1. 13 Mar, 2014 1 commit
  2. 07 Oct, 2013 1 commit
  3. 21 Aug, 2013 1 commit
  4. 10 Apr, 2013 1 commit
  5. 23 Jan, 2013 1 commit
  6. 27 Nov, 2012 1 commit
  7. 13 Nov, 2012 1 commit
  8. 31 Oct, 2012 1 commit
  9. 30 Oct, 2012 2 commits
  10. 07 Aug, 2012 1 commit
  11. 05 Aug, 2012 1 commit
  12. 11 Apr, 2012 1 commit
  13. 08 Feb, 2012 1 commit
  14. 27 Jan, 2012 1 commit
  15. 15 Aug, 2011 1 commit
  16. 12 Aug, 2011 2 commits
  17. 29 Jul, 2011 1 commit
  18. 14 Jun, 2011 1 commit
  19. 13 Jun, 2011 2 commits
  20. 31 May, 2011 1 commit
  21. 17 May, 2011 1 commit
  22. 14 May, 2011 1 commit
  23. 19 Mar, 2011 1 commit
  24. 14 Jan, 2011 1 commit
  25. 26 Sep, 2010 1 commit
  26. 24 Sep, 2010 2 commits
  27. 14 Sep, 2010 1 commit
    • Ronald S. Bultje's avatar
      Rename h264_idct_sse2.asm to h264_idct.asm; move inline IDCT asm from · 1d16a1cf
      Ronald S. Bultje authored
      h264dsp_mmx.c to h264_idct.asm (as yasm code). Because the loops are now
      coded in asm instead of C, this is (depending on the function) up to 50%
      faster for cases where gcc didn't do a great job at looping.
      
      Since h264_idct_add8() is now faster than the manual loop setup in h264.c,
      in-asm idct calling can now be enabled for chroma as well (see r16207). For
      MMX, this is 5% faster. For SSE2 (which isn't done for chroma if h264.c does
      the looping), this makes it up to 50% faster. Speed gain overall is ~0.5-1.0%.
      
      Originally committed as revision 25119 to svn://svn.ffmpeg.org/ffmpeg/trunk
      1d16a1cf