1. 10 Mar, 2016 1 commit
  2. 01 Mar, 2016 1 commit
  3. 26 Feb, 2016 1 commit
    • Geza Lore's avatar
      Port interintra experiment from nextgen. · 7ded038a
      Geza Lore authored
      The interintra experiment, which combines an inter prediction and an
      inter prediction have been ported from the nextgen branch. The
      experiment is merged into ext_inter, so there is no separate configure
      option to enable it.
      
      Change-Id: I0cc20cefd29e9b77ab7bbbb709abc11512320325
      7ded038a
  4. 20 Feb, 2016 1 commit
  5. 09 Feb, 2016 1 commit
    • Jingning Han's avatar
      Entropy coding for dynamic ref mv modes · 4958987b
      Jingning Han authored
      This commit enables entropy coding for dynamic reference motion
      vector modes. The probability model is contexted on the ranking
      categories of the reference motion vector candidates.
      
      Change-Id: I09b58d98a409d63ec1a407331e29f8945b7ef17d
      4958987b
  6. 03 Feb, 2016 1 commit
    • hui su's avatar
      Add 8-tap interpolation filter options for intra prediction · 3b1c7668
      hui su authored
      BD-rate performance improvement (on top of ext-intra):
      derflr  0.22%
      hevclr  0.36%
      hevcmr  0.48%
      hevchr  0.37%
      stdhd   0.19%
      
      Average speed impact on some derf clips is about 40% slower (on
      top of ext-intra). Speed improvment is a to-do.
      
      Change-Id: I8fe3fe8c5e4f60d0462778adbcc15c84dfbe7a25
      3b1c7668
  7. 22 Jan, 2016 1 commit
    • Yue Chen's avatar
      Adding new compound modes to EXT_INTER experiment · 968bbc7b
      Yue Chen authored
      Combinations of different mv modes for two reference frames
      are allowed in compound inter modes. 9 options are enabled,
      including NEAREST_NEARESTMV, NEAREST_NEARMV, NEAR_NEARESTMV,
      NEAREST_NEWMV, NEW_NEARESTMV, NEAR_NEWMV, NEW_NEARMV, ZERO_ZEROMV,
      and NEW_NEWMV.
      This experiment is mostly deported from the nextgen branch.
      It is made compatible with other experiments
      
      Coding gain of EXT_INTER(derflr/hevcmr/hevchd): 0.533%/0.728%/0.639%
      
      Change-Id: Id47e97284e6481b186870afbad33204b7a33dbb0
      968bbc7b
  8. 15 Jan, 2016 1 commit
    • Yue Chen's avatar
      EXT_INTER experiment · 1ac85879
      Yue Chen authored
      NEW2MV is enabled, representing a new motion vector predicted from
      NEARMV. It is mostly ported from nextgen, where it was named
      NEW_INTER.
      A few fixes are done for sub8x8 RDO to correct some misused
      mv references in the original patch.
      A 'bug-fix' for encoding complexity is done, reducing the additional
      encoding time from 50% to 20%. In sub8x8 case, the old patch
      did motion search for every interpolation filter (vp9 only
      searches once). This fix also slightly improves the coding gain.
      This experiment has been made compatible with REF_MV and EXT_REFS.
      
      Coding gain (derflr/hevcmr/hevchd): 0.267%/0.542%/0.257%
      
      Change-Id: I9a94c5f292e7454492a877f65072e8aedba087d4
      1ac85879
  9. 08 Jan, 2016 2 commits
  10. 05 Jan, 2016 1 commit
    • Debargha Mukherjee's avatar
      Super transform - ported from nextgen branch · 3787b174
      Debargha Mukherjee authored
      Various additional changes were made to make the experiment
      compatible with misc_fixes.
      
      derflr: +0.979%
      hevcmr: +0.865%
      
      Speed-wise with --enable-supertx the encoder is only about 10%
      slower than without. Decoding impact is about 30% slowdown.
      
      Note this does not work with ext-tx or var-tx yet. That is
      a TODO.
      
      Change-Id: If25af4241a7a9efbd28f58eda3c4f044c7a7ef4b
      3787b174
  11. 10 Dec, 2015 1 commit
  12. 23 Nov, 2015 1 commit
    • Debargha Mukherjee's avatar
      Reduce transform options for ext-tx experiment · 56ab215d
      Debargha Mukherjee authored
      Reduces the transform optons for INTRA as well as INTER when
      transform size is 16x16 to not use any of the DSTs.
      Thus, a total of 10 options are used for 16x16, while 4x4
      and 8x8 still uses 17 options.
      
      derflr/hevchd actually improves a little, while hevcmr drops
      a little.
      
      About 10% speed improvement.
      
      Change-Id: I920a182231e052cdd622f8bb67085c16c572cb1e
      56ab215d
  13. 21 Nov, 2015 1 commit
    • Zoe Liu's avatar
      Added 3 more reference frames for inter prediction. · 3ec1601e
      Zoe Liu authored
      Under the experiment of EXT_REFS: LAST2_FRAME, LAST3_FRAME, and
      LAST4_FRAME.
      
      Coding efficiency: derflr +1.601%; hevchr +1.895%
      Speed: Encoder slowed down by ~75%
      
      Change-Id: Ifeee5f049c2c1f7cb29bc897622ef88897082ecf
      3ec1601e
  14. 17 Nov, 2015 1 commit
    • hui su's avatar
      Merge MISC_FIXES · 66f2f65e
      hui su authored
      Remove MISC_FIXES flags except for the changes on MV precision, which
      has a 0.1% performance drop.
      
      On derflr, the impact is -0.012%.
      
      Change-Id: I0a74e5a212dd0cb827192a318c92a714c9681e45
      66f2f65e
  15. 09 Nov, 2015 1 commit
    • Johann's avatar
      Release v1.5.0 · cbecf57f
      Johann authored
      Javan Whistling Duck release.
      
      Change-Id: If44c9ca16a8188b68759325fbacc771365cb4af8
      cbecf57f
  16. 04 Nov, 2015 1 commit
    • hui su's avatar
      ext-intra experiment · be3559ba
      hui su authored
      Currently there are two parts in this experiment: extra directional intra
      prediction modes and the filter intra modes migrated from the nextgen branch.
      
      Several macros are defined in "blockd.h" to provide controls of the experiment
      settings. Setting "DR_ONLY" as 1 (default is 0) means we only use directional
      modes, and skip the filter-intra modes; "EXT_INTRA_ANGLES" (default is 128)
      defines the number of different angles we want to support; setting
      "ANGLE_FAST_SEARCH" as 1 (default is 1) means we use fast sub-optimal search
      for the best prediction angle, instead of exhaustive search. The fast search
      is about 6 times faster than the exhaustive search, while preserving about
      60% of the coding gains.
      
      With extra directional prediction modes (fast search), we observe the following
      code gains (number in parentheses is for all-key-frame setting):
      derflr +0.42%  (+1.79%)
      hevclr +0.78%  (+2.19%)
      hevcmr +1.20%  (+3.49%)
      stdhd  +0.56%
      Speed-wise, about 110% slower for key frames, and 30% slower overall.
      
      The gains of filter intra modes mostly add up with the gains of directional
      modes. The overall coding gain of this experiment:
      derflr +0.94%
      hevclr +1.46%
      hevcmr +1.94%
      stdhd  +1.58%
      
      Change-Id: Ida9ad00cdb33aff422d06eb42b4f4e5f25df8a2a
      be3559ba
  17. 29 Oct, 2015 2 commits
  18. 27 Oct, 2015 1 commit
    • Peter de Rivaz's avatar
      Accumulate EXT_TX counts for multithread · 325b96dc
      Peter de Rivaz authored
      EXT_TX introduces some new symbols to be decoded.
      The encoder counts how many times these are used.
      In multithreaded mode, the counts from the worker threads
      need to be accumulated into the main thread.
      
      This change means that VP10/VPxEncoderThreadTest now works
      with more choices of cpu-used and number of passes.
      
      Change-Id: Ibe7e6a3c58145265f4ead155ff98fb4cb37c3513
      325b96dc
  19. 16 Oct, 2015 1 commit
    • Ronald S. Bultje's avatar
      vp10: make segmentation probs use generic probability model. · 6e5a1165
      Ronald S. Bultje authored
      Locate them (code-wise) in frame_context, and have them be updated
      as any other probability using the subexp forward and adaptive bw
      updates.
      
      See issue 1040 point 1.
      
      TODOs:
      - real-world default probabilities
      - why is counts sometimes NULL in the decoder? Does that mean bw
        adaptivity updates only work on some frames? (I haven't looked
        very closely yet, maybe this is a red herring.)
      
      Change-Id: I23b57b4e5e7574b75f16eb64823b29c22fbab42e
      6e5a1165
  20. 31 Aug, 2015 1 commit
  21. 27 Aug, 2015 1 commit
  22. 13 Aug, 2015 1 commit
  23. 12 Aug, 2015 2 commits
  24. 02 Jul, 2015 1 commit
  25. 29 Apr, 2015 1 commit
    • James Zern's avatar
      vpx_mem: remove vpx_memset · f58011ad
      James Zern authored
      vestigial. replace instances with memset() which they already were being
      defined to.
      
      Change-Id: Ie030cfaaa3e890dd92cf1a995fcb1927ba175201
      f58011ad
  26. 21 Apr, 2015 1 commit
    • Scott LaVarnway's avatar
      Revert "Remove mi_grid_* structures." · 8b17f7f4
      Scott LaVarnway authored
      (see I3a05cf1610679fed26e0b2eadd315a9ae91afdd6)
      
      For the test clip used, the decoder performance improved by ~2%.
      This is also an intermediate step towards adding back the
      mode_info streams.
      
      Change-Id: Idddc4a3f46e4180fbebddc156c4bbf177d5c2e0d
      8b17f7f4
  27. 24 Mar, 2015 1 commit
  28. 10 Mar, 2015 1 commit
  29. 14 Feb, 2015 1 commit
    • James Zern's avatar
      loop_filter_rows_mt: remove dependency on 'last_height' · 0dd591be
      James Zern authored
      using this to control reallocation would miss a change if the function
      were not called for every frame.
      fixes potential memory corruption by the subsequent memset
      
      Change-Id: I4c6bb6ab68803104fc824c7e27cc2f9b2cf53e33
      0dd591be
  30. 06 Feb, 2015 2 commits
  31. 20 Jan, 2015 1 commit
  32. 17 Jan, 2015 1 commit
    • Yunqing Wang's avatar
      vp9_ethread: add parallel loopfilter · e76eaf05
      Yunqing Wang authored
      1. Added row-based loopfilter in encoder;
      2. Moved common multi-threaded loopfilter functions from decoder
         to common;
      3. Merged multi-threaded loopfilter code, and made encoder/
         decoder call same function to reduce code duplication.
      
      Encoder tests showed that 1% - 2% speedup was seen for good-quality
      2-pass mode(at speed 3); 1% - 3% speedup using 2 threads and 4% - 6%
      speedup using 4 threads were seen for real-time mode(at speed 7).
      
      Change-Id: I8a4ac51c2ad9bab9fa7b864e90743931c53ec1c4
      e76eaf05
  33. 08 Dec, 2014 1 commit
  34. 23 Oct, 2014 1 commit
  35. 22 Oct, 2014 1 commit
    • Hangyu Kuang's avatar
      Implement frame parallel decode for VP9. · 9ce3a7d7
      Hangyu Kuang authored
      Using 4 threads, frame parallel decode is ~3x faster than single thread
      decode and around 30% faster than tile parallel decode for frame parallel
      encoded video on both Android and desktop with 4 threads. Decode speed is
      scalable to threads too which means decode could be even faster with more threads.
      
      Change-Id: Ia0a549aaa3e83b5a17b31d8299aa496ea4f21e3e
      9ce3a7d7
  36. 16 Oct, 2014 1 commit
    • James Zern's avatar
      move LFWorkerData allocation to VP9LfSync · e9b8810b
      James Zern authored
      this removes an assumption that worker->data1 would be pointing to a
      TileWorkerData allocation.
      additionally, within the multi-threaded loopfilter pass VP9LfSync as a
      parameter to the worker hook, removing the need for a shadow pointer in
      LFWorkerData.
      
      Change-Id: Ic7b2faa34e3eb59dbcb8a7c67f333448fa047c88
      e9b8810b