1. 31 Mar, 2018 1 commit
  2. 30 Mar, 2018 3 commits
  3. 28 Mar, 2018 4 commits
  4. 26 Mar, 2018 1 commit
  5. 20 Mar, 2018 2 commits
  6. 10 Mar, 2018 2 commits
  7. 08 Mar, 2018 1 commit
  8. 07 Mar, 2018 1 commit
  9. 02 Mar, 2018 1 commit
  10. 27 Feb, 2018 2 commits
  11. 24 Feb, 2018 1 commit
  12. 22 Feb, 2018 2 commits
  13. 21 Feb, 2018 4 commits
  14. 16 Feb, 2018 2 commits
  15. 15 Feb, 2018 2 commits
  16. 12 Feb, 2018 2 commits
    • Frank Barchard's avatar
      Revert "Revert "Fixing libyuv gn check."" · 439fc3ce
      Frank Barchard authored
      This reverts commit 724dbeba.
      
      Reason for revert: bots remain red after revert.
      
      Original change's description:
      > Revert "Fixing libyuv gn check."
      > 
      > This reverts commit b625f7b9.
      > 
      > Reason for revert: ios builds broke shortly after this CL, so trying a revert to get builds back to green.
      > 
      > Original change's description:
      > > Fixing libyuv gn check.
      > > 
      > > Starting from [1], GN is able to ensure that the inclusion or headers
      > > with relative paths is matched by a GN dependency.
      > > 
      > > This CL fixes the libyuv build graph according to GN.
      > > 
      > > [1] - https://chromium-review.googlesource.com/c/chromium/src/+/827014
      > > 
      > > Bug: webrtc:8850
      > > Change-Id: I7e0f9a8bd1ae2d205213dc75bf322be587efd1f5
      > > Reviewed-on: https://chromium-review.googlesource.com/903843
      > > Reviewed-by: Frank Barchard <fbarchard@chromium.org>
      > > Commit-Queue: Frank Barchard <fbarchard@chromium.org>
      > 
      > TBR=fbarchard@chromium.org,mbonadei@chromium.org
      > 
      > # Not skipping CQ checks because original CL landed > 1 day ago.
      > 
      > Bug: webrtc:8850
      > Change-Id: I8585de252bd83e2c628a37b0a0d5324ed961209e
      > Reviewed-on: https://chromium-review.googlesource.com/912178
      > Reviewed-by: Frank Barchard <fbarchard@chromium.org>
      > Commit-Queue: Frank Barchard <fbarchard@chromium.org>
      
      TBR=fbarchard@chromium.org,mbonadei@chromium.org
      
      # Not skipping CQ checks because original CL landed > 1 day ago.
      
      Bug: webrtc:8850
      Change-Id: Idfd37e0e20d278b374c57d7e2c5465971aae3a52
      Reviewed-on: https://chromium-review.googlesource.com/914529Reviewed-by: 's avatarFrank Barchard <fbarchard@chromium.org>
      439fc3ce
    • Frank Barchard's avatar
      Tidy applied with all safe checks on all arm, mips and intel, 32 and 64 bit · 8a00c2bb
      Frank Barchard authored
      Using clang-tidy 7.
      warnings=-*,mpi-*,objc-*,llvm-*,hicpp-*,-hicpp-use-noexcept,llvm-*,-hicpp-deprecated-headers,-hicpp-use-auto,bugprone-*,cert-*,google-*,-google-readability-casting,misc-*,,-misc-unused-parameters,-misc-macro-parentheses,cppcoreguidelines-*,-cppcoreguidelines-pro-type-member-init,readability-*,-readability-non-const-parameter,-readability-implicit-bool-conversion,fuchsia-*,-fuchsia-multiple-inheritance,-android-cloexec-*
      
      ~/bin/clang-tidy -fix-errors -format-style=file -checks=$warnings $* -- -Iinclude -D__ARM_NEON__ -D__arm__   -D__clang__ -D__clang_major__=6 -DHAVE_JPEG
      ~/bin/clang-tidy -fix-errors -format-style=file -checks=$warnings $* -- -Iinclude -D__mips_msa               -D__clang__ -D__clang_major__=6 -DHAVE_JPEG
      ~/bin/clang-tidy -fix-errors -format-style=file -checks=$warnings $* -- -Iinclude -D__aarch64__              -D__clang__ -D__clang_major__=6 -DHAVE_JPEG
      ~/bin/clang-tidy -fix-errors -format-style=file -checks=$warnings $* -- -Iinclude -D_MSC_VER=1600 -D_M_IX86  -D__clang__ -D__clang_major__=6 -DHAVE_JPEG
      ~/bin/clang-tidy -fix-errors -format-style=file -checks=$warnings $* -- -Iinclude -D_MSC_VER=1600 -D_M_X64   -D__clang__ -D__clang_major__=6 -DHAVE_JPEG
      ~/bin/clang-tidy -fix-errors -format-style=file -checks=$warnings $* -- -Iinclude -D__i386__                 -D__clang__ -D__clang_major__=6 -DHAVE_JPEG
      ~/bin/clang-tidy -fix-errors -format-style=file -checks=$warnings $* -- -Iinclude -D__x86_64__               -D__clang__ -D__clang_major__=6 -DHAVE_JPEG
      
      Bug: libyuv:750
      Test: builds and runs and passes more tidy tests
      Change-Id: Ieb0f026c5b5a1d2daf8aca18b9290927fdaaa55c
      Reviewed-on: https://chromium-review.googlesource.com/907853Reviewed-by: 's avatarWeiyong Yao <braveyao@chromium.org>
      8a00c2bb
  17. 10 Feb, 2018 1 commit
  18. 09 Feb, 2018 1 commit
  19. 08 Feb, 2018 1 commit
  20. 07 Feb, 2018 2 commits
  21. 06 Feb, 2018 1 commit
  22. 05 Feb, 2018 1 commit
  23. 02 Feb, 2018 2 commits
    • Frank Barchard's avatar
      I422ToUYVYRow_AVX2 use vpmovzxbd instead of vpermq · 5790a765
      Frank Barchard authored
      I422ToUYVYRow_AVX2 optimized from 7 cycles per 32 pixels to 4.6 cycles.
      Instead of 2 vpermq and vpunpcklbw:
      vmovdqu    (%1),%%xmm2
      vmovdqu    0x00(%1,%2,1),%%xmm3
      vpermq     $0xd8,%%ymm2,%%ymm2
      vpermq     $0xd8,%%ymm3,%%ymm3
      vpunpcklbw %%ymm3,%%ymm2,%%ymm2
      
      ..use vpmovzxbd to expand the bytes to shorts, then vpslld and vpor
      vpmovzxbd  (%1),%%ymm2
      vpmovzxbd  0x00(%1,%2,1),%%ymm3
      vpslld     $0x10,%%ymm3,%%ymm3
      vpor       %%ymm3,%%ymm2,%%ymm2
      which reduces the port 5 bottleneck by 1 cycle.
      
      Bug: libyuv:556
      Test: out/Release/libyuv_unittest --gtest_filter=*I42?To*UY*Opt
      
      Change-Id: I53799e53cc6b090a1a695c839094c193be3eecaf
      Reviewed-on: https://chromium-review.googlesource.com/899873
      Commit-Queue: Frank Barchard <fbarchard@chromium.org>
      Reviewed-by: 's avatarrichard winterton <rrwinterton@gmail.com>
      Reviewed-by: 's avatarCheng Wang <wangcheng@google.com>
      5790a765
    • Frank Barchard's avatar
      I422ToYUY2Row_AVX2 use vpmovzxbd instead of vpermq · 7ff53f32
      Frank Barchard authored
      I422ToYUY2Row_AVX2 optimized from 7 cycles per 32 pixels to 6 cycles.
      Instead of 2 vpermq and vpunpcklbw:
      vmovdqu    (%1),%%xmm2
      vmovdqu    0x00(%1,%2,1),%%xmm3
      lea        0x10(%1),%1
      vpermq     $0xd8,%%ymm2,%%ymm2
      vpermq     $0xd8,%%ymm3,%%ymm3
      vpunpcklbw %%ymm3,%%ymm2,%%ymm2
      
      ..use vpmovzxbd to expand the bytes to shorts, then vpslld and vpor
      vpmovzxbd  (%1),%%ymm2
      vpmovzxbd  0x00(%1,%2,1),%%ymm3
      vpslld     $0x10,%%ymm3,%%ymm3
      vpor       %%ymm3,%%ymm2,%%ymm2
      which reduces the port 5 bottleneck by 1 cycle.
      
      Bug: libyuv:556
      Test: out/Release/libyuv_unittest --gtest_filter=*I42?To*UY*Opt
      
      I422ToYUY2Row_AVX2 optimization
      
      Improve performance of AVX2 code by avoiding vpermq
      
      Bug: libyuv:556
      Test: /usr/local/google/home/fbarchard/iaca-lin64/bin/iaca.sh -reduceout -arch BDW out/Release/obj/libyuv_internal/row_gcc.o
      Change-Id: Ie36732da23ecea1ffcc6b297bacc962780b59ef1
      Reviewed-on: https://chromium-review.googlesource.com/898067
      Commit-Queue: Frank Barchard <fbarchard@chromium.org>
      Reviewed-by: 's avatarrichard winterton <rrwinterton@gmail.com>
      7ff53f32