We used to step at a 4-pixel stride as long as possible, then run up to 3 times, one pixel at a time. Now replace those 1-at-a-time runs with a single tail stamp if there are 1-3 remaining pixels.
This style is simply more efficient: e.g. we'll blend and lerp once for 3 pixels instead of 3 times. This should make short blits significantly more efficient. It's also more future-oriented... AVX+ on Intel and SVE on ARM support masked loads and stores, so we can do the entire tail in one direct step.
This also makes it possible to re-arrange the code a bit to encapsulate each stage better. I think generally this code reads more clearly than the old code, but YMMV. I've arranged things so you write one function, but it's compiled into two specializations, one for tail=0 (Body) and one for tail>0 (Tail). It's pretty tidy.
For now I've just burned a register to pass around tail. It's 2 bits now, maybe soon 3 with AVX, and capped at 4 for even the craziest new toys, so there are plenty of places we can pack it if we want to get clever.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2717
Change-Id: I45852a3e5d4c5b5e9315302c46601aee0d32265f
Reviewed-on: https://skia-review.googlesource.com/2717
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reason for revert:
Regression on displacement GM when sRGB support is lacking.
Original issue's description:
> Tag checkerboard bitmaps as sRGB
>
> Significantly reduces the diff between legacy and sRGB/F16 on about 25
> GMs. This is just the biggest piece of low-hanging fruit. Many GMs create
> N32 raster surfaces to procedurally generate source textures, and I'd like
> to fix all of them. It's much easier to reason about the GMs (is sRGB
> doing the right thing) when everything is tagged like this - the only
> expected differences are due to filtering and blending.
>
> BUG=skia:
> GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2368933003
>
> Committed: https://skia.googlesource.com/skia/+/fe843cea499ba163d53281425af210b1887d28e7TBR=mtklein@google.com,reed@google.com,robertphillips@google.com
# Not skipping CQ checks because original CL landed more than 1 days ago.
BUG=skia:
Review-Url: https://codereview.chromium.org/2375063002
Unlike nanobench this tool has no purpose when built in Debug mode.
Just don't let it happen.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2718
Change-Id: Iaa7b8c44d46024485d4f5ce3d9c3e33d865b99d7
Reviewed-on: https://skia-review.googlesource.com/2718
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
Gradients (and other shaders) are going to end up serializing this
particular color space very frequently, so we want a shorthand way of
writing it out. I think it's also helpful to have a clearer way of
creating it (vs. NewNamed(kSRGB_Named)->makeLinearGamma()).
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2377763002
Review-Url: https://codereview.chromium.org/2377763002
Today if you use the simple SK_RASTER_STAGE interface to build a pipeline, each stage you add calls into a next stage. The last stage you add calls into a special backstop stage JustReturn that, well, just returns, ending the pipeline.
This adds last(), which cuts that last stage off the pipeline. Instead, the stage you add using last() returns directly, ending the pipeline itself without jumping into JustReturn.
This reduces the overhead of using the pipelined version of SkRasterPipelineBench from ~25% to ~20% on my desktop.
Also, add docs.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2713
Change-Id: I11469378e2765c6e34db52eb3eef648d6612da3f
Reviewed-on: https://skia-review.googlesource.com/2713
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
I'm not seeing any problems with these locally. Perhaps the bots have something to say.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2709
Change-Id: I6f0c7045c8f270efcd71d837f22a40e9f9d3e9b7
Reviewed-on: https://skia-review.googlesource.com/2709
Commit-Queue: Ben Wagner <bungeman@google.com>
Reviewed-by: Ben Wagner <bungeman@google.com>
I don't know _why_ Clang would like these .inc files to have a newline at the end of the file, but it seems a harmless way to silence the warning.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2711
Change-Id: I6c530ee5096c48c91ddf322aca916e70a0dd770b
Reviewed-on: https://skia-review.googlesource.com/2711
Reviewed-by: Ethan Nicholas <ethannicholas@google.com>
I've even found the code that's making this happen, just don't know why.
I've added a test to assert that it's safe to assume malloc() is 8-byte aligned.
Test should compile this time.
CQ_INCLUDE_TRYBOTS=master.client.skia.android:Test-Android-Clang-NexusPlayer-CPU-Moorefield-x86-Release-GN_Android-Trybot
Change-Id: I48714b99670c20704adf4f7f216da0d60d7d9bcd
Reviewed-on: https://skia-review.googlesource.com/2662
Reviewed-on: https://skia-review.googlesource.com/2703
Reviewed-by: Mike Klein <mtklein@chromium.org>
Commit-Queue: Mike Klein <mtklein@chromium.org>
This reverts commit If8a2898ab3a77571622eb125c97f676e029b902c.
Reason for revert:
../../../../../work/skia/tests/OverAlignedTest.cpp: In function 'void test_OverAligned(skiatest::Reporter*, sk_gpu_test::GrContextFactory*)':
../../../../../work/skia/tests/OverAlignedTest.cpp:19:33: error: invalid operands of types 'void*' and 'int' to binary 'operator&'
REPORTER_ASSERT(r, SkIsAlign8(p));
^
ninja: build stopped: subcommand failed.
Original issue's description:
> Focus -Wno-over-aligned to just 32-bit x86 Android.
>
> I've even found the code that's making this happen, just don't know why.
> I've added a test to assert that it's safe to assume malloc() is 8-byte aligned.
>
> BUG=skia:
>
> GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2662
>
> CQ_INCLUDE_TRYBOTS=master.client.skia.android:Test-Android-Clang-NexusPlayer-CPU-Moorefield-x86-Release-GN_Android-Trybot
>
TBR=mtklein@chromium.org,bungeman@google.com
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
Change-Id: Ic9b30ce980d8d5155528a6f2b4e1913e5fa95dc0
Reviewed-on: https://skia-review.googlesource.com/2702
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Mike Reed <reed@google.com>
I've even found the code that's making this happen, just don't know why.
I've added a test to assert that it's safe to assume malloc() is 8-byte aligned.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2662
CQ_INCLUDE_TRYBOTS=master.client.skia.android:Test-Android-Clang-NexusPlayer-CPU-Moorefield-x86-Release-GN_Android-Trybot
Change-Id: If8a2898ab3a77571622eb125c97f676e029b902c
Reviewed-on: https://skia-review.googlesource.com/2662
Commit-Queue: Ben Wagner <bungeman@google.com>
Reviewed-by: Ben Wagner <bungeman@google.com>
Reason for revert:
Let's see if reverting this helps the roll.
Original issue's description:
> My take on SkAlign changes.
>
> Like the other change, it makes SkAlignN(x) macros work for pointers, and makes the macros themselves just syntax sugar for SkAlign<N>(x). We can still decide if we want to sed away the macros independently.
>
> This just does it in a somewhat less repetitive way, and adds some tests.
>
> BUG=skia:
> GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2368293002
>
> No public API changes.
> TBR=reed@google.com
>
> Committed: https://skia.googlesource.com/skia/+/e1a5f4e292384046678edc5c1e360b3e13dc118cTBR=cblume@chromium.org,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/2372083002
The warning looks to helpfully pre-warn about possible link failures, but it's warning exclusively in places where we're doing things right.
The worst that happens ignoring this warning is a missing-symbol linker error.
I've taken the opportunity to batch in a few other de-escalations:
- Wconditional-uninitialized is done better by MSAN
- It'll take some work to dig Wformat-literal out of our shader compiler, but nothing looks unsafe
- Most of Wshift-sign-overflow is 0xff << 24. Don't want to ban that.
- Wdeprecated is mostly warning about features C++11 technically deprecated that might be removed in later releases. Punt!
- Wcovered-switch-default is pretty much the opposite of what we want.
- Wshadow is triggering too often to fix quickly. Probably mostly false positives.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2620
Change-Id: I20a85a77d2e19ed05a536b23037bd988350f821e
Reviewed-on: https://skia-review.googlesource.com/2620
Reviewed-by: Ben Wagner <bungeman@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
It was not a fan of this (blatant) aliasing.
I suspect this best_non_simd_srcover_srgb_srgb() function has several
other aliasing issues that use undefined behavior, but this is all it's
complaining about for now.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2606
Change-Id: I25a8800e810bccf5068c8a10e9c8c8f565e57304
Reviewed-on: https://skia-review.googlesource.com/2606
Commit-Queue: Mike Klein <mtklein@chromium.org>
Commit-Queue: Herb Derby <herb@google.com>
Reviewed-by: Herb Derby <herb@google.com>
Significantly reduces the diff between legacy and sRGB/F16 on about 25
GMs. This is just the biggest piece of low-hanging fruit. Many GMs create
N32 raster surfaces to procedurally generate source textures, and I'd like
to fix all of them. It's much easier to reason about the GMs (is sRGB
doing the right thing) when everything is tagged like this - the only
expected differences are due to filtering and blending.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2368933003
Review-Url: https://codereview.chromium.org/2368933003
This cleans up 3 remaining sites using , that probably meant ;
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2605
Change-Id: I5e48bcd85d72a205d2b0c860461dab1ec793dd18
Reviewed-on: https://skia-review.googlesource.com/2605
Reviewed-by: Brian Salomon <bsalomon@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
Like the other change, it makes SkAlignN(x) macros work for pointers, and makes the macros themselves just syntax sugar for SkAlign<N>(x). We can still decide if we want to sed away the macros independently.
This just does it in a somewhat less repetitive way, and adds some tests.
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2368293002
No public API changes.
TBR=reed@google.com
Review-Url: https://codereview.chromium.org/2368293002
