1. 09 Feb, 2013 3 commits
    • John Koleszar's avatar
      Replace as_mv struct with array · 7ca517f7
      John Koleszar authored
      Replace as_mv.{first, second} with a two element array, so that they
      can easily be processed with an index variable.
      
      Change-Id: I1e429155544d2a94a5b72a5b467c53d8b8728190
      7ca517f7
    • Ronald S. Bultje's avatar
      Add sad64x64 and sad32x32 SSE2 versions. · 02ff360b
      Ronald S. Bultje authored
      Also port the 4x4, 16x16, 8x16 and 16x8 versions to x86inc.asm; this
      makes them all slightly faster, particularly on x86-64. Remove SSE3
      sad16x16 version, since the SSE2 version is now faster.
      
      About 1.5% overall encoding speedup.
      
      Change-Id: Id4011a78cce7839f554b301d0800d5ca021af797
      02ff360b
    • Ronald S. Bultje's avatar
      Make cost_coeffs() more efficient. · 639b863d
      Ronald S. Bultje authored
      Cache the constant offset in one variable to prevent re-loading that
      in each loop iteration, and mark the function as inline so we can use
      the fact that the transform size is always known in the caller.
      
      Almost 1% faster encoding overall.
      
      Change-Id: Id78325a60b025057d8f4ecd9003a74086ccbf85a
      639b863d
  2. 08 Feb, 2013 5 commits
    • John Koleszar's avatar
      Pass macroblock index to pick inter functions · 6125a1ed
      John Koleszar authored
      Pass the current mb row and column around rather than the
      recon_yoffset and recon_uvoffset, since those offsets will
      change from predictor to predictor, based on the reference
      frame selection.
      
      Change-Id: If3f9df059e00f5048ca729d3d083ff428e1859c1
      6125a1ed
    • John Koleszar's avatar
      Initial support for resolution changes on P-frames · 393b4856
      John Koleszar authored
      Allows inter-frames to change resolution. Currently these are
      almost equivalent to keyframes, as only intra prediction modes
      are allowed, but without the other context resets that occur on
      keyframes.
      
      Change-Id: Icd1a2a5af0d9462cc792588427b0a1f5b12e40d3
      393b4856
    • John Koleszar's avatar
      Avoid allocating memory when resizing frames · c03d45de
      John Koleszar authored
      As long as the new frame is smaller than the size that was originally
      allocated, we don't need to free and reallocate the memory allocated.
      Instead, do the allocation on the size of the first frame. We could
      make this passed in from the application instead, if we wanted to
      support external upscaling.
      
      Change-Id: I204d17a130728bbd91155bb4bd863a99bb99b038
      c03d45de
    • John Koleszar's avatar
      Adds a test for the VP8E_SET_SCALEMODE control · 88f99f4e
      John Koleszar authored
      Tests that the external interface to set the internal codec scaling
      works as expected. Also updates the test to pull the height from
      the decoded frame size rather than parsing the keyframe header,
      in anticipation of allowing resolution changes on non-keyframes.
      
      Change-Id: I3ed92117d8e5288fbbd1e7b618f2f233d0fe2c17
      88f99f4e
    • John Koleszar's avatar
      Restore SSSE3 subpixel filters in new convolve framework · 29d47ac8
      John Koleszar authored
      This commit adds the 8 tap SSSE3 subpixel filters back into the code
      underneath the convolve API. The C code is still called for 4x4
      blocks, as well as compound prediction modes. This restores the
      encode performance to be within about 8% of the baseline.
      
      Change-Id: Ife0d81477075ae33c05b53c65003951efdc8b09c
      29d47ac8
  3. 07 Feb, 2013 5 commits
    • Yaowu Xu's avatar
      move dct/idct constants to a header file · e6ad9ab0
      Yaowu Xu authored
      also removed some un-unsed functions.
      
      Change-Id: Ie363bcc8d94441d054137d2ef7c4fe59f56027e5
      e6ad9ab0
    • Jingning Han's avatar
      Butterfly ADST based hybrid transform · d15e1da4
      Jingning Han authored
      Refactor the 8x8 inverse hybrid transform. It is now consistent
      with the new inverse DCT. Overall performance loss (due to the
      use of this variant ADST, and the rounding errors in the butterfly
      implementation) for std-hd is -0.02.
      
      Fixed BUILD warning.
      
      Devise a variant of the original ADST, which allows butterfly
      computation structure. This new transform has kernel of the
      form: sin((2k+1)*(2n+1) / (4N)). One of its butterfly structures
      using floating-point multiplications was reported in Z. Wang,
      "Fast algorithms for the discrete W transform and for the discrete
      Fourier transform", IEEE Trans. on ASSP, 1984.
      
      This patch includes the butterfly implementation of the inverse
      ADST/DCT hybrid transform of dimension 8x8.
      
      Change-Id: I3533cb715f749343a80b9087ce34b3e776d1581d
      d15e1da4
    • Paul Wilkins's avatar
      Added skip switches for SB32 and SB64 · 29731308
      Paul Wilkins authored
      Added switches and code to skip/breakout from
      doing SB32 and SB64 tests based on whether
      the 16x16 MB tests used split modes. Also to
      optionally skip 64x64 if 16x16 was chosen over
      32x32.
      
      Impact varies depending on clip from a few %
      up to almost 50% on encode speed. Only the
      split mode breakout is currently enabled.
      
      Change-Id: Ib5836140b064b350ffa3057778ed2cadcc495cf8
      29731308
    • Ronald S. Bultje's avatar
      Use fdct8x4 instead of fdct4x4 where the block size allows it. · 5cfd82bc
      Ronald S. Bultje authored
      This allows for faster SIMD implementations in the future (currently
      there is no speed impact).
      
      Change-Id: I732647e9148b5dcb44e6bc8728138f0141218329
      5cfd82bc
    • Ronald S. Bultje's avatar
      Use configure checks for various inline keywords. · aac73df1
      Ronald S. Bultje authored
      Change-Id: I8508f1a3d3430f998bb9295f849e88e626a52a24
      aac73df1
  4. 06 Feb, 2013 4 commits
  5. 05 Feb, 2013 7 commits
    • Ronald S. Bultje's avatar
      [WIP] Add column-based tiling. · 1407bdc2
      Ronald S. Bultje authored
      This patch adds column-based tiling. The idea is to make each tile
      independently decodable (after reading the common frame header) and
      also independendly encodable (minus within-frame cost adjustments in
      the RD loop) to speed-up hardware & software en/decoders if they used
      multi-threading. Column-based tiling has the added advantage (over
      other tiling methods) that it minimizes realtime use-case latency,
      since all threads can start encoding data as soon as the first SB-row
      worth of data is available to the encoder.
      
      There is some test code that does random tile ordering in the decoder,
      to confirm that each tile is indeed independently decodable from other
      tiles in the same frame. At tile edges, all contexts assume default
      values (i.e. 0, 0 motion vector, no coefficients, DC intra4x4 mode),
      and motion vector search and ordering do not cross tiles in the same
      frame.
      t log
      
      Tile independence is not maintained between frames ATM, i.e. tile 0 of
      frame 1 is free to use motion vectors that point into any tile of frame
      0. We support 1 (i.e. no tiling), 2 or 4 column-tiles.
      
      The loopfilter crosses tile boundaries. I discussed this briefly with Aki
      and he says that's OK. An in-loop loopfilter would need to do some sync
      between tile threads, but that shouldn't be a big issue.
      
      Resuls: with tiling disabled, we go up slightly because of improved edge
      use in the intra4x4 prediction. With 2 tiles, we lose about ~1% on derf,
      ~0.35% on HD and ~0.55% on STD/HD. With 4 tiles, we lose another ~1.5%
      on derf ~0.77% on HD and ~0.85% on STD/HD. Most of this loss is
      concentrated in the low-bitrate end of clips, and most of it is because
      of the loss of edges at tile boundaries and the resulting loss of intra
      predictors.
      
      TODO:
      - more tiles (perhaps allow row-based tiling also, and max. 8 tiles)?
      - maybe optionally (for EC purposes), motion vectors themselves
        should not cross tile edges, or we should emulate such borders as
        if they were off-frame, to limit error propagation to within one
        tile only. This doesn't have to be the default behaviour but could
        be an optional bitstream flag.
      
      Change-Id: I5951c3a0742a767b20bc9fb5af685d9892c2c96f
      1407bdc2
    • Ronald S. Bultje's avatar
      Add SSE3 versions for sad{32x32,64x64}x4d functions. · 58c983d1
      Ronald S. Bultje authored
      Overall encoding about 15% faster.
      
      Change-Id: I176a775c704317509e32eee83739721804120ff2
      58c983d1
    • John Koleszar's avatar
      Convert subpixel filters to use convolve framework · 7a07eea1
      John Koleszar authored
      Update the code to call the new convolution functions to do subpixel
      prediction rather than the existing functions. Remove the old C and
      assembly code, since it is unused. This causes a 50% performance
      reduction on the decoder, but that will be resolved when the asm for
      the new functions is available.
      
      There is no consensus for whether 6-tap or 2-tap predictors will be
      supported in the final codec, so these filters are implemented in
      terms of the 8-tap code, so that quality testing of these modes
      can continue. Implementing the lower complexity algorithms is a
      simple exercise, should it be necessary.
      
      This code produces slightly better results in the EIGHTTAP_SMOOTH
      case, since the filter is now applied in only one direction when
      the subpel motion is only in one direction. Like the previous code,
      the filtering is skipped entirely on full-pel MVs. This combination
      seems to give the best quality gains, but this may be indicative of a
      bug in the encoder's filter selection, since the encoder could
      achieve the result of skipping the filtering on full-pel by selecting
      one of the other filters. This should be revisited.
      
      Quality gains on derf positive on almost all clips. The only clip
      that seemed to be hurt at all datarates was football
      (-0.115% PSNR average, -0.587% min). Overall averages 0.375% PSNR,
      0.347% SSIM.
      
      Change-Id: I7d469716091b1d89b4b08adde5863999319d69ff
      7a07eea1
    • John Koleszar's avatar
      Add 8-tap generic convolver · 5ca6a366
      John Koleszar authored
      This commit introduces a new convolution function which will be used to
      replace the existing subpixel interpolation functions. It is much the
      same as the existing functions, but allows for changing the filter
      kernel on a per-pixel basis, and doesn't bake in knowledge of the
      filter to be applied or the size of the resulting block into the
      function name.
      
      Replacing the existing subpel filters will come in a later commit.
      
      Change-Id: Ic9a5615f2f456cb77f96741856fc650d6d78bb91
      5ca6a366
    • Yaowu Xu's avatar
      rewrite 4x4 idct and fdct · fa36981e
      Yaowu Xu authored
      This commit changes the 4x4 iDCT to use same algorithm & constants as
      other iDCTs. The 4x4 fDCT is also changed to be based on the new iDCT.
      
      Change-Id: Ib1a902693228af903862e1f5a08078c36f2089b0
      fa36981e
    • Paul Wilkins's avatar
      Change definition of NearestMV. · 81043e8d
      Paul Wilkins authored
      This commit makes the NearestMV match the chosen
      best reference MV. It can be a 0,0 or non zero vector
      which means the the compound nearest mv mode can
      combine a 0,0 and a non zero vector.
      
      Change-Id: I2213d09996ae2916e53e6458d7d110350dcffd7a
      81043e8d
    • Scott LaVarnway's avatar
      Added vp9_short_idct1_32x32_c · 5780c4cb
      Scott LaVarnway authored
      and called this function in vp9_dequant_idct_add_32x32_c when
      eob == 1.  For the test clip used, the decoder performance improved
      by 21+%.  Based on Yaowu's 16 point idct work.
      
      Change-Id: Ib579a90fed531d45777980e04bf0c9b23c093c43
      5780c4cb
  6. 04 Feb, 2013 3 commits
    • Paul Wilkins's avatar
      Re-factor code for rd thresholds. · 3ab53876
      Paul Wilkins authored
      Separate out code to set the main encode speed
      related rd thresholds. Some values changed from
      the initial defaults for various new modes.
      
      Quality test results pending but even the addition
      of some further non-zero defaults helps encode speed
      somewhat in limited testing on derf clips.
      
      Adjustment of thresholds for quality / speed tradeoff
      to follow.
      
      Change-Id: I117ee473157e151a1b93193d5f393449328de20d
      3ab53876
    • Yaowu Xu's avatar
      re-write 8 point idct · 1eb79dc1
      Yaowu Xu authored
      to be consistent with idct16 and idct32.
      
      Change-Id: Ie89dbd32b65c33274b7fecb4b41160fcf1962204
      1eb79dc1
    • Yaowu Xu's avatar
      a couple of minor fixes · ccaaeb4b
      Yaowu Xu authored
      fixed a function prototypes to prevent compiler warnings;
      removed a function not in use;
      un-capitialize "Refstride" to ref_stride
      
      Change-Id: Ib4472b6084f357d96328c6a06e795b6813a9edba
      ccaaeb4b
  7. 01 Feb, 2013 1 commit
    • Yaowu Xu's avatar
      Changes 16 point idct · 91e0e801
      Yaowu Xu authored
      This commit changes the inverse 16 point dct to use the same algorithm
      as the one for 32 point idct. In fact, now 16 point dct uses the exact
      version of the souce code for even portion of the 32 point idct.
      
      Tests showed current implementation has significant better accuracy
      than the previous version. With this implementation and the minor bug
      fix on forward 16 point dct, encoding tests showed about 0.2% better
      compression of CIF set, test results on std-hd setting pending.
      
      Change-Id: I68224b60c816ba03434e9f08bee147c7e344fb63
      91e0e801
  8. 31 Jan, 2013 2 commits
    • Yaowu Xu's avatar
      fix a small bug in 16 point forward dct · ab1cad9b
      Yaowu Xu authored
      The commit fixes a minor error in 16 point fdct where in a rotation can
      produce result of -1 instead of 0.
      
      Change-Id: I45aac4a52bcd06225c6d04e643547a13e1c1aade
      ab1cad9b
    • Yaowu Xu's avatar
      A fix point implementation of 32x32 idct · 5149d7f7
      Yaowu Xu authored
      This commit changes the 32x32 idct to use integer only. The algorithm
      was taken directly from "A Fast Computational Algorithm for the
      Discrete Cosine Tranform" by W. Chen, et al., which was published in
      IEEE Transaction on Communication Vol. Com.-25 No. 9, 1977. The signal
      flow graph in the original paper is for a 32 point forward dct, the
      current implementation of inverse DCT was done by follow the graph in
      reversed direction.
      
      With this implementation, the 32 point inverse dct contains a 16 point
      inverse dct in its even portion, similarly the 16 point idct further
      contains 8 point and 4 point inverse dcts.
      
      As of patch 4, encoding tests showed there is no compression loss when
      compared against the floating point baseline. Numbers even showed very
      small postives. (cif: .01%, std-hd: .05%).
      
      Change-Id: I2d2d17a424b0b04b42422ef33ec53f5802b0f378
      5149d7f7
  9. 30 Jan, 2013 4 commits
  10. 29 Jan, 2013 3 commits
    • Ronald S. Bultje's avatar
      Fix block pointer corruption in intra8x8 prediction with 4x4 transform. · ffc2e4f4
      Ronald S. Bultje authored
      The RD loop would change the pointer after the first mode (DC) was tested,
      leading to corrupt block objects being provided for the others. This
      would essentially render the i8x8 predictor useless.
      
      Change-Id: I16c5906ca64fb34878ac32ce59af8974e4582bb8
      ffc2e4f4
    • Paul Wilkins's avatar
      Remove eob_max_offset markers. · 93762ca9
      Paul Wilkins authored
      Remove eob_max_offset markers and replace
      with the generic skip_block flag to indicate
      to the quantizer that all coeffs to be set to 0
      and eob position set to 0;
      
      Change-Id: Id477e8f8d4ec1a5562758904071013c24b76bfd7
      93762ca9
    • Deb Mukherjee's avatar
      Further improvement on compound inter-intra expt · 3b04d467
      Deb Mukherjee authored
      Adds a special combination mode specific to intra prediciton
      mode D45.
      
      Current results with the compound inter/intra experiment:
      derf: 0.2%
      yt: 0.55%
      std-hd: 0.75%
      hd: 0.74%
      
      Change-Id: I8976bdf3b9b0b66ab8c5c628bbc62c14fc72ca86
      3b04d467
  11. 28 Jan, 2013 2 commits
    • Paul Wilkins's avatar
      Segment Skip Flag · 0ff9b033
      Paul Wilkins authored
      First step in simplifying the segment mode and
      segment EOB flags into a simpler segment skip
      flag that implies 0,0 mv and EOB at position 0.
      
      Change-Id: Ib750cac31a7a02dc21082580498efd9f7d8d72a5
      0ff9b033
    • Paul Wilkins's avatar
      Simplify Zero bin and zero bin run code. · 8e2c03fb
      Paul Wilkins authored
      Simplification to eliminate a number of very large data
      data structures. All zero run, zbin boosts for different
      transform sizes are now limited to a maximum run length
      of 15 before they max out the boost.
      
      Some further work still needs be done to refactor, rationalize
      and optimize the multiple quantizer functions.
      
      The simplification coupled with tweaks to the 16 element array
      now used for all transform sizes, has minimal effect on quality.
      
      Change-Id: I6f3948b8ca0418b60d4db9030ff19026a34ed423
      8e2c03fb
  12. 26 Jan, 2013 1 commit