[FFmpeg-devel] [PATCH 0/6] avcodec/vc1: Arm optimisations

[Ben Avison <bavison@riscosopen.org>]

The VC1 decoder was missing lots of important fast paths for Arm, especially
for 64-bit Arm. This submission fills in implementations for all functions
where a fast path already existed and the fallback C implementation was
taking 1% or more of the runtime, and adds a new fast path to permit
vc1_unescape_buffer() to be overridden.

I've measured the playback speed on a 1.5 GHz Cortex-A72 (Raspberry Pi 4)
using `ffmpeg -i <bitstream> -f null -` for a couple of example streams:

Architecture:  AArch32    AArch32    AArch64    AArch64
Stream:        1          2          1          2
Before speed:  1.22x      0.82x      1.00x      0.67x
After speed:   1.31x      0.98x      1.39x      1.06x
Improvement:   7.4%       20%        39%        58%

`make fate` passes on both AArch32 and AArch64.

Ben Avison (6):
  avcodec/vc1: Arm 64-bit NEON deblocking filter fast paths
  avcodec/vc1: Arm 32-bit NEON deblocking filter fast paths
  avcodec/vc1: Arm 64-bit NEON inverse transform fast paths
  avcodec/idctdsp: Arm 64-bit NEON block add and clamp fast paths
  avcodec/blockdsp: Arm 64-bit NEON block clear fast paths
  avcodec/vc1: Introduce fast path for unescaping bitstream buffer

 libavcodec/aarch64/Makefile                |    6 +-
 libavcodec/aarch64/blockdsp_init_aarch64.c |   42 +
 libavcodec/aarch64/blockdsp_neon.S         |   43 +
 libavcodec/aarch64/idctdsp_init_aarch64.c  |   26 +-
 libavcodec/aarch64/idctdsp_neon.S          |  130 ++
 libavcodec/aarch64/vc1dsp_init_aarch64.c   |   93 ++
 libavcodec/aarch64/vc1dsp_neon.S           | 1552 ++++++++++++++++++++
 libavcodec/arm/vc1dsp_init_neon.c          |   74 +
 libavcodec/arm/vc1dsp_neon.S               |  761 ++++++++++
 libavcodec/blockdsp.c                      |    2 +
 libavcodec/blockdsp.h                      |    1 +
 libavcodec/vc1dec.c                        |   20 +-
 libavcodec/vc1dsp.c                        |    2 +
 libavcodec/vc1dsp.h                        |    3 +
 14 files changed, 2736 insertions(+), 19 deletions(-)
 create mode 100644 libavcodec/aarch64/blockdsp_init_aarch64.c
 create mode 100644 libavcodec/aarch64/blockdsp_neon.S
 create mode 100644 libavcodec/aarch64/idctdsp_neon.S
 create mode 100644 libavcodec/aarch64/vc1dsp_neon.S

-- 
2.25.1

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".