[FFmpeg-devel] [PATCH 0/5] x86: hevc_mc: port to SSSE3 v2

Christophe Gisquet christophe.gisquet at gmail.com
Sun Aug 24 10:46:29 CEST 2014


Since last iteration:
- PACKUSWD macro to support both sse4 and ssse3;
- Instanciate SSE4 functions for WP;
- Various side cleanups.

The first 3 patches I think don't have any caveat.

However, the last one shows that we have issues in the current code:
instead of having actual instances for every combination of operations
and widths, more proxy functions could be used. It's a mind-numbing
task which I don't think I'm up for. Looking at the object size, there
might even be a speed benefit, though.

Christophe Gisquet (5):
  x86: hevc_mc: split differently calls
  x86: hevc_mc: correct unneeded use of SSE4 code
  x86: hevc_mc: make WP proxy functions static
  x86: hevc_mc: convert to ssse3
  x86: hevc_mc: reimplement SSE4 versions for WP

 libavcodec/x86/hevc_mc.asm    |  98 ++++--
 libavcodec/x86/hevcdsp.h      |  54 ++--
 libavcodec/x86/hevcdsp_init.c | 717 +++++++++++++++++++++++++++---------------
 3 files changed, 571 insertions(+), 298 deletions(-)

-- 
1.9.2.msysgit.0



More information about the ffmpeg-devel mailing list