1. 16 Jun, 2015 1 commit
  2. 31 May, 2015 1 commit
  3. 24 Nov, 2014 1 commit
  4. 11 Nov, 2014 2 commits
  5. 10 Oct, 2014 1 commit
  6. 17 Jul, 2014 1 commit
  7. 13 Jul, 2014 1 commit
  8. 11 Jul, 2014 1 commit
  9. 09 Jul, 2014 1 commit
  10. 06 Jul, 2014 1 commit
  11. 18 Jun, 2014 1 commit
  12. 27 May, 2014 1 commit
  13. 20 Mar, 2014 6 commits
  14. 13 Mar, 2014 1 commit
  15. 14 Feb, 2014 1 commit
    • Janne Grunau's avatar
      ppc: reduce overreads when loading 8 pixels in altivec dsp functions · 98fdfa99
      Janne Grunau authored
      Altivec can only load naturally aligned vectors. To handle possibly
      unaligned data a second vector is loaded from an offset of the original
      location and the data is recovered through a vector permutation.
      Overreads are minimal if the offset for second load points to the last
      element of data. This is 7 for loading eight 8-bit pixels and overreads
      are reduced from 16 bytes to 8 bytes if the pixels are 64-bit aligned.
      For unaligned pixels the overread is reduced from 23 bytes to 15 bytes
      in the worst case.
      98fdfa99
  16. 19 Apr, 2013 1 commit
  17. 13 Mar, 2013 1 commit
  18. 05 Feb, 2013 2 commits
  19. 23 Jan, 2013 1 commit
  20. 20 Jan, 2013 1 commit
  21. 09 Sep, 2012 1 commit
  22. 08 Jun, 2012 1 commit
  23. 30 Apr, 2012 1 commit
    • Mans Rullgard's avatar
      ppc: dsputil: do unaligned block accesses correctly · 4c387c70
      Mans Rullgard authored
      To load unaligned vector data in the usual way, explicit vec_ld()
      should be used rather than dereferencing a pointer to a vector type.
      When the VSX extension is enabled, gcc may compile vector pointer
      dereferences using the VSX lxvw4x instruction instead of the lvx
      instruction typically used with Altivec/VMX.  As the behaviour of
      these instructions with unaligned addresses differs, it is important
      that only lvx is used here.
      Signed-off-by: 's avatarMans Rullgard <mans@mansr.com>
      4c387c70
  24. 15 Feb, 2012 2 commits
  25. 21 Jul, 2011 2 commits
  26. 16 Jul, 2011 1 commit
  27. 10 May, 2011 1 commit
    • Oskar Arvidsson's avatar
      Adds 8-, 9- and 10-bit versions of some of the functions used by the h264 decoder. · 19a0729b
      Oskar Arvidsson authored
      This patch lets e.g. dsputil_init chose dsp functions with respect to
      the bit depth to decode. The naming scheme of bit depth dependent
      functions is <base name>_<bit depth>[_<prefix>] (i.e. the old
      clear_blocks_c is now named clear_blocks_8_c).
      
      Note: Some of the functions for high bit depth is not dependent on the
      bit depth, but only on the pixel size. This leaves some room for
      optimizing binary size.
      
      Preparatory patch for high bit depth h264 decoding support.
      Signed-off-by: 's avatarRonald S. Bultje <rsbultje@gmail.com>
      19a0729b
  28. 10 Apr, 2011 1 commit
    • Oskar Arvidsson's avatar
      Adds 8-, 9- and 10-bit versions of some of the functions used by the h264 decoder. · 8dbe5856
      Oskar Arvidsson authored
      This patch lets e.g. dsputil_init chose dsp functions with respect to
      the bit depth to decode. The naming scheme of bit depth dependent
      functions is <base name>_<bit depth>[_<prefix>] (i.e. the old
      clear_blocks_c is now named clear_blocks_8_c).
      
      Note: Some of the functions for high bit depth is not dependent on the
      bit depth, but only on the pixel size. This leaves some room for
      optimizing binary size.
      
      Preparatory patch for high bit depth h264 decoding support.
      Signed-off-by: 's avatarMichael Niedermayer <michaelni@gmx.at>
      8dbe5856
  29. 19 Mar, 2011 1 commit
  30. 30 Jan, 2011 1 commit
  31. 29 Jan, 2011 1 commit