1. 10 Sep, 2013 8 commits
  2. 09 Sep, 2013 8 commits
  3. 08 Sep, 2013 2 commits
    • Yaowu Xu's avatar
      Reduce the amount of extension in src frames · 65c2444e
      Yaowu Xu authored
      The commit changes the border pixel extension from 160 pixel each side
      to what is necessary in arnr filter or motion estimation portion, i.e.
      16 pixel on top and left side. For right or bottom side, the extension
      is changed to either round up image size to multiple of 64 or at least
      16 pixels.
      
      Change-Id: Ic05e19b94368c1ab4df568723aae5734e6c3d2c5
      65c2444e
    • Jim Bankoski's avatar
      Merge "New mode_info_context storage" · e3785660
      Jim Bankoski authored
      e3785660
  4. 07 Sep, 2013 1 commit
    • Jingning Han's avatar
      Fix overflow issue in 16x16 quantization SSSE3 · 09bc942b
      Jingning Han authored
      The 16x16 transform unit test suggested that the peak coefficient
      value can reach 32639. This could cause potential overflow issue
      in the SSSE3 implmentation of 16x16 block quantization. This commit
      fixes this issue by replacing addition with saturated addition.
      
      Change-Id: I6d5bb7c5faad4a927be53292324bd2728690717e
      09bc942b
  5. 06 Sep, 2013 7 commits
    • Deb Mukherjee's avatar
      d1268c59
    • Paul Wilkins's avatar
      Enable kf restrictions at speed 4 · f15cdc74
      Paul Wilkins authored
      Change-Id: I453409d3be3f5fe118b15affde45cb52184aef20
      f15cdc74
    • Deb Mukherjee's avatar
      Support a constant quality mode in VP9 · e378a89b
      Deb Mukherjee authored
      Adds a new end-usage option for constant quality encoding in vpx. This
      first version implemented for VP9, encodes all regular inter frames
      using the quality specified in the --cq-level= option, while encoding
      all key frames and golden/altref frames at a quality better than that.
      
      The current performance on derfraw300 is +0.910% up from bitrate control,
      but achieved without multiple recode loops per frame.
      
      The decision for qp for each altref/golden/key frame will be improved
      in subsequent patches based on better use of stats from the first pass.
      Further, the qp for regular inter frames may also be varied around the
      provided cq-level.
      
      Change-Id: I6c4a2a68563679d60e0616ebcb11698578615fb3
      e378a89b
    • Yaowu Xu's avatar
      cleanup cpplint warnings · afffa3d9
      Yaowu Xu authored
      Suggested by James Zern to clear out cpplint warnings for all unit
      test code.
      
      Change-Id: I731a3fa4d2a257eb9ef733426ba84286fbd7ea34
      afffa3d9
    • Scott LaVarnway's avatar
      New mode_info_context storage · dae17734
      Scott LaVarnway authored
      mode_info_context was stored as a grid of MODE_INFO structs.
      The grid now constists of a pointer to a MODE_INFO struct and
      a "in the image" flag.  The MODE_INFO structs are now stored
      as a stream, eliminating unnecessary copies and is a little
      more cache friendly.
      
      For the test clips used, the decoder performance improved
      by ~4.3% (1080p) and ~9.7% (720p).
      
      Patch Set 2: Re-encoded clips with latest. Now ~1.7% (1080p)
      and 5.9% (720p).
      
      Change-Id: I846f29e88610fce2523ca697a9a9ef2a182e9256
      dae17734
    • Jim Bankoski's avatar
    • hkuang's avatar
      Merge "Speed up idct8x8 by rearrange instructions. Speed improve from 264% ~... · 34764049
      hkuang authored
      Merge "Speed up idct8x8 by rearrange instructions. Speed improve from 264% ~ 270% to 280% ~ 300% base on assembly-perf."
      34764049
  6. 05 Sep, 2013 12 commits
  7. 04 Sep, 2013 2 commits
    • Yaowu Xu's avatar
      make bsize requirement for SEG_LVL_SKIP explicit · 1ee66933
      Yaowu Xu authored
      The segment feature SEG_LVL_SKIP requires the prediction unit size
      to be at least BLOCK_8X8. This commit makes the requirement to be
      explicit. This is to prevent future encoder implementations from
      making wrong choices.
      
      Change-Id: I0127f0bd4c66e130b81f0cb0a8d3dbfe3b2da5c2
      1ee66933
    • hkuang's avatar
      Speed up idct8x8 by rearrange instructions. · 01c4e044
      hkuang authored
      Speed improve from 264% ~ 270% to 280% ~ 300% base on assembly-perf.
      
      Change-Id: I3e2cc818ec14b432204ff43732f39b6438db685d
      01c4e044