1. 07 Aug, 2012 1 commit
  2. 03 Aug, 2012 1 commit
    • Ronald S. Bultje's avatar
      dsputil: make add_hfyu_left_prediction_sse4() support unaligned src. · da6505ad
      Ronald S. Bultje authored
      This makes add_hfyu_left_prediction_sse4() handle sources that are not
      16-byte aligned in its own function rather than by proxying the call to
      add_hfyu_left_prediction_ssse3(). This fixes a crash on Win64, since the
      sse4 version clobberes xmm6, but the ssse3 version (which uses MMX regs)
      does not restore it, thus leading to XMM clobbering and RSP being off.
      
      Fixes bug 342.
      da6505ad
  3. 26 Jul, 2012 1 commit
  4. 22 Jul, 2012 1 commit
  5. 08 Jun, 2012 1 commit
  6. 22 May, 2012 1 commit
  7. 21 May, 2012 1 commit
  8. 13 Apr, 2012 1 commit
    • Ronald S. Bultje's avatar
      dsputil: fix optimized emu_edge function on Win64. · b089ca87
      Ronald S. Bultje authored
      Recent register allocation changes (x86inc.asm update) changed the
      register order and thus opcodes for the inner loops. One of them became
      >128bytes, which confuses other parts of this function where it jumps
      to fixed-offset positions to extend the edge by fixed amounts. A simple
      register change fixes this.
      b089ca87
  9. 11 Apr, 2012 1 commit
  10. 04 Apr, 2012 1 commit
  11. 07 Mar, 2012 1 commit
  12. 02 Feb, 2012 1 commit
  13. 30 Jan, 2012 1 commit
    • Christophe Gisquet's avatar
      x86 dsputil: provide SSE2/SSSE3 versions of bswap_buf · 6b039003
      Christophe Gisquet authored
      
      
      While pshufb allows emulating bswap on XMM registers for SSSE3, more
      shuffling is needed for SSE2. Alignment is critical, so specific codepaths
      are provided for this case.
      
      For the huffyuv sequence "angels_480-huffyuvcompress.avi":
      C (using bswap instruction): ~ 55k cycles
      SSE2:                        ~ 40k cycles
      SSSE3 using unaligned loads: ~ 35k cycles
      SSSE3 using aligned loads:   ~ 30k cycles
      Signed-off-by: default avatarDiego Biurrun <diego@biurrun.de>
      6b039003
  14. 27 Jan, 2012 1 commit
  15. 22 Nov, 2011 2 commits
  16. 11 Nov, 2011 1 commit
  17. 07 Nov, 2011 1 commit
  18. 21 Oct, 2011 1 commit
  19. 18 Aug, 2011 1 commit
  20. 15 Aug, 2011 1 commit
  21. 12 Aug, 2011 1 commit
  22. 01 Jul, 2011 1 commit
  23. 20 May, 2011 1 commit
  24. 14 May, 2011 1 commit
  25. 23 Mar, 2011 1 commit
  26. 19 Mar, 2011 1 commit
  27. 08 Feb, 2011 1 commit
    • Ronald S. Bultje's avatar
      Fix ff_emu_edge_core_sse() on Win64. · 17cf7c68
      Ronald S. Bultje authored
      Fix emu_edge_v_extend_15 to be <128 bytes on Win64, by being more strict
      on the size of registers and which registers are being used for operations
      where multiple are available. This fixes segfaults in emulated_edge()
      function calls on Win64.
      17cf7c68
  28. 02 Feb, 2011 1 commit
  29. 01 Feb, 2011 1 commit
  30. 23 Jun, 2010 1 commit
  31. 22 Jan, 2010 1 commit
  32. 08 Dec, 2009 1 commit
  33. 05 Dec, 2009 2 commits
  34. 03 Dec, 2009 1 commit
  35. 18 Oct, 2009 3 commits
  36. 08 Feb, 2009 1 commit