diff options
| author | Lynne <dev@lynne.ee> | 2019-03-15 14:43:04 +0000 |
|---|---|---|
| committer | Carl Eugen Hoyos <ceffmpeg@gmail.com> | 2019-04-01 00:22:00 +0200 |
| commit | 605e3303109e7945a841c5fb5ff60881393933a3 (patch) | |
| tree | a29fd08a08cb983a73bb937538b1b4c1add6dafb /libavcodec/opusdsp.h | |
| parent | 0cea3ca8943b5a3f28a3672037f424b4d03853b8 (diff) | |
x86/opusdsp: implement FMA3 accelerated postfilter and deemphasis
58893 decicycles in deemphasis_c, 130548 runs, 524 skips
9475 decicycles in deemphasis_fma3, 130686 runs, 386 skips -> 6.21x speedup
24866 decicycles in postfilter_c, 65386 runs, 150 skips
5268 decicycles in postfilter_fma3, 65505 runs, 31 skips -> 4.72x speedup
Total decoder speedup: ~14%
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;
}
Diffstat (limited to 'libavcodec/opusdsp.h')
| -rw-r--r-- | libavcodec/opusdsp.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/libavcodec/opusdsp.h b/libavcodec/opusdsp.h index 05bf2ba1a4..e3eb457f1b 100644 --- a/libavcodec/opusdsp.h +++ b/libavcodec/opusdsp.h @@ -30,4 +30,6 @@ typedef struct OpusDSP { void ff_opus_dsp_init(OpusDSP *ctx); +void ff_opus_dsp_init_x86(OpusDSP *ctx); + #endif /* AVCODEC_OPUSDSP_H */ |