Files
ffmpeg/libavcodec/aarch64/Makefile
Krzysztof Pyrkosz 83e4b068d9 avcodec/aarch64/aacencdsp: NEON implementation
This patch supplies handwritten NEON code for AAC.

The benchmarks below were collected by invoking these two commands on
each of my boards, A78, A72 and Thinkpad x13s:
1) ./tests/checkasm/checkasm --test=aacencdsp --bench --runs=12
2) ./ffmpeg -y -t 10:00 -f lavfi -i sine /tmp/foo.aac (the first line is
speed without the patch, second, with)

- A78
abs_pow34_c:                                          4161.5 ( 1.00x)
abs_pow34_neon:                                       3586.2 ( 1.16x)
quant_bands_signed_c:                                 5548.0 ( 1.00x)
quant_bands_signed_neon:                              1126.8 ( 4.92x)
quant_bands_unsigned_c:                               3979.2 ( 1.00x)
quant_bands_unsigned_neon:                             800.2 ( 4.97x)

size=    5251KiB time=00:10:00.00 bitrate=  71.7kbits/s speed=71.6x
size=    5251KiB time=00:10:00.00 bitrate=  71.7kbits/s speed=82.3x

- A72
abs_pow34_c:                                         15362.2 ( 1.00x)
abs_pow34_neon:                                      15382.5 ( 1.00x)
quant_bands_signed_c:                                 9926.5 ( 1.00x)
quant_bands_signed_neon:                              2467.8 ( 4.02x)
quant_bands_unsigned_c:                               5469.8 ( 1.00x)
quant_bands_unsigned_neon:                            2089.5 ( 2.62x)

size=    5251KiB time=00:10:00.00 bitrate=  71.7kbits/s speed=34.3x
size=    5251KiB time=00:10:00.00 bitrate=  71.7kbits/s speed=37.8

- x13s
abs_pow34_c:                                          2413.4 ( 1.00x)
abs_pow34_neon:                                       1796.2 ( 1.34x)
quant_bands_signed_c:                                 2968.9 ( 1.00x)
quant_bands_signed_neon:                               675.6 ( 4.39x)
quant_bands_unsigned_c:                               2311.9 ( 1.00x)
quant_bands_unsigned_neon:                             477.1 ( 4.85x)

size=    5251KiB time=00:10:00.00 bitrate=  71.7kbits/s speed= 135x
size=    5251KiB time=00:10:00.00 bitrate=  71.7kbits/s speed= 159x

Signed-off-by: Martin Storsjö <martin@martin.st>
2025-01-28 10:44:40 +02:00

79 lines
4.7 KiB
Makefile

# subsystems
OBJS-$(CONFIG_AC3DSP) += aarch64/ac3dsp_init_aarch64.o
OBJS-$(CONFIG_FDCTDSP) += aarch64/fdctdsp_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-$(CONFIG_IDCTDSP) += aarch64/idctdsp_init_aarch64.o
OBJS-$(CONFIG_ME_CMP) += aarch64/me_cmp_init_aarch64.o
OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_init.o
OBJS-$(CONFIG_MPEGVIDEOENC) += aarch64/mpegvideoencdsp_init.o
OBJS-$(CONFIG_NEON_CLOBBER_TEST) += aarch64/neontest.o
OBJS-$(CONFIG_PIXBLOCKDSP) += aarch64/pixblockdsp_init_aarch64.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_AAC_ENCODER) += aarch64/aacencdsp_init.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/vp9mc_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-$(CONFIG_AAC_ENCODER) += aarch64/aacencdsp_neon.o
NEON-OBJS-$(CONFIG_AC3DSP) += aarch64/ac3dsp_neon.o
NEON-OBJS-$(CONFIG_FDCTDSP) += aarch64/fdctdsp_neon.o
NEON-OBJS-$(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_neon.o \
aarch64/simple_idct_neon.o
NEON-OBJS-$(CONFIG_ME_CMP) += aarch64/me_cmp_neon.o
NEON-OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_neon.o
NEON-OBJS-$(CONFIG_MPEGVIDEOENC) += aarch64/mpegvideoencdsp_neon.o
NEON-OBJS-$(CONFIG_PIXBLOCKDSP) += aarch64/pixblockdsp_neon.o
NEON-OBJS-$(CONFIG_VC1DSP) += aarch64/vc1dsp_neon.o
NEON-OBJS-$(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-$(CONFIG_VP9_DECODER) += aarch64/vp9itxfm_16bpp_neon.o \
aarch64/vp9itxfm_neon.o \
aarch64/vp9lpf_16bpp_neon.o \
aarch64/vp9lpf_neon.o \
aarch64/vp9mc_16bpp_neon.o \
aarch64/vp9mc_neon.o
NEON-OBJS-$(CONFIG_HEVC_DECODER) += aarch64/hevcdsp_deblock_neon.o \
aarch64/hevcdsp_idct_neon.o \
aarch64/hevcdsp_init_aarch64.o \
aarch64/h26x/epel_neon.o \
aarch64/h26x/qpel_neon.o \
aarch64/h26x/sao_neon.o