git.libav.org Git - libav.git/rss log

Les articles publiés sur le site

• aarch64 : vp9itxfm : Fix incorrect vertical alignment

  3 janvier 2017, par Martin Storsjö

  aarch64: vp9itxfm: Fix incorrect vertical alignment
  
  Signed-off-by: Martin Storsjö <martin@martin.st>
  

  • [DBH] libavcodec/aarch64/vp9itxfm_neon.S

• aarch64 : vp9itxfm : Use a single lane ld1 instead of ld1r where possible

  3 janvier 2017, par Martin Storsjö

  aarch64: vp9itxfm: Use a single lane ld1 instead of ld1r where possible
  
  The ld1r is a leftover from the arm version, where this trick is
  beneficial on some cores.
  
  Use a single-lane load where we don't need the semantics of ld1r.
  
  Signed-off-by: Martin Storsjö <martin@martin.st>
  

  • [DBH] libavcodec/aarch64/vp9itxfm_neon.S

• arm : vp9itxfm : Avoid reloading the idct32 coefficients

  2 janvier 2017, par Martin Storsjö

  arm: vp9itxfm: Avoid reloading the idct32 coefficients
  
  The idct32x32 function actually pushed q4-q7 onto the stack even
  though it didn't clobber them; there are plenty of registers that
  can be used to allow keeping all the idct coefficients in registers
  without having to reload different subsets of them at different
  stages in the transform.
  
  Since the idct16 core transform avoids clobbering q4-q7 (but clobbers
  q2-q3 instead, to avoid needing to back up and restore q4-q7 at all
  in the idct16 function), and the lanewise vmul needs a register in
  the q0-q3 range, we move the stored coefficients from q2-q3 into q4-q5
  while doing idct16.
  
  While keeping these coefficients in registers, we still can skip pushing
  q7.
  
  Before:                              Cortex A7       A8       A9      A53
  vp9_inv_dct_dct_32x32_sub32_add_neon:  18553.8  17182.7  14303.3  12089.7
  After:
  vp9_inv_dct_dct_32x32_sub32_add_neon:  18470.3  16717.7  14173.6  11860.8
  
  Signed-off-by: Martin Storsjö <martin@martin.st>
  

  • [DBH] libavcodec/arm/vp9itxfm_neon.S

• aarch64 : vp9itxfm : Avoid reloading the idct32 coefficients

  2 janvier 2017, par Martin Storsjö

  aarch64: vp9itxfm: Avoid reloading the idct32 coefficients
  
  The idct32x32 function actually pushed d8-d15 onto the stack even
  though it didn't clobber them; there are plenty of registers that
  can be used to allow keeping all the idct coefficients in registers
  without having to reload different subsets of them at different
  stages in the transform.
  
  After this, we still can skip pushing d12-d15.
  
  Before:
  vp9_inv_dct_dct_32x32_sub32_add_neon: 8128.3
  After:
  vp9_inv_dct_dct_32x32_sub32_add_neon: 8053.3
  
  Signed-off-by: Martin Storsjö <martin@martin.st>
  

  • [DBH] libavcodec/aarch64/vp9itxfm_neon.S

• cmdutils : update copyright year to 2017

  1er janvier 2017, par Sean McGovern

  cmdutils: update copyright year to 2017
  
  CC: libav-stable@libav.org
  

  • [DBH] cmdutils.c