mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-12-26 01:02:33 +00:00
4d2f62150d
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.
61 lines
3.4 KiB
Makefile
61 lines
3.4 KiB
Makefile
# subsystems
|
|
OBJS-$(CONFIG_FFT) += aarch64/fft_init_aarch64.o
|
|
OBJS-$(CONFIG_FMTCONVERT) += aarch64/fmtconvert_init.o
|
|
OBJS-$(CONFIG_H264CHROMA) += aarch64/h264chroma_init_aarch64.o
|
|
OBJS-$(CONFIG_H264DSP) += aarch64/h264dsp_init_aarch64.o
|
|
OBJS-$(CONFIG_H264PRED) += aarch64/h264pred_init.o
|
|
OBJS-$(CONFIG_H264QPEL) += aarch64/h264qpel_init_aarch64.o
|
|
OBJS-$(CONFIG_HPELDSP) += aarch64/hpeldsp_init_aarch64.o
|
|
OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_init.o
|
|
OBJS-$(CONFIG_NEON_CLOBBER_TEST) += aarch64/neontest.o
|
|
OBJS-$(CONFIG_VIDEODSP) += aarch64/videodsp_init.o
|
|
OBJS-$(CONFIG_VP8DSP) += aarch64/vp8dsp_init_aarch64.o
|
|
|
|
# decoders/encoders
|
|
OBJS-$(CONFIG_AAC_DECODER) += aarch64/aacpsdsp_init_aarch64.o \
|
|
aarch64/sbrdsp_init_aarch64.o
|
|
OBJS-$(CONFIG_DCA_DECODER) += aarch64/synth_filter_init.o
|
|
OBJS-$(CONFIG_OPUS_DECODER) += aarch64/opusdsp_init.o
|
|
OBJS-$(CONFIG_RV40_DECODER) += aarch64/rv40dsp_init_aarch64.o
|
|
OBJS-$(CONFIG_VC1DSP) += aarch64/vc1dsp_init_aarch64.o
|
|
OBJS-$(CONFIG_VORBIS_DECODER) += aarch64/vorbisdsp_init.o
|
|
OBJS-$(CONFIG_VP9_DECODER) += aarch64/vp9dsp_init_10bpp_aarch64.o \
|
|
aarch64/vp9dsp_init_12bpp_aarch64.o \
|
|
aarch64/vp9dsp_init_aarch64.o
|
|
|
|
# ARMv8 optimizations
|
|
|
|
# subsystems
|
|
ARMV8-OBJS-$(CONFIG_VIDEODSP) += aarch64/videodsp.o
|
|
|
|
# NEON optimizations
|
|
|
|
# subsystems
|
|
NEON-OBJS-$(CONFIG_AAC_DECODER) += aarch64/sbrdsp_neon.o
|
|
NEON-OBJS-$(CONFIG_FFT) += aarch64/fft_neon.o
|
|
NEON-OBJS-$(CONFIG_FMTCONVERT) += aarch64/fmtconvert_neon.o
|
|
NEON-OBJS-$(CONFIG_H264CHROMA) += aarch64/h264cmc_neon.o
|
|
NEON-OBJS-$(CONFIG_H264DSP) += aarch64/h264dsp_neon.o \
|
|
aarch64/h264idct_neon.o
|
|
NEON-OBJS-$(CONFIG_H264PRED) += aarch64/h264pred_neon.o
|
|
NEON-OBJS-$(CONFIG_H264QPEL) += aarch64/h264qpel_neon.o \
|
|
aarch64/hpeldsp_neon.o
|
|
NEON-OBJS-$(CONFIG_HPELDSP) += aarch64/hpeldsp_neon.o
|
|
NEON-OBJS-$(CONFIG_IDCTDSP) += aarch64/idctdsp_init_aarch64.o \
|
|
aarch64/simple_idct_neon.o
|
|
NEON-OBJS-$(CONFIG_MDCT) += aarch64/mdct_neon.o
|
|
NEON-OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_neon.o
|
|
NEON-OBJS-$(CONFIG_VP8DSP) += aarch64/vp8dsp_neon.o
|
|
|
|
# decoders/encoders
|
|
NEON-OBJS-$(CONFIG_AAC_DECODER) += aarch64/aacpsdsp_neon.o
|
|
NEON-OBJS-$(CONFIG_DCA_DECODER) += aarch64/synth_filter_neon.o
|
|
NEON-OBJS-$(CONFIG_OPUS_DECODER) += aarch64/opusdsp_neon.o
|
|
NEON-OBJS-$(CONFIG_VORBIS_DECODER) += aarch64/vorbisdsp_neon.o
|
|
NEON-OBJS-$(CONFIG_VP9_DECODER) += aarch64/vp9itxfm_16bpp_neon.o \
|
|
aarch64/vp9itxfm_neon.o \
|
|
aarch64/vp9lpf_16bpp_neon.o \
|
|
aarch64/vp9lpf_neon.o \
|
|
aarch64/vp9mc_16bpp_neon.o \
|
|
aarch64/vp9mc_neon.o
|