1. 29 Sep, 2014 1 commit
    • Deb Mukherjee's avatar
      Adds two new subpel search methods · 4e9c0d2a
      Deb Mukherjee authored
      One is a more aggressive version of the pruned subpel tree
      search where only a single halfpel candidate is searched.
      The search candidate is based on a surface fit result.
      The other is a method to obtain the subpel position at one
      shot based on the same surface fit.
      
      The methods have not been deployed in any speed setting yet.
      
      Change-Id: I34fef3f2e34f11396c9d1ba97f4be8c4ffca62d3
      4e9c0d2a
  2. 26 Sep, 2014 1 commit
    • Yunqing Wang's avatar
      Skip the partition search for still frames · 1fcbf6ed
      Yunqing Wang authored
      This patch re-enabled the feature in Pengchong's patch
      (commit 12861260). Originally, it
      was turned on while use_lastframe_partitioning > 0(not used anymore).
      Now it was added as a feature, and turned on while speed >= 2.
      As described in the original patch, this feature helps speed up the
      slideshows in YouTube.
      
      Change-Id: I1b0f18d65da1ee1c8d1e117dabba910c5207c471
      1fcbf6ed
  3. 22 Sep, 2014 1 commit
    • Jingning Han's avatar
      Adaptive mode search scheduling · eee904c9
      Jingning Han authored
      This commit enables an adaptive mode search order scheduling scheme
      in the rate-distortion optimization. It changes the compression
      performance by -0.433% and -0.420% for derf and stdhd respectively.
      It provides speed improvement for speed 3:
      
      bus CIF 1000 kbps
      24590 b/f, 35.513 dB, 7864 ms ->
      24696 b/f, 35.491 dB, 7408 ms (6% speed-up)
      
      stockholm 720p 1000 kbps
      8983 b/f, 35.078 dB, 65698 ms ->
      8962 b/f, 35.054 dB, 60298 ms (8%)
      
      old_town_cross 720p 1000 kbps
      11804 b/f, 35.666 dB, 62492 ms ->
      11778 b/f, 35.609 dB, 56040 ms (10%)
      
      blue_sky 1080p 1500 kbps
      57173 b/f, 36.179 dB, 77879 ms ->
      57199 b/f, 36.131 dB, 69821 ms (10%)
      
      pedestrian_area 1080p 2000 kbps
      74241 b/f, 41.105 dB, 144031 ms ->
      74271 b/f, 41.091 dB, 133614 ms (8%)
      
      Change-Id: Iaad28cbc99399030fc5f9951eb5aa7fa633f320e
      eee904c9
  4. 11 Sep, 2014 2 commits
    • Jingning Han's avatar
      Remove unused speed feature · 00fe92c2
      Jingning Han authored
      The speed feature that skips compound inter prediction modes was
      subsumed by other speed features and effectively was not in use.
      This commit removes it.
      
      Change-Id: I22b0c71a8ddd15d93b25d86fa63a1dce2ba6a1a9
      00fe92c2
    • Jingning Han's avatar
      Refactor to remove speed feature dependency on mode search order · f9f08797
      Jingning Han authored
      This commit refactor the rate-distortion optimization search for
      regular block sizes to remove the speed feature dependency on mode
      search order.
      
      Change-Id: Ied033ee484c2957e17baa7b6450b720fe7dd0e7d
      f9f08797
  5. 29 Aug, 2014 1 commit
    • Jingning Han's avatar
      Skip intra mode tests depending on inter residuals · 4282955e
      Jingning Han authored
      This commit allows encoder to skip intra coding mode test, when
      the known inter residual is less than the source variance. It
      reduces the runtime of speed 3 for test clips:
      bus cif 1000 kbps: 8587 ms -> 8260 ms, 3.8% speed-up
      pedestrian 1080p 2000 kbps: 161381 ms -> 155241 ms, 3.7% speed-up.
      
      The compression performance is down by
      derf   -0.36%
      stdhd  -0.25%
      
      Change-Id: I75ce1e035b4da2153cb1ac14111d1a07c05a735d
      4282955e
  6. 28 Aug, 2014 2 commits
    • Yunqing Wang's avatar
      Early termination in encoding partition search · 4d2c3769
      Yunqing Wang authored
      In the partition search, the encoder checks all possible
      partitionings in the superblock's partition search tree.
      This patch proposed a set of criteria for partition search
      early termination, which effectively decided whether or
      not to terminate the search in current branch based on the
      "skippable" result of the quantized transform coefficients.
      The "skippable" information was gathered during the
      partition mode search, and no overhead calculations were
      introduced.
      
      This patch gives significant encoding speed gains without
      sacrificing the quality.
      
      Borg test results:
      1. At speed 1,
         stdhd set: psnr: +0.074%, ssim: +0.093%;
         derf set:  psnr: -0.024%, ssim: +0.011%;
      2. At speed 2,
         stdhd set: psnr: +0.033%, ssim: +0.100%;
         derf set:  psnr: -0.062%, ssim: +0.003%;
      3. At speed 3,
         stdhd set: psnr: +0.060%, ssim: +0.190%;
         derf set:  psnr: -0.064%, ssim: -0.002%;
      4. At speed 4,
         stdhd set: psnr: +0.070%, ssim: +0.143%;
         derf set:  psnr: -0.104%, ssim: +0.039%;
      
      The speedup ranges from several percent to 60+%.
                       speed1    speed2    speed3    speed4
      (1080p, 100f):
      old_town_cross:  48.2%     23.9%     20.8%     16.5%
      park_joy:        11.4%     17.8%     29.4%     18.2%
      pedestrian_area: 10.7%      4.0%      4.2%      2.4%
      (720p, 200f):
      mobcal:          68.1%     36.3%     34.4%     17.7%
      parkrun:         15.8%     24.2%     37.1%     16.8%
      shields:         45.1%     32.8%     30.1%      9.6%
      (cif, 300f)
      bus:              3.7%     10.4%     14.0%      7.9%
      deadline:        13.6%     14.8%     12.6%     10.9%
      mobile:           5.3%     11.5%     14.7%     10.7%
      
      Change-Id: I246c38fb952ad762ce5e365711235b605f470a66
      4d2c3769
    • Deb Mukherjee's avatar
      Updates vp9_pattern search to return integer sads · 04b100b2
      Deb Mukherjee authored
      Updates the vp9_pattern_search function to return integer one-away
      neighbors' sad values, for subsequent use in speeding up the
      sub-pel search. Also, removes code for the do_refine option
      which is not being used currently.
      Updates the integer and subpel functions to pass in a 5-element
      sad list for output or input.
      
      A new pruned sub-pel search algorithm is implemented that uses
      the sad returned from the integer pel search. But it is not
      deployed yet.
      
      Change-Id: Ifa9f5ad024b5b660570366d2bd900343e1891520
      04b100b2
  7. 26 Aug, 2014 1 commit
    • Yaowu Xu's avatar
      add a new interp filter search strategy. · 1144fee3
      Yaowu Xu authored
      This commit addes a new strategy to reduce the search for optimal
      interpolation filter type. The encoder counts and store how many each
      filter type is selected and used for each of the reference frames.
      A filter type that is rarely used for all three reference frames is
      masked out to avoid computation.
      
      The impact on compression is neglectible:
      -0.02% on derf
      +0.02% on stdhd
      
      Encoding time is seen to reduce by 2~3%.
      
      Change-Id: Ibafa92291b51185de40da513716222db4b230383
      1144fee3
  8. 18 Aug, 2014 2 commits
    • Yunqing Wang's avatar
      Add early termination in transform size search · ba70f160
      Yunqing Wang authored
      In the full-rd transform size search, we go through all transform
      sizes to choose the one with best rd score. In this patch, an
      early termination is added to stop the search once we see that the
      smaller size won't give better rd score than the larger size. Also,
      the search starts from largest transform size, then goes down to
      smallest size.
      
      A speed feature tx_size_search_breakout is added, which is turned off
      at speed 0, and on for other speeds. The transform size search is
      turned on at speed 1.
      
      Borg test results:
      1. At speed 1,
         derf set: psnr gain: 0.618%, ssim gain: 0.377%;
         stdhd set: psnr gain: 0.594%, ssim gain: 0.162%;
         No noticeable speed change.
      3. At speed 2,
         derf set: psnr loss: 0.157%, ssim loss: 0.175%;
         stdhd set: psnr loss: 0.090%, ssim loss: 0.101%;
         speed gain: ~4%.
      
      Change-Id: I22535cd2017b5e54f2a62bb6a38231aea4268b3f
      ba70f160
    • Jingning Han's avatar
      Speed up mode search depending on relative ref frame position · 6a464eca
      Jingning Han authored
      This commit enables the encoder to record the location of the
      center frame to generate alter reference frame. It then allows to
      skip checking prediction modes of other reference frame types when
      it comes to encode this frame.
      
      The speed 3 runtime is reduced for the test sequences:
      bus at CIF 1000 kbps, 9791 ms -> 9446 ms, i.e., 3.5% speed-up,
      pedestrian at 1080p 2000 kbps, 184043 ms -> 175730 ms, i.e., 4.5%
      speed-up.
      
      No compression performance change observed.
      
      Change-Id: Iacfde3bcc1445964e7a241f239bd6ea11cb94bd1
      6a464eca
  9. 15 Aug, 2014 2 commits
    • Pengchong Jin's avatar
      Add a speed feature to give the tighter search range · eca93642
      Pengchong Jin authored
      Add a speed feature to give the tighter partition search
      range. Before partition search, calculate the histogram
      of the partition sizes of the left, above and previous
      co-located blocks of the current block. If the variance of
      observed partition sizes is small enough, adjust the search
      range around the mean partition size, which will be tigher.
      
      The feature is currently turned on at speed 2. Experiments on
      sample youtube clips show on average the runtime is reduced
      by 3-7%.
      
      For hard stdhd clips:
      park_joy_1080p @ 15000kbps:       509251 ms -> 491953 ms (3.3%)
      pedestrian_area_1080p @ 2000kbps: 223941 ms -> 214226 ms (4.3%)
      
      The PSNR performance is changed:
      derf: -0.112%
      yt:   -0.099%
      hd:   -0.090%
      stdhd:-0.102%
      
      Change-Id: Ie205ec5325bf92ec5676c243e30ba9d0adca10f2
      eca93642
    • Yunqing Wang's avatar
      Remove a unused speed feature · 28b1437d
      Yunqing Wang authored
      Removed disable_split_var_thresh, which is not used anymore.
      
      Change-Id: I50119b150442e1571157433b5effc6aae0dbe0fd
      28b1437d
  10. 13 Aug, 2014 1 commit
    • Jingning Han's avatar
      Enable motion field based mode seach skip · 0daadeb6
      Jingning Han authored
      This commit allows the encoder to check the above and left neighbor
      blocks' reference frames and motion vectors. If they are all
      consistent, skip checking the NEARMV and ZEROMV modes. This is
      enabled in speed 3. The coding performance is improved:
      
      pedestrian area 1080p at 2000 kbps,
      from  74773 b/f, 41.101 dB, 198064 ms
      to    74795 b/f, 41.099 dB, 193078 ms
      
      park joy 1080p at 15000 kbps,
      from 290727 b/f, 30.640 dB, 609113 ms
      to   290558 b/f, 30.630 dB, 592815 ms
      
      Overall compression performance of speed 3 is changed
      derf  -0.171%
      stdhd -0.168%
      
      Change-Id: I8d47dd543a5f90d7a1c583f74035b926b6704b95
      0daadeb6
  11. 30 Jul, 2014 1 commit
    • Jingning Han's avatar
      Chessboard pattern partition search · ca2dcb7f
      Jingning Han authored
      This commit enables a chessboard pattern constrained partition
      search for 720p and above resolutions. The scheme applies stricter
      partition search to alternative blocks based on its above/left
      neighboring blocks' partition range, as well as that of the
      collocated blocks in the previous frame. It is currently turned
      on at 16x16 block size level. The chessboard pattern is flipped
      per coding frame.
      
      The speed 3 runtime is reduced:
      park_joy_1080p, 652832 ms -> 607738 ms (7% speed-up)
      pedestrian_area_1080p, 215998 ms -> 200589 ms (8% speed-up)
      
      The compression performance is changed:
      hd     -0.223%
      stdhd  -0.295%
      
      Change-Id: I2d4d123ae89f7171562f618febb4d81789575b19
      ca2dcb7f
  12. 22 Jul, 2014 1 commit
    • Jingning Han's avatar
      Enable chessboard inter prediction filter type search · 54ad0958
      Jingning Han authored
      This commit enables a chessboard pattern prediction filter type
      search scheme for rate-distortion optimization speed-up. For the
      inferred motion vector modes, the encoder can re-use its above/left
      neighbor blocks' prediction filter type and skip a full test on
      all possible filter types. Such operation is turned on/off
      alternatively in a chessboard manner.
      
      It is turned on in speed 3. For test clip pedestrian 1080p, the
      runtime is reduced from 231500 ms -> 221700 ms. The compression
      performance is changed:
      derf:  -0.147%
      yt:    -0.134%
      hd:    -0.079%
      stdhd: -0.220%
      
      Change-Id: I1912f278e7576c2dc632688e3ad7a257410c605a
      54ad0958
  13. 16 Jul, 2014 1 commit
  14. 07 Jul, 2014 1 commit
    • Alex Converse's avatar
      Cleanup motion search speed features. · f60a1178
      Alex Converse authored
      * Replace max_step_search_steps with constant MAX_MVSEARCH_STEPS
      * Fold (reduce_first_step_size + speed > 5) into reduce_first_step_size
        replacing uses of reduce_first_step_size that don't add the speed
        check with zero.
      
      Change-Id: Iae46395dbf3eaca138bf4d18b838a9e364b5a198
      f60a1178
  15. 02 Jul, 2014 2 commits
    • Yaowu Xu's avatar
      Added a speed feature controlling a motion search parameter · 92a6db79
      Yaowu Xu authored
      This commit added a speed feature to control the step_param used in
      full pixel motion search. The intention is to reduced the search
      steps for high speed real time coding.
      
      Change-Id: I21d2f0105c2b647783a6688615da7fcf2b6d670b
      92a6db79
    • Jingning Han's avatar
      Re-design quantization process · 9ac2f663
      Jingning Han authored
      This commit re-designs the quantization process for transform
      coefficient blocks of size 4x4 to 16x16. It improves compression
      performance for speed 7 by 3.85%. The SSSE3 version for the
      new quantization process is included.
      
      The average runtime of the 8x8 block quantization is reduced
      from 285 cycles -> 255 cycles, i.e., over 10% faster.
      
      Change-Id: I61278aa02efc70599b962d3314671db5b0446a50
      9ac2f663
  16. 01 Jul, 2014 1 commit
    • Yunqing Wang's avatar
      Elevate NEWMV mode checking threshold in real time · f31ff029
      Yunqing Wang authored
      The current threshold is knid of low, and in many cases NEWMV
      mode is checked but not picked as the best mode. This patch
      added a speed feature to increase NEWMV threshold, so that
      less partition mode checking goes to check NEWMV. This feature
      is enabled for speed 6 and 7.
      
      Rtc set borg tests showed:
      1. Speed 6, overall psnr: -0.088%, ssim: -1.339%;
         Average speedup on rtc set is 11.1%.
      2. Speed 7, overall psnr: -0.505%, ssim: -2.320%
         Average speedup on rtc set is 12.9%.
      
      Change-Id: I953b849eeb6e0d5a1f13eacba30c14204472c5be
      f31ff029
  17. 30 Jun, 2014 2 commits
    • Yunqing Wang's avatar
      Enable encode breakout in real time · dee5782f
      Yunqing Wang authored
      For real time speed 7, once encode breakout is on(i.e. encoding
      setting --static-thresh=1), a proper encode breakout threshold
      is set to speed up the encoder.
      
      Set --static-thresh=1, RTC set borg test showed a slight overall
      psnr loss of 0.162%, but ssim gain of 0.287%. The average speedup
      on RTC set is 6%, and for some clips, the speedup can be 10+%.
      
      Change-Id: Id522d9ce779ff7c699936d13d0c47083de4afb85
      dee5782f
    • Yunqing Wang's avatar
      Decide the partitioning threshold from the variance histogram · 9d41313e
      Yunqing Wang authored
      Before encoding a frame, calculate and store each 16x16 block's
      variance of source difference between last and current frame.
      Find partitioning threshold T for the frame from its variance
      histogram, and then use T to make partition decisions.
      
      Comparing with fixed 16x16 partitioning, rtc set test showed an
      overall psnr gain of 3.242%, and ssim gain of 3.751%. The best
      psnr gain is 8.653%.
      
      The overall encoding speed didn't change much. It got faster for
      some clips(for example, 12% speedup for vidyo1), and a little
      slower for others.
      
      Also, a minor modification was made in datarate unit test.
      
      Change-Id: Ie290743aa3814e83607b93831b667a2a49d0932c
      9d41313e
  18. 27 Jun, 2014 1 commit
  19. 24 Jun, 2014 2 commits
    • Yunqing Wang's avatar
      Reuse inter prediction result in real-time speed 6 · 0aae1000
      Yunqing Wang authored
      In real-time speed 6, no partition search is done. The inter
      prediction results got from picking mode can be reused in the
      following encoding process. A speed feature reuse_inter_pred_sby
      is added to only enable the resue in speed 6.
      
      This patch doesn't change encoding result. RTC set tests showed
      that the encoding speed gain is 2% - 5%.
      
      Change-Id: I3884780f64ef95dd8be10562926542528713b92c
      0aae1000
    • Paul Wilkins's avatar
      Fix some bugs in multi-arf · 8160a26f
      Paul Wilkins authored
      Fix some bugs relating to the use of buffers
      in the overlay frames.
      
      Fix bug where a mid sequence overlay was
      propagating large partition and transform sizes into
      the subsequent frame because of :-
        sf->last_partitioning_redo_frequency  > 1 and
        sf->tx_size_search_method == USE_LARGESTALL
      
      Change-Id: Ibf9ef39a5a5150f8cbdd2c9275abb0316c67873a
      8160a26f
  20. 12 Jun, 2014 1 commit
    • Dmitry Kovalev's avatar
      Adding MV_SPEED_FEATURES struct. · 4ff1a614
      Dmitry Kovalev authored
      Moving all motion vector related speed parameters from SPEED_FEATURES to
      MV_SPEED_FEATURES.
      
      Change-Id: I3e9af0039c7162f8671878c5920bce3cb256a84e
      4ff1a614
  21. 10 Jun, 2014 1 commit
  22. 09 Jun, 2014 1 commit
    • Yunqing Wang's avatar
      Use small transform size in non-rd real-time mode · b04d7668
      Yunqing Wang authored
      In non-rd real-time mode, choosing smaller transform size in
      encoding gives better video quality and good speed gain than
      choosing larger transform size. This patch set tx size search
      method to ALLOW_8X8, which is better than using 4x4 or other
      larger sizes.
      
      Borg tests on rtc set at speed 6 showed significant gain on quality.
      PSNR gain: 11.034% and SSIM gain: 15.466%.
      
      The speed gain is 5% - 12% for <720p clips, and 2% - 7% for
      720p clips.
      
      Change-Id: If4dc74ed2df359346b059f47fb73b4a0193ec548
      b04d7668
  23. 06 Jun, 2014 1 commit
  24. 29 May, 2014 1 commit
  25. 21 May, 2014 1 commit
    • Yaowu Xu's avatar
      Enable various thresholds of motion detection · 3bda7ec1
      Yaowu Xu authored
      This commit changed to enable the encoder to adjust motion dection
      speed threshold based on picture size. In addition, cpu-used 1 now
      does a partition search every other frame instead of every third
      frame for low resolution inputs.
      
      The change has no quality/speed impact for 720p and above. Test
      showed the change increase encoding time by between 3% to 6% for
      cpu-used 2 encodiong of 360p sequences. It also has a compression
      gain about .3%.
      
      For cpu-used 2, the change resolved some very disturbing visual
      artifacts in certain sequences when large block partitionings and
      transforms are used as a result of copying the partition from a
      previous frame.
      
      Change-Id: Ic7fd22508cdb811d4ca935655adbf20109286cfa
      3bda7ec1
  26. 19 May, 2014 1 commit
    • Yunqing Wang's avatar
      Add static-threshold skipping in non-rd mode · b91b146d
      Yunqing Wang authored
      Added a skipping test in non-rd inter-mode. After interpolation
      prediction step, the residuals are tested to see if they will be
      quantized to 0 based on modeling between spatial domain and
      frequency domain.
      
      Set static-thresh to 800 for >=720p and 300 for <720p, rtc set
      tests showed
      1. Speed 5, psnr: -0.514%; ssim: -1.748%;
         speedup on related clips: 5% -11%
      2. Speed 6, psbr: -0.628%; ssim: -1.637%;
         speedup on related clips: 4% - 9%
      
      Change-Id: I62fbf26bc043ecd2b584f255f1a4ee5ab52bfcf3
      b91b146d
  27. 12 May, 2014 1 commit
  28. 01 May, 2014 1 commit
  29. 23 Apr, 2014 1 commit
    • Jingning Han's avatar
      Chessboard pattern prediction filter type search in non-RD coding · 8969f7c8
      Jingning Han authored
      This commit introduces a chessboard pattern search for the prediction
      filter type search. It runs extensive search in alternate blocks and
      allows the rest blocks to refer coding decisions of their nearby
      neighbors.
      
      For pedestrian 1080p at 4000 kbps, the runtime of speed -5 goes down
      from 43990 ms to 42200 ms. The overall compression performance for
      RTC set is changed by -1.37%.
      
      Change-Id: Icfe220c49451cda796f0ca91d935c9ed01e56c9d
      8969f7c8
  30. 10 Apr, 2014 1 commit
  31. 09 Apr, 2014 1 commit
    • Yunqing Wang's avatar
      Use source frame difference to make partition decision · 4e66293f
      Yunqing Wang authored
      Calculate the difference variance between last source frame and
      current source frame. The variance is calculated at 16x16 block
      level. The variances are compared to several thresholds to decide
      final partition sizes.
      
      An adaptive strategy is implemented to decide using
      SOURCE_VAR_BASED_PARTITION or FIXED_PARTITION based on motions
      in the video. The switching test is done once every
      search_type_check_frequency frames.
      
      The selection of source_var_thresh needs to be investigated
      further later.
      
      RTC set Borg test showed 0.424% overall psnr gain, and 0.357%
      ssim gain. For clips with large enough static area, the
      encoding speedup is around 2% to 15%.
      
      Change-Id: Id7d268f1d8cbca7fb8026aa4a53b3c77459dc156
      4e66293f
  32. 07 Apr, 2014 1 commit
  33. 04 Apr, 2014 1 commit