1. 06 Nov, 2015 6 commits
  2. 05 Nov, 2015 3 commits
    • James Zern's avatar
      vp9_spatial_svc_encoder.sh: fix command line param · 892130f7
      James Zern authored
      -l -> -sl, renamed in:
      be3b08da [svc] Temporal svc with two pass rate control
      
      Change-Id: I5a7b179b33d94e20e54825090659156dece928c0
      892130f7
    • Yunqing Wang's avatar
      57cae22c
    • Geza Lore's avatar
      Add AVX vectorized vp9_diamond_search_sad · f1342a7b
      Geza Lore authored
      This function now has an AVX intrinsics version which is about 80%
      faster compared to the C implementation. This provides a 2-4% total
      speed-up for encode, depending on encoding parameters. The function
      utilizes 3 properties of the cost function lookup table, constructed
      in 'cal_nmvjointsadcost' and 'cal_nmvsadcosts'.
      For the joint cost:
        - mvjointsadcost[1] == mvjointsadcost[2] == mvjointsadcost[3]
      For the component costs:
        - For all i: mvsadcost[0][i] == mvsadcost[1][i]
              (equal per component cost)
        - For all i: mvsadcost[0][i] == mvsadcost[0][-i]
              (Cost function is even)
      These must hold, otherwise the AVX version of the function cannot be used.
      
      Change-Id: I184055b864c5a2dc37b2d8c5c9012eb801e9daf6
      f1342a7b
  3. 04 Nov, 2015 21 commits
    • Angie Chiang's avatar
      Add vp10_inv_txfm1d_test · 444acd77
      Angie Chiang authored
      Change-Id: I3b76c0146af7f191cdae31d2b53ab6d51ac791a4
      444acd77
    • Angie Chiang's avatar
      Add iadst32 · b0df5e0f
      Angie Chiang authored
      Change-Id: I3a53ee51146d0bd4b0fe4b27c286e8c921f9823b
      b0df5e0f
    • Angie Chiang's avatar
      Add iadst16 · 35486a6b
      Angie Chiang authored
      Change-Id: I093881aacaf9a070f78cc4eea2e8a6ede8a71792
      35486a6b
    • Angie Chiang's avatar
      Add iadst8 · 0ca0cc24
      Angie Chiang authored
      Change-Id: Ia58e4735d7d7bfd2ac55259c32705118c6745c6d
      0ca0cc24
    • Angie Chiang's avatar
      Add iadst4 · ba69089e
      Angie Chiang authored
      Change-Id: Ie419b2b1e939a41c30ed609e1ba46f5f6609b2a5
      ba69089e
    • Angie Chiang's avatar
      Add idct32 · 74678334
      Angie Chiang authored
      Change-Id: I75412bdc4bd0d9c90e8b56e02e0e467a2d9957f9
      74678334
    • Angie Chiang's avatar
      Add idct16 · d3cee565
      Angie Chiang authored
      Change-Id: I8e5ba3a3f9b64ccbf038e371525e897774729b06
      d3cee565
    • Angie Chiang's avatar
      Add idct8 · bd9db2f5
      Angie Chiang authored
      Change-Id: I8092a6f229b196c5c8b7dcd2dff8aaf68253e422
      bd9db2f5
    • Angie Chiang's avatar
      Add idct4 · 7d2b7b69
      Angie Chiang authored
      Change-Id: I1d1b6822452772cec95160491c7bc6d3bba1f5c2
      7d2b7b69
    • Angie Chiang's avatar
      Add vp10_fwd_txfm1d_test · b934148f
      Angie Chiang authored
      Change-Id: If3bef2be355227cfc2932e4471b84c21c7cd2b90
      b934148f
    • Angie Chiang's avatar
      Add fadst32 · a9253a20
      Angie Chiang authored
      Change-Id: I77299f0e39fc7cef91e7e420513dbd05194f320a
      a9253a20
    • Angie Chiang's avatar
      Add fadst16 · a7d26f4e
      Angie Chiang authored
      Change-Id: I5175e39b5df73646488f74b2a9e4a463ae79d91a
      a7d26f4e
    • Debargha Mukherjee's avatar
    • Angie Chiang's avatar
      Merge "Add fadst8" into nextgenv2 · 3813c2bc
      Angie Chiang authored
      3813c2bc
    • Angie Chiang's avatar
      Merge "Add fadst4" into nextgenv2 · 498866b6
      Angie Chiang authored
      498866b6
    • Jingning Han's avatar
    • Jingning Han's avatar
      Simplify txfm rate-distortion optimization · 493d0234
      Jingning Han authored
      This commit refactors the rate-distortion optimization scheme for
      transform block coding. When both ext-tx and var-tx experiments
      are turned on, the encoding time for bus_cif at 1000 kbps goes down
      from 706377 ms to 666503 ms (5.6% speed-up). The coding statics
      remain unchanged.
      
      Change-Id: I20835db573725580aad79c16220f799ce01f2093
      493d0234
    • Geza Lore's avatar
      Flip the result of the inverse transform for FLIPADST. · 4f510809
      Geza Lore authored
      When using FLIPADST, the vp10_inv_txfm_add functions used to flip
      the destination array, add the result of the inverse transform, to it
      and then flip the destination back. This has been replaced by
      flipping the result of the inverse transform before adding it to the
      destination. Up-Down flipping is done by negating the destination
      stride, and staring from the bottom, so it should now be free.
      Left-right flipping is done with the usual SSE2 instructions in the
      optimized code.
      
      The C functions match the SSE2 functions as expected, so the C functions
      now do the flipping as well when required. Adding this cleanly required
      some refactoring of the C functions, but there is no measurable
      performance impact when ext-tx is not enabled.
      
      Encode speedup with ext-tx enabled is about 3%.
      
      Change-Id: I5b04e5d720f0b9f0d54fd8607a8764f2314c7234
      4f510809
    • Yaowu Xu's avatar
      Merge branch 'master' into nextgenv2 · 4aafd018
      Yaowu Xu authored
      4aafd018
    • 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
    • Marco Paniconi's avatar
      c6641709
  4. 03 Nov, 2015 10 commits