[FFmpeg-devel] [PATCH v4 2/2] lavc/aarch64: add pred16x16 10-bit functions

[Martin Storsjö]

On Thu, 15 Apr 2021, Mikhail Nitenko wrote:

> Benchmarks:                      A53     A72
> pred16x16_dc_10_c:              136.0   124.0
> pred16x16_dc_10_neon:           121.2   106.0
> pred16x16_horizontal_10_c:      155.0    73.2
> pred16x16_horizontal_10_neon:    82.2    67.7
> pred16x16_top_dc_10_c:          106.0    93.7
> pred16x16_top_dc_10_neon:        87.7    77.2
> pred16x16_vertical_10_c:         83.0    67.7
> pred16x16_vertical_10_neon:      54.2    61.7
>
> Some functions work slower than C and are left commented out.
> ---

It's usually good to add an annotation (i.e. below the '---', so it won't 
be part of the commit message when applied) where you mention what has 
changed from the previous round, for other readers who you haven't talked 
directly to.

> libavcodec/aarch64/h264pred_init.c |  11 +++
> libavcodec/aarch64/h264pred_neon.S | 108 +++++++++++++++++++++++++++++
> 2 files changed, 119 insertions(+)

The change itself looks good to me now.

// Martin