Our interlaced approach works pretty well for x86, but on ARM we're a
lot better off deinterlacing in loads and reinterlacing in stores.
This leaves the stages mostly looking like the float stages, and cuts
out some awkward parts from the code generation.
Diffs are all invisible. Performance is noticeably better for some
blend modes like Overlay.
Change-Id: Ie599e823602bfd14552de78df44a621aea66e1a2
Reviewed-on: https://skia-review.googlesource.com/40100
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reviewed-by: Florin Malita <fmalita@chromium.org>
We don't really use anything very ARMv8 specific in the 8-bit NEON
stages, so we can just naturally extend what we're doing to ARMv7 too.
Note that unlike the float stages, we're not requiring VFPv4 either,
just NEON. VFPv4 is for FMA and F16<->F32 conversion, both of which are
unnecessary for the integer pipeline.
GMs and perf improvement are similar to the previous ARMv8 change.
Change-Id: Id618801ea1920564c1deee144a640a4133c4505f
Reviewed-on: https://skia-review.googlesource.com/39840
Commit-Queue: Mike Klein <mtklein@chromium.org>
Reviewed-by: Mike Klein <mtklein@chromium.org>
Reviewed-by: Herb Derby <herb@google.com>
This mainly consists of rm origin from GrSurface and the wrapBackEnd*
methods and then re-adding an explicit origin parameter to all the
GrGpu methods that need it.
TBR=bsalomon@google.com
Change-Id: I4248b2a4749ef844da4233ce53b0dc504bc9eb74
Reviewed-on: https://skia-review.googlesource.com/30280
Commit-Queue: Robert Phillips <robertphillips@google.com>
Reviewed-by: Brian Salomon <bsalomon@google.com>
This is a partial revert of https://skia-review.googlesource.com/c/20280,
adding back L32 support for 4f gradients and switching off the legacy
impl.
If it sticks, we should be able to completely delete the legacy gradient
code.
Change-Id: Iaa6d722ea4dfd8e4d959bb76eca815a30ca7098f
Reviewed-on: https://skia-review.googlesource.com/31425
Reviewed-by: Herb Derby <herb@google.com>
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Florin Malita <fmalita@chromium.org>
This reverts commit 6d13575108.
Now with guards for "errors" like this:
external/skia/src/jumper/SkJumper_stages_8bit.cpp:240:50: error:
'memcpy' called with size bigger than buffer
case 12: memcpy(&v, src, 12*sizeof(T)); break;
This code is unreachable and generally removed by Clang's optimizer
anyway... as far as I can tell the code generation diff is arbitrary.
Change-Id: I6216567caaa6166f71258bd25343a09e93892a10
Reviewed-on: https://skia-review.googlesource.com/39961
Reviewed-by: Mike Klein <mtklein@chromium.org>
Commit-Queue: Mike Klein <mtklein@chromium.org>
This reverts commit 08133583d5.
Reason for revert: Blocking Android Autoroller on compile error.
Original change's description:
> 8-bit jumper on armv8
>
> The GM diffs are all minor and what you'd expect.
>
> I did a quick performance sanity check, which also looks fine.
>
> $ out/ok bench rp filter:search=Modulate
> [blendmode_rect_Modulate] 30.2ms @0 32ms @95 32ms @100
> [blendmode_mask_Modulate] 12.6ms @0 12.6ms @95 14.5ms @100
> ~~~>
> [blendmode_rect_Modulate] 11.2ms @0 11.7ms @95 12.4ms @100
> [blendmode_mask_Modulate] 10.5ms @0 23.6ms @95 23.9ms @100
>
> This isn't even really the fastest we can make 8-bit go on ARMv8;
> it's actually much more natural to work de-interlaced there. Lots
> of room to follow up.
>
> Change-Id: I86b1099f6742bcb0b8b4fa153e85eaba9567cbf7
> Reviewed-on: https://skia-review.googlesource.com/39740
> Reviewed-by: Florin Malita <fmalita@chromium.org>
> Commit-Queue: Mike Klein <mtklein@chromium.org>
TBR=mtklein@chromium.org,herb@google.com,fmalita@chromium.org,reed@google.com
Change-Id: I71425d8b7fbb66be5cb50025871dd81358111da4
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Reviewed-on: https://skia-review.googlesource.com/39980
Reviewed-by: Derek Sollenberger <djsollen@google.com>
Commit-Queue: Derek Sollenberger <djsollen@google.com>
a42a4e5ebf..ff161f83ce
$ git log a42a4e5eb..ff161f83c --date=short --no-merges --format='%ad %ae %s'
2017-08-26 jmadill Fix EP generation event output format for uint.
Created with:
roll-dep skia/third_party/externals/angle2
Documentation for the AutoRoller is here:
https://skia.googlesource.com/buildbot/+/master/autoroll/README.md
If the roll is causing failures, see:
http://www.chromium.org/developers/tree-sheriffs/sheriff-details-chromium#TOC-Failures-due-to-DEPS-rolls
CQ_INCLUDE_TRYBOTS=skia.primary:Perf-Win10-MSVC-AlphaR2-GPU-RadeonR9M470X-x86_64-Debug-ANGLE,Perf-Win10-MSVC-NUC5i7RYH-GPU-IntelIris6100-x86_64-Debug-ANGLE,Perf-Win10-MSVC-NUC6i5SYK-GPU-IntelIris540-x86_64-Debug-ANGLE,Perf-Win10-MSVC-NUCD34010WYKH-GPU-IntelHD4400-x86_64-Debug-ANGLE,Perf-Win10-MSVC-ShuttleC-GPU-GTX960-x86_64-Debug-ANGLE,Perf-Win10-MSVC-ZBOX-GPU-GTX1070-x86_64-Debug-ANGLE,Test-Win10-MSVC-AlphaR2-GPU-RadeonR9M470X-x86_64-Debug-ANGLE,Test-Win10-MSVC-NUC5i7RYH-GPU-IntelIris6100-x86_64-Debug-ANGLE,Test-Win10-MSVC-NUC6i5SYK-GPU-IntelIris540-x86_64-Debug-ANGLE,Test-Win10-MSVC-NUCD34010WYKH-GPU-IntelHD4400-x86_64-Debug-ANGLE,Test-Win10-MSVC-ShuttleC-GPU-GTX960-x86_64-Debug-ANGLE,Test-Win10-MSVC-ZBOX-GPU-GTX1070-x86_64-Debug-ANGLE
TBR=djsollen@google.com
Change-Id: I2a87310d1a5a95da10cbc73adeed07a2894cb4ab
Reviewed-on: https://skia-review.googlesource.com/39822
Reviewed-by: angle-deps-roller . <angle-deps-roller@chromium.org>
Commit-Queue: angle-deps-roller . <angle-deps-roller@chromium.org>
The GM diffs are all minor and what you'd expect.
I did a quick performance sanity check, which also looks fine.
$ out/ok bench rp filter:search=Modulate
[blendmode_rect_Modulate] 30.2ms @0 32ms @95 32ms @100
[blendmode_mask_Modulate] 12.6ms @0 12.6ms @95 14.5ms @100
~~~>
[blendmode_rect_Modulate] 11.2ms @0 11.7ms @95 12.4ms @100
[blendmode_mask_Modulate] 10.5ms @0 23.6ms @95 23.9ms @100
This isn't even really the fastest we can make 8-bit go on ARMv8;
it's actually much more natural to work de-interlaced there. Lots
of room to follow up.
Change-Id: I86b1099f6742bcb0b8b4fa153e85eaba9567cbf7
Reviewed-on: https://skia-review.googlesource.com/39740
Reviewed-by: Florin Malita <fmalita@chromium.org>
Commit-Queue: Mike Klein <mtklein@chromium.org>
This was undone in an editor, but didn't get commited.
Change-Id: Id410de0a066b3fe65119d0b72c6f29a1f91d1ebb
Reviewed-on: https://skia-review.googlesource.com/39700
Reviewed-by: Ben Wagner <bungeman@google.com>
Commit-Queue: Ben Wagner <bungeman@google.com>
1) Replace a couple commas with semicolons.
2) Make sure to zero a couple vectors.
1) has no effect on code generation.
2) does add a bunch of self-vxorps, but they're cheap and we already do
the equivalent for <AVX SSE code, and they're in not very
performance-critical routines. We could circle back and guard these
with !defined(JUMPER_IS_OFFLINE) if we really need the vectors to start
uninitialized for speed.
CQ_INCLUDE_TRYBOTS=skia.primary:Build-Debian9-Clang-x86_64-Release-Fast
Change-Id: I1a13f3eb28d664dbc345d71c3adbc62be5ff7c45
Reviewed-on: https://skia-review.googlesource.com/39661
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
Just recalculates these points instead of investing the code
complexity and memory bandwidth in passing them around.
Bug: skia:
Change-Id: Ib6fc7af49363469de91b4c59baf238015045d79c
Reviewed-on: https://skia-review.googlesource.com/39540
Reviewed-by: Greg Daniel <egdaniel@google.com>
Commit-Queue: Chris Dalton <csmartdalton@google.com>
This avoids the dangerous overload problem of
growToInclude(0, 0)
matching to (const SkPoint[], count) rather than growToInclude(x, y)
Bug: skia:
Change-Id: Iaba8b1a579638ff363fde62e4e3004052dd2b2ac
Reviewed-on: https://skia-review.googlesource.com/39501
Reviewed-by: Ben Wagner <bungeman@google.com>
Commit-Queue: Mike Reed <reed@google.com>
The baseline compiled into Skia is now pretty much identical.
Minor diffs due to the offline code using -ffp-contract=fast, and the
baseline not. Explicit calls to fma() are still FMAs, but we're no
longer letting the compiler uncover FMAs we didn't explicitly call out.
If this goes well, we should be able to turn on the 8-bit pipeline.
Change-Id: I8f73157cfce7373574c20f6435fe86b46477afa9
Reviewed-on: https://skia-review.googlesource.com/39520
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
This was created by looking at warnings produced by clang's
-Wzero-as-null-pointer-constant. This updates most issues in
Skia code. However, there are places where GL and Vulkan want
pointer values which are explicitly 0, external headers which
use NULL directly, and possibly more uses in un-compiled
sources (for other platforms).
Change-Id: Id22fbac04d5c53497a53d734f0896b4f06fe8345
Reviewed-on: https://skia-review.googlesource.com/39521
Reviewed-by: Mike Reed <reed@google.com>
Commit-Queue: Ben Wagner <bungeman@google.com>
Cleans up calc_inverse_transpose_power_basis_matrix and makes it
publicly visible.
Bug: skia:
Change-Id: I568c2b8518c74931962ece23ed07490e7e10e94b
Reviewed-on: https://skia-review.googlesource.com/39180
Commit-Queue: Chris Dalton <csmartdalton@google.com>
Reviewed-by: Greg Daniel <egdaniel@google.com>
Whether JUMPER is defined is starting to get a little overloaded:
- are we compiling offline (defined) or as part of Skia (!defined)?
- are we using Clang vector extensions (defined) or scalars (!defined)?
This splits JUMPER into these two separate concerns:
- JUMPER_IS_OFFLINE
- JUMPER_IS_SCALAR, JUMPER_IS_NEON, JUMPER_IS_AVX2, etc.
The upshot is that we'll now use Clang vector extensions when available
for our "portable" baseline. On x86-64 and ARMv8 compiled by Clang,
we're guaranteed to pick up SSE2 and NEON respectively. Our -Fast
bot should even get all the way to AVX2.
Another CL will do some refactoring in SkJumper to remove the redundant
copies of guaranteed vector code on x86-64 and ARMv8. I didn't want to
do that here yet to demonstrate that there is zero effect on the .S
files from this CL.
Change-Id: Ib5e8f00b35e8721b2cc7180e294840ffaf9dddce
Reviewed-on: https://skia-review.googlesource.com/39500
Reviewed-by: Herb Derby <herb@google.com>
Commit-Queue: Mike Klein <mtklein@chromium.org>
Enough ccpr-specific geometry code is in flight that it feels like it
should have its own file.
Bug: skia:
Change-Id: I99ef620a7dc35178cf774b3a4ec6159d46f401c7
Reviewed-on: https://skia-review.googlesource.com/39162
Commit-Queue: Chris Dalton <csmartdalton@google.com>
Reviewed-by: Brian Salomon <bsalomon@google.com>
Motivated by wanting to speed-up A8 blits in general (and at the moment, aarect blits). More to come in these areas.
Bug: skia:
Change-Id: I45e8ef951b8e89a825af72b1918049be10920137
Reviewed-on: https://skia-review.googlesource.com/39401
Reviewed-by: Yuqian Li <liyuqian@google.com>
Commit-Queue: Mike Reed <reed@google.com>
If the gamma is linear, the corresponding LUT for adjusting colors
is not initialized. This change takes that into account when computing
distance adjustments for SDF text.
Change-Id: I7ca1410bb27cf29ef08ccd666297bf5c3cd3dcdd
Reviewed-on: https://skia-review.googlesource.com/38940
Reviewed-by: Brian Salomon <bsalomon@google.com>
Commit-Queue: Jim Van Verth <jvanverth@google.com>
generate method links from
fiddle names to keep them
consistent and unique.
Docs-Preview: https://skia.org/?cl=38727
Bug: skia:6898
Change-Id: I3434801b46002a3a9095e007d456e9e871307304
Reviewed-on: https://skia-review.googlesource.com/38727
Commit-Queue: Cary Clark <caryclark@skia.org>
Reviewed-by: Cary Clark <caryclark@skia.org>
This is then used when need to update GPU only buffers with data of size
greater than 65536. We create a temporary transfer buffer and then copy
that buffer into our GPU buffer.
Bug: skia:
Change-Id: I4bb9cb660f2ac1ccbbd1b508bb4ca6876342136f
Reviewed-on: https://skia-review.googlesource.com/38725
Reviewed-by: Jim Van Verth <jvanverth@google.com>
Commit-Queue: Greg Daniel <egdaniel@google.com>
qualify bookmaker links to remove
file reference if intra-file and
add class reference if part of
a class
TBR=caryclark@google.com
Docs-Preview: https://skia.org/?cl=38722
Bug: skia: 6898
Change-Id: Ie0548485a6e3f596efc0f15b819bd5060e983a5b
Reviewed-on: https://skia-review.googlesource.com/38722
Reviewed-by: Cary Clark <caryclark@skia.org>
Commit-Queue: Cary Clark <caryclark@skia.org>
This is a prerequisite for being able to resize the atlas with impunity.
Change-Id: Iccc9c7ced43f38a7d8483a7bd12a458d59a3453a
Reviewed-on: https://skia-review.googlesource.com/38362
Reviewed-by: Jim Van Verth <jvanverth@google.com>
Commit-Queue: Robert Phillips <robertphillips@google.com>
The tiny path added to PathTest.cpp has
tinier cross products (e.g. 1e-12)
so appears to be a series of unbending
lines as far as getConvexity is concerned.
This point fix looks for paths that
do not bend left or right or go backwards,
but do have a bounds, and calls them
concave.
A better fix may be to consider empty
and degenerate paths to be concave
instead of convex; I don't know if
anyone relies on the existing behavior.
Another better fix may be to change
the math to compute the path turns
even though the numbers are very small;
on the surface, very difficult.
R=bsalomon@google.com,reed@google.com
Bug:755839
Change-Id: Ie2280f3f0b95fecab2899f5fc579fd39258e0647
Reviewed-on: https://skia-review.googlesource.com/38720
Reviewed-by: Brian Salomon <bsalomon@google.com>
Commit-Queue: Cary Clark <caryclark@google.com>
