1. 22 Jul, 2017 1 commit
  2. 20 Jul, 2017 7 commits
  3. 19 Jul, 2017 5 commits
    • Johann Koenig's avatar
      Merge "Earmark extra space for VSX." · e1809501
      Johann Koenig authored
      e1809501
    • Jerome Jiang's avatar
    • Johann's avatar
      quantize test: eob is output · bde2e4aa
      Johann authored
      eob values are generated by the function.
      
      Change-Id: I8ce92100e83022bff99888a5a7e6ef378c49fda3
      bde2e4aa
    • Han Shen's avatar
      Earmark extra space for VSX. · b72d3e8a
      Han Shen authored
      Backend specific optimization for PPC VSX reads 16 bytes, whereas arm neon /
      sse2 only reads <= 8 bytes. Although the extra bytes read are actually never
      used, this is not a warrant for groping around.  Fixed by allocating more when
      building for VSX. This is reported by asan.
      
      Also note - PPC does have assembly that loads 64-bit content from memory - lxsdx
      loads one 64-bit doubleword (whereas lxvd2x loads two 64-bit doubleword) from
      memory. However, we only have "vec_vsx_ld" builtins that mapped to lxvd2x, no
      builtins to lxsdx. The only way to access lxsdx is through inline assembly,
      which does not fit well in the origin paradigm.
      
      Refer:
        vsx:
          vpx_tm_predictor_4x4_vsx @ third_party/libvpx/git_root/vpx_dsp/ppc/intrapred_vsx.c
        neon:
          vpx_tm_predictor_4x4_neon @ third_party/libvpx/git_root/vpx_dsp/arm/intrapred_neon_asm.asm
        sse2:
          tm_predictor_4x4 @ third_party/libvpx/git_root/vpx_dsp/x86/intrapred_sse2.asm
      
      BUG=b/63112600
      
      Tested:
        asan tests passed.
      
      Change-Id: I5f74b56e35c05b67851de8b5530aece213f2ce9d
      b72d3e8a
    • Johann Koenig's avatar
      Merge "variance: call C comp_avg_pred" · 89a116f4
      Johann Koenig authored
      89a116f4
  4. 18 Jul, 2017 12 commits
  5. 17 Jul, 2017 2 commits
    • Marco's avatar
      vp9: Fix to setting content_state for real-time mode. · ad563713
      Marco authored
      When content_state_sb is set to LowVarHighSumdiff, don't reset
      it to VeryHighSad. Visually better on clips with strong lighting changes.
      
      Small/negligible change in RTC metrics and speed.
      
      Change-Id: I20c383e3c4cf8d1149de5f9260449c0b7cf7c6aa
      ad563713
    • Marco's avatar
      vp9: Reuse motion from choose_partitioning in NEWMV search. · 0c9e2f4c
      Marco authored
      When int_pro_motion_estimation is done for superblock in
      choose_partitioning, use it to avoid the full_pixel_search
      for NEWMV mode, if bsize is >= 32X32.
      
      For speed > 7.
      Small/neutral change on RTC metrics.
      ~1-2% speedup on arm on high motion clip.
      
      Change-Id: I3cfe6833ff4bf75d4afa83eaf058ad45729de85b
      0c9e2f4c
  6. 15 Jul, 2017 1 commit
  7. 14 Jul, 2017 2 commits
  8. 13 Jul, 2017 2 commits
    • Johann's avatar
      quantize test: use Buffer · e3fa4ae8
      Johann authored
      Although the low bitdepth functions are identical (excepting the need
      for larger intermediate values) they do not pass these tests. This
      improves the error output to aid debugging.
      
      Simplify buffer usage with Buffer and removing unnecessarily aligned
      variables.
      
      eob is a single element and never written using aligned instructions.
      
      BUG=webm:1426
      
      Change-Id: Ic95789a135cf1e8a3846d85270f2b818f6ec7e35
      e3fa4ae8
    • James Zern's avatar
      fix 'make exampletest' w/CONFIG_REALTIME_ONLY · 96046693
      James Zern authored
      for tests that aren't explicitly testing 2-pass behavior use --passes=1
      with this configuration
      
      Change-Id: I6a1520ecc65d0f626486604310af29dacb9f197f
      96046693
  9. 12 Jul, 2017 8 commits