mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-09-22 14:26:52 +00:00
c62bbd4d20
checkasm benchmarks on 1.5 GHz Cortex-A72 are as follows. Note that the C version can still outperform the NEON version in specific cases. The balance between different code paths is stream-dependent, but in practice the best case happens about 5% of the time, the worst case happens about 40% of the time, and the complexity of the remaining cases fall somewhere in between. Therefore, taking the average of the best and worst case timings is probably a conservative estimate of the degree by which the NEON code improves performance. vc1dsp.vc1_h_loop_filter4_bestcase_c: 10.7 vc1dsp.vc1_h_loop_filter4_bestcase_neon: 43.5 vc1dsp.vc1_h_loop_filter4_worstcase_c: 184.5 vc1dsp.vc1_h_loop_filter4_worstcase_neon: 73.7 vc1dsp.vc1_h_loop_filter8_bestcase_c: 31.2 vc1dsp.vc1_h_loop_filter8_bestcase_neon: 62.2 vc1dsp.vc1_h_loop_filter8_worstcase_c: 358.2 vc1dsp.vc1_h_loop_filter8_worstcase_neon: 88.2 vc1dsp.vc1_h_loop_filter16_bestcase_c: 51.0 vc1dsp.vc1_h_loop_filter16_bestcase_neon: 107.7 vc1dsp.vc1_h_loop_filter16_worstcase_c: 722.7 vc1dsp.vc1_h_loop_filter16_worstcase_neon: 140.5 vc1dsp.vc1_v_loop_filter4_bestcase_c: 9.7 vc1dsp.vc1_v_loop_filter4_bestcase_neon: 43.0 vc1dsp.vc1_v_loop_filter4_worstcase_c: 178.7 vc1dsp.vc1_v_loop_filter4_worstcase_neon: 69.0 vc1dsp.vc1_v_loop_filter8_bestcase_c: 30.2 vc1dsp.vc1_v_loop_filter8_bestcase_neon: 50.7 vc1dsp.vc1_v_loop_filter8_worstcase_c: 353.0 vc1dsp.vc1_v_loop_filter8_worstcase_neon: 69.2 vc1dsp.vc1_v_loop_filter16_bestcase_c: 60.0 vc1dsp.vc1_v_loop_filter16_bestcase_neon: 90.0 vc1dsp.vc1_v_loop_filter16_worstcase_c: 714.2 vc1dsp.vc1_v_loop_filter16_worstcase_neon: 97.2 Signed-off-by: Ben Avison <bavison@riscosopen.org> Signed-off-by: Martin Storsjö <martin@martin.st>
68 lines
3.9 KiB
Makefile
68 lines
3.9 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-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_init.o
|
|
OBJS-$(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/simple_idct_neon.o
|
|
NEON-OBJS-$(CONFIG_MDCT) += aarch64/mdct_neon.o
|
|
NEON-OBJS-$(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
|