diff options
author | Lynne <dev@lynne.ee> | 2019-03-15 14:37:31 +0000 |
---|---|---|
committer | Carl Eugen Hoyos <ceffmpeg@gmail.com> | 2019-04-10 01:08:54 +0200 |
commit | 4d2f62150dba814eeb28de0d6723f6beb3638be9 (patch) | |
tree | db8525d9d273b177f6423a6d8629d5c659e1e798 /libavcodec/opusdsp.c | |
parent | 1c50d61a5a689f8eabef37f504c6f8f33eb178ba (diff) | |
download | ffmpeg-4d2f62150dba814eeb28de0d6723f6beb3638be9.tar.gz |
aarch64/opusdsp: implement NEON accelerated postfilter and deemphasis
153372 UNITS in postfilter_c, 65536 runs, 0 skips
73164 UNITS in postfilter_neon, 65536 runs, 0 skips -> 2.1x speedup
80591 UNITS in deemphasis_c, 131072 runs, 0 skips
43969 UNITS in deemphasis_neon, 131072 runs, 0 skips -> 1.83x speedup
Total decoder speedup: ~15% on a Raspberry Pi 3 (from 28.1x to 33.5x realtime)
Deemphasis SIMD based on the following unrolling:
const float c1 = CELT_EMPH_COEFF, c2 = c1*c1, c3 = c2*c1, c4 = c3*c1;
float state = coeff;
for (int i = 0; i < len; i += 4) {
y[0] = x[0] + c1*state;
y[1] = x[1] + c2*state + c1*x[0];
y[2] = x[2] + c3*state + c1*x[1] + c2*x[0];
y[3] = x[3] + c4*state + c1*x[2] + c2*x[1] + c3*x[0];
state = y[3];
y += 4;
x += 4;
}
Unlike the x86 version, duplication is used instead of pslldq so
the structure and tables are different.
Diffstat (limited to 'libavcodec/opusdsp.c')
-rw-r--r-- | libavcodec/opusdsp.c | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/libavcodec/opusdsp.c b/libavcodec/opusdsp.c index 17e819f977..0e179c98c9 100644 --- a/libavcodec/opusdsp.c +++ b/libavcodec/opusdsp.c @@ -61,4 +61,7 @@ av_cold void ff_opus_dsp_init(OpusDSP *ctx) if (ARCH_X86) ff_opus_dsp_init_x86(ctx); + + if (ARCH_AARCH64) + ff_opus_dsp_init_aarch64(ctx); } |