[FFmpeg-devel] [PATCH] lavc/aarch64: Add pix_abs16_x2 neon implementation

[Hubert Mazur]

Thanks for the feedback. I made changes to the patch.
The performance has increased now to ~7 boost compared
to C implementation.

Changes:
- Do not use v8-v15 registers.
- Use urhadd instruction.
- Reorder the instructions to increase performance.

// Hubert