1. 09 Mar, 2013 1 commit
    • Deb Mukherjee's avatar
      Continued experiment with nonzero count · a28139c8
      Deb Mukherjee authored
      Adds probability updates for extra bits for the nzcs, code for
      getting nzc stats, plus some minor cleanups and fixes.
      
      Change-Id: If2814e7f04fb52f5025ad9f400f3e6c50a00b543
      a28139c8
  2. 08 Mar, 2013 3 commits
    • Yunqing Wang's avatar
      Add vp9_idct4_1d_sse2 · 11ca81f8
      Yunqing Wang authored
      Added SSE2 idct4_1d which is called by vp9_short_iht4x4. Also,
      modified the parameter type passed to vp9_short_iht functions to
      make it work with rtcd prototype.
      
      Change-Id: I81ba7cb4db6738f1923383b52a06deb760923ffe
      11ca81f8
    • Jingning Han's avatar
      Extend diff MV limit from +/-256 to +/-1024 · 2a5278bd
      Jingning Han authored
      Increase the motion search range by 4x. Change MV_CLASS tree of the
      entropy coding to allow two additional mv classes to cover the
      extended motion vector limit. The codec determines the effective
      motion search range conditioned on the actual frame dimension.
      
      It provides coding gains:
      
      stdhd 0.39%
      yt    0.56%
      hd    0.47%
      
      Major coding performance gains are packed in several sequences with
      intense motion activities, e.g., ped_1080p gains 7% at high bit-rates,
      and on average 3%.
      
      TODO: Need to further tune the rate control and motion search units.
      
      Change-Id: Ib842540a6796fbee5a797809433ef6a477c6d78d
      2a5278bd
    • Ronald S. Bultje's avatar
      Add support for tx_select in i8x8 encoding in keyframes. · b41dee84
      Ronald S. Bultje authored
      Also enable tx_select for keyframes.
      
      Change-Id: Iadb1231d9fa7af0c8dce3d9b41830b93a302479e
      b41dee84
  3. 07 Mar, 2013 7 commits
    • Yunqing Wang's avatar
      Optimize add_constant_residual function · f2407826
      Yunqing Wang authored
      Optimized adding constant diff to predictor, which gave about
      2% decoder performance gain.
      
      Change-Id: I47db20c31428e8c4a8f16214a85cbe386a6e9303
      f2407826
    • Yunqing Wang's avatar
      Allocate 16-byte aligned diff buffer · b339aea6
      Yunqing Wang authored
      This was done based on John's suggestion.
      
      Change-Id: I62516a513c31fe3dbea0d6cd063df79d9e819ec8
      b339aea6
    • Dmitry Kovalev's avatar
      Consistent usage of ROUND_POWER_OF_TWO macro. · 3603dfb6
      Dmitry Kovalev authored
      Change-Id: I44660975e9985310d8c654c158ee7a61291b5a08
      3603dfb6
    • Ronald S. Bultje's avatar
      Update ADST selection if tx_size < block_size. · 89e4ce20
      Ronald S. Bultje authored
      Change-Id: Ic9b336486774c95ffbb92adcb110cc0fc2a83cc5
      89e4ce20
    • Ronald S. Bultje's avatar
      Re-add support for ADST in superblocks. · d3724abe
      Ronald S. Bultje authored
      This also changes the RD search to take account of the correct block
      index when searching (this is required for ADST positioning to work
      correctly in combination with tx_select).
      
      Change-Id: Ie50d05b3a024a64ecd0b376887aa38ac5f7b6af6
      d3724abe
    • Yunqing Wang's avatar
      Fix issue in add_residual intrinsic function · 31623715
      Yunqing Wang authored
      Yaowu found this function had a compiling issue with MSVC because
      of using _mm_storel_pi((__m64 *)(dest + 0 * stride), (__m128)p0).
      To be safe, changed back to use integer store instruction.
      
      Also, for some build, diff could not always be 16-byte aligned.
      Changed that in the code.
      
      Change-Id: I9995e5446af15dad18f3c5c0bad1ae68abef6c0d
      31623715
    • Deb Mukherjee's avatar
      Coding con-zero count rather than EOB for coeffs · eb6ef241
      Deb Mukherjee authored
      This patch revamps the entropy coding of coefficients to code first
      a non-zero count per coded block and correspondingly remove the EOB
      token from the token set.
      
      STATUS:
      Main encode/decode code achieving encode/decode sync - done.
      Forward and backward probability updates to the nzcs - done.
      Rd costing updates for nzcs - done.
      Note: The dynamic progrmaming apporach used in trellis quantization
      is not exactly compatible with nzcs. A suboptimal approach has been
      used instead where branch costs are updated to account for changes
      in the nzcs.
      
      TODO:
      Training the default probs/counts for nzcs
      
      Change-Id: I951bc1e22f47885077a7453a09b0493daa77883d
      eb6ef241
  4. 06 Mar, 2013 2 commits
    • Paul Wilkins's avatar
      Added stricter Q control flag. · db6ad013
      Paul Wilkins authored
      Added a variant of the one shot maxQ flag
      for two pass that forces a fixed Q for the
      normal inter frames. Disabled by default.
      Also small adjustment to the Bits per MB
      estimation.
      Change-Id: I87efdfb2d094fe1340ca9ddae37470d7b278c8b8
      db6ad013
    • Yunqing Wang's avatar
      Optimize add_residual function · 943c6d71
      Yunqing Wang authored
      Optimized adding diff to predictor, which gave 0.8% decoder
      performance gain.
      
      Change-Id: Ic920f0baa8cbd13a73fa77b7f9da83b58749f0f8
      943c6d71
  5. 05 Mar, 2013 2 commits
    • Dmitry Kovalev's avatar
      Code cleanup. · 7f99c3c5
      Dmitry Kovalev authored
      Removing redundant 'extern' keywords, fixing formatting and #include order,
      code simplification.
      
      Change-Id: I0e5fdc8009010f3f885f13b5d76859b9da511758
      7f99c3c5
    • Ronald S. Bultje's avatar
      Make superblocks independent of macroblock code and data. · 111ca421
      Ronald S. Bultje authored
      Split macroblock and superblock tokenization and detokenization
      functions and coefficient-related data structs so that the bitstream
      layout and related code of superblock coefficients looks less like it's
      a hack to fit macroblocks in superblocks.
      
      In addition, unify chroma transform size selection from luma transform
      size (i.e. always use the same size, as long as it fits the predictor);
      in practice, this means 32x32 and 64x64 superblocks using the 16x16 luma
      transform will now use the 16x16 (instead of the 8x8) chroma transform,
      and 64x64 superblocks using the 32x32 luma transform will now use the
      32x32 (instead of the 16x16) chroma transform.
      
      Lastly, add a trellis optimize function for 32x32 transform blocks.
      
      HD gains about 0.3%, STDHD about 0.15% and derf about 0.1%. There's
      a few negative points here and there that I might want to analyze
      a little closer.
      
      Change-Id: Ibad7c3ddfe1acfc52771dfc27c03e9783e054430
      111ca421
  6. 04 Mar, 2013 2 commits
    • Yunqing Wang's avatar
      Optimize vp9_short_idct4x4llm function · e8bc9f42
      Yunqing Wang authored
      Wrote a SSE2 vp9_short_idct4x4llm to improve the decoder
      performance.
      
      Change-Id: I90b9d48c4bf37aaf47995bffe7e584e6d4a2c000
      e8bc9f42
    • Jingning Han's avatar
      Support 16K sequence coding · 5957b2b5
      Jingning Han authored
      Fixed a couple of variable/function definitions, as well as header
      handling to support 16K sequence coding at high bit-rates.
      
      The width and height are each specified by two bytes in the header.
      Use an extra byte to explicitly indicate the scaling factors in
      both directions, each ranging from 0 to 15.
      
      Tested coding up to 16400x16400 dimension.
      
      Change-Id: Ibc2225c6036620270f2c0cf5172d1760aaec10ec
      5957b2b5
  7. 02 Mar, 2013 3 commits
  8. 01 Mar, 2013 2 commits
    • Yaowu Xu's avatar
      Adjust the max_gf_interval initialization · cea8cd08
      Yaowu Xu authored
      to be a fixed value of 15.
      
      Test results:
      cif:  .124%, .068%, .081%
      std-hd: 2.809%, 3.174%, 2.705%
      
      Change-Id: I380c8152c973506094da15eab59e3aa22b75a983
      cea8cd08
    • Yunqing Wang's avatar
      Add eob<=10 case in idct32x32 · c550bb3b
      Yunqing Wang authored
      Simplified idct32x32 calculation when there are only 10 or less
      non-zero coefficients in 32x32 block. This helps the decoder
      performance.
      
      Change-Id: If7f8893d27b64a9892b4b2621a37fdf4ac0c2a6d
      c550bb3b
  9. 28 Feb, 2013 12 commits
  10. 27 Feb, 2013 6 commits
    • Dmitry Kovalev's avatar
      Code cleanup. · 347f3a0a
      Dmitry Kovalev authored
      Fixing code style, using array lookup instead of switch statements for
      forward hybrid transforms (in the same way as for their inverses).
      Consistent usage of ROUND_POWER_OF_TWO macro in appropriate places.
      
      Change-Id: I0d3822ae11f928905fdbfbe4158f91d97c71015f
      347f3a0a
    • Dmitry Kovalev's avatar
      Motion vectors code cleanup. · 0c0de002
      Dmitry Kovalev authored
      Fixing indentation, removing redundant parenthesis, deciphering single
      letter variable names, better spacing.
      
      Change-Id: I1d447a7d69eddbf1e94e0820423615f40ea2d591
      0c0de002
    • Yunqing Wang's avatar
      Remove unused file · bf6cca44
      Yunqing Wang authored
      Removed vp9/decoder/x86/vp9_idct_blk_mmx.c
      
      Change-Id: I07ab06382a394cf556fa5a8e3c98b91f6e4f9ce8
      bf6cca44
    • Yunqing Wang's avatar
      Remove unused file · 5ef694cf
      Yunqing Wang authored
      Removed vp9_idctllm_mmx.asm
      
      Change-Id: I7152756f23a5a09ed69e8fb40edb2ab3237290fe
      5ef694cf
    • Ronald S. Bultje's avatar
      Move eob from BLOCKD to MACROBLOCKD. · e8c74e2b
      Ronald S. Bultje authored
      Consistent with VP8.
      
      Change-Id: I8c316ee49f072e15abbb033a80e9c36617891f07
      e8c74e2b
    • John Koleszar's avatar
      Remove unused vp9_copy32xn · 7ad8dbe4
      John Koleszar authored
      This function was part of an optimization used in VP8 that required
      caching two macroblocks. This is unused in VP9, and might not
      survive refactoring to support superblocks, so removing it for now.
      
      Change-Id: I744e585206ccc1ef9a402665c33863fc9fb46f0d
      7ad8dbe4