1. 23 May, 2015 1 commit
    • James Zern's avatar
      add vp9/common/x86/convolve.h · ef2b3cce
      James Zern authored
      collect the vp9_convolve function definition macros there; this will
      allow some relocation of functions from vp9_asm_stubs.c
      
      Change-Id: Idadd117fa256dd48748379856973fd985b8204e8
      ef2b3cce
  2. 08 May, 2015 1 commit
  3. 07 May, 2015 1 commit
  4. 05 May, 2015 1 commit
  5. 30 Apr, 2015 1 commit
    • Yaowu Xu's avatar
      Remove vp9_idct16x16_10_add_ssse3() · 47767609
      Yaowu Xu authored
      The rotation computation using 2X of cos(pi/16) has a potential to
      overflow 32 bit, this commit disable the function to allow further
      investigation and optimization.
      
      Change-Id: I4a9803bc71303d459cb1ec5bbd7c4aaf8968e5cf
      47767609
  6. 29 Apr, 2015 1 commit
  7. 21 Apr, 2015 3 commits
  8. 18 Apr, 2015 1 commit
  9. 09 Apr, 2015 1 commit
  10. 01 Apr, 2015 1 commit
  11. 06 Feb, 2015 1 commit
  12. 19 Jan, 2015 1 commit
    • JackyChen's avatar
      SSE2 code for the filter in MFQE. · 09673deb
      JackyChen authored
      The SSE2 code is from VP8 MFQE, reuse it in VP9. No change on VP8
      side. In our testing, we achieve 2X speed by adopting this change.
      
      Change-Id: Ib2b14144ae57c892005c1c4b84e3379d02e56716
      09673deb
  13. 17 Jan, 2015 1 commit
    • Yunqing Wang's avatar
      vp9_ethread: add parallel loopfilter · e76eaf05
      Yunqing Wang authored
      1. Added row-based loopfilter in encoder;
      2. Moved common multi-threaded loopfilter functions from decoder
         to common;
      3. Merged multi-threaded loopfilter code, and made encoder/
         decoder call same function to reduce code duplication.
      
      Encoder tests showed that 1% - 2% speedup was seen for good-quality
      2-pass mode(at speed 3); 1% - 3% speedup using 2 threads and 4% - 6%
      speedup using 4 threads were seen for real-time mode(at speed 7).
      
      Change-Id: I8a4ac51c2ad9bab9fa7b864e90743931c53ec1c4
      e76eaf05
  14. 07 Jan, 2015 2 commits
  15. 17 Dec, 2014 1 commit
  16. 16 Dec, 2014 2 commits
    • James Yu's avatar
      VP9 common for ARMv8 by using NEON intrinsics 16 · aa8dd897
      James Yu authored
      Add vp9_reconintra_neon.c
      - vp9_v_predictor_4x4_neon
      - vp9_v_predictor_8x8_neon
      - vp9_v_predictor_16x16_neon
      - vp9_v_predictor_32x32_neon
      - vp9_h_predictor_4x4_neon
      - vp9_h_predictor_8x8_neon
      - vp9_h_predictor_16x16_neon
      - vp9_h_predictor_32x32_neon
      - vp9_tm_predictor_4x4_neon
      - vp9_tm_predictor_8x8_neon
      - vp9_tm_predictor_16x16_neon
      - vp9_tm_predictor_32x32_neon
      
      Change-Id: Ib5d54a4766a1b5127169045659974f33aa98376d
      Signed-off-by: 's avatarJames Yu <james.yu@linaro.org>
      aa8dd897
    • James Yu's avatar
      VP9 common for ARMv8 by using NEON intrinsics 19 · ba05a4c6
      James Yu authored
      Delete vp9_dc_only_idct_add_neon.c
      
      The function was merged with vp9_short_idct4x4_1_add (later
      vp9_idct4x4_1_add) in d2de1ca3 and should have been deleted then.
      
      Change-Id: Ie58ba3dd9dc7330a8f1238dd7dd71c9ed4639b94
      Signed-off-by: 's avatarJames Yu <james.yu@linaro.org>
      ba05a4c6
  17. 15 Dec, 2014 2 commits
  18. 11 Dec, 2014 3 commits
    • JackyChen's avatar
      Multiframe Quality Enhancement(MFQE) in VP9. · 7ac3e3c1
      JackyChen authored
      It is the first version of MFQE in VP9. There are a few TODOs included
      in this version.
      Usage: Add flag --enable-vp9-postproc to config the project.
      In decoder, use flag --mfqe in the command line to enable
      MFQE in postproc.
      Note: Need to have key frame with low quality to see the effect of this
      new patch. In my experiment, I fixed the qindex to 200 in key frame.
      
      Change-Id: I021f9ce4616ed3574c81e48d968662994b56a396
      7ac3e3c1
    • James Yu's avatar
      VP9 common for ARMv8 by using NEON intrinsics 18 · 3f7c12da
      James Yu authored
      Add vp9_idct32x32_add_neon.c
      - vp9_idct32x32_1024_add_neon
      
      Change-Id: Ic598b772c28bd3487a8ead7a4598a66b25f9b00f
      Signed-off-by: 's avatarJames Yu <james.yu@linaro.org>
      3f7c12da
    • James Yu's avatar
      VP9 common for ARMv8 by using NEON intrinsics 14 · 3cfed4bf
      James Yu authored
      Add vp9_idct16x16_add_neon.c
      - vp9_idct16x16_256_add_neon_pass1
      - vp9_idct16x16_256_add_neon_pass2
      - vp9_idct16x16_10_add_neon_pass1
      - vp9_idct16x16_10_add_neon_pass2
      
      Change-Id: I54d25b54a36f4371760f54e4036693aaea40a5de
      Signed-off-by: 's avatarJames Yu <james.yu@linaro.org>
      3cfed4bf
  19. 10 Dec, 2014 10 commits
  20. 09 Dec, 2014 1 commit
  21. 23 Sep, 2014 1 commit
  22. 18 Sep, 2014 1 commit
  23. 16 Sep, 2014 1 commit
  24. 05 Sep, 2014 1 commit
    • Dmitry Kovalev's avatar
      Removing postproc mmx code. · 1100e262
      Dmitry Kovalev authored
      Removed functions:
      * vp9_post_proc_down_and_across_mmx
      * vp9_mbpost_proc_down_mmx
      * vp9_plane_add_noise_mmx
      
      They all have sse2 equivalent.
      
      Change-Id: I59c1fac12b7c96ca4538d455e4400c2b7875feff
      1100e262