[x264-devel] x86: SSSE3 LUT-based faster coeff_level_run

Jason Garrett-Glaser git at videolan.org
Tue Apr 23 23:03:09 CEST 2013


x264 | branch: master | Jason Garrett-Glaser <jason at x264.com> | Thu Apr  4 18:00:23 2013 -0700| [b5acf1803b1f764a707efbb615efce76b367b46d] | committer: Jason Garrett-Glaser

x86: SSSE3 LUT-based faster coeff_level_run

~2x faster coeff_level_run.
Faster CAVLC encoding: {1%,2%,7%} overall with {superfast,medium,slower}.
Uses the same pshufb LUT abuse trick as in the previous ads_mvs patch.

> http://git.videolan.org/gitweb.cgi/x264.git/?a=commit;h=b5acf1803b1f764a707efbb615efce76b367b46d
---

 common/bitstream.h     |    6 +-
 common/quant.c         |   16 +++++
 common/x86/const-a.asm |    9 +++
 common/x86/pixel-a.asm |   24 ++++---
 common/x86/quant-a.asm |  170 ++++++++++++++++++++++++++++++++++++++++++++++--
 common/x86/quant.h     |   10 +++
 common/x86/x86inc.asm  |    2 +-
 encoder/cavlc.c        |    6 +-
 tools/checkasm.c       |    7 ++
 9 files changed, 226 insertions(+), 24 deletions(-)

Diff:   http://git.videolan.org/gitweb.cgi/x264.git/?a=commitdiff;h=b5acf1803b1f764a707efbb615efce76b367b46d


More information about the x264-devel mailing list