matt Sarett <msarett@google.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This clamps to [0,1] premul just before every store to memory.
By making the clamp a stage itself, this design makes it easy to move the clamp
around, to replace it with a debug-only assert-we're-clamped stage for certain
formats, clamp in more places, programatically not clamp, etc. etc.
Before this change, clamping was a little haphazard: store_srgb clamped
R, G and B to [0,1], but not A, and didn't clamp the colors to A. 565
didn't clamp at all.
6 GMs draw subtly differently in sRGB, I think because we've started clamping
colors to alpha to enforce premultiplication better. No changes for 565.
My hope is that now no other stage need ever concern itself with clamping.
So we don't double-clamp, I've added a _noclamp version of sk_linear_to_srgb()
that simply asserts a clamp isn't necessary. This happens to expose the Sk4f
_needs_trunc version that might be useful for power users (*cough* Matt *cough*).
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2178793002
Review-Url: https://codereview.chromium.org/2178793002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Improves performance for xforms toSRGB and to2Dot2. Seems
more optimal to save clamping until the end. That way we
don't stall the mul pipeline with a min/max.
toSRGB: 371us -> 346us
to2Dot2: 404us -> 387us
FWIW, it probably makes sense to clamp inside
sk_linear_to_srgb anyway. If not, we should potentially
provide two versions (one that clamps and one that
doesn't).
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2173803002
CQ_INCLUDE_TRYBOTS=master.client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
Review-Url: https://codereview.chromium.org/2173803002
|
|
|
|
|
|
|
|
|
|
|
|
| |
I basically just ran a big 5-deep for-loop over the five constants here.
This is the first set of coefficients I found that round trips all bytes.
I suspect there are many such sets.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2162063003
CQ_INCLUDE_TRYBOTS=master.client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
Review-Url: https://codereview.chromium.org/2162063003
|
|
|
|
|
|
|
|
|
| |
Rounding is enough. No need for an explicit clamp if the inputs are in range.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2161223002
Review-Url: https://codereview.chromium.org/2161223002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This makes them a little easier to use outside SkColorXform code.
I've added some notes about how best to use them and their eccentricities, and added a test.
Ultimately any software sRGB <-> linear conversion should funnel somehow through here.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2128893002
CQ_EXTRA_TRYBOTS=client.skia.android:Test-Android-GCC-Nexus5-CPU-NEON-Arm7-Release-Trybot;client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
Committed: https://skia.googlesource.com/skia/+/45e58c8807179638980aae8503573b950b844e4c
Review-Url: https://codereview.chromium.org/2128893002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(patchset #5 id:80001 of https://codereview.chromium.org/2128893002/ )
Reason for revert:
Monotonicity assert is failing on ARM. (Different rsqrt() and invert() precision?) Will investigate a bit tomorrow... might reland with the test TODO.
Original issue's description:
> Move sRGB <-> linear conversion components to their own files.
>
> This makes them a little easier to use outside SkColorXform code.
>
> I've added some notes about how best to use them and their eccentricities, and added a test.
>
> Ultimately any software sRGB <-> linear conversion should funnel somehow through here.
>
> BUG=skia:
> GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2128893002
> CQ_EXTRA_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
>
> Committed: https://skia.googlesource.com/skia/+/45e58c8807179638980aae8503573b950b844e4c
TBR=reed@google.com,msarett@google.com,mtklein@chromium.org
# Skipping CQ checks because original CL landed less than 1 days ago.
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:
Review-Url: https://codereview.chromium.org/2131793002
|
|
This makes them a little easier to use outside SkColorXform code.
I've added some notes about how best to use them and their eccentricities, and added a test.
Ultimately any software sRGB <-> linear conversion should funnel somehow through here.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2128893002
CQ_EXTRA_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot
Review-Url: https://codereview.chromium.org/2128893002
|