1. 31 Mar, 2017 5 commits
    • Urvang Joshi's avatar
      RTCD defs: Remove empty specialize statements once and for all. · 5ddac0aa
      Urvang Joshi authored
      A similar cleanup happened before, but the empty statements have since
      reappeared. I added a check in 'specialize' subroutine to die whenever
      such an empty specialize call is found, so that config+make would fail.
      
      Change-Id: I300ca0f0b077c0aeca8096d6460d8fb1c364d9b9
      5ddac0aa
    • David Barker's avatar
      Allow NEAR_NEARMV and NEW_NEWMV modes to use ref_mv_idx · 404b2e87
      David Barker authored
      When ext-inter and ref-mv are both enabled, this patch
      allows the NEAR_NEARMV and NEW_NEWMV modes to pick from
      the extended reference mv list, just like the NEARMV and
      NEWMV modes can.
      
      Change-Id: Ibcc9e19dba7779422c1c9589d5498159e83bf61e
      404b2e87
    • Alex Converse's avatar
      Crop distortion to visible MIs · 61f37b87
      Alex Converse authored
      Ported from VP9 with some heavy modifications
      
      bsize_dist@2017-03-29T23:18:27.564Z -> bcropped_dist@2017-03-29T23:21:00.200Z
      
         PSNR | PSNR Cb | PSNR Cr | PSNR HVS |    SSIM | MS SSIM | CIEDE 2000
      -0.0966 | -0.0922 |  0.0032 |  -0.0618 | -0.0579 | -0.0441 |  -0.0959
      
      Change-Id: Icdfcf47a9017fd3180e7fbc963196a43c5376c4e
      61f37b87
    • Alex Converse's avatar
      variance: Add odd size sse functions · 29608d84
      Alex Converse authored
      Change-Id: I5eb7870d4b1b83bb907e539528f27f80a42e2fad
      29608d84
    • Yaowu Xu's avatar
      update md5 to reflect bitstream change · 19e0c4b6
      Yaowu Xu authored
      Making CDEF enabled by default changed the output bitstream of this
      test.
      
      Change-Id: I73a10d0cc339b7159bd30994b13127e9a4bf709a
      19e0c4b6
  2. 30 Mar, 2017 11 commits
    • Yi Luo's avatar
      High bit depth inter prediction filter AVX2 · 9d247355
      Yi Luo authored
      On i7-6700:
      - Function level speed improvement: 23%-29%
      - User level speed improvement:
         decoder: ~%2-%4.
         encoder: <1%.
      
      Change-Id: I02937a72304c3b356ca41e580352790df391f0a2
      9d247355
    • Yi Luo's avatar
      Add SSE2 av1_fht32x32 · 9a3d29ea
      Yi Luo authored
      BUG=aomedia:407
      
      Change-Id: I27a7a230bbc701920a996d1e22ae4d22ca8cfead
      9a3d29ea
    • James Zern's avatar
      clpf_test: mark TestSpeed disabled · e5034e34
      James Zern authored
      performance characteristics in test environments vary, speed tests
      should be for local performance testing. these can still be run with:
      --gtest_filter=*TestSpeed* --gtest_also_run_disabled_tests
      
      Change-Id: I96a05fe72336b7654ae832d3d2114dacc8203aa5
      e5034e34
    • James Zern's avatar
      dering_test: mark TestSpeed disabled · 22c0d57c
      James Zern authored
      performance characteristics in test environments vary, speed tests
      should be for local performance testing. these can still be run with:
      --gtest_filter=*TestSpeed* --gtest_also_run_disabled_tests
      
      Change-Id: I4c00ca6970ba7dc8387ee509e695ec922810c3ae
      22c0d57c
    • Jean-Marc Valin's avatar
      Prevent PVQ SSE search from putting pulses beyond n-1 · 133a9878
      Jean-Marc Valin authored
      Change-Id: Ib9fec5f2e00ecd73006a603a61d3fddee5229cf8
      133a9878
    • Yunqing Wang's avatar
      Enable/disable unit tests correctly in decoder-only build case · 80360585
      Yunqing Wang authored
      While building the decoder-only AV1, the unit tests need to be the ones
      that only call decoder functions.
      
      BUG=aomedia:395
      
      Change-Id: Iac7b464aa222a177c06b2e037faa6717305cd59d
      80360585
    • Debargha Mukherjee's avatar
      A few fixes for global motion · 11f0e40d
      Debargha Mukherjee authored
      Handles a rare divisin by 0 case.
      Also adds a check on global motion parameters to disable
      if the parameters obtained are outside the range that the
      shear supports. This fixes a rare assert failure.
      Also changes the recode loop threshold somewhat.
      
      Change-Id: I4c6e74b914ac653cd9caa0563d78b0a19a2a8627
      11f0e40d
    • Alex Converse's avatar
      Make aom_sum_squares_2d_i16 take width and height parameters. · 4c5b0204
      Alex Converse authored
      SSE2 may be needed for nx4 and 4xn.
      
      Change-Id: I3c10112447fdb5fe51a68bc2c6e2f2641b102723
      4c5b0204
    • Jean-Marc Valin's avatar
      SSIM-like contrast term for CDEF distortion function · 2d5c2016
      Jean-Marc Valin authored
      high-latency, cpu=0:
      
        PSNR | PSNR Cb | PSNR Cr | PSNR HVS |    SSIM | MS SSIM | CIEDE 2000
      0.0378 |  0.1946 |  0.1385 |  -0.1159 | -0.2058 | -0.2085 |     0.1353
      
      low-latency, cpu=0:
      
        PSNR | PSNR Cb | PSNR Cr | PSNR HVS |    SSIM | MS SSIM | CIEDE 2000
      0.2388 |  0.2234 |  0.3290 |   0.0623 | -0.1716 | -0.1704 |     0.2542
      
      low-latency, cpu=4:
      
        PSNR | PSNR Cb | PSNR Cr | PSNR HVS |    SSIM | MS SSIM | CIEDE 2000
      0.4089 |  0.3477 |  0.6132 |   0.1729 | -0.1905 | -0.1610 |     0.5522
      
      Change-Id: I35b8596667d82a127847b209416ad83e3b839a9a
      2d5c2016
    • Steinar Midtskogen's avatar
      Optimise od_dir_find8() for SSE4.1 · 40fbd217
      Steinar Midtskogen authored
      Change-Id: I56a35b0d3d76294cc7b3d601770f7dcef12a8bc9
      40fbd217
    • Yue Chen's avatar
      Restrict # of neighbors in obmc blending · 1bd42be6
      Yue Chen authored
      Only blend with the first N neighbors at each side. If the size of
      one dimenstion is 8/16/32/64, the max # of neighbors to overlap
      with is 1/2/3/4.
      Previously we disable obmc mode if there are too many neighbors.
      
      Change of performance in AWCY, compared to disabling obmc if
      at any side there are more than 2 overlappable neighbors.
      HL improved by 0.02%
      LL improved by 0.09%
      
      Change-Id: I93d9a65c6c4aabf0b4a4946e2253d3e2ef21a662
      1bd42be6
  3. 29 Mar, 2017 14 commits
  4. 28 Mar, 2017 10 commits