1. 18 May, 2017 1 commit
    • Luc Trudeau's avatar
      [CFL] Add cfl_update_cost function · 1a47430b
      Luc Trudeau authored
      Encapsulates the logic to update the rate of each CfL codeword.
      The if statements are removed from the loop and the arrays are
      stored in CFL_CTX instead of being declared every time.
      
      Change-Id: I0cb208b14e6c6a888210dd33c5e8fe8d74dd87f4
      1a47430b
  2. 17 May, 2017 6 commits
  3. 16 May, 2017 6 commits
    • David Barker's avatar
      Further speedups to warp filter · 58616eb0
      David Barker authored
      * Calculate sx4, sy4 by truncation instead of rounding
      * Move some repeated calculations out of the filter loop
      
      This is expected to have a roughly neutral effect on BDRATE.
      The speedup of each filter (SSE2, lowbd SSSE3, highbd SSSE3) is
      7-10%, for a total speedup of 14-18% when considered together
      with patches f7a5ee53 and 14b8112b.
      
      Change-Id: I692f649202214c7ab53ecf81f81386f1503e2d20
      58616eb0
    • hui su's avatar
      Palette: use uint16_t to store palette colors · fa4ff85b
      hui su authored
      Harmonize the low-bitdepth and high-bitdepth.
      
      Change-Id: I533f717ca189a5e577719821ea5aea940e3b6223
      fa4ff85b
    • James Zern's avatar
      half_btf_avx2: correct fn sig for visual studio · 52b14161
      James Zern authored
      fixes:
      formal parameter with __declspec(align('32')) won't be aligned
      
      this is the same change that was made previously for sse4:
      5bedd5dc idct16x16_sse4_1: correct fn sig for visual studio
      
      Change-Id: Ib520bde439b03f81d5e84a2711ed61215debe862
      52b14161
    • Nathan E. Egge's avatar
      Merge NEW_TOKENSET experiment into EC_MULTISYMBOL. · ad66b816
      Nathan E. Egge authored
      Change-Id: I0ed6d8f2b6a83641f65096cf41fcde94e70d94d4
      ad66b816
    • Joe Young's avatar
      [intra-edge] Filter intra edge samples · 12c0bc03
      Joe Young authored
      For ext-intra directional modes, filter intra edge samples
      dependent on block size and prediction angle.
      
      Congiguration:
      ./configure --enable-experimental --enable-ext-intra
        --enable-internal-stats --disable-cdef --disable-delta-q
      
      Coding gain (1 frame Intra):
      cif:    -0.03%
      midres: -0.01
      720p:   -0.65
      1080p:  -0.83
      4k:     -1.19
      
      Change-Id: I372bfc7614f6a07fe1d8e7b61bd0b6660f9fb4a1
      12c0bc03
    • Yunqing Wang's avatar
      Fix debugmodes file · d097ec14
      Yunqing Wang authored
      Fixed debugmodes.c to incorporate the mi size change in CB4X4.
      
      Change-Id: Id4d44866636a1a0715e03a7a4c9884c51ca7f59d
      d097ec14
  4. 15 May, 2017 11 commits
  5. 13 May, 2017 2 commits
  6. 12 May, 2017 5 commits
    • Urvang Joshi's avatar
      warped motion: fix some UBsan errors. · 378644ca
      Urvang Joshi authored
      Fixes the following UBSan errors due to left shifting
      negative values.
      
      Change-Id: I578ca3f56417a94ffe83f634171903897117aa6b
      378644ca
    • hui su's avatar
      Palette: use color cache to compress base colors · 33567b21
      hui su authored
      Get a list of palette base colors that are used in the above and
      left blocks, referred to as "color cache". For each cache color,
      signal if it is present in current block's palette, so that we
      don't need to transmit their raw values.
      
      When palette-delta-encoding is enabled, compression is improved
      by 2% on keyframe and 1% overall for the screen_content testset.
      
      Change-Id: I4cb027f1904aa9d0ab1c8f00ea9ee34bf5f16234
      33567b21
    • Fergus Simpson's avatar
      frame_superres: Move av1_scale_if_requrired to common · 090bb60f
      Fergus Simpson authored
      This commit moves the av1_scale_if_required functions from
      av1/encoder/encoder to av1/common/resize. They take the
      scale_and_extend_frame_nonnormative function with them.
      
      This will be useful for resizing received frames in the decoder for the
      FRAME_SUPERRES experiment.
      
      Change-Id: I83afc3d97ff8ebce5ecb2e1205ba6c271156cb31
      090bb60f
    • emilkeyder@google.com's avatar
      Split av1_warp_erroradv into av1_{frame,warp}_error. · 6e3557c9
      emilkeyder@google.com authored
      This avoids repeatedly computing the frame error in
      refine_integerized_param.
      
      Change-Id: If4af77b68a7e61a700bafa3f60940b9017e12b40
      6e3557c9
    • Luc Trudeau's avatar
      [CFL] move cfl_idx_to_alpha to header · 04120190
      Luc Trudeau authored
      Move cfl_idx_to_alpha in the header to facilitate inlining.
      Remove the forward MB_MODE_INFO forward declaration
      
      Change-Id: Id33fb0228d88b6285252843e2345a0d3ae875cd2
      04120190
  7. 11 May, 2017 9 commits
    • Yue Chen's avatar
      Add CONFIG_INTERINTRA flags and reduce # of interintra modes to 4 · 4d26acb4
      Yue Chen authored
      Use CONFIG_INTERINTRA to properly separate interintra from the basic
      ext_inter experiment.
      When macro REDUCE_INTERINTRA_MODES is 1, only 4 ii modes are enabled
      so as to reduce the complexity overhead.
      (Right now the flag is off)
      
      Change-Id: Iec6f36a1000f181adbb822ad66c7d5b2625e9cc7
      4d26acb4
    • Urvang Joshi's avatar
      Handle tx64x64 correctly in get_entropy_contexts. · 4c6d4369
      Urvang Joshi authored
      This unhandled case was causing an assertion failure.
      
      BUG=aomedia:532
      
      Change-Id: I46665c380ad171e2b9ddf4d41b6e9fff838f8b3e
      4c6d4369
    • Luc Trudeau's avatar
      [CFL] Rename cfl_alpha_ind to cfl_alpha_idx · a9bd85f7
      Luc Trudeau authored
      Change-Id: Id14d83bdce8321bef81972a4f5530a50589d9578
      a9bd85f7
    • Alex Converse's avatar
      Fix build with global motion disabled · ea166870
      Alex Converse authored
      Change-Id: I1c00925f83c6a858b0e799ddd90f241570a40575
      ea166870
    • Urvang Joshi's avatar
      dr_prediction_z2: check that index into 'left' is valid. · 56bc7ef6
      Urvang Joshi authored
      For 'left' array indices -1 onwards are valid (left[-1] == above[-1] ==
      the top-left reference pixel).
      So, make sure that 'base2' is in that range too.
      
      Change-Id: If5118d97d4ef85f6520363bd648bfe6948c1211f
      56bc7ef6
    • Sean Purser-Haskell's avatar
      Extra rounding to let hw to use narrower integers. · 14b8112b
      Sean Purser-Haskell authored
      Change-Id: I175d6ff03f31a2e0d2fe7cd1c3852210d6e0ddf5
      14b8112b
    • David Barker's avatar
      More accurate chroma warping · f7a5ee53
      David Barker authored
      Previously, the projected positions of chroma pixels would effectively
      undergo double rounding, since we round both when calculating x4 / y4
      and when calculating the filter index. Further, the two roundings
      were different: x4 / y4 used ROUND_POWER_OF_TWO_SIGNED, whereas
      the filter index uses ROUND_POWER_OF_TWO.
      
      It is slightly more accurate (and faster) to replace the first
      rounding by a shift; this is motivated by the fact that
      ROUND_POWER_OF_TWO(x >> a, b) == ROUND_POWER_OF_TWO(x, a + b)
      
      Change-Id: Ia52b05745168d0aeb05f0af4c75ff33eee791d82
      f7a5ee53
    • Yi Luo's avatar
      Partial IDCT 32x32 avx2 · 40f22ef8
      Yi Luo authored
      - Function level improvement (ms):
      Functions       ssse3  avx2   Percentage
      idct32x32_1024  794    374    52.9%
      idct32x32_135   354    169    52.2%
      idct32x32_34    197    142    27.9%
      idct32x32_1     n/a     26    n/a
      
      - Integrating in default scan order.
      
      Change-Id: I84815112b26b8a8cb800281a1cfb1706342af57d
      40f22ef8
    • David Barker's avatar
      Vectorize corner matching function · ee674323
      David Barker authored
      Add an SSE4 version of compute_cross_correlation() from
      corner_match.c. This function is about 3.4x the speed of
      the scalar code; determine_correspondence as a whole is about
      2.5-3x the speed it was previously.
      
      BUG=aomedia:487
      
      Change-Id: I707b7cfd5c513c025d3ee7fb6a5f1fa335ecd495
      ee674323