[x264-devel] x86: AVX2 plane_copy_deinterleave

[Henrik Gramner]

x264 | branch: master | Henrik Gramner <henrik at gramner.com> | Tue Jan 17 21:59:47 2017 +0100| [c22c10ddb21e9f5af1da83d37122e6f7388e1342] | committer: Henrik Gramner

x86: AVX2 plane_copy_deinterleave

50% faster than SSSE3 in 8-bit.
25% faster than AVX in high bit-depth.

Also drop the MMX versions of deinterleave functions in favor of SSE2.

> http://git.videolan.org/gitweb.cgi/x264.git/?a=commit;h=c22c10ddb21e9f5af1da83d37122e6f7388e1342
---

 common/x86/mc-a2.asm | 109 ++++++++++++++++++++++++++-------------------------
 common/x86/mc-c.c    |  20 ++++------
 encoder/encoder.c    |   4 +-
 tools/checkasm.c     |   2 +-
 4 files changed, 65 insertions(+), 70 deletions(-)

Diff:   http://git.videolan.org/gitweb.cgi/x264.git/?a=commitdiff;h=c22c10ddb21e9f5af1da83d37122e6f7388e1342