Commit 9d2afd1e authored by Martin Storsjö's avatar Martin Storsjö

aarch64: vp9: Implement NEON loop filters

This work is sponsored by, and copyright, Google.

These are ported from the ARM version; thanks to the larger
amount of registers available, we can do the loop filters with
16 pixels at a time. The implementation is fully templated, with
a single macro which can generate versions for both 8 and
16 pixels wide, for both 4, 8 and 16 pixels loop filters
(and the 4/8 mixed versions as well).

For the 8 pixel wide versions, it is pretty close in speed (the
v_4_8 and v_8_8 filters are the best examples of this; the h_4_8
and h_8_8 filters seem to get some gain in the load/transpose/store
part). For the 16 pixels wide ones, we get a speedup of around
1.2-1.4x compared to the 32 bit version.

Examples of runtimes vs the 32 bit version, on a Cortex A53:
                                       ARM AArch64
vp9_loop_filter_h_4_8_neon:          144.0   127.2
vp9_loop_filter_h_8_8_neon:          207.0   182.5
vp9_loop_filter_h_16_8_neon:         415.0   328.7
vp9_loop_filter_h_16_16_neon:        672.0   558.6
vp9_loop_filter_mix2_h_44_16_neon:   302.0   203.5
vp9_loop_filter_mix2_h_48_16_neon:   365.0   305.2
vp9_loop_filter_mix2_h_84_16_neon:   365.0   305.2
vp9_loop_filter_mix2_h_88_16_neon:   376.0   305.2
vp9_loop_filter_mix2_v_44_16_neon:   193.2   128.2
vp9_loop_filter_mix2_v_48_16_neon:   246.7   218.4
vp9_loop_filter_mix2_v_84_16_neon:   248.0   218.5
vp9_loop_filter_mix2_v_88_16_neon:   302.0   218.2
vp9_loop_filter_v_4_8_neon:           89.0    88.7
vp9_loop_filter_v_8_8_neon:          141.0   137.7
vp9_loop_filter_v_16_8_neon:         295.0   272.7
vp9_loop_filter_v_16_16_neon:        546.0   453.7

The speedup vs C code in checkasm tests is around 2-7x, which is
pretty much the same as for the 32 bit version. Even if these functions
are faster than their 32 bit equivalent, the C version that we compare
to also became around 1.3-1.7x faster than the C version in 32 bit.

Based on START_TIMER/STOP_TIMER wrapping around a few individual
functions, the speedup vs C code is around 4-5x.

Examples of runtimes vs C on a Cortex A57 (for a slightly older version
of the patch):
                         A57 gcc-5.3  neon
loop_filter_h_4_8_neon:        256.6  93.4
loop_filter_h_8_8_neon:        307.3 139.1
loop_filter_h_16_8_neon:       340.1 254.1
loop_filter_h_16_16_neon:      827.0 407.9
loop_filter_mix2_h_44_16_neon: 524.5 155.4
loop_filter_mix2_h_48_16_neon: 644.5 173.3
loop_filter_mix2_h_84_16_neon: 630.5 222.0
loop_filter_mix2_h_88_16_neon: 697.3 222.0
loop_filter_mix2_v_44_16_neon: 598.5 100.6
loop_filter_mix2_v_48_16_neon: 651.5 127.0
loop_filter_mix2_v_84_16_neon: 591.5 167.1
loop_filter_mix2_v_88_16_neon: 855.1 166.7
loop_filter_v_4_8_neon:        271.7  65.3
loop_filter_v_8_8_neon:        312.5 106.9
loop_filter_v_16_8_neon:       473.3 206.5
loop_filter_v_16_16_neon:      976.1 327.8

The speed-up compared to the C functions is 2.5 to 6 and the cortex-a57
is again 30-50% faster than the cortex-a53.
Signed-off-by: 's avatarMartin Storsjö <martin@martin.st>
parent 52d196fb
......@@ -45,4 +45,5 @@ NEON-OBJS-$(CONFIG_DCA_DECODER) += aarch64/dcadsp_neon.o \
aarch64/synth_filter_neon.o
NEON-OBJS-$(CONFIG_VORBIS_DECODER) += aarch64/vorbisdsp_neon.o
NEON-OBJS-$(CONFIG_VP9_DECODER) += aarch64/vp9itxfm_neon.o \
aarch64/vp9lpf_neon.o \
aarch64/vp9mc_neon.o
......@@ -195,8 +195,53 @@ static av_cold void vp9dsp_itxfm_init_aarch64(VP9DSPContext *dsp)
}
}
#define define_loop_filter(dir, wd, len) \
void ff_vp9_loop_filter_##dir##_##wd##_##len##_neon(uint8_t *dst, ptrdiff_t stride, int E, int I, int H)
#define define_loop_filters(wd, len) \
define_loop_filter(h, wd, len); \
define_loop_filter(v, wd, len)
define_loop_filters(4, 8);
define_loop_filters(8, 8);
define_loop_filters(16, 8);
define_loop_filters(16, 16);
define_loop_filters(44, 16);
define_loop_filters(48, 16);
define_loop_filters(84, 16);
define_loop_filters(88, 16);
static av_cold void vp9dsp_loopfilter_init_aarch64(VP9DSPContext *dsp)
{
int cpu_flags = av_get_cpu_flags();
if (have_neon(cpu_flags)) {
dsp->loop_filter_8[0][1] = ff_vp9_loop_filter_v_4_8_neon;
dsp->loop_filter_8[0][0] = ff_vp9_loop_filter_h_4_8_neon;
dsp->loop_filter_8[1][1] = ff_vp9_loop_filter_v_8_8_neon;
dsp->loop_filter_8[1][0] = ff_vp9_loop_filter_h_8_8_neon;
dsp->loop_filter_8[2][1] = ff_vp9_loop_filter_v_16_8_neon;
dsp->loop_filter_8[2][0] = ff_vp9_loop_filter_h_16_8_neon;
dsp->loop_filter_16[0] = ff_vp9_loop_filter_h_16_16_neon;
dsp->loop_filter_16[1] = ff_vp9_loop_filter_v_16_16_neon;
dsp->loop_filter_mix2[0][0][0] = ff_vp9_loop_filter_h_44_16_neon;
dsp->loop_filter_mix2[0][0][1] = ff_vp9_loop_filter_v_44_16_neon;
dsp->loop_filter_mix2[0][1][0] = ff_vp9_loop_filter_h_48_16_neon;
dsp->loop_filter_mix2[0][1][1] = ff_vp9_loop_filter_v_48_16_neon;
dsp->loop_filter_mix2[1][0][0] = ff_vp9_loop_filter_h_84_16_neon;
dsp->loop_filter_mix2[1][0][1] = ff_vp9_loop_filter_v_84_16_neon;
dsp->loop_filter_mix2[1][1][0] = ff_vp9_loop_filter_h_88_16_neon;
dsp->loop_filter_mix2[1][1][1] = ff_vp9_loop_filter_v_88_16_neon;
}
}
av_cold void ff_vp9dsp_init_aarch64(VP9DSPContext *dsp)
{
vp9dsp_mc_init_aarch64(dsp);
vp9dsp_loopfilter_init_aarch64(dsp);
vp9dsp_itxfm_init_aarch64(dsp);
}
This diff is collapsed.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment