1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-12 19:18:44 +02:00
FFmpeg/libavcodec/aarch64/Makefile
Martin Storsjö 383d96aa22 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>
2016-11-10 11:15:56 +02:00

48 lines
2.4 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_IMDCT15) += aarch64/imdct15_init.o
OBJS-$(CONFIG_MDCT) += aarch64/mdct_init.o
OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_init.o
OBJS-$(CONFIG_NEON_CLOBBER_TEST) += aarch64/neontest.o
OBJS-$(CONFIG_VIDEODSP) += aarch64/videodsp_init.o
# decoders/encoders
OBJS-$(CONFIG_DCA_DECODER) += aarch64/dcadsp_init.o
OBJS-$(CONFIG_RV40_DECODER) += aarch64/rv40dsp_init_aarch64.o
OBJS-$(CONFIG_VC1_DECODER) += aarch64/vc1dsp_init_aarch64.o
OBJS-$(CONFIG_VORBIS_DECODER) += aarch64/vorbisdsp_init.o
OBJS-$(CONFIG_VP9_DECODER) += aarch64/vp9dsp_init_aarch64.o
# ARMv8 optimizations
# subsystems
ARMV8-OBJS-$(CONFIG_VIDEODSP) += aarch64/videodsp.o
# NEON optimizations
# subsystems
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_IMDCT15) += aarch64/imdct15_neon.o
NEON-OBJS-$(CONFIG_MDCT) += aarch64/mdct_neon.o
NEON-OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_neon.o
# decoders/encoders
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/vp9mc_neon.o