1. 29 Jul, 2013 3 commits
  2. 27 Jul, 2013 2 commits
    • Ronald S. Bultje's avatar
      Inverse dimension order in token_cost array. · 118ccdcd
      Ronald S. Bultje authored
      This allows us to increment the position at the band-level only as
      we go from one band to the next; more importantly, that allows us to
      use an add instead of multiply instruction, and omit the instruction
      altogether if the band doesn't change from one coef to the next, thus
      being slightly faster (probably more noticeable on systems where a
      multiply is expensive, like arm).
      Change-Id: I4343fe35b9f9a47fa00b217bdcbf5f91ff96c381
    • Jingning Han's avatar
      Shortcut 8x8/16x16 inverse 2D-DCT · 38fa4871
      Jingning Han authored
      This commit brought back the shortcut implementation of 8x8/16x16
      inverse 2D-DCT. When the eob <= 10, it skips the inverse transform
      operations on row 4:7/4:15 in the first round. For bus_cif at 1000
      kbps, this provides about 2% speed-up at speed 0.
      Change-Id: I453e2d72956467d75be4ad8c04b4482ab889d572
  3. 26 Jul, 2013 3 commits
    • Jingning Han's avatar
      Special handle on DC only inverse 8x8 2D-DCT · 325e0aa6
      Jingning Han authored
      This commit enables a special handle for the 8x8 inverse 2D-DCT,
      where only DC coefficient is quantized to be non-zero. For bus_cif
      at 2000 kbps, it provides about 1% speed-up at speed 0.
      Change-Id: I2523222359eec26b144cf8fd4c63a4ad63b1b011
    • Paul Wilkins's avatar
      Auto min and max partition size experiment. · fe5e2a91
      Paul Wilkins authored
      Speed feature experiment to set an upper and lower
      partition size limit based on what has been seen
      in spatial neighbors.
      This seems to gives quite reasonable speed gains in local
      (10-15%) and when used with speed 0 the losses are small
      (0.25% derf, 0.35% stdhd). However, for now I am only
      enabling it on speed 1 as there may be clashes with the existing
      temporal partition selection in speed 2.
      Using a tighter min / max around the range derived from the
      neighbors increases speed further but at the cost of a
      bigger quality loss. However,  I think this spatial method could
      be combined with data from either the last frame or a variance
      method (or both) to refine the range of minimum and maximum
      partition size. I.e. consider the min and max from spatial and
      temporal neighbors and the variance recommendation.
      Change-Id: I1b96bf8b84368d6aad0c7aa600fe141b4f07435f
    • Yunqing Wang's avatar
      Modify static threshold calculation · 52256cdb
      Yunqing Wang authored
      Used 3 * standard_deviation in internal threshold calculation
      instead of fit curve. This actually approached the algorithm
      For comparison, similar tests were done:
      The overall psnr loss is less than before.
      1. derf set:
      when static-thresh = 1, psnr loss is 0.329%;
      when static-thresh = 500, psnr loss is 0.970%;
      2. stdhd set:
      when static-thresh = 1, psnr loss is 0.922%;
      when static-thresh = 500, psnr loss is 1.307%;
      Similar speedup is achieved. For example,
      clip            bitrate  static-thresh psnr    time
      akiyo(cif)       500        0          48.952  5.077s(50f)
      akiyo            500        500        48.866  4.169s(50f)
      parkjoy(1080p)   4000       0          30.388  78.20s(30f)
      parkjoy          4000       500        30.367  70.85s(30f)
      sunflower(1080p) 4000       0          44.402  74.55s(30f)
      sunflower        4000       500        44.414  68.69s(30f)
      Change-Id: Ic78833642ce1911dbbd1cb6c899a2d7e2dfcc1f3
  4. 25 Jul, 2013 7 commits
    • Yunqing Wang's avatar
      Add encoding option --static-thresh · d36852b7
      Yunqing Wang authored
      This option exists in VP8, and it was rewritten in VP9 to support
      skipping on different partition levels. After prediction is done,
      we can check if the residuals in the partition block will be all
      quantized to 0. If this is true, the skip flag is set, and only
      prediction data are needed in reconstruction. Based on DCT's energy
      conservation property, the skipping check can be estimated in
      spatial domain.
      The prediction error is calculated and compared to a threshold.
      The threshold is determined by the dequant values, and also
      adjusted by partition sizes. To be precise, the DC and AC parts
      for Y, U, and V planes are checked to decide skipping or not.
      Test showed that
      1. derf set:
      when static-thresh = 1, psnr loss is 0.666%;
      when static-thresh = 500, psnr loss is 1.162%;
      2. stdhd set:
      when static-thresh = 1, psnr loss is 1.249%;
      when static-thresh = 500, psnr loss is 1.668%;
      For different clips, encoding speedup range is between several
      percentage and 20+% when static-thresh <= 500. For example,
      clip            bitrate  static-thresh psnr    time
      akiyo(cif)       500        0          48.923  5.635s(50f)
      akiyo            500        500        48.863  4.402s(50f)
      parkjoy(1080p)   4000       0          30.380  77.54s(30f)
      parkjoy          4000       500        30.384  69.59s(30f)
      sunflower(1080p) 4000       0          44.461  85.2s(30f)
      sunflower        4000       500        44.418  78.1s(30f)
      Higher static-thresh values give larger speedup with larger
      quality loss.
      Change-Id: I857031ceb466ff314ab580ac5ec5d18542203c53
    • Dmitry Kovalev's avatar
      General cleanups. · 7131cb0e
      Dmitry Kovalev authored
      Removing unused constants, macros, and function declarations. Using
      ROUND_POWER_OF_TWO macro, vp9_zero, vp9_copy where possible. Moving
      #include from *.h to *.c. Merging for loops for motion vectors.
      Change-Id: Ic3bf841764a2bb177128bb3a6d7aa8f68229cd13
    • Dmitry Kovalev's avatar
      Adding lookup table for size group. · 08fd41cc
      Dmitry Kovalev authored
      Change-Id: Ia6144d77ebed66e0739b62e4d673e26a95aa9550
    • Adrian Grange's avatar
      Simplify handling of sub-partition motion vectors · be700e14
      Adrian Grange authored
      Simplified the code that extracts and uses the motion
      vectors for the 4 sub-partitions in rd_pick_partition.
      Change-Id: Iaf698ef7ee3aef9edd59015e1ae065dd359b17d9
    • Jingning Han's avatar
      Make coeff_optimize initialized per-plane · 2f58faff
      Jingning Han authored
      This commit makes the initialization of trellis coeff optimization
      a per-plane operation, thereby eliminating the redundant steps in
      encode_sby and encode_sbuv. It makes the encoder at speed 0 slightly
      Change-Id: Iffe9faca6a109dafc0dd69dc7273cbdec19b17cd
    • Dmitry Kovalev's avatar
      Removing vp9_adapt_mode_context function. · 47d61f00
      Dmitry Kovalev authored
      Moving code from vp9_adapt_mode_context to vp9_adapt_mode_probs.
      Change-Id: I60829c30b28968cd813551ef3a206dfb98d323c9
    • Yaowu Xu's avatar
      fix a bug where flags are not reset · 3e386aef
      Yaowu Xu authored
      The feature that uses small partition results as a measure to skip
      mode evaluation at larger partition requires the flags to be reset.
      The reset was missing in the code path that calls rd_use_partition().
      Change-Id: Ia0a3a0aee1a862b6e2333d596808db7c48033d50
  5. 24 Jul, 2013 7 commits
  6. 23 Jul, 2013 10 commits
    • Jingning Han's avatar
      Unify the use of encode_b_args/optimize_block_args · ab77828b
      Jingning Han authored
      The struct optimize_block_args is defined same as encode_b_args.
      Remove this redundant definition, and use encode_b_args consistently.
      Change-Id: I1703aeeb3bacf92e98a34f4355202712110173d9
    • Dmitry Kovalev's avatar
      Removing LOW_PRECISION_MV_UPDATE define. · 8d13b0d1
      Dmitry Kovalev authored
      Change-Id: I78d16ee758e1fae0200b746f00031f6d9c6d6ce7
    • Adrian Grange's avatar
      Rolled-up several for loops into one · 646edbc1
      Adrian Grange authored
      Several consecutive for loops executed over the same
      index range, so I rolled them into one.
      Change-Id: I5cfcc8c38c738478965768409cca9d09adf224e1
    • Dmitry Kovalev's avatar
      Removing vp9_is_interpolating_filter array. · db7f5d28
      Dmitry Kovalev authored
      All filters are interpolating now, so we don't need this array, all
      values from this array are evaluated to true.
      Change-Id: I9af6d8219ae0eb984063cd15e4e2296374ae4961
    • Jingning Han's avatar
      Make xform_quant operations tx_type independent · e9e2fe8e
      Jingning Han authored
      The xform_quant() module is only used by inter modes, hence removing
      the redundant switches therein conditioned on tx_type.
      Change-Id: Ib87ce5b2f2e4cbf3ceb133a1108afa173c933a3f
    • Jingning Han's avatar
      Skip inverse transform when eob is zero · 0359ad7f
      Jingning Han authored
      When all the transform coefficients were quantized to zero, skip
      the inverse transform operation. For bus_cif at 1000 kbps, the
      runtime goes from 154967ms -> 149842ms, i.e., about 3% speed-up,
      at speed 0.
      Change-Id: Ic0a813fff5e28972d4888ee42d8747846a6c3cc6
    • Scott LaVarnway's avatar
      pack_inter_mode_mvs cleanup · 7bc294a3
      Scott LaVarnway authored
      xd->mode_info_context is set to m prior to this call.
      Change-Id: Ibc442529961750c29ccf0c6cae08cb2b0431415f
    • Jim Bankoski's avatar
      clean up bw, bh · 86a9dec7
      Jim Bankoski authored
      many structures use bw and bh and they have different meanings.   This cl attempts
      to start this clean up and remove unneccessary 2 step look up log and then
      shift operations...
      also removed partition type multiple operation code in bitstream.c.
      Change-Id: I7e03e552bdfc0939738e430862e3073d30fdd5db
    • Paul Wilkins's avatar
      Renaming of segment constants. · 32042af1
      Paul Wilkins authored
      The minimum unit for segmentation in the segment map
      is now 8x8 so it is misleading to use MB_ as macro-block
      traditionally refers to a 16x16 region.
      Change-Id: I0b55a6f0426bb46dd13435fcfa5bae0a30a7fa22
    • James Zern's avatar
      vp9: make some static tables const · 3c8cce35
      James Zern authored
      Change-Id: I8bcae51271673da8755c66a51aea005dfe6a3739
  7. 22 Jul, 2013 8 commits
    • Ronald S. Bultje's avatar
      More optimizations for cost_coeffs(). · e20fcd95
      Ronald S. Bultje authored
      4x4:    163 ->  123 cycles (33% faster)
      8x8:    491 ->  399 cycles (23% faster)
      16x16: 1889 -> 1763 cycles (7% faster)
      32x32: 8311 -> 8180 cycles (1.6% faster)
      Overall encoding time of first 50 frames of bus (speed 0) @ 1500kbps
      goes from 1min4.33 to 1min3.00, i.e. 2.11% faster.
      Change-Id: Ib52d1dbb5649b14de769d3e7a74af67440b5284f
    • Dmitry Kovalev's avatar
      Adding update_tx_counts function. · b2fc6fa9
      Dmitry Kovalev authored
      Moving common encoder/decoder code to update_tx_counts. Also renaming
      vp9_get_pred_probs_tx_size to get_tx_probs2 and adding get_tx_probs to
      call vp9_get_pred_context_tx_size inside read_selected_tx_size only once
      (twice before).
      Change-Id: Ia50247f3893de88ef8e9041b0d44be44a40aaa4d
    • Yaowu Xu's avatar
      fix a build error · fc186dca
      Yaowu Xu authored
      Change-Id: I3b05687f439ff6a7c426d2c97a6c58c831fa51ac
    • Deb Mukherjee's avatar
      Diamond search change to accelerate movement · a1e2d50b
      Deb Mukherjee authored
      Optional change in diamond search to continue in the best move
      direction until that move turns worse.
      This is still WIP since the exact way the new method is to be used is
      under investigation. One option is to make it an option in diamond
      search and use it only when motion is large.
      Overall slightly positive on derfraw300 +0.02%, stdhdraw +0.13%,
      but works a lot better for high motion sequences (ex. football : +1%).
      Change-Id: If88e01a6021daa0cda934680cdc70be1ee04f798
    • Jingning Han's avatar
      Optimize operation flow in sub8x8 rd loop · 409e77f2
      Jingning Han authored
      Stack the rate-distortion statistics in the sub8x8 rd loop. This allows
      the encoder to skip the forward transform, quantization, and coeff cost
      estimation, in the sub8x8 rd optimization search, if the motion
      vector(s) are of integer pixel value, and have been tested in the
      previous prediction filter type rd loops of the same block.
      This gives about 2% speed-up for bus_cif at 2000 kpbs, for speed 0.
      Its efficacy depends how frequently the motion search will select an
      integer motion vector.
      Change-Id: Iee15d4283ad4adea05522c1d40b198b127e6dd97
    • Paul Wilkins's avatar
      Re-order mode search in rd. · 1d189d64
      Paul Wilkins authored
      Mode search order in rd loop changed to better reflect
      observed hit counts.
      Also some adjustment of the baseline mode rd thresholds
      to reflect the order change and observed frequencies.
      Change-Id: I47a131cc83e11551df8add6d6d8d413d78d3a63c
    • Jim Bankoski's avatar
      fix left over overflow · 2ac8b50c
      Jim Bankoski authored
      This cl fixes issues rbultje brought up. that I somehow neglected when I
      submitted yaowu's patch.
      Change-Id: I07ad18796317822510b96e951c88d29f194a3c2e
    • Paul Wilkins's avatar
      Fix build error. · 888375d2
      Paul Wilkins authored
      When CONFIG_POSTPROC is set there was a now
      invalid reference to cm->filter_level.
      Changed to cpi->mb.e_mbd.lf.filter_level in line with
      change Iaf5fb71c33719cdfa1b991f671caf071be9ea035
      Change-Id: If746e60044903f7ba8d0d346225b3d015226c7d0