1. 11 Dec, 2008 1 commit
    • Fiona Glaser's avatar
      Much faster CAVLC residual coding · 99448f6c
      Fiona Glaser authored
      Use a VLC table for common levelcodes instead of constructing them on-the-spot
      Branchless version of i_trailing calculation (2x faster on Nehalem)
      Completely remove array_non_zero_count and instead use the count calculated in level/run coding.  Note: this slightly changes output with subme > 7 due to different nonzero counts being stored during qpel RD.
  2. 05 Dec, 2008 1 commit
  3. 30 Nov, 2008 1 commit
  4. 29 Nov, 2008 3 commits
  5. 28 Nov, 2008 2 commits
    • Fiona Glaser's avatar
      10L in r1041 · df72b08c
      Fiona Glaser authored
    • Fiona Glaser's avatar
      Significantly faster CABAC and CAVLC residual coding and bit cost calculation · c1d73389
      Fiona Glaser authored
      Early-terminate in residual writing using stored nnz counts
      To allow the above, store nnz counts for luma and chroma DC
      Add assembly functions to find the last nonzero coefficient in a block
      Overall ~1.9% faster at subme9+8x8dct+qp25 with CAVLC, ~0.7% faster with CABAC
      Note this changes output slightly with CABAC RDO because it requires always storing correct nnz values during RDO, which wasn't done before in cases it wasn't useful.
      CAVLC output should be equivalent.
  6. 27 Nov, 2008 2 commits
  7. 26 Nov, 2008 1 commit
    • Fiona Glaser's avatar
      Remove nasm support · c5c0a7fd
      Fiona Glaser authored
      Nasm won't correctly parse the SSE4 code introduced a few revisions ago, so we're removing support.
      Users should upgrade to yasm 0.6.1 or later.
  8. 25 Nov, 2008 7 commits
  9. 23 Nov, 2008 1 commit
    • Fiona Glaser's avatar
      Phenom CPU optimizations · 80ea99c0
      Fiona Glaser authored
      Faster hpel_filter by using unaligned loads instead of emulated PALIGNR
      Faster hpel_filter on 64-bit by using the 32-bit version (the cost of emulated PALIGNR is high enough that the savings from caching intermediate values is not worth it).
      Add support for misaligned_mask on Phenom: ~2% faster hpel_filter, ~4% faster width16 multisad, 7% faster width20 get_ref.
      Replace width12 mmx with width16 sse on Phenom and Nehalem: 32% faster width12 get_ref on Phenom.
      Merge cpu-32.asm and cpu-64.asm
      Thanks to Easy123 for contributing a Phenom box for a weekend so I could write these optimizations.
  10. 21 Nov, 2008 1 commit
  11. 13 Nov, 2008 1 commit
  12. 11 Nov, 2008 1 commit
  13. 10 Nov, 2008 4 commits
    • Fiona Glaser's avatar
      Fix minor memory leak in r1022 · ebe1103b
      Fiona Glaser authored
    • Fiona Glaser's avatar
      r1024 borked checkasm · ac675e30
      Fiona Glaser authored
      Remove idct/dct2x2 from checkasm as they are no longer in dctf
    • Fiona Glaser's avatar
      Faster chroma encoding · be121180
      Fiona Glaser authored
      9-12% faster chroma encode.
      Move all functions for handling chroma DC that don't have assembly versions to macroblock.c and inline them, along with a few other tweaks.
    • Fiona Glaser's avatar
      Various cosmetics and minor fixes · ae51235d
      Fiona Glaser authored
      Disable hadamard_ac sse2/ssse3 under stack_mod4
      Fix one MSVC compilation warning
      Fix compilation in debug mode in certain cases on x64
      Remove eval.c from MSVC project
      Fix crash when VBV is used in CQP mode
      Patches by MasterNobody
  14. 09 Nov, 2008 1 commit
    • Fiona Glaser's avatar
      Faster b-adapt + adaptive quantization · 0c841de6
      Fiona Glaser authored
      Factor out pow to be only called once per macroblock.  Speeds up b-adapt, especially b-adapt 2, considerably.
      Speed boost is as high as 24% with b-adapt 2 + b-frames 16.
  15. 07 Nov, 2008 1 commit
  16. 06 Nov, 2008 1 commit
  17. 05 Nov, 2008 3 commits
  18. 30 Oct, 2008 1 commit
  19. 29 Oct, 2008 1 commit
    • Fiona Glaser's avatar
      Full sub8x8 RD mode decision · fb1af79e
      Fiona Glaser authored
      Small speed penalty with p4x4 enabled, but significant quality gain at subme >= 6
      As before, gain is proportional to the amount of p4x4 actually useful in a given input at the given bitrate.
  20. 27 Oct, 2008 1 commit
    • Fiona Glaser's avatar
      Optimize CABAC bit cost calculation · e09f55cc
      Fiona Glaser authored
      Speed up cabac mvd and add new precalculated transition/entropy table.
      Add "noup" function for cabac operations to not update the state table when it isn't necessary.
      1-3% faster macroblock_size_cabac.
  21. 24 Oct, 2008 1 commit
  22. 23 Oct, 2008 1 commit
  23. 22 Oct, 2008 3 commits