1. 04 Mar, 2009 4 commits
  2. 03 Mar, 2009 1 commit
  3. 26 Feb, 2009 1 commit
  4. 16 Feb, 2009 1 commit
  5. 14 Feb, 2009 1 commit
  6. 11 Feb, 2009 2 commits
  7. 10 Feb, 2009 1 commit
    • Manuel Rommel's avatar
      fix 10l in 75b495f2723fcb77f · 65304078
      Manuel Rommel authored
      Original thread:
      date: Mon, Feb 9, 2009 at 9:37 PM
      subject: [x264-devel] commit: Spare a vec_perm and a vec_mergeh though using a LUT of permutation vectors . (Guillaume Poirier )
      65304078
  8. 09 Feb, 2009 7 commits
  9. 08 Feb, 2009 1 commit
  10. 04 Feb, 2009 2 commits
  11. 03 Feb, 2009 2 commits
  12. 01 Feb, 2009 1 commit
  13. 30 Jan, 2009 1 commit
    • Fiona Glaser's avatar
      Massive overhaul of nnz/cbp calculation · e394bd60
      Fiona Glaser authored
      Modify quantization to also calculate array_non_zero.
      PPC assembly changes by gpoirior.
      New quant asm includes some small tweaks to quant and SSE4 versions using ptest for the array_non_zero.
      Use this new feature of quant to merge nnz/cbp calculation directly with encoding and avoid many unnecessary calls to dequant/zigzag/decimate/etc.
      Also add new i16x16 DC-only iDCT with asm.
      Since intra encoding now directly calculates nnz, skip_intra now backs up nnz/cbp as well.
      Output should be equivalent except when using p4x4+RDO because of a subtlety involving old nnz values lying around.
      Performance increase in macroblock_encode: ~18% with dct-decimate, 30% without at CRF 25.
      Overall performance increase 0-6% depending on encoding settings.
      e394bd60
  14. 29 Jan, 2009 2 commits
  15. 28 Jan, 2009 3 commits
  16. 27 Jan, 2009 1 commit
    • Fiona Glaser's avatar
      Much faster chroma encoding and other opts · 83d805fe
      Fiona Glaser authored
      ~15% faster chroma encode by reorganizing CBP calculation and adding special-case idct_dc function, since most coded chroma blocks are DC-only.
      Small optimization in cache_save (skip_bp)
      Fix array_non_zero to not violate strict aliasing (should eliminate miscompilation issues in the future)
      Add in automatic substitutions for some asm instructions that have an equivalent smaller representation.
      83d805fe
  17. 26 Jan, 2009 1 commit
  18. 23 Jan, 2009 2 commits
  19. 20 Jan, 2009 2 commits
  20. 19 Jan, 2009 1 commit
  21. 18 Jan, 2009 2 commits
  22. 17 Jan, 2009 1 commit