diff options
| author | Martin Storsjö <martin@martin.st> | 2016-11-10 11:06:26 +0200 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2016-11-10 11:15:56 +0200 |
| commit | 383d96aa2229f644d9bd77b821ed3a309da5e9fc (patch) | |
| tree | b2daa4f73e9eec8146710747e847220e1f8deac4 /libavcodec/vp9block.c | |
| parent | c44a8a3eabcd6acd2ba79f32ec8a432e6ebe552c (diff) | |
| download | ffmpeg-383d96aa2229f644d9bd77b821ed3a309da5e9fc.tar.gz | |
aarch64: vp9: Add NEON optimizations of VP9 MC functions
This work is sponsored by, and copyright, Google.
These are ported from the ARM version; it is essentially a 1:1
port with no extra added features, but with some hand tuning
(especially for the plain copy/avg functions). The ARM version
isn't very register starved to begin with, so there's not much
to be gained from having more spare registers here - we only
avoid having to clobber callee-saved registers.
Examples of runtimes vs the 32 bit version, on a Cortex A53:
ARM AArch64
vp9_avg4_neon: 27.2 23.7
vp9_avg8_neon: 56.5 54.7
vp9_avg16_neon: 169.9 167.4
vp9_avg32_neon: 585.8 585.2
vp9_avg64_neon: 2460.3 2294.7
vp9_avg_8tap_smooth_4h_neon: 132.7 125.2
vp9_avg_8tap_smooth_4hv_neon: 478.8 442.0
vp9_avg_8tap_smooth_4v_neon: 126.0 93.7
vp9_avg_8tap_smooth_8h_neon: 241.7 234.2
vp9_avg_8tap_smooth_8hv_neon: 690.9 646.5
vp9_avg_8tap_smooth_8v_neon: 245.0 205.5
vp9_avg_8tap_smooth_64h_neon: 11273.2 11280.1
vp9_avg_8tap_smooth_64hv_neon: 22980.6 22184.1
vp9_avg_8tap_smooth_64v_neon: 11549.7 10781.1
vp9_put4_neon: 18.0 17.2
vp9_put8_neon: 40.2 37.7
vp9_put16_neon: 97.4 99.5
vp9_put32_neon/armv8: 346.0 307.4
vp9_put64_neon/armv8: 1319.0 1107.5
vp9_put_8tap_smooth_4h_neon: 126.7 118.2
vp9_put_8tap_smooth_4hv_neon: 465.7 434.0
vp9_put_8tap_smooth_4v_neon: 113.0 86.5
vp9_put_8tap_smooth_8h_neon: 229.7 221.6
vp9_put_8tap_smooth_8hv_neon: 658.9 621.3
vp9_put_8tap_smooth_8v_neon: 215.0 187.5
vp9_put_8tap_smooth_64h_neon: 10636.7 10627.8
vp9_put_8tap_smooth_64hv_neon: 21076.8 21026.9
vp9_put_8tap_smooth_64v_neon: 9635.0 9632.4
These are generally about as fast as the corresponding ARM
routines on the same CPU (at least on the A53), in most cases
marginally faster.
The speedup vs C code is pretty much the same as for the 32 bit
case; on the A53 it's around 6-13x for ther larger 8tap filters.
The exact speedup varies a little, since the C versions generally
don't end up exactly as slow/fast as on 32 bit.
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libavcodec/vp9block.c')
| -rw-r--r-- | libavcodec/vp9block.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/libavcodec/vp9block.c b/libavcodec/vp9block.c index 54f76d6e1c..194d619ce2 100644 --- a/libavcodec/vp9block.c +++ b/libavcodec/vp9block.c @@ -1176,7 +1176,7 @@ static av_always_inline void mc_luma_dir(VP9Context *s, vp9_mc_func(*mc)[2], ff_thread_await_progress(ref_frame, FFMAX(th, 0), 0); // FIXME bilinear filter only needs 0/1 pixels, not 3/4 - // The arm _hv filters read one more row than what actually is + // The arm/aarch64 _hv filters read one more row than what actually is // needed, so switch to emulated edge one pixel sooner vertically // (!!my * 5) than horizontally (!!mx * 4). if (x < !!mx * 3 || y < !!my * 3 || @@ -1221,7 +1221,7 @@ static av_always_inline void mc_chroma_dir(VP9Context *s, vp9_mc_func(*mc)[2], ff_thread_await_progress(ref_frame, FFMAX(th, 0), 0); // FIXME bilinear filter only needs 0/1 pixels, not 3/4 - // The arm _hv filters read one more row than what actually is + // The arm/aarch64 _hv filters read one more row than what actually is // needed, so switch to emulated edge one pixel sooner vertically // (!!my * 5) than horizontally (!!mx * 4). if (x < !!mx * 3 || y < !!my * 3 || |