ffmpeg | branch: master | Martin Storsjö | Thu Feb 23
23:33:58 2017 +0200| [3bf9c48320f25f3d5557485b0202f22ae60748b0] | committer:
Martin Storsjö
aarch64: vp9lpf: Use dup+rev16+uzp1 instead of dup+lsr+dup+trn1
This is one cycle faster in total, and three instructions fewer.
Before:
vp9_loop_f
ffmpeg | branch: master | Martin Storsjö | Thu Feb 23
23:33:58 2017 +0200| [f32690a298badbf2df66319e9b38236ad3d3e321] | committer:
Martin Storsjö
aarch64: vp9lpf: Use dup+rev16+uzp1 instead of dup+lsr+dup+trn1
This is one cycle faster in total, and three instructions fewer.
Before:
vp9_loop_f