1. 07 Nov, 2014 1 commit
    • Johann's avatar
      Remove asm offset dependencies · 6eec73a7
      Johann authored
      The obj_int_extract code is no longer worth maintaining. It creates
      significant issues when adapting for different build systems and no
      longer offers as significant of a performance benefit due to
      improvements in intrinsics.
      
      Source files will remain until the various third-party builds are updated.
      
      The neon fast quantizer has been moved to intrinsics. The armv6 version
      has been removed because so few remaining targets require it.
      
      Compilers and processors have improved significantly since the
      pack_tokens code was written. The assembly is no longer faster than the
      C code.
      
      pack_tokens were the only optimizations for the armv5te targets so the targets
      will be removed after the test infrastructure has been updated.
      
      BUG=710
      
      Change-Id: Ic785b167cd9f95eeff31c7c76b7b736c07fb30eb
      6eec73a7
  2. 06 Nov, 2014 1 commit
    • Yunqing Wang's avatar
      Modify the frame context memory deallocation · 12284334
      Yunqing Wang authored
      This patch was to fix the vpxdec fuzzing3 test failure. When an
      error occurs, setjmp() is invoked, which calls the decoder
      removing routine. In multiple thread situation, other threads
      could try to access the frame context memory that is already
      deallocated, thus causing a segfault.
      
      An invalid unit test was added for this issue.
      
      Change-Id: Ida7442154f3d89759483f0f4fe0324041fffb952
      12284334
  3. 05 Nov, 2014 2 commits
  4. 04 Nov, 2014 2 commits
    • Johann's avatar
      Align structures in quantize test · dae280d5
      Johann authored
      MACROBLOCKD structures require alignment.
      
      This fixes an issue caught by clang IOC.
      
      Change-Id: Ibb5bcc122f531b4302a87e1144e4feaf46c1de64
      dae280d5
    • Johann's avatar
      Add some indirection to the quantize test · 9c6ce43d
      Johann authored
      Visual Studio and XCode require the address of the functions be passed.
      
      Change-Id: Id39cab8e50061fdc6ac6018371a3a158c713e14b
      9c6ce43d
  5. 03 Nov, 2014 1 commit
    • Johann's avatar
      vp8 quantize test · 53b68de5
      Johann authored
      Test for Regular, Fast and Pair quantization
      
      Change-Id: I0a26c164afe632db869099402189826c0d43f9a2
      53b68de5
  6. 01 Nov, 2014 1 commit
    • levytamar82's avatar
      WORKAROUND FIX FOR GCC4.9.1 · 86175a57
      levytamar82 authored
      In the function mb_lpf_horizontal_edge_w_avx2_16 the usage of the intrinsic
      _mm256_cvtepu8_epi16 cause a compiler bug in gcc 4.9.1.
      until it will be fixed I created a workaround that create the up convert by
      using broadcast128+shuffle.
      The bug was reported here:
      https://code.google.com/p/webm/issues/detail?id=867
      
      Change-Id: I73452e6806f42e0fadcde96b804ea3afa7eeb351
      86175a57
  7. 29 Oct, 2014 1 commit
  8. 21 Oct, 2014 1 commit
  9. 19 Oct, 2014 1 commit
    • levytamar82's avatar
      SAD32xh and SAD64xh for AVX2 · 7045aec0
      levytamar82 authored
      All sad function that process above 32 consecutive elements are optimized
      for AVX2:
      vp9_sad64x64
      vp9_sad64x32
      vp9_sad32x64
      vp9_sad32x32
      vp9_sad32x16
      vp9_sad64x64_avg
      vp9_sad64x32_avg
      vp9_sad32x64_avg
      vp9_sad32x32_avg
      vp9_sad32x16_avg
      The functions that appeared as a hotspot is vp9_sad32x32 and vp9_sad64x64
      vp9_sad32x32 was optimized by 68% and vp9_sad64x64 was optimized by 90%
      both of them gave and overall ~2.3% user level gain
      
      Change-Id: Iccf86b375a2b54c5fbbe685902ead0c9a561b9fd
      7045aec0
  10. 16 Oct, 2014 3 commits
  11. 14 Oct, 2014 1 commit
    • Minghai Shang's avatar
      [spatial svc]Another workaround to avoid using prev_mi · c113457a
      Minghai Shang authored
      We encode a empty invisible frame in front of the base layer frame to
      avoid using prev_mi. Since there's a restriction for reference frame
      scaling factor, we have to make it smaller and smaller gradually until
      its size is 16x16.
      Change-Id: I60b680314e33a60b4093cafc296465ee18169c19
      c113457a
  12. 13 Oct, 2014 2 commits
  13. 09 Oct, 2014 3 commits
  14. 08 Oct, 2014 1 commit
    • JackyChen's avatar
      Add unit test for VP8 denoiser. · 09fbe886
      JackyChen authored
      The unit test is to check the bitexactness of SSE2 code with C code.
      
      Change-Id: I13cc08a557b02357e5d6c2db7a49e93ce0d8e16f
      09fbe886
  15. 07 Oct, 2014 1 commit
    • Jim Bankoski's avatar
      experimental : partition using 1/8 x 1/8 image · 0ce51d82
      Jim Bankoski authored
      The concept:
      
      There's too much noise in source pixels for variance and at low bitrate
      the reconstructed looks nothing like the source so we have problems
      getting good partitionings with either.   This skirts the issue by using
      a box blur scaled down version for variance calculations.  To compare
      against source_var_ moved keyframe to be rd based like source_var.
      
      Change-Id: Ie3babdbfadae324b7b5a76bea192893af27f0624
      0ce51d82
  16. 06 Oct, 2014 2 commits
    • JackyChen's avatar
      Add SSE2 code and unit test for VP9 denoiser. · 80465dae
      JackyChen authored
      This SSE2 is based on VP8 denoiser's SSE2 code. In VP8, there are
      only 16x16 blocks in denoiser, while in VP9, there are 13 different
      block sizes.
      
      By adding this SSE2 code, the improvement of encoder speed is around
      20%(using C code vs using SSE2 code), vary for different clips.
      
      The unit test for VP9 denoiser is to confirm that the SSE2 code is
      bit-exact with the C code. The unit test covers all block size.
      
      Change-Id: Ic8d8ac26db4ea40a5f146b5678a065af07eaaa3d
      80465dae
    • Jingning Han's avatar
      Add range check in inverse ADST 16x16 · 12344f26
      Jingning Han authored
      Bit-stream clarification related to Issue 868.
      
      Change-Id: I92a7bc5b7782c9ea5c3f6cceec761742183c9514
      12344f26
  17. 03 Oct, 2014 1 commit
    • Deb Mukherjee's avatar
      Incorporate WRAPLOW macro into non-highbitdepth tx · d50716fa
      Deb Mukherjee authored
      Incorporates the WRAPLOW macro into the non-highbitdepth transforms
      to aid hardware verification between a software C model and an
      intended hardware implementation though the use of the configure
      options: --enable-experimental --enable-emulate-hardware.
      Note that to avoid further discrepancies between the sse/sse2
      implementations of the transforms and the C implementation, when the
      emulate hardware option is invoked, we also disable sse/sse2/etc.
      
      Also incudes some minor cleanups/renaming etc.
      
      Change-Id: Ib864d8493313927d429cce402982f1c8e45b3287
      d50716fa
  18. 02 Oct, 2014 1 commit
  19. 01 Oct, 2014 1 commit
  20. 23 Sep, 2014 1 commit
  21. 22 Sep, 2014 1 commit
  22. 20 Sep, 2014 1 commit
    • hkuang's avatar
      Fix compile warning. · db71c1bd
      hkuang authored
      warning: comparison between signed and unsigned integer expressions.
      
      Change-Id: Ib6ee7500fe910983f290fc321ad89c0ab9989455
      db71c1bd
  23. 19 Sep, 2014 2 commits
  24. 18 Sep, 2014 5 commits
  25. 16 Sep, 2014 1 commit
  26. 15 Sep, 2014 2 commits
    • Frank Galligan's avatar
      Remove memset of every external frame buffer. · 175d9dfe
      Frank Galligan authored
      Libvpx was memseting every external frame buffer before decode. This
      was to work around a valgrind issue in our C loop filter. Most of
      the time this was not needed and we have noticed some significant
      performance loss on some platforms. Now we require the application to
      zero out the buffers if it is using external frame buffers.
      
      Change-Id: I7330d00a315e65137ed30edd5f813e8929b76242
      175d9dfe
    • Scott LaVarnway's avatar
      VP8 encoder for ARMv8 by using NEON intrinsics 1 · fe2cc873
      Scott LaVarnway authored
      Add vp8_mse16x16_neon.c
      - vp8_mse16x16_neon
      - vp8_get4x4sse_cs_neon
      
      Change-Id: I108952f60a9ae50613f0ce3903c2c81df19d99d0
      Signed-off-by: 's avatarJames Yu <james.yu@linaro.org>
      fe2cc873