1. 07 Dec, 2012 1 commit
    • Ronald S. Bultje's avatar
      32x32 transform for superblocks. · c456b35f
      Ronald S. Bultje authored
      This adds Debargha's DCT/DWT hybrid and a regular 32x32 DCT, and adds
      code all over the place to wrap that in the bitstream/encoder/decoder/RD.
      
      Some implementation notes (these probably need careful review):
      - token range is extended by 1 bit, since the value range out of this
        transform is [-16384,16383].
      - the coefficients coming out of the FDCT are manually scaled back by
        1 bit, or else they won't fit in int16_t (they are 17 bits). Because
        of this, the RD error scoring does not right-shift the MSE score by
        two (unlike for 4x4/8x8/16x16).
      - to compensate for this loss in precision, the quantizer is halved
        also. This is currently a little hacky.
      - FDCT and IDCT is double-only right now. Needs a fixed-point impl.
      - There are no default probabilities for the 32x32 transform yet; I'm
        simply using the 16x16 luma ones. A future commit will add newly
        generated probabilities for all transforms.
      - No ADST version. I don't think we'll add one for this level; if an
        ADST is desired, transform-size selection can scale back to 16x16
        or lower, and use an ADST at that level.
      
      Additional notes specific to Debargha's DWT/DCT hybrid:
      - coefficient scale is different for the top/left 16x16 (DCT-over-DWT)
        block than for the rest (DWT pixel differences) of the block. Therefore,
        RD error scoring isn't easily scalable between coefficient and pixel
        domain. Thus, unfortunately, we need to compute the RD distortion in
        the pixel domain until we figure out how to scale these appropriately.
      
      Change-Id: I00386f20f35d7fabb19aba94c8162f8aee64ef2b
      c456b35f
  2. 05 Dec, 2012 2 commits
    • Johann's avatar
      Begin to refactor vpx_scale usage in VP9 · 52d350fe
      Johann authored
      Only declare the functions in vpx_scale RTCD and include the relevant
      header.
      
      Remove unused files and functions in vpx_scale to avoid wasting time
      renaming. vpx_scale/win32/scaleopt.c contains functions which have not
      been called in a long time but are potentially optimized.
      
      The 'vp8' functions have not been renamed yet. That is for after the
      cleanup.
      
      Change-Id: I2c325a101d60fa9d27e7dfcd5b52a864b4a1e09c
      52d350fe
    • Johann's avatar
      Remove ARM optimizations from VP9 · a9056729
      Johann authored
      Change-Id: I9f0ae635fb9a95c4aa1529c177ccb07e2b76970b
      a9056729
  3. 03 Dec, 2012 2 commits
    • Johann's avatar
      Begin to refactor vpx_scale usage in VP9 · c6bd29e2
      Johann authored
      Only declare the functions in vpx_scale RTCD and include the relevant
      header.
      
      Remove unused files and functions in vpx_scale to avoid wasting time
      renaming. vpx_scale/win32/scaleopt.c contains functions which have not
      been called in a long time but are potentially optimized.
      
      The 'vp8' functions have not been renamed yet. That is for after the
      cleanup.
      
      Change-Id: I2c325a101d60fa9d27e7dfcd5b52a864b4a1e09c
      c6bd29e2
    • Johann's avatar
      Remove ARM optimizations from VP9 · 34591b54
      Johann authored
      Change-Id: I9f0ae635fb9a95c4aa1529c177ccb07e2b76970b
      34591b54
  4. 30 Nov, 2012 1 commit
  5. 29 Nov, 2012 1 commit
  6. 28 Nov, 2012 1 commit
    • Jim Bankoski's avatar
      remove postproc invokes · 85cba19e
      Jim Bankoski authored
      and some miscellaneous invoke left overs
      
      Change-Id: I63191b1bfd3bea4ce30cceaeb686ec850570fc43
      85cba19e
  7. 27 Nov, 2012 1 commit
    • John Koleszar's avatar
      Add vp9_ prefix to all vp9 files · fcccbcbb
      John Koleszar authored
      Support for gyp which doesn't support multiple objects in the same
      static library having the same basename.
      
      Change-Id: Ib947eefbaf68f8b177a796d23f875ccdfa6bc9dc
      fcccbcbb
  8. 26 Nov, 2012 1 commit
    • Yunqing Wang's avatar
      Improve sad3x16 SSE2 function · e7cd8071
      Yunqing Wang authored
      Vp9_sad3x16_sse2() is heavily called in decoder, in which the
      unaligned reads consume lots of cpu cycles. When CONFIG_SUBPELREFMV
      is off, the unaligned offset is 1. In this situation,
      we can adjust the src_ptr to be 4-byte aligned, and then do the
      aligned reads. This reduced the reading time significantly. Tests
      on 1080p clip showed over 2% decoder performance gain with
      CONFIG_SUBPELREFM off.
      
      Change-Id: I953afe3ac5406107933ef49d0b695eafba9a6507
      e7cd8071
  9. 25 Nov, 2012 1 commit
  10. 21 Nov, 2012 1 commit
  11. 18 Nov, 2012 1 commit
    • Jim Bankoski's avatar
      clean out some of the rtcd code. · f4871b6a
      Jim Bankoski authored
      This removes functions that are no longer needed and cleans up some warnings.
      
      Change-Id: I292a4c3694e9c1d68ce99cea390905b198434719
      f4871b6a
  12. 17 Nov, 2012 1 commit
  13. 16 Nov, 2012 1 commit
  14. 15 Nov, 2012 1 commit
  15. 13 Nov, 2012 2 commits
  16. 08 Nov, 2012 1 commit
    • Yunqing Wang's avatar
      Optimize 16x16 dequant and idct · 6c17c9fa
      Yunqing Wang authored
      As suggested by Yaowu, simplified 16x16 dequant and idct. In decoder,
      after detoken step, we know the number of non-zero dct coefficients
      (eobs) in a macroblock. Idct calculation can be skipped or simplified
      based on eobs, which improves the decoder performance.
      
      Change-Id: I9ffa1cb134bcb5a7d64fcf90c81871a96d1b4018
      6c17c9fa
  17. 07 Nov, 2012 1 commit
  18. 06 Nov, 2012 2 commits
    • Yaowu Xu's avatar
      fixed function prototype · a879b4e6
      Yaowu Xu authored
      so they are consistent with actual definitions of the functions
      
      Change-Id: Ie4b4e81b3da3e288fc2edbbd2b393a5c54d2556b
      a879b4e6
    • Jim Bankoski's avatar
      remove invoke_search macro · 7849aa20
      Jim Bankoski authored
      Removed invoke search from encoder
      
      Change-Id: I3d809b795abe6df0e71366edfe94026aaede14fb
      7849aa20
  19. 02 Nov, 2012 3 commits
    • Yunqing Wang's avatar
      Fix eobs data type · d41b0e64
      Yunqing Wang authored
      The block sizes for decoding tokens are up to 16x16, which means
      eobs is within [0, 256]. Using (signed) char is not enough. Changed
      eobs data type to unsigned short to fix the problem.
      
      Change-Id: I88a7d3098e1f1604c336d6adb88ffec971fb03a6
      d41b0e64
    • Ronald S. Bultje's avatar
      Place non-static function prototypes in a header file. · 3c4f47e8
      Ronald S. Bultje authored
      Change-Id: I7cd21b9f1e69f4e0b3338bfe27b3c67e4b47de58
      3c4f47e8
    • John Koleszar's avatar
      vpx_scale: sync from master · 06f3e51d
      John Koleszar authored
      Update vpx_scale from current code in master, run style transform, fix
      lint warnings.
      
      Change-Id: I47eadeb5b6881d448ea3728537f9b8a5b5aac78e
      06f3e51d
  20. 01 Nov, 2012 2 commits
  21. 31 Oct, 2012 4 commits
  22. 30 Oct, 2012 2 commits
  23. 29 Oct, 2012 2 commits
  24. 26 Oct, 2012 1 commit
    • Scott LaVarnway's avatar
      Faster 8t filtering · ce811f87
      Scott LaVarnway authored
      Quickly modified the ssse3 sixtap filters to support eight taps.  For the test
      clip used, a 23+% boost in decoder performance was seen.  We can
      revisit later and improve further.
      
      Change-Id: I5f59860459e80d6fa23e6cc0fd91296a969f5240
      ce811f87
  25. 25 Oct, 2012 2 commits
  26. 22 Oct, 2012 2 commits