FFmpeg/libavcodec/aarch64/Makefile
Swinney, Jonathan c471cc7474 lavc/aarch64: motion estimation functions in neon
- ff_pix_abs16_neon
 - ff_pix_abs16_xy2_neon

In direct micro benchmarks of these ff functions verses their C implementations,
these functions performed as follows on AWS Graviton 3.

ff_pix_abs16_neon:
pix_abs_0_0_c: 141.1
pix_abs_0_0_neon: 19.6

ff_pix_abs16_xy2_neon:
pix_abs_0_3_c: 269.1
pix_abs_0_3_neon: 39.3

Tested with:
./tests/checkasm/checkasm --test=motion --bench --disable-linux-perf

Signed-off-by: Jonathan Swinney <jswinney@amazon.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
2022-06-28 00:51:39 +03:00

71 lines
4.1 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_IDCTDSP) += aarch64/idctdsp_init_aarch64.o
OBJS-$(CONFIG_ME_CMP) += aarch64/me_cmp_init_aarch64.o
OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_init.o
OBJS-$(CONFIG_NEON_CLOBBER_TEST) += aarch64/neontest.o
OBJS-$(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_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_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-$(CONFIG_IDCTDSP) += aarch64/idctdsp_neon.o \
aarch64/simple_idct_neon.o
NEON-OBJS-$(CONFIG_MDCT) += aarch64/mdct_neon.o
NEON-OBJS-$(CONFIG_ME_CMP) += aarch64/me_cmp_neon.o
NEON-OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_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_idct_neon.o \
aarch64/hevcdsp_init_aarch64.o \
aarch64/hevcdsp_sao_neon.o