aboutsummaryrefslogtreecommitdiffhomepage
path: root/src/opts
Commit message (Collapse)AuthorAge
* refine NEON checks in raster pipelineGravatar Mike Klein2018-07-25
| | | | | | | | | | | | | | | | | This replaces most defined(__ARM_NEON) with defined(JUMPER_IS_NEON), which is defined(__ARM_NEON) && defined(__clang__). When compiled by Clang like our bots and primary users, this is a noop, but will avoid some of the NEON paths for compilers defining __ARM_NEON that are not Clang. Bug: skia:8178 Change-Id: Ifaea940c95b61d2fefadbd4e752cc477c571eafa Reviewed-on: https://skia-review.googlesource.com/143301 Commit-Queue: Herb Derby <herb@google.com> Auto-Submit: Mike Klein <mtklein@chromium.org> Reviewed-by: Herb Derby <herb@google.com>
* collapse parametric_{r,g,b} into parametric, remove _a and gamma_dstGravatar Mike Klein2018-07-11
| | | | | | | | | | | | | parametric_a and gamma_dst were unused outside of unit tests. In all other cases, we always use parametric_{r,g,b} together and always pass them the same argument. So we can collapse them into a single stage like gamma and to/from_srgb. Change-Id: I08cea896c7744f97b4f4bf9e029f5d643e45e177 Reviewed-on: https://skia-review.googlesource.com/140576 Commit-Queue: Mike Klein <mtklein@chromium.org> Reviewed-by: Brian Osman <brianosman@google.com>
* Reland "transform paint color to dst colorspace"Gravatar Mike Klein2018-07-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is a reland of 6eb36214461794626291a01c3150f7239e4a91a3 I've added an unbounded_uniform_color stage to allow lowp to keep working when colors are in range and to force floats when colors go out of range, most commonly in "narrow" config. Original change's description: > transform paint color to dst colorspace > > Hopefully I can start to knock off effects that need > to be converted to dst colorspace one at a time now. > > My rough list is, > - paint color <---- > - image shader > - sprite blitter > - gradients? > - mode color filter > - lighting color filter > - high contrast filter > - toSRGB color filter > > This change cuts the diffs between 8888 and srgb from > ~540 to ~500. > > I left myself a note about not being able to interpret null > to sRGB at a high level yet. That'd cause a ton of 8888 diffs, > and I think SkColorSpaceXformCanvas diffs too. > > Change-Id: Id66a63e0e92130927f267719aeccb8bbcd92973a > Reviewed-on: https://skia-review.googlesource.com/140244 > Reviewed-by: Brian Osman <brianosman@google.com> > Commit-Queue: Mike Klein <mtklein@google.com> Change-Id: I56dbf3ad3547d668e4b41f3126ef61d70b295f7c Reviewed-on: https://skia-review.googlesource.com/140460 Reviewed-by: Mike Klein <mtklein@chromium.org> Commit-Queue: Mike Klein <mtklein@chromium.org>
* update (non-sprite) image shader color managementGravatar Mike Klein2018-07-10
| | | | | | | | | | | | | | | | | Just another little step... diffs down to ~450 from ~500. The A8 handling has changed a little, keeping the paint color in sRGB just to make the append_misc() logic a bit more streamlined. I may want to refactor things a little later so that I can get an easy signal to use to_srgb and from_srgb stages instead of sending them through the generic parametric stages. Change-Id: Iefff3206b06a3aa7d81f85fd169272b6ac9c20e0 Reviewed-on: https://skia-review.googlesource.com/140250 Reviewed-by: Brian Osman <brianosman@google.com> Commit-Queue: Mike Klein <mtklein@google.com>
* basic first pass at RGBA F32 supportGravatar Mike Klein2018-06-26
| | | | | | | | | | | | | Draws basically the same as f16. The existing load_f32, load_f32_dst, and store_f32 stages all had the same bug that we'd never noticed because dy was always 0 until now. Change-Id: Ibbd393fa1acc5df414be4cdef0f5a9d11dcccdb3 Reviewed-on: https://skia-review.googlesource.com/137585 Commit-Queue: Mike Klein <mtklein@chromium.org> Reviewed-by: Brian Osman <brianosman@google.com> Reviewed-by: Mike Reed <reed@google.com>
* Stop using SkTSwap.Gravatar Ben Wagner2018-06-19
| | | | | | | | | | | | | Use std::swap instead. It does not appear that any external user specializes SkTSwap, but some may still use it. This removes all use in Skia so that SkTSwap can later be removed in a smaller CL. After that the <utility> include can be removed from SkTypes.h. Change-Id: If03d4ee07dbecda961aa9f0dc34d171ef5168753 Reviewed-on: https://skia-review.googlesource.com/135578 Reviewed-by: Hal Canary <halcanary@google.com> Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Ben Wagner <bungeman@google.com>
* remove lowp bilerp_clamp_8888 stageGravatar Mike Klein2018-06-18
| | | | | | | | | | | | | | | | I encountered some trouble getting this turned on in Chromium, so we've got some undesirable skew between what's tested and shipping. No one has complained about software rasterization perf to me lately, so let's just drop this, keeping the already-launched highp bilerp_clamp_8888 stage. Change-Id: I9a6557d9b468765989f97369a976c5028f81eab3 Reviewed-on: https://skia-review.googlesource.com/135563 Commit-Queue: Mike Klein <mtklein@chromium.org> Commit-Queue: Florin Malita <fmalita@chromium.org> Auto-Submit: Mike Klein <mtklein@chromium.org> Reviewed-by: Florin Malita <fmalita@chromium.org>
* Revert "Revert "SkTypes: extract SkTo""Gravatar Hal Canary2018-06-14
| | | | | | | | | | | | | | | | This reverts commit fdcfb8b7c23fbf18f872d2c31d27978235033876. > Original change's description: > > SkTypes: extract SkTo > > > > Change-Id: I8de790d5013db2105ad885fa2683303d7c250b09 > > Reviewed-on: https://skia-review.googlesource.com/133620 > > Reviewed-by: Mike Klein <mtklein@google.com> Change-Id: Ida74fbc5c21248a724a5edbf9fae18a33bcb23aa Reviewed-on: https://skia-review.googlesource.com/134506 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Hal Canary <halcanary@google.com>
* Revert "SkTypes: extract SkTo"Gravatar Hal Canary2018-06-13
| | | | | | | | | | | | | | | | | | | | | | | This reverts commit 2a2f67592602b18527bc3fd449132d420cd5b62e. Reason for revert: this appears to be what is holding up the Chrome roll. Original change's description: > SkTypes: extract SkTo > > Change-Id: I8de790d5013db2105ad885fa2683303d7c250b09 > Reviewed-on: https://skia-review.googlesource.com/133620 > Reviewed-by: Mike Klein <mtklein@google.com> TBR=mtklein@google.com,halcanary@google.com No-Presubmit: true No-Tree-Checks: true No-Try: true Change-Id: Iafd738aedfb679a23c061a51afe4b98a8d4cdfae Reviewed-on: https://skia-review.googlesource.com/134504 Reviewed-by: Hal Canary <halcanary@google.com> Commit-Queue: Hal Canary <halcanary@google.com>
* avoid immintrin.h in SkNx_sse.hGravatar Mike Klein2018-06-12
| | | | | | | | | | | | | | | | | | | | | | | Including <immintrin.h> is an easy way to get all the supported Intel intrinsics for the current build flags, and for intrinsics since AVX, the only supported way. But, including immintrin.h can pull in more headers than needed, and for pieces of code like SkNx.h, that extra include cost is measurable. Here we'll include only the intrisnics we'll use. $ gn clean out && time ninja -C out Before: 131.57 real 4207.95 user 249.18 sys After: 125.60 real 3988.18 user 241.64 sys Seems like a win. Change-Id: I81543202d889be403ff0aa393c13c19ed89c5373 Reviewed-on: https://skia-review.googlesource.com/134325 Reviewed-by: Hal Canary <halcanary@google.com> Commit-Queue: Hal Canary <halcanary@google.com> Auto-Submit: Mike Klein <mtklein@chromium.org>
* SkTypes: extract SkToGravatar Hal Canary2018-06-12
| | | | | | Change-Id: I8de790d5013db2105ad885fa2683303d7c250b09 Reviewed-on: https://skia-review.googlesource.com/133620 Reviewed-by: Mike Klein <mtklein@google.com>
* Clean up a few IWYU issuesGravatar Mike Klein2018-06-11
| | | | | | | | | Spun off from the SkTFitsIn CL. Change-Id: I686d680df6a36ebc02db3847ad5e2cedcbcd67ef Reviewed-on: https://skia-review.googlesource.com/134083 Reviewed-by: Mike Klein <mtklein@chromium.org> Commit-Queue: Mike Klein <mtklein@chromium.org>
* Implement Sk2f::floorGravatar Chris Dalton2018-06-08
| | | | | | | | Bug: skia: Change-Id: Id40e7165a338d321df71a1852b48eb2570ecd75b Reviewed-on: https://skia-review.googlesource.com/133460 Commit-Queue: Mike Klein <mtklein@google.com> Reviewed-by: Mike Klein <mtklein@google.com>
* remove linear-blended sRGB dst support in softwareGravatar Mike Klein2018-06-06
| | | | | | | | | | | | | | | | | This is the mechanism we'd want to add back if we add an sRGBA SkColorType. This will break the DM "srgb" config hard. Landing this first should help flush out GMs that are incidentally using sRGB offscreens. Updated tests/AnimatedImageTest.cpp to avoid linear sRGB 8888 surfaces. CQ_INCLUDE_TRYBOTS=master.tryserver.blink:linux_trusty_blink_rel Change-Id: Idb5035cf4d60fcd1dc24c303d43a406fc4a603fa Reviewed-on: https://skia-review.googlesource.com/132261 Commit-Queue: Mike Klein <mtklein@chromium.org> Reviewed-by: Brian Osman <brianosman@google.com>
* fix a weird edge case in to_srgb stageGravatar Mike Klein2018-06-01
| | | | | | | | | | | | | | I just uncovered this by porting the Chromecast bots from an old GCC to an old Clang. In to_srgb() we tune our constants so that 1.0f maps to exactly 1.0f, but because both JUMPER_IS_NEON and JUMPER_IS_SCALAR were defined, we picked the NEON values instead of the scalar values we want. Undefining JUMPER_IS_NEON when JUMPER_IS_SCALAR should do the trick. Change-Id: I6c6f76b78b3419e204c0b4df351459baf05315bc Reviewed-on: https://skia-review.googlesource.com/131582 Reviewed-by: Brian Osman <brianosman@google.com> Commit-Queue: Mike Klein <mtklein@chromium.org>
* remove map() from SkRasterPipeline_opts.hGravatar Mike Klein2018-05-31
| | | | | | | | | | | It seems to be confusing some obscure build configuration in Google3. I don't really mind writing these out longform. Change-Id: I78e82d9fa18726d89d206e692fd260317c5f8686 Reviewed-on: https://skia-review.googlesource.com/131108 Auto-Submit: Mike Klein <mtklein@chromium.org> Commit-Queue: Florin Malita <fmalita@chromium.org> Reviewed-by: Florin Malita <fmalita@chromium.org>
* Reland "start cleaning up non-skcms SkColorSpaceXforms"Gravatar Mike Klein2018-05-23
| | | | | | | | | | | | | | | | | | | | | | | | This is a reland of 339133f82c30cd3080672db28e6f72c894cba05a Original change's description: > start cleaning up non-skcms SkColorSpaceXforms > > I think this gets rid of > - SkColorSpaceXform_Base > - SkColorSpaceXform_XYZ > - SkColorSpaceXform_A2B > and lots of support code. Might be more left to clean up? > > Change-Id: I560d974d1e879dfd6a63ee2244a3dd88bd495c8a > Reviewed-on: https://skia-review.googlesource.com/129512 > Commit-Queue: Brian Osman <brianosman@google.com> > Auto-Submit: Mike Klein <mtklein@chromium.org> > Reviewed-by: Brian Osman <brianosman@google.com> Change-Id: I33ee0d8bcfd72c401823a2e7d5168c9ecc9a5181 Reviewed-on: https://skia-review.googlesource.com/129624 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Mike Klein <mtklein@google.com>
* Revert "start cleaning up non-skcms SkColorSpaceXforms"Gravatar Mike Klein2018-05-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 339133f82c30cd3080672db28e6f72c894cba05a. Reason for revert: broke NinePatchDrawableTest.testGetPadding? stranger things have happened. Original change's description: > start cleaning up non-skcms SkColorSpaceXforms > > I think this gets rid of > - SkColorSpaceXform_Base > - SkColorSpaceXform_XYZ > - SkColorSpaceXform_A2B > and lots of support code. Might be more left to clean up? > > Change-Id: I560d974d1e879dfd6a63ee2244a3dd88bd495c8a > Reviewed-on: https://skia-review.googlesource.com/129512 > Commit-Queue: Brian Osman <brianosman@google.com> > Auto-Submit: Mike Klein <mtklein@chromium.org> > Reviewed-by: Brian Osman <brianosman@google.com> TBR=mtklein@chromium.org,brianosman@google.com Change-Id: I9e76195481b8658b34936aeece278d81c286c0fa No-Presubmit: true No-Tree-Checks: true No-Try: true Reviewed-on: https://skia-review.googlesource.com/129680 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Mike Klein <mtklein@google.com>
* start cleaning up non-skcms SkColorSpaceXformsGravatar Mike Klein2018-05-22
| | | | | | | | | | | | | | I think this gets rid of - SkColorSpaceXform_Base - SkColorSpaceXform_XYZ - SkColorSpaceXform_A2B and lots of support code. Might be more left to clean up? Change-Id: I560d974d1e879dfd6a63ee2244a3dd88bd495c8a Reviewed-on: https://skia-review.googlesource.com/129512 Commit-Queue: Brian Osman <brianosman@google.com> Auto-Submit: Mike Klein <mtklein@chromium.org> Reviewed-by: Brian Osman <brianosman@google.com>
* rewrite while to for loop to avoid last incrementGravatar Mike Reed2018-05-09
| | | | | | | | | | | | Can we efficiently avoid the last "increment" step for these sorts of loops? We are always calculating one more value than we actually need (we do this everywhere we forward-difference something). Bug: oss-fuzz:8146 Cq-Include-Trybots: skia.primary:Test-Debian9-Clang-GCE-CPU-AVX2-x86_64-Release-All-SKNX_NO_SIMD Change-Id: I8b2838cc51370d53b8854191fce9ff87e5dc669d Reviewed-on: https://skia-review.googlesource.com/127042 Commit-Queue: Mike Reed <reed@google.com> Reviewed-by: Cary Clark <caryclark@google.com>
* avoid overflow by using tmp 64bitsGravatar Mike Reed2018-04-17
| | | | | | | | | Bug: oss-fuzz:7746 Cq-Include-Trybots: skia.primary:Test-Debian9-Clang-GCE-CPU-AVX2-x86_64-Release-All-SKNX_NO_SIMD Change-Id: Iba3ea50331fa06ca201ac316e33d4f79ab8ef459 Reviewed-on: https://skia-review.googlesource.com/121802 Reviewed-by: Mike Reed <reed@google.com> Commit-Queue: Mike Reed <reed@google.com>
* Reland "low-hanging bilerp_clamp_8888 wins"Gravatar Mike Klein2018-04-17
| | | | | | | | | | | | | | | | | | | | | | | | | This is a reland of f946b41643e049f3b81f40316373ad22e1518818 Patches since the original make sure the sample area sums to 1. Original change's description: > low-hanging bilerp_clamp_8888 wins > > - support sampling bgra too > - lowp impl > > Bug: skia:7810 > > Change-Id: I21db805483f612024802f2b508c140c42a029c54 > Reviewed-on: https://skia-review.googlesource.com/121582 > Commit-Queue: Mike Klein <mtklein@google.com> > Reviewed-by: Florin Malita <fmalita@chromium.org> Bug: skia:7810 Change-Id: If20d31b4f8c4163bdb567b4f15a62035265b1b30 Reviewed-on: https://skia-review.googlesource.com/121464 Reviewed-by: Mike Klein <mtklein@chromium.org> Commit-Queue: Mike Klein <mtklein@chromium.org>
* Revert "low-hanging bilerp_clamp_8888 wins"Gravatar Mike Klein2018-04-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit f946b41643e049f3b81f40316373ad22e1518818. Reason for revert: nervous diffs Original change's description: > low-hanging bilerp_clamp_8888 wins > > - support sampling bgra too > - lowp impl > > Bug: skia:7810 > > Change-Id: I21db805483f612024802f2b508c140c42a029c54 > Reviewed-on: https://skia-review.googlesource.com/121582 > Commit-Queue: Mike Klein <mtklein@google.com> > Reviewed-by: Florin Malita <fmalita@chromium.org> TBR=mtklein@chromium.org,mtklein@google.com,fmalita@chromium.org Change-Id: Id91d583151091a082a2d3f301d85f3acb12f4b19 No-Presubmit: true No-Tree-Checks: true No-Try: true Bug: skia:7810 Reviewed-on: https://skia-review.googlesource.com/121589 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Mike Klein <mtklein@google.com>
* low-hanging bilerp_clamp_8888 winsGravatar Mike Klein2018-04-16
| | | | | | | | | | | | - support sampling bgra too - lowp impl Bug: skia:7810 Change-Id: I21db805483f612024802f2b508c140c42a029c54 Reviewed-on: https://skia-review.googlesource.com/121582 Commit-Queue: Mike Klein <mtklein@google.com> Reviewed-by: Florin Malita <fmalita@chromium.org>
* Implement Sk2f Load2Gravatar Chris Dalton2018-04-12
| | | | | | | | Bug: skia: Change-Id: I7d37a76bcb9df9c5a1c22eb1b0277387816df7bb Reviewed-on: https://skia-review.googlesource.com/120602 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Chris Dalton <csmartdalton@google.com>
* Implement Sk4f min/maxGravatar Chris Dalton2018-04-12
| | | | | | | | Bug: skia: Change-Id: Icf235dea81e9f125c1c8590ec87cb3591393036c Reviewed-on: https://skia-review.googlesource.com/120281 Commit-Queue: Mike Klein <mtklein@google.com> Reviewed-by: Mike Klein <mtklein@google.com>
* Implement Sk2f::Store2Gravatar Chris Dalton2018-04-09
| | | | | | | | Bug: skia: Change-Id: Ifea5957458e5547ee428809d9599286e70f3f8f9 Reviewed-on: https://skia-review.googlesource.com/119860 Commit-Queue: Mike Klein <mtklein@google.com> Reviewed-by: Mike Klein <mtklein@google.com>
* specialize arm64 allTrue()/anyTrue()Gravatar Mike Klein2018-03-26
| | | | | | | | | | | | | | | | | aarch64 added vector-wise add/mul/min/max instructions. We can use min and max to implement allTrue() and anyTrue(), respectively. (This CL is mostly so I don't forget these intrinsics exist.) In assembly, these actually compile to two instructions, the folding operation into a vector register, then a move from the vector register to a general purpose register. Change-Id: Ia6a999ac250740de765e871094e911979a8711c7 Reviewed-on: https://skia-review.googlesource.com/116482 Reviewed-by: Chris Dalton <csmartdalton@google.com> Commit-Queue: Mike Klein <mtklein@chromium.org>
* Revert "Implement Sk2f::Store2"Gravatar Chris Dalton2018-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 8a8a8e9dd5c47f3fc930064bd030790f98af27af. Reason for revert: Needs non-SIMD impl Original change's description: > Implement Sk2f::Store2 > > Bug: skia: > Change-Id: Ieedd05ced376a7604936e9d2729fc20a8669496e > Reviewed-on: https://skia-review.googlesource.com/115531 > Commit-Queue: Chris Dalton <csmartdalton@google.com> > Reviewed-by: Mike Klein <mtklein@google.com> TBR=mtklein@google.com,csmartdalton@google.com Change-Id: I8dfbd87c5871b041a4fc6ef3816f121c72083a20 No-Presubmit: true No-Tree-Checks: true No-Try: true Bug: skia: Reviewed-on: https://skia-review.googlesource.com/116240 Reviewed-by: Chris Dalton <csmartdalton@google.com> Commit-Queue: Chris Dalton <csmartdalton@google.com>
* Implement Sk2f::Store2Gravatar Chris Dalton2018-03-23
| | | | | | | | Bug: skia: Change-Id: Ieedd05ced376a7604936e9d2729fc20a8669496e Reviewed-on: https://skia-review.googlesource.com/115531 Commit-Queue: Chris Dalton <csmartdalton@google.com> Reviewed-by: Mike Klein <mtklein@google.com>
* small ABI + narrow/wide code updatesGravatar Mike Klein2018-03-21
| | | | | | | | | | | | | | | | | | | | The only tangible effect this CL should have is to use __vectorcall on all Windows builds, including scalar ones. The code generation is a little better there with __vectorcall than not, so might as well. This is a baby step towards vector stages with MSVC, but a very baby step indeed. Mostly this refactors and regroups a bunch of logic to reflect my current thoughts. The BUILD.gn changes are essentially no-ops, but they simplify things and make our flags more similar to how those targets are built in Chromium. (And I cleaned up other /arch: uses so this works.) Change-Id: I73dd39d15cdc7b3d268231a707952bbbfd91496e Reviewed-on: https://skia-review.googlesource.com/115644 Reviewed-by: Herb Derby <herb@google.com> Commit-Queue: Mike Klein <mtklein@chromium.org>
* detect nonfinite cubic pointsGravatar Mike Reed2018-03-20
| | | | | | | | | Bug: oss-fuzz:7031 Cq-Include-Trybots: skia.primary:Test-Debian9-Clang-GCE-CPU-AVX2-x86_64-Release-All-SKNX_NO_SIMD Change-Id: I657c0652dc863256f445a84c084ccc37d287f534 Reviewed-on: https://skia-review.googlesource.com/115222 Reviewed-by: Mike Klein <mtklein@chromium.org> Commit-Queue: Mike Reed <reed@google.com>
* exact divide by 255 with NEONGravatar Mike Klein2018-03-14
| | | | | | | Change-Id: Ib121eb0d5af1f22f48f517fe909112a77d92032e Reviewed-on: https://skia-review.googlesource.com/113666 Commit-Queue: Mike Klein <mtklein@chromium.org> Reviewed-by: Herb Derby <herb@google.com>
* Small cleanups suggested by ClangTidyGravatar Kevin Lubick2018-03-12
| | | | | | | | | Bug: skia: Cq-Include-Trybots: skia.primary:Test-Debian9-Clang-GCE-CPU-AVX2-x86_64-Release-All-SKNX_NO_SIMD Change-Id: Idd95e359838fdaecbdccc3a2c5a1b36971f20b8b Reviewed-on: https://skia-review.googlesource.com/113703 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Kevin Lubick <kjlubick@google.com>
* with no more offline codegen, seed_shader can be normalGravatar Mike Klein2018-03-11
| | | | | | | | | | | | | | We passed this iota array as an argument before because it was generating awkward code for our object file parser to handle (relocations, other weird things, can't quite remember). Now that we're compiling pipeline code normally, we can make seed_shader a normal stage again, with no special iota ctx pointer needed. Change-Id: I3929d61bfb6f914248f360c2c2326ce3d1f23163 Reviewed-on: https://skia-review.googlesource.com/113667 Reviewed-by: Herb Derby <herb@google.com> Commit-Queue: Mike Klein <mtklein@chromium.org>
* follow JUMPER_NARROW_STAGES in lowp stages tooGravatar Mike Klein2018-03-10
| | | | | | | | | | | | | | Should give dramatically better codegen for all 32-bit builds and 64-bit Windows builds, bringing it in line with how we make highp float stages. May help this bug, which is mostly Windows perf regressions. Bug: chromium:820469 Change-Id: I223f7568a09dea28ec614b18555766ea7d8365fa Reviewed-on: https://skia-review.googlesource.com/113665 Reviewed-by: Herb Derby <herb@google.com> Commit-Queue: Mike Klein <mtklein@chromium.org>
* Reland "Reland "make SkJumper stages normal Skia code""Gravatar Mike Klein2018-03-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is a reland of 78cb579f33943421afc8423a39867fcfd69fed44 This time, lowp stages are controlled by !defined(JUMPER_IS_SCALAR), not by defined(__clang__). The two are usually the same, except when we opt Clang builds into JUMPER_IS_SCALAR artificially. Some Google3 builds use compilers old enough that they barf when compiling our NEON code. It's conceivably also possible to define JUMPER_IS_SCALAR yourself, but I don't think anyone does that. Original change's description: > Reland "make SkJumper stages normal Skia code" > > This is a reland of 22e536e3a1a09405d1c0e6f071717a726d86e8d4 > > Now with fixed #include paths in SkRasterPipeline_opts.h, > and -ffp-contract=fast for the :hsw target to minimize > diffs on non-Windows Clang AVX2/AVX-512 bots. > > Original change's description: > > make SkJumper stages normal Skia code > > > > Enough clients are using Clang now that we can say, use Clang to build > > if you want these software pipeline stages to go fast. > > > > This lets us drop the offline build aspect of SkJumper stages, instead > > building as part of Skia using the SkOpts framework. > > > > I think everything should work, except I've (temporarily) removed > > AVX-512 support. I will put this back in a follow up. > > > > I have had to drop Windows down to __vectorcall and our narrower > > stage calling convention that keeps the d-registers on the stack. > > I tried forcing sysv_abi, but that crashed Clang. :/ > > > > Added a TODO to up the same narrower stage calling convention > > for lowp stages... we just *don't* today, for no good reason. > > > > Change-Id: Iaaa792ffe4deab3508d2dc5d0008c163c24b3383 > > Reviewed-on: https://skia-review.googlesource.com/110641 > > Commit-Queue: Mike Klein <mtklein@chromium.org> > > Reviewed-by: Herb Derby <herb@google.com> > > Reviewed-by: Florin Malita <fmalita@chromium.org> > > Change-Id: I44f2c03d33958e3807747e40904b6351957dd448 > Reviewed-on: https://skia-review.googlesource.com/112742 > Reviewed-by: Mike Klein <mtklein@chromium.org> Change-Id: I3d71197d4bbb19ca4a94961a97fa2e54d5cbfb0d Reviewed-on: https://skia-review.googlesource.com/112744 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Mike Klein <mtklein@google.com>
* Revert "Reland "make SkJumper stages normal Skia code""Gravatar Mike Klein2018-03-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 78cb579f33943421afc8423a39867fcfd69fed44. Reason for revert: lowp should be controlled by defined(JUMPER_IS_SCALAR), not defined(__clang__). So close. Original change's description: > Reland "make SkJumper stages normal Skia code" > > This is a reland of 22e536e3a1a09405d1c0e6f071717a726d86e8d4 > > Now with fixed #include paths in SkRasterPipeline_opts.h, > and -ffp-contract=fast for the :hsw target to minimize > diffs on non-Windows Clang AVX2/AVX-512 bots. > > Original change's description: > > make SkJumper stages normal Skia code > > > > Enough clients are using Clang now that we can say, use Clang to build > > if you want these software pipeline stages to go fast. > > > > This lets us drop the offline build aspect of SkJumper stages, instead > > building as part of Skia using the SkOpts framework. > > > > I think everything should work, except I've (temporarily) removed > > AVX-512 support. I will put this back in a follow up. > > > > I have had to drop Windows down to __vectorcall and our narrower > > stage calling convention that keeps the d-registers on the stack. > > I tried forcing sysv_abi, but that crashed Clang. :/ > > > > Added a TODO to up the same narrower stage calling convention > > for lowp stages... we just *don't* today, for no good reason. > > > > Change-Id: Iaaa792ffe4deab3508d2dc5d0008c163c24b3383 > > Reviewed-on: https://skia-review.googlesource.com/110641 > > Commit-Queue: Mike Klein <mtklein@chromium.org> > > Reviewed-by: Herb Derby <herb@google.com> > > Reviewed-by: Florin Malita <fmalita@chromium.org> > > Change-Id: I44f2c03d33958e3807747e40904b6351957dd448 > Reviewed-on: https://skia-review.googlesource.com/112742 > Reviewed-by: Mike Klein <mtklein@chromium.org> TBR=mtklein@chromium.org,herb@google.com,fmalita@chromium.org Change-Id: Ie64da98f5187d44e03c0ce05d7cb189d4a6e6663 No-Presubmit: true No-Tree-Checks: true No-Try: true Reviewed-on: https://skia-review.googlesource.com/112743 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Mike Klein <mtklein@google.com>
* Reland "make SkJumper stages normal Skia code"Gravatar Mike Klein2018-03-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is a reland of 22e536e3a1a09405d1c0e6f071717a726d86e8d4 Now with fixed #include paths in SkRasterPipeline_opts.h, and -ffp-contract=fast for the :hsw target to minimize diffs on non-Windows Clang AVX2/AVX-512 bots. Original change's description: > make SkJumper stages normal Skia code > > Enough clients are using Clang now that we can say, use Clang to build > if you want these software pipeline stages to go fast. > > This lets us drop the offline build aspect of SkJumper stages, instead > building as part of Skia using the SkOpts framework. > > I think everything should work, except I've (temporarily) removed > AVX-512 support. I will put this back in a follow up. > > I have had to drop Windows down to __vectorcall and our narrower > stage calling convention that keeps the d-registers on the stack. > I tried forcing sysv_abi, but that crashed Clang. :/ > > Added a TODO to up the same narrower stage calling convention > for lowp stages... we just *don't* today, for no good reason. > > Change-Id: Iaaa792ffe4deab3508d2dc5d0008c163c24b3383 > Reviewed-on: https://skia-review.googlesource.com/110641 > Commit-Queue: Mike Klein <mtklein@chromium.org> > Reviewed-by: Herb Derby <herb@google.com> > Reviewed-by: Florin Malita <fmalita@chromium.org> Change-Id: I44f2c03d33958e3807747e40904b6351957dd448 Reviewed-on: https://skia-review.googlesource.com/112742 Reviewed-by: Mike Klein <mtklein@chromium.org>
* Revert "make SkJumper stages normal Skia code"Gravatar Mike Klein2018-03-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 22e536e3a1a09405d1c0e6f071717a726d86e8d4. Reason for revert: wrong include path :/ Original change's description: > make SkJumper stages normal Skia code > > Enough clients are using Clang now that we can say, use Clang to build > if you want these software pipeline stages to go fast. > > This lets us drop the offline build aspect of SkJumper stages, instead > building as part of Skia using the SkOpts framework. > > I think everything should work, except I've (temporarily) removed > AVX-512 support. I will put this back in a follow up. > > I have had to drop Windows down to __vectorcall and our narrower > stage calling convention that keeps the d-registers on the stack. > I tried forcing sysv_abi, but that crashed Clang. :/ > > Added a TODO to up the same narrower stage calling convention > for lowp stages... we just *don't* today, for no good reason. > > Change-Id: Iaaa792ffe4deab3508d2dc5d0008c163c24b3383 > Reviewed-on: https://skia-review.googlesource.com/110641 > Commit-Queue: Mike Klein <mtklein@chromium.org> > Reviewed-by: Herb Derby <herb@google.com> > Reviewed-by: Florin Malita <fmalita@chromium.org> TBR=mtklein@chromium.org,herb@google.com,fmalita@chromium.org Change-Id: I2bdc709c80cdfa6b13ff24e024b3721bef887f46 No-Presubmit: true No-Tree-Checks: true No-Try: true Reviewed-on: https://skia-review.googlesource.com/112741 Reviewed-by: Mike Klein <mtklein@chromium.org> Commit-Queue: Mike Klein <mtklein@chromium.org>
* make SkJumper stages normal Skia codeGravatar Mike Klein2018-03-07
| | | | | | | | | | | | | | | | | | | | | | | | Enough clients are using Clang now that we can say, use Clang to build if you want these software pipeline stages to go fast. This lets us drop the offline build aspect of SkJumper stages, instead building as part of Skia using the SkOpts framework. I think everything should work, except I've (temporarily) removed AVX-512 support. I will put this back in a follow up. I have had to drop Windows down to __vectorcall and our narrower stage calling convention that keeps the d-registers on the stack. I tried forcing sysv_abi, but that crashed Clang. :/ Added a TODO to up the same narrower stage calling convention for lowp stages... we just *don't* today, for no good reason. Change-Id: Iaaa792ffe4deab3508d2dc5d0008c163c24b3383 Reviewed-on: https://skia-review.googlesource.com/110641 Commit-Queue: Mike Klein <mtklein@chromium.org> Reviewed-by: Herb Derby <herb@google.com> Reviewed-by: Florin Malita <fmalita@chromium.org>
* Implement Sk2f::Store4Gravatar Chris Dalton2018-02-07
| | | | | | | | Bug: skia: Change-Id: I2adb983d68625d327e7c00e53b6ae4703b46252f Reviewed-on: https://skia-review.googlesource.com/104761 Commit-Queue: Chris Dalton <csmartdalton@google.com> Reviewed-by: Mike Klein <mtklein@chromium.org>
* Enable conditional-uninitialized flagGravatar Kevin Lubick2018-01-05
| | | | | | | | | Bug: skia:7462 Cq-Include-Trybots: skia.primary:Test-Debian9-Clang-GCE-CPU-AVX2-x86_64-Release-All-SKNX_NO_SIMD Change-Id: I1c0a09984bf28a5c620a89af56040f018bae6310 Reviewed-on: https://skia-review.googlesource.com/90941 Commit-Queue: Kevin Lubick <kjlubick@google.com> Reviewed-by: Mike Klein <mtklein@chromium.org>
* Remove previous blur image implementation. Try 2Gravatar Herbert Derby2017-12-06
| | | | | | | | | | | The last version had a problem with the no simd compilation. TBR=mtklein@google.com Change-Id: I139388cf3bf1b55cb4a49133a98be129fd9711c6 Reviewed-on: https://skia-review.googlesource.com/80983 Reviewed-by: Herb Derby <herb@google.com> Commit-Queue: Herb Derby <herb@google.com>
* Revert "Remove previous blur image implementation"Gravatar Herb Derby2017-12-06
| | | | | | | | | | | | | | | | | | | | | | | | This reverts commit a11346dd24fa7122246dc96ba15604713e460036. Reason for revert: Compile problems on linux Original change's description: > Remove previous blur image implementation > > Change-Id: Ie3bada767f0ba945cb17f174f179510768eb178d > Reviewed-on: https://skia-review.googlesource.com/77583 > Commit-Queue: Herb Derby <herb@google.com> > Reviewed-by: Mike Klein <mtklein@google.com> TBR=mtklein@google.com,herb@google.com Change-Id: I5f157fbc2fd4e2a37618dc9c0e72621ff9892ef6 No-Presubmit: true No-Tree-Checks: true No-Try: true Reviewed-on: https://skia-review.googlesource.com/81100 Reviewed-by: Herb Derby <herb@google.com> Commit-Queue: Herb Derby <herb@google.com>
* Remove previous blur image implementationGravatar Herbert Derby2017-12-06
| | | | | | | Change-Id: Ie3bada767f0ba945cb17f174f179510768eb178d Reviewed-on: https://skia-review.googlesource.com/77583 Commit-Queue: Herb Derby <herb@google.com> Reviewed-by: Mike Klein <mtklein@google.com>
* Add Store3 to Sk2fGravatar Chris Dalton2017-12-01
| | | | | | | | Bug: skia: Change-Id: I0377e6a1dd8259e944f7902a5c68af524fa588c7 Reviewed-on: https://skia-review.googlesource.com/79382 Reviewed-by: Mike Klein <mtklein@chromium.org> Commit-Queue: Chris Dalton <csmartdalton@google.com>
* add Load2() to Sk4fGravatar Mike Klein2017-12-01
| | | | | | | | | and test it. Change-Id: Ib0c2cf93c63d8d3c36a7d4d60bbec4ecede29bc7 Reviewed-on: https://skia-review.googlesource.com/78480 Reviewed-by: Chris Dalton <csmartdalton@google.com> Commit-Queue: Mike Klein <mtklein@chromium.org>
* Fix Sk8b reading too many bytesGravatar Herb Derby2017-11-16
| | | | | | | Change-Id: I0e94ef1620b54405a23470507e2b2c4bb54731c9 Reviewed-on: https://skia-review.googlesource.com/72860 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Herb Derby <herb@google.com>
* Support for direct gaussian blur evaluationGravatar Herb Derby2017-11-02
| | | | | | | Change-Id: I1b00ba2720648b75fce47d3f4d0f56fb8f2cd171 Reviewed-on: https://skia-review.googlesource.com/67041 Reviewed-by: Mike Klein <mtklein@chromium.org> Commit-Queue: Herb Derby <herb@google.com>
generated by cgit v1.2.3 (git 2.39.1) at 2024-05-17 22:35:44 +0000