aboutsummaryrefslogtreecommitdiffhomepage
path: root/bench
Commit message (Collapse)AuthorAge
...
* resources: orgainize directory.Gravatar Hal Canary2017-12-08
| | | | | | | | | Should make it easier to ask just for images. Change-Id: If821743dc924c4bfbc6b2b2d29b14affde7b3afd Reviewed-on: https://skia-review.googlesource.com/82684 Commit-Queue: Hal Canary <halcanary@google.com> Reviewed-by: Leon Scroggins <scroggo@google.com>
* Delete GLBench and subclassesGravatar Brian Salomon2017-12-07
| | | | | | | | Bug: skia:6305 Change-Id: I3b2f2a8898f25d3dd0ec47668895dd4d00668575 Reviewed-on: https://skia-review.googlesource.com/82040 Reviewed-by: Brian Osman <brianosman@google.com> Commit-Queue: Brian Salomon <bsalomon@google.com>
* remove ThermalManagerGravatar Mike Klein2017-12-06
| | | | | | | | | | | | It throttles 1000x more than intended, and I suspect that some of the trip points it uses to decide when to throttle make no sense. We've already turned it off on the Nexus 5x. Change-Id: Idf556a83fe61ccc5f63c7bede3eecbe80087e28b Reviewed-on: https://skia-review.googlesource.com/81303 Reviewed-by: Kevin Lubick <kjlubick@google.com> Reviewed-by: Brian Osman <brianosman@google.com> Commit-Queue: Mike Klein <mtklein@chromium.org>
* Test performance of 565 bitmap scalingGravatar Yuqian Li2017-12-06
| | | | | | | | | | | | | | | | | | | | | This would catch b/70172912 On Linux desktops, see the difference between 8888 and 565 using: nanobench --config 8888 -m ^bitmap_RGB_565_scale$ ^bitmap_BGRA_8888_scale$ ^bitmap_RGB_565_scale_bilerp$ ^bitmap_BGRA_8888_scale_bilerp$ On Android, use: nanobench --config 8888 -m ^bitmap_RGB_565_scale$ ^bitmap_RGBA_8888_scale$ ^bitmap_RGB_565_scale_bilerp$ ^bitmap_RGBA_8888_scale_bilerp$ The results are similar if nanobench is run with --config 565. So it seems that the destination color type isn't very critical. Bug: skia: Change-Id: I71defda4d9e089a9a973cdb0c161773bc16e4a24 Reviewed-on: https://skia-review.googlesource.com/81141 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Yuqian Li <liyuqian@google.com>
* add benchType deserial to time deserializing picturesGravatar Mike Reed2017-12-06
| | | | | | | | | | | Piece of the larger effort to merge readbuffer and validatingreadbuffer Bug: skia: Change-Id: I79305e27c4712c3b91d213d09d6c2ef24b86e671 Reviewed-on: https://skia-review.googlesource.com/81120 Commit-Queue: Mike Reed <reed@google.com> Commit-Queue: Mike Klein <mtklein@chromium.org> Reviewed-by: Mike Klein <mtklein@chromium.org>
* Fix shader linker errors on several GL benchmarksGravatar Brian Osman2017-11-17
| | | | | | | | | | | | | | These were using an obsolete shader caps bit to manaully declare their own FP output variable. That led to two outputs (after SkSL added sk_FragColor), which led to errors about multiple outputs being declared (without specifying location). SkSL handles all of this, so just use sk_FragColor directly. Bug: skia: Change-Id: Id38657b6bf8c63c8f80d6ae3354a1507734a209f Reviewed-on: https://skia-review.googlesource.com/73344 Reviewed-by: Ethan Nicholas <ethannicholas@google.com> Commit-Queue: Brian Osman <brianosman@google.com>
* Revert "Revert "Direct evaluation of gaussian""Gravatar Herb Derby2017-11-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit a53d999007f92ecd4244b078fa909b76fd0d9f3b. Reason for revert: Bug in SkNx_sse fixed. Original change's description: > Revert "Direct evaluation of gaussian" > > This reverts commit 5e18cdea0a0a3f23d8e8b8140c82a4b54e121402. > > Reason for revert: ASAN > Original change's description: > > Direct evaluation of gaussian > > > > The SVG(CSS) standard allows the 3 pass algorithm for sigma >= 2. But > > sigma < 2, the code must evaluate to the convolution. The old code used > > an interpolation scheme between windowed filters. This code directly > > evaluates the gaussian kernel for sigma < 2. > > > > This code produces cleaner results, is 25% faster, and does not use a > > temporary memory buffer. > > > > Change-Id: Ibd0caa73cadd06b637f55ba7bd4fefcfe7ac73db > > Reviewed-on: https://skia-review.googlesource.com/62540 > > Commit-Queue: Herb Derby <herb@google.com> > > Reviewed-by: Mike Klein <mtklein@google.com> > > TBR=mtklein@google.com,herb@google.com > > Change-Id: I936077dfa659d71bc361339d98340c55545a1eb8 > No-Presubmit: true > No-Tree-Checks: true > No-Try: true > Reviewed-on: https://skia-review.googlesource.com/72481 > Reviewed-by: Brian Osman <brianosman@google.com> > Commit-Queue: Brian Osman <brianosman@google.com> TBR=mtklein@google.com,herb@google.com,brianosman@google.com Change-Id: I4c30e3481308a8148d40223519e286885ec6f880 Reviewed-on: https://skia-review.googlesource.com/72900 Commit-Queue: Herb Derby <herb@google.com> Reviewed-by: Herb Derby <herb@google.com>
* Revert "Direct evaluation of gaussian"Gravatar Brian Osman2017-11-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 5e18cdea0a0a3f23d8e8b8140c82a4b54e121402. Reason for revert: ASAN Original change's description: > Direct evaluation of gaussian > > The SVG(CSS) standard allows the 3 pass algorithm for sigma >= 2. But > sigma < 2, the code must evaluate to the convolution. The old code used > an interpolation scheme between windowed filters. This code directly > evaluates the gaussian kernel for sigma < 2. > > This code produces cleaner results, is 25% faster, and does not use a > temporary memory buffer. > > Change-Id: Ibd0caa73cadd06b637f55ba7bd4fefcfe7ac73db > Reviewed-on: https://skia-review.googlesource.com/62540 > Commit-Queue: Herb Derby <herb@google.com> > Reviewed-by: Mike Klein <mtklein@google.com> TBR=mtklein@google.com,herb@google.com Change-Id: I936077dfa659d71bc361339d98340c55545a1eb8 No-Presubmit: true No-Tree-Checks: true No-Try: true Reviewed-on: https://skia-review.googlesource.com/72481 Reviewed-by: Brian Osman <brianosman@google.com> Commit-Queue: Brian Osman <brianosman@google.com>
* Direct evaluation of gaussianGravatar Herbert Derby2017-11-16
| | | | | | | | | | | | | | | The SVG(CSS) standard allows the 3 pass algorithm for sigma >= 2. But sigma < 2, the code must evaluate to the convolution. The old code used an interpolation scheme between windowed filters. This code directly evaluates the gaussian kernel for sigma < 2. This code produces cleaner results, is 25% faster, and does not use a temporary memory buffer. Change-Id: Ibd0caa73cadd06b637f55ba7bd4fefcfe7ac73db Reviewed-on: https://skia-review.googlesource.com/62540 Commit-Queue: Herb Derby <herb@google.com> Reviewed-by: Mike Klein <mtklein@google.com>
* Add clipping options to path text bench and samplesGravatar Chris Dalton2017-11-07
| | | | | | | | Bug: skia: Change-Id: I632a2fa5627ef1438d9ab451318a42d12c61b802 Reviewed-on: https://skia-review.googlesource.com/67683 Reviewed-by: Brian Salomon <bsalomon@google.com> Commit-Queue: Chris Dalton <csmartdalton@google.com>
* remove SkThread, using std::thread insteadGravatar Mike Klein2017-10-30
| | | | | | | Change-Id: I871dd5eea4496e87c206b46d9eae81cb521b11ce Reviewed-on: https://skia-review.googlesource.com/65103 Reviewed-by: Hal Canary <halcanary@google.com> Commit-Queue: Mike Klein <mtklein@chromium.org>
* - add bench for pixmap orientGravatar Mike Reed2017-10-25
| | | | | | | | | | - reduce code size by using a draw instead of custom blits Bug: skia: Change-Id: I90f9fb2abf40496e771f1f725556c178d730b590 Reviewed-on: https://skia-review.googlesource.com/62860 Reviewed-by: Mike Klein <mtklein@chromium.org> Commit-Queue: Mike Reed <reed@google.com>
* Fix shader compilation error in GrInstancedArraysBenchGravatar Jim Van Verth2017-10-23
| | | | | | | Change-Id: Ifd87e752fe1712ab4adef6c5f5de8798ab6c4991 Reviewed-on: https://skia-review.googlesource.com/50680 Reviewed-by: Ethan Nicholas <ethannicholas@google.com> Commit-Queue: Jim Van Verth <jvanverth@google.com>
* Enable CCPR for volatile pathsGravatar Chris Dalton2017-10-17
| | | | | | | | | | Enables for volatile paths and when path mask caching is disabled. Bug: skia: Change-Id: I644b17f2a4f77a4ddf85265f520599499c0800cf Reviewed-on: https://skia-review.googlesource.com/60481 Reviewed-by: Brian Salomon <bsalomon@google.com> Commit-Queue: Chris Dalton <csmartdalton@google.com>
* Add a tooling flag for path mask cachingGravatar Chris Dalton2017-10-13
| | | | | | | | | | | Adds the flag and a disables caching on the CCPR bots. Bug: skia: Change-Id: Icb85e77f89634dda1d419dacac5b8a93340723f0 Reviewed-on: https://skia-review.googlesource.com/59740 Reviewed-by: Eric Boren <borenet@google.com> Reviewed-by: Brian Osman <brianosman@google.com> Commit-Queue: Chris Dalton <csmartdalton@google.com>
* Add benchmark for comparing multitexturing to non-multitexturing image draws.Gravatar Brian Salomon2017-10-11
| | | | | | | | | | | Allows benchmarks to override GrContextOptions. Removes the ability to use the same GrContext for all benchmarks in a config. Change-Id: I5ab9f6e81055451ac912a66537843d1a49f3b479 Reviewed-on: https://skia-review.googlesource.com/34080 Reviewed-by: Brian Osman <brianosman@google.com> Commit-Queue: Brian Salomon <bsalomon@google.com>
* Warmup for one extra frame in nanobenchGravatar Brian Osman2017-10-10
| | | | | | | | | | On ANGLE, at least, this frame gives us much more consistent results. Bug: skia: Change-Id: Ifdecc8451ef51490c08057645214738180b1a366 Reviewed-on: https://skia-review.googlesource.com/57884 Reviewed-by: Greg Daniel <egdaniel@google.com> Commit-Queue: Brian Osman <brianosman@google.com>
* Remove trailing whitespace.Gravatar Ben Wagner2017-10-09
| | | | | | | | | | | Also adds a presubmit to prevent adding trailing whitespace to source code in the future. Change-Id: I41a4df81487f6f00aa19b188f0cac6a3377efde6 Reviewed-on: https://skia-review.googlesource.com/57380 Reviewed-by: Ravi Mistry <rmistry@google.com> Reviewed-by: Mike Reed <reed@google.com> Commit-Queue: Ben Wagner <bungeman@google.com>
* Revert[4] "guard old apis for querying byte-size of a bitmap/imageinfo/pixmap"Gravatar Mike Reed2017-10-03
| | | | | | | | | | This reverts commit 5a2e50edc51006ce91366e177a9d21a16775d7fd. Bug: skia: Change-Id: I8d28b5c07d90130e5a1653923740eaf189ecb954 Reviewed-on: https://skia-review.googlesource.com/53900 Reviewed-by: Mike Reed <reed@google.com> Commit-Queue: Mike Reed <reed@google.com>
* Do not try to time kFailedLoopsGravatar Leon Scroggins III2017-10-02
| | | | | | | | | | | | Move the check for kFailedLoops above code that times the benchmark. This matches the comment ("Can't be timed") and prevents an infinite loop. Bug: skia:6774 Change-Id: Iacdc1ca1d11afcf05afac60e4eb0d8d9a12f800e Reviewed-on: https://skia-review.googlesource.com/53803 Reviewed-by: Yuqian Li <liyuqian@google.com> Commit-Queue: Leon Scroggins <scroggo@google.com>
* Revert "Revert "Revert "guard old apis for querying byte-size of a ↵Gravatar Mike Reed2017-10-02
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | bitmap/imageinfo/pixmap""" This reverts commit cd284c532376d16fcc4ed75baf3da65c3e4a2e95. Reason for revert: assert fired in SkMallocPixelRef.cpp:61: fatal error: "assert(info.computeByteSize(rowBytes) == info.getSafeSize(rowBytes))" google3 thinks it was from surface_rowbytes Original change's description: > Revert "Revert "guard old apis for querying byte-size of a bitmap/imageinfo/pixmap"" > > This reverts commit 809cbedd4b252be221b2ac3b4269d312fd8f53a0. > > Bug: skia: > Change-Id: I680d8daeeeeb15526b44c1305d8fb0c6bfa38e1d > Reviewed-on: https://skia-review.googlesource.com/52665 > Commit-Queue: Mike Reed <reed@google.com> > Reviewed-by: Florin Malita <fmalita@chromium.org> TBR=fmalita@chromium.org,reed@google.com Change-Id: I41e3f7a3f791cc8183291847e783ed8a53bc91d2 No-Presubmit: true No-Tree-Checks: true No-Try: true Bug: skia: Reviewed-on: https://skia-review.googlesource.com/53802 Reviewed-by: Mike Reed <reed@google.com> Commit-Queue: Mike Reed <reed@google.com>
* Revert "Revert "guard old apis for querying byte-size of a ↵Gravatar Mike Reed2017-10-02
| | | | | | | | | | | | bitmap/imageinfo/pixmap"" This reverts commit 809cbedd4b252be221b2ac3b4269d312fd8f53a0. Bug: skia: Change-Id: I680d8daeeeeb15526b44c1305d8fb0c6bfa38e1d Reviewed-on: https://skia-review.googlesource.com/52665 Commit-Queue: Mike Reed <reed@google.com> Reviewed-by: Florin Malita <fmalita@chromium.org>
* Revert "guard old apis for querying byte-size of a bitmap/imageinfo/pixmap"Gravatar Jim Van Verth2017-09-27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 88757dacd4f532a0f647c02ae0ee596d31ab5c68. Reason for revert: Still seems to be failing Chromium "telemetry_perf_unittests (with patch) on Android" on android_n5x_swarming_rel. Original change's description: > guard old apis for querying byte-size of a bitmap/imageinfo/pixmap > > Now with legacy behavior for allocpixels > > This was reverted, so the current CL is a "fix" on top of ... > https://skia-review.googlesource.com/c/skia/+/50980 > > Related update to Chrome (in preparation for this change) > https://chromium-review.googlesource.com/c/chromium/src/+/685719 > > Bug: skia: > Change-Id: I4b370ee7e95083ab27421f008132219c9c7b86e9 > Reviewed-on: https://skia-review.googlesource.com/51341 > Reviewed-by: Florin Malita <fmalita@chromium.org> > Commit-Queue: Mike Reed <reed@google.com> TBR=fmalita@chromium.org,reed@google.com Change-Id: I827a0ca1d1e3909e648fde3342cdb8601d34da8d No-Presubmit: true No-Tree-Checks: true No-Try: true Bug: skia: Reviewed-on: https://skia-review.googlesource.com/52381 Reviewed-by: Jim Van Verth <jvanverth@google.com> Commit-Queue: Jim Van Verth <jvanverth@google.com>
* guard old apis for querying byte-size of a bitmap/imageinfo/pixmapGravatar Mike Reed2017-09-27
| | | | | | | | | | | | | | | | Now with legacy behavior for allocpixels This was reverted, so the current CL is a "fix" on top of ... https://skia-review.googlesource.com/c/skia/+/50980 Related update to Chrome (in preparation for this change) https://chromium-review.googlesource.com/c/chromium/src/+/685719 Bug: skia: Change-Id: I4b370ee7e95083ab27421f008132219c9c7b86e9 Reviewed-on: https://skia-review.googlesource.com/51341 Reviewed-by: Florin Malita <fmalita@chromium.org> Commit-Queue: Mike Reed <reed@google.com>
* Revert "guard old apis for querying byte-size of a bitmap/imageinfo/pixmap"Gravatar Greg Daniel2017-09-26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 98a6216b18b57c2f7a0d58f542c60503686aed69. Reason for revert: breaking the chrome roll. Looks like they may be writing data to create an image across all the row bytes and thus writing to unalloced data on the last row. Link to example failing bot: https://build.chromium.org/p/tryserver.chromium.win/builders/win_chromium_rel_ng/builds/539960 Original change's description: > guard old apis for querying byte-size of a bitmap/imageinfo/pixmap > > Previously we had size_t and uint64_t variations. > > The new (simpler) API always.. > - returns size_t, or 0 if the calculation overflowed > - returns the trimmed size (does not include rowBytes padding for the last row) > > Bug: skia: > Change-Id: I05173e877918327c7b207d2f7f1ab0db36892e2e > Reviewed-on: https://skia-review.googlesource.com/50980 > Commit-Queue: Mike Reed <reed@google.com> > Reviewed-by: Florin Malita <fmalita@chromium.org> > Reviewed-by: Leon Scroggins <scroggo@google.com> TBR=mtklein@google.com,herb@google.com,scroggo@google.com,fmalita@chromium.org,reed@google.com Change-Id: I726f6ab1b36b14979ba6f37105e0a469b3f0dbc0 No-Presubmit: true No-Tree-Checks: true No-Try: true Bug: skia: Reviewed-on: https://skia-review.googlesource.com/51262 Reviewed-by: Greg Daniel <egdaniel@google.com> Commit-Queue: Greg Daniel <egdaniel@google.com>
* switched gl_Position and gl_PointSize to sk_*Gravatar Ethan Nicholas2017-09-26
| | | | | | | | Bug: skia: Change-Id: Ie7508991aa975c1400bac23ae49d81041a313968 Reviewed-on: https://skia-review.googlesource.com/51320 Reviewed-by: Greg Daniel <egdaniel@google.com> Commit-Queue: Ethan Nicholas <ethannicholas@google.com>
* guard old apis for querying byte-size of a bitmap/imageinfo/pixmapGravatar Mike Reed2017-09-26
| | | | | | | | | | | | | | | Previously we had size_t and uint64_t variations. The new (simpler) API always.. - returns size_t, or 0 if the calculation overflowed - returns the trimmed size (does not include rowBytes padding for the last row) Bug: skia: Change-Id: I05173e877918327c7b207d2f7f1ab0db36892e2e Reviewed-on: https://skia-review.googlesource.com/50980 Commit-Queue: Mike Reed <reed@google.com> Reviewed-by: Florin Malita <fmalita@chromium.org> Reviewed-by: Leon Scroggins <scroggo@google.com>
* switched SkSL's temporary 'highfloat' type back to 'float'Gravatar Ethan Nicholas2017-09-22
| | | | | | | | Bug: skia: Change-Id: If0debae7318b6b5b4a7cb85d458996a09931127e Reviewed-on: https://skia-review.googlesource.com/48760 Commit-Queue: Ethan Nicholas <ethannicholas@google.com> Reviewed-by: Brian Salomon <bsalomon@google.com>
* Run the first bench for 1000ms to warm up the nanobench if FLAGS_ms < 1000.Gravatar Yuqian Li2017-09-21
| | | | | | | | | | | | | | | | | | | | | | | | Otherwise, the first few benches' measurements will be inaccurate. For example, without this CL, the first few measurements are: 337ns, 566µs, 1000µs, ... without "--ms 1000" arg 211ns, 285µs, 874µs, ... with "--ms 1000" arg With this CL, the first few measurements are: 195ns, 296µs, 1.03ms, ... without "--ms 1000" arg 204ns, 280µs, 859µs, ... with "--ms 1000" arg In the example above, the first two measurements are vastly (>50%) different without this CL. I think that's the reason why I keep using "--ms 1000" arg locally. But it's really only necessary for the first bench to warm up nanobench. It's a waste to apply "--ms 1000" to all the following benches. Bug: skia: Change-Id: I1924ba3ff9185ed89aeda72794fafd1fe6625eef Reviewed-on: https://skia-review.googlesource.com/49742 Reviewed-by: Yuqian Li <liyuqian@google.com> Commit-Queue: Yuqian Li <liyuqian@google.com>
* re-land of new SkSL precisionsGravatar Ethan Nicholas2017-09-18
| | | | | | | | Bug: skia: Change-Id: Ic1deb3db2cbda6ca45f93dee99832971a36a2119 Reviewed-on: https://skia-review.googlesource.com/47841 Commit-Queue: Ethan Nicholas <ethannicholas@google.com> Reviewed-by: Ethan Nicholas <ethannicholas@google.com>
* Revert "Revert "Revert "Switched highp float to highfloat and mediump float ↵Gravatar Ethan Nicholas2017-09-18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | to half.""" This reverts commit 05d5a13fea6246648de7e41358ed338d53c85ea2. Reason for revert: looks like it broke filterfastbounds Original change's description: > Revert "Revert "Switched highp float to highfloat and mediump float to half."" > > This reverts commit 1d816b92bb7cf2258007f3f74ffd143b89f25d01. > > Bug: skia: > Change-Id: I388b5e5e9bf619db48297a80c9a80c039f26c9f1 > Reviewed-on: https://skia-review.googlesource.com/46464 > Reviewed-by: Brian Salomon <bsalomon@google.com> > Commit-Queue: Ethan Nicholas <ethannicholas@google.com> TBR=bsalomon@google.com,ethannicholas@google.com # Not skipping CQ checks because original CL landed > 1 day ago. Bug: skia: Change-Id: Iddf6aef2ab084aa73da7ceebdfc303a1d2b80cde Reviewed-on: https://skia-review.googlesource.com/47441 Reviewed-by: Ethan Nicholas <ethannicholas@google.com> Commit-Queue: Ethan Nicholas <ethannicholas@google.com>
* Revert "Revert "Switched highp float to highfloat and mediump float to half.""Gravatar Ethan Nicholas2017-09-15
| | | | | | | | | | This reverts commit 1d816b92bb7cf2258007f3f74ffd143b89f25d01. Bug: skia: Change-Id: I388b5e5e9bf619db48297a80c9a80c039f26c9f1 Reviewed-on: https://skia-review.googlesource.com/46464 Reviewed-by: Brian Salomon <bsalomon@google.com> Commit-Queue: Ethan Nicholas <ethannicholas@google.com>
* make most of SkColorPriv.h privateGravatar Cary Clark2017-09-15
| | | | | | | | | | | | | created new file src/core/SkColorData.h for internal consumption. Note that many of the functions there are unused as well. Bug: skia: 6898 R: reed@google.com Change-Id: I25bfd5a9c21f53558c4ca65a77eb5d322d897c6d Reviewed-on: https://skia-review.googlesource.com/46848 Commit-Queue: Cary Clark <caryclark@google.com> Reviewed-by: Mike Reed <reed@google.com>
* Do not divide loops in PathBenchGravatar Yuqian Li2017-09-14
| | | | | | | | | | | | | That breaks the assumption that the work is proportional to loops. For example, loops = 5 and loops = 7 would result in the same count if count = loops / 4. Bug: skia: Change-Id: Idae86d658cbfba8a7f49b983ed61a8b7fbea007a Reviewed-on: https://skia-review.googlesource.com/46600 Commit-Queue: Yuqian Li <liyuqian@google.com> Commit-Queue: Herb Derby <herb@google.com> Reviewed-by: Herb Derby <herb@google.com>
* Add a benchmark for SkXfermodeImageFilter mode kSrcInGravatar Xianzhu Wang2017-09-11
| | | | | | | | | This should exercise the performance benefits of https://skia-review.googlesource.com/c/skia/+/38921. Change-Id: Ic9b4c280308aeadbc50152d17ee5d38387be6913 Reviewed-on: https://skia-review.googlesource.com/42181 Commit-Queue: Stephen White <senorblanco@chromium.org> Reviewed-by: Stephen White <senorblanco@chromium.org>
* Copy benchmark names, which may be transient stringsGravatar Brian Osman2017-09-08
| | | | | | | | | Bug: skia: Change-Id: Ic4073aa17a04e8b400cc4a9db9a0669ee4a5c894 Reviewed-on: https://skia-review.googlesource.com/44203 Commit-Queue: Brian Osman <brianosman@google.com> Commit-Queue: Mike Klein <mtklein@google.com> Reviewed-by: Mike Klein <mtklein@google.com>
* Fix config strings in nanobench tracingGravatar Brian Osman2017-08-31
| | | | | | | | | | These are transient, so need to be copied. Bug: skia: Change-Id: Id24db0b96f343ecd034dd015da6e19ea61579b56 Reviewed-on: https://skia-review.googlesource.com/41741 Reviewed-by: Brian Osman <brianosman@google.com> Commit-Queue: Brian Osman <brianosman@google.com>
* Add top-level trace markers for each benchmarkGravatar Brian Osman2017-08-31
| | | | | | | | | | Also add new paragraph about using systrace correctly Docs-Preview: https://skia.org/?cl=41502 Change-Id: I114c14cc2e87a8b72aec46d8c354d3ea877a41ab Reviewed-on: https://skia-review.googlesource.com/41502 Reviewed-by: Mike Klein <mtklein@google.com> Commit-Queue: Brian Osman <brianosman@google.com>
* Threaded generation of software pathsGravatar Brian Osman2017-08-30
| | | | | | | | | | | | | | | | | | | | | | | | | | | Re-land of: https://skia-review.googlesource.com/36560 All information needed by the thread is captured by the prepare callback object, the lambda captures a pointer to that, and does the mask render. Once it's done, it signals the semaphore (also owned by the callback). The callback defers the semaphore wait even longer (into the ASAP upload), so the odds of waiting for the thread are REALLY low. Also did a bunch of cleanup along the way, and put in some trace markers so we can monitor how well this is working. Traces of a GM that includes GPU and SW path rendering (path-reverse): Original: https://screenshot.googleplex.com/f5BG3901tQg.png Threaded, with wait in the callback (notice pre flush callback blocking): https://screenshot.googleplex.com/htOSZFE2s04.png Current version, with wait deferred to ASAP upload function: https://screenshot.googleplex.com/GHjD0U3C34q.png Bug: skia: Change-Id: Idb92f385590749f41328a9aec65b2a93f4775079 Reviewed-on: https://skia-review.googlesource.com/40775 Reviewed-by: Brian Salomon <bsalomon@google.com> Commit-Queue: Brian Osman <brianosman@google.com>
* add 'a8' config for nanobench, specialize blitV for raster-pipelineGravatar Mike Reed2017-08-28
| | | | | | | | | | 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>
* Revert "Threaded generation of software paths"Gravatar Brian Salomon2017-08-24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 76323bc0615044a5921afef0e19a350f3d04ffe0. Reason for revert: Breaking NUC bots in threaded gm comparison: https://chromium-swarm.appspot.com/task?id=382e589753187f10&refresh=10 Original change's description: > Threaded generation of software paths > > All information needed by the thread is captured by the prepare > callback object, the lambda captures a pointer to that, and does the > mask render. Once it's done, it signals the semaphore (also owned by the > callback). The callback defers the semaphore wait even longer (into the > ASAP upload), so the odds of waiting for the thread are REALLY low. > > Also did a bunch of cleanup along the way, and put in some trace markers > so we can monitor how well this is working. > > Traces of a GM that includes GPU and SW path rendering (path-reverse): > > Original: > https://screenshot.googleplex.com/f5BG3901tQg.png > Threaded, with wait in the callback (notice pre flush callback blocking): > https://screenshot.googleplex.com/htOSZFE2s04.png > Current version, with wait deferred to ASAP upload function: > https://screenshot.googleplex.com/GHjD0U3C34q.png > > Bug: skia: > Change-Id: I3d5a230bbd68eb35e1f0574b308485c691435790 > Reviewed-on: https://skia-review.googlesource.com/36560 > Commit-Queue: Brian Osman <brianosman@google.com> > Reviewed-by: Brian Salomon <bsalomon@google.com> TBR=egdaniel@google.com,mtklein@google.com,bsalomon@google.com,robertphillips@google.com,brianosman@google.com Change-Id: Icac0918a3771859f671b69ae07ae0fedd3ebb3db No-Presubmit: true No-Tree-Checks: true No-Try: true Bug: skia: Reviewed-on: https://skia-review.googlesource.com/38560 Reviewed-by: Brian Salomon <bsalomon@google.com> Commit-Queue: Brian Salomon <bsalomon@google.com>
* Threaded generation of software pathsGravatar Brian Osman2017-08-24
| | | | | | | | | | | | | | | | | | | | | | | | | | All information needed by the thread is captured by the prepare callback object, the lambda captures a pointer to that, and does the mask render. Once it's done, it signals the semaphore (also owned by the callback). The callback defers the semaphore wait even longer (into the ASAP upload), so the odds of waiting for the thread are REALLY low. Also did a bunch of cleanup along the way, and put in some trace markers so we can monitor how well this is working. Traces of a GM that includes GPU and SW path rendering (path-reverse): Original: https://screenshot.googleplex.com/f5BG3901tQg.png Threaded, with wait in the callback (notice pre flush callback blocking): https://screenshot.googleplex.com/htOSZFE2s04.png Current version, with wait deferred to ASAP upload function: https://screenshot.googleplex.com/GHjD0U3C34q.png Bug: skia: Change-Id: I3d5a230bbd68eb35e1f0574b308485c691435790 Reviewed-on: https://skia-review.googlesource.com/36560 Commit-Queue: Brian Osman <brianosman@google.com> Reviewed-by: Brian Salomon <bsalomon@google.com>
* Revert "Switched highp float to highfloat and mediump float to half."Gravatar Brian Salomon2017-08-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 88d99c63878c2d3d340120f0321676f72afcb4f0. Reason for revert: Believed to be causing unit test failures in Chrome roll: https://build.chromium.org/p/tryserver.chromium.android/builders/linux_android_rel_ng/builds/364433 https://luci-logdog.appspot.com/v/?s=chromium%2Fbb%2Ftryserver.chromium.android%2Flinux_android_rel_ng%2F364433%2F%2B%2Frecipes%2Fsteps%2Fcontent_browsertests__with_patch__on_Android%2F0%2Flogs%2FWebRtcCaptureFromElementBrowserTest.VerifyCanvasWebGLCaptureColor%2F0 Original change's description: > Switched highp float to highfloat and mediump float to half. > > The ultimate goal is to end up with "float" and "half", but this > intermediate step uses "highfloat" so that it is clear if I missed a > "float" somewhere. Once this lands, a subsequent CL will switch all > "highfloats" back to "floats". > > Bug: skia: > Change-Id: Ia13225c7a0a0a2901e07665891c473d2500ddcca > Reviewed-on: https://skia-review.googlesource.com/31000 > Commit-Queue: Ethan Nicholas <ethannicholas@google.com> > Reviewed-by: Brian Salomon <bsalomon@google.com> TBR=bsalomon@google.com,csmartdalton@google.com,ethannicholas@google.com Change-Id: I8bfa97547ac3920d433665f161d27df3f15c83aa No-Presubmit: true No-Tree-Checks: true No-Try: true Bug: skia: Reviewed-on: https://skia-review.googlesource.com/35705 Commit-Queue: Brian Salomon <bsalomon@google.com> Reviewed-by: Brian Salomon <bsalomon@google.com>
* Switched highp float to highfloat and mediump float to half.Gravatar Ethan Nicholas2017-08-16
| | | | | | | | | | | | | The ultimate goal is to end up with "float" and "half", but this intermediate step uses "highfloat" so that it is clear if I missed a "float" somewhere. Once this lands, a subsequent CL will switch all "highfloats" back to "floats". Bug: skia: Change-Id: Ia13225c7a0a0a2901e07665891c473d2500ddcca Reviewed-on: https://skia-review.googlesource.com/31000 Commit-Queue: Ethan Nicholas <ethannicholas@google.com> Reviewed-by: Brian Salomon <bsalomon@google.com>
* Replace SkFAIL with SK_ABORT.Gravatar Ben Wagner2017-08-16
| | | | | | | | | | | | SkFAIL is a legacy macro which is just SK_ABORT. This CL mechanically changes uses of SkFAIL to SK_ABORT in preparation for its removal. The related sk_throw macro will be changed independently, due to needing to actually clean up its users. Change-Id: Id70b5c111a02d2458dc60c8933f444df27d9cebb Reviewed-on: https://skia-review.googlesource.com/35284 Reviewed-by: Derek Sollenberger <djsollen@google.com> Commit-Queue: Ben Wagner <bungeman@google.com>
* Switch SkSL to std::stringGravatar Brian Osman2017-08-14
| | | | | | | | | | | | | | On desktop, this saves just over 5% of the time in the SkSL compiler. As written, the code will now build either way, so it's much easier to switch back (or even have some platforms use SkString, if that's ever required). Bug: skia: Change-Id: I634f26a4f6fcb404e59bda6a5c6a21a9c6d73c0b Reviewed-on: https://skia-review.googlesource.com/34381 Reviewed-by: Brian Osman <brianosman@google.com> Commit-Queue: Brian Osman <brianosman@google.com>
* Abort dm/nanobench on bad configs.Gravatar Ben Wagner2017-08-11
| | | | | | | | | Adjust the configs specified by recipes to avoid the new error. Change-Id: I23e31355e2faaab919d92abdb37a6f70cd2da1ff Reviewed-on: https://skia-review.googlesource.com/32862 Reviewed-by: Brian Osman <brianosman@google.com> Commit-Queue: Ben Wagner <benjaminwagner@google.com>
* add gamma stageGravatar Mike Klein2017-08-09
| | | | | | | | | | | | | | | | Until now we've been using 3 separate parametric stages to apply gamma to r,g,b. That works fine, but is kind of unnecessarily slow, and again less clear in a stack trace than seeing "gamma". The new bench runs in about 60% of the time the old one does on my Trashcan. BUG=skia:6939 Change-Id: I079698d3009b081f1c23a2e27fc26e373b439610 Reviewed-on: https://skia-review.googlesource.com/32721 Reviewed-by: Mike Reed <reed@google.com> Commit-Queue: Mike Klein <mtklein@chromium.org>
* use unsigned to avoid runtime overflow detectionGravatar Mike Reed2017-08-09
| | | | | | | | | Bug: skia: Change-Id: I487930955f75048ea27a1bcc61f7e0849c63759b Reviewed-on: https://skia-review.googlesource.com/32681 Commit-Queue: Mike Reed <reed@google.com> Commit-Queue: Mike Klein <mtklein@google.com> Reviewed-by: Mike Klein <mtklein@google.com>
* handle overflows in float->intGravatar Mike Reed2017-08-09
| | | | | | | | | | rects are already auto-vectorized, so no need to explicitly write a 4f version of SkRect::round() Bug: skia: Change-Id: I098945767bfcaa7093d770c376bd17ff3bdc9983 Reviewed-on: https://skia-review.googlesource.com/32060 Commit-Queue: Mike Reed <reed@google.com> Reviewed-by: Florin Malita <fmalita@chromium.org>
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-04 20:27:54 +0000