1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-23 12:43:46 +02:00
FFmpeg/libavcodec/aarch64/Makefile

67 lines
3.8 KiB
Makefile
Raw Normal View History

# 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-$(CONFIG_RV40_DECODER) += aarch64/rv40dsp_init_aarch64.o
2016-09-25 12:56:55 +02:00
OBJS-$(CONFIG_VC1DSP) += aarch64/vc1dsp_init_aarch64.o
OBJS-$(CONFIG_VORBIS_DECODER) += aarch64/vorbisdsp_init.o
aarch64: Add NEON optimizations for 10 and 12 bit vp9 MC This work is sponsored by, and copyright, Google. This has mostly got the same differences to the 8 bit version as in the arm version. For the horizontal filters, we do 16 pixels in parallel as well. For the 8 pixel wide vertical filters, we can accumulate 4 rows before storing, just as in the 8 bit version. Examples of runtimes vs the 32 bit version, on a Cortex A53: ARM AArch64 vp9_avg4_10bpp_neon: 35.7 30.7 vp9_avg8_10bpp_neon: 93.5 84.7 vp9_avg16_10bpp_neon: 324.4 296.6 vp9_avg32_10bpp_neon: 1236.5 1148.2 vp9_avg64_10bpp_neon: 4639.6 4571.1 vp9_avg_8tap_smooth_4h_10bpp_neon: 130.0 128.0 vp9_avg_8tap_smooth_4hv_10bpp_neon: 440.0 440.5 vp9_avg_8tap_smooth_4v_10bpp_neon: 114.0 105.5 vp9_avg_8tap_smooth_8h_10bpp_neon: 327.0 314.0 vp9_avg_8tap_smooth_8hv_10bpp_neon: 918.7 865.4 vp9_avg_8tap_smooth_8v_10bpp_neon: 330.0 300.2 vp9_avg_8tap_smooth_16h_10bpp_neon: 1187.5 1155.5 vp9_avg_8tap_smooth_16hv_10bpp_neon: 2663.1 2591.0 vp9_avg_8tap_smooth_16v_10bpp_neon: 1107.4 1078.3 vp9_avg_8tap_smooth_64h_10bpp_neon: 17754.6 17454.7 vp9_avg_8tap_smooth_64hv_10bpp_neon: 33285.2 33001.5 vp9_avg_8tap_smooth_64v_10bpp_neon: 16066.9 16048.6 vp9_put4_10bpp_neon: 25.5 21.7 vp9_put8_10bpp_neon: 56.0 52.0 vp9_put16_10bpp_neon/armv8: 183.0 163.1 vp9_put32_10bpp_neon/armv8: 678.6 563.1 vp9_put64_10bpp_neon/armv8: 2679.9 2195.8 vp9_put_8tap_smooth_4h_10bpp_neon: 120.0 118.0 vp9_put_8tap_smooth_4hv_10bpp_neon: 435.2 435.0 vp9_put_8tap_smooth_4v_10bpp_neon: 107.0 98.2 vp9_put_8tap_smooth_8h_10bpp_neon: 303.0 290.0 vp9_put_8tap_smooth_8hv_10bpp_neon: 893.7 828.7 vp9_put_8tap_smooth_8v_10bpp_neon: 305.5 263.5 vp9_put_8tap_smooth_16h_10bpp_neon: 1089.1 1059.2 vp9_put_8tap_smooth_16hv_10bpp_neon: 2578.8 2452.4 vp9_put_8tap_smooth_16v_10bpp_neon: 1009.5 933.5 vp9_put_8tap_smooth_64h_10bpp_neon: 16223.4 15918.6 vp9_put_8tap_smooth_64hv_10bpp_neon: 32153.0 31016.2 vp9_put_8tap_smooth_64v_10bpp_neon: 14516.5 13748.1 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 around 4-9x. Signed-off-by: Martin Storsjö <martin@martin.st>
2016-12-14 23:48:35 +02:00
OBJS-$(CONFIG_VP9_DECODER) += aarch64/vp9dsp_init_10bpp_aarch64.o \
aarch64/vp9dsp_init_12bpp_aarch64.o \
aarch64/vp9mc_aarch64.o \
aarch64: Add NEON optimizations for 10 and 12 bit vp9 MC This work is sponsored by, and copyright, Google. This has mostly got the same differences to the 8 bit version as in the arm version. For the horizontal filters, we do 16 pixels in parallel as well. For the 8 pixel wide vertical filters, we can accumulate 4 rows before storing, just as in the 8 bit version. Examples of runtimes vs the 32 bit version, on a Cortex A53: ARM AArch64 vp9_avg4_10bpp_neon: 35.7 30.7 vp9_avg8_10bpp_neon: 93.5 84.7 vp9_avg16_10bpp_neon: 324.4 296.6 vp9_avg32_10bpp_neon: 1236.5 1148.2 vp9_avg64_10bpp_neon: 4639.6 4571.1 vp9_avg_8tap_smooth_4h_10bpp_neon: 130.0 128.0 vp9_avg_8tap_smooth_4hv_10bpp_neon: 440.0 440.5 vp9_avg_8tap_smooth_4v_10bpp_neon: 114.0 105.5 vp9_avg_8tap_smooth_8h_10bpp_neon: 327.0 314.0 vp9_avg_8tap_smooth_8hv_10bpp_neon: 918.7 865.4 vp9_avg_8tap_smooth_8v_10bpp_neon: 330.0 300.2 vp9_avg_8tap_smooth_16h_10bpp_neon: 1187.5 1155.5 vp9_avg_8tap_smooth_16hv_10bpp_neon: 2663.1 2591.0 vp9_avg_8tap_smooth_16v_10bpp_neon: 1107.4 1078.3 vp9_avg_8tap_smooth_64h_10bpp_neon: 17754.6 17454.7 vp9_avg_8tap_smooth_64hv_10bpp_neon: 33285.2 33001.5 vp9_avg_8tap_smooth_64v_10bpp_neon: 16066.9 16048.6 vp9_put4_10bpp_neon: 25.5 21.7 vp9_put8_10bpp_neon: 56.0 52.0 vp9_put16_10bpp_neon/armv8: 183.0 163.1 vp9_put32_10bpp_neon/armv8: 678.6 563.1 vp9_put64_10bpp_neon/armv8: 2679.9 2195.8 vp9_put_8tap_smooth_4h_10bpp_neon: 120.0 118.0 vp9_put_8tap_smooth_4hv_10bpp_neon: 435.2 435.0 vp9_put_8tap_smooth_4v_10bpp_neon: 107.0 98.2 vp9_put_8tap_smooth_8h_10bpp_neon: 303.0 290.0 vp9_put_8tap_smooth_8hv_10bpp_neon: 893.7 828.7 vp9_put_8tap_smooth_8v_10bpp_neon: 305.5 263.5 vp9_put_8tap_smooth_16h_10bpp_neon: 1089.1 1059.2 vp9_put_8tap_smooth_16hv_10bpp_neon: 2578.8 2452.4 vp9_put_8tap_smooth_16v_10bpp_neon: 1009.5 933.5 vp9_put_8tap_smooth_64h_10bpp_neon: 16223.4 15918.6 vp9_put_8tap_smooth_64hv_10bpp_neon: 32153.0 31016.2 vp9_put_8tap_smooth_64v_10bpp_neon: 14516.5 13748.1 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 around 4-9x. Signed-off-by: Martin Storsjö <martin@martin.st>
2016-12-14 23:48:35 +02:00
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_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
2017-01-03 14:35:54 +02:00
NEON-OBJS-$(CONFIG_VP9_DECODER) += aarch64/vp9itxfm_16bpp_neon.o \
aarch64/vp9itxfm_neon.o \
aarch64/vp9lpf_16bpp_neon.o \
aarch64: vp9: Implement NEON loop filters This work is sponsored by, and copyright, Google. These are ported from the ARM version; thanks to the larger amount of registers available, we can do the loop filters with 16 pixels at a time. The implementation is fully templated, with a single macro which can generate versions for both 8 and 16 pixels wide, for both 4, 8 and 16 pixels loop filters (and the 4/8 mixed versions as well). For the 8 pixel wide versions, it is pretty close in speed (the v_4_8 and v_8_8 filters are the best examples of this; the h_4_8 and h_8_8 filters seem to get some gain in the load/transpose/store part). For the 16 pixels wide ones, we get a speedup of around 1.2-1.4x compared to the 32 bit version. Examples of runtimes vs the 32 bit version, on a Cortex A53: ARM AArch64 vp9_loop_filter_h_4_8_neon: 144.0 127.2 vp9_loop_filter_h_8_8_neon: 207.0 182.5 vp9_loop_filter_h_16_8_neon: 415.0 328.7 vp9_loop_filter_h_16_16_neon: 672.0 558.6 vp9_loop_filter_mix2_h_44_16_neon: 302.0 203.5 vp9_loop_filter_mix2_h_48_16_neon: 365.0 305.2 vp9_loop_filter_mix2_h_84_16_neon: 365.0 305.2 vp9_loop_filter_mix2_h_88_16_neon: 376.0 305.2 vp9_loop_filter_mix2_v_44_16_neon: 193.2 128.2 vp9_loop_filter_mix2_v_48_16_neon: 246.7 218.4 vp9_loop_filter_mix2_v_84_16_neon: 248.0 218.5 vp9_loop_filter_mix2_v_88_16_neon: 302.0 218.2 vp9_loop_filter_v_4_8_neon: 89.0 88.7 vp9_loop_filter_v_8_8_neon: 141.0 137.7 vp9_loop_filter_v_16_8_neon: 295.0 272.7 vp9_loop_filter_v_16_16_neon: 546.0 453.7 The speedup vs C code in checkasm tests is around 2-7x, which is pretty much the same as for the 32 bit version. Even if these functions are faster than their 32 bit equivalent, the C version that we compare to also became around 1.3-1.7x faster than the C version in 32 bit. Based on START_TIMER/STOP_TIMER wrapping around a few individual functions, the speedup vs C code is around 4-5x. Examples of runtimes vs C on a Cortex A57 (for a slightly older version of the patch): A57 gcc-5.3 neon loop_filter_h_4_8_neon: 256.6 93.4 loop_filter_h_8_8_neon: 307.3 139.1 loop_filter_h_16_8_neon: 340.1 254.1 loop_filter_h_16_16_neon: 827.0 407.9 loop_filter_mix2_h_44_16_neon: 524.5 155.4 loop_filter_mix2_h_48_16_neon: 644.5 173.3 loop_filter_mix2_h_84_16_neon: 630.5 222.0 loop_filter_mix2_h_88_16_neon: 697.3 222.0 loop_filter_mix2_v_44_16_neon: 598.5 100.6 loop_filter_mix2_v_48_16_neon: 651.5 127.0 loop_filter_mix2_v_84_16_neon: 591.5 167.1 loop_filter_mix2_v_88_16_neon: 855.1 166.7 loop_filter_v_4_8_neon: 271.7 65.3 loop_filter_v_8_8_neon: 312.5 106.9 loop_filter_v_16_8_neon: 473.3 206.5 loop_filter_v_16_16_neon: 976.1 327.8 The speed-up compared to the C functions is 2.5 to 6 and the cortex-a57 is again 30-50% faster than the cortex-a53. This is an adapted cherry-pick from libav commits 9d2afd1eb8c5cc0633062430e66326dbf98c99e0 and 31756abe29eb039a11c59a42cb12e0cc2aef3b97. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2016-11-14 12:32:27 +02:00
aarch64/vp9lpf_neon.o \
aarch64: Add NEON optimizations for 10 and 12 bit vp9 MC This work is sponsored by, and copyright, Google. This has mostly got the same differences to the 8 bit version as in the arm version. For the horizontal filters, we do 16 pixels in parallel as well. For the 8 pixel wide vertical filters, we can accumulate 4 rows before storing, just as in the 8 bit version. Examples of runtimes vs the 32 bit version, on a Cortex A53: ARM AArch64 vp9_avg4_10bpp_neon: 35.7 30.7 vp9_avg8_10bpp_neon: 93.5 84.7 vp9_avg16_10bpp_neon: 324.4 296.6 vp9_avg32_10bpp_neon: 1236.5 1148.2 vp9_avg64_10bpp_neon: 4639.6 4571.1 vp9_avg_8tap_smooth_4h_10bpp_neon: 130.0 128.0 vp9_avg_8tap_smooth_4hv_10bpp_neon: 440.0 440.5 vp9_avg_8tap_smooth_4v_10bpp_neon: 114.0 105.5 vp9_avg_8tap_smooth_8h_10bpp_neon: 327.0 314.0 vp9_avg_8tap_smooth_8hv_10bpp_neon: 918.7 865.4 vp9_avg_8tap_smooth_8v_10bpp_neon: 330.0 300.2 vp9_avg_8tap_smooth_16h_10bpp_neon: 1187.5 1155.5 vp9_avg_8tap_smooth_16hv_10bpp_neon: 2663.1 2591.0 vp9_avg_8tap_smooth_16v_10bpp_neon: 1107.4 1078.3 vp9_avg_8tap_smooth_64h_10bpp_neon: 17754.6 17454.7 vp9_avg_8tap_smooth_64hv_10bpp_neon: 33285.2 33001.5 vp9_avg_8tap_smooth_64v_10bpp_neon: 16066.9 16048.6 vp9_put4_10bpp_neon: 25.5 21.7 vp9_put8_10bpp_neon: 56.0 52.0 vp9_put16_10bpp_neon/armv8: 183.0 163.1 vp9_put32_10bpp_neon/armv8: 678.6 563.1 vp9_put64_10bpp_neon/armv8: 2679.9 2195.8 vp9_put_8tap_smooth_4h_10bpp_neon: 120.0 118.0 vp9_put_8tap_smooth_4hv_10bpp_neon: 435.2 435.0 vp9_put_8tap_smooth_4v_10bpp_neon: 107.0 98.2 vp9_put_8tap_smooth_8h_10bpp_neon: 303.0 290.0 vp9_put_8tap_smooth_8hv_10bpp_neon: 893.7 828.7 vp9_put_8tap_smooth_8v_10bpp_neon: 305.5 263.5 vp9_put_8tap_smooth_16h_10bpp_neon: 1089.1 1059.2 vp9_put_8tap_smooth_16hv_10bpp_neon: 2578.8 2452.4 vp9_put_8tap_smooth_16v_10bpp_neon: 1009.5 933.5 vp9_put_8tap_smooth_64h_10bpp_neon: 16223.4 15918.6 vp9_put_8tap_smooth_64hv_10bpp_neon: 32153.0 31016.2 vp9_put_8tap_smooth_64v_10bpp_neon: 14516.5 13748.1 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 around 4-9x. Signed-off-by: Martin Storsjö <martin@martin.st>
2016-12-14 23:48:35 +02:00
aarch64/vp9mc_16bpp_neon.o \
aarch64: vp9: Add NEON itxfm routines This work is sponsored by, and copyright, Google. These are ported from the ARM version; thanks to the larger amount of registers available, we can do the 16x16 and 32x32 transforms in slices 8 pixels wide instead of 4. This gives a speedup of around 1.4x compared to the 32 bit version. The fact that aarch64 doesn't have the same d/q register aliasing makes some of the macros quite a bit simpler as well. Examples of runtimes vs the 32 bit version, on a Cortex A53: ARM AArch64 vp9_inv_adst_adst_4x4_add_neon: 90.0 87.7 vp9_inv_adst_adst_8x8_add_neon: 400.0 354.7 vp9_inv_adst_adst_16x16_add_neon: 2526.5 1827.2 vp9_inv_dct_dct_4x4_add_neon: 74.0 72.7 vp9_inv_dct_dct_8x8_add_neon: 271.0 256.7 vp9_inv_dct_dct_16x16_add_neon: 1960.7 1372.7 vp9_inv_dct_dct_32x32_add_neon: 11988.9 8088.3 vp9_inv_wht_wht_4x4_add_neon: 63.0 57.7 The speedup vs C code (2-4x) is smaller than in the 32 bit case, mostly because the C code ends up significantly faster (around 1.6x faster, with GCC 5.4) when built for aarch64. Examples of runtimes vs C on a Cortex A57 (for a slightly older version of the patch): A57 gcc-5.3 neon vp9_inv_adst_adst_4x4_add_neon: 152.2 60.0 vp9_inv_adst_adst_8x8_add_neon: 948.2 288.0 vp9_inv_adst_adst_16x16_add_neon: 4830.4 1380.5 vp9_inv_dct_dct_4x4_add_neon: 153.0 58.6 vp9_inv_dct_dct_8x8_add_neon: 789.2 180.2 vp9_inv_dct_dct_16x16_add_neon: 3639.6 917.1 vp9_inv_dct_dct_32x32_add_neon: 20462.1 4985.0 vp9_inv_wht_wht_4x4_add_neon: 91.0 49.8 The asm is around factor 3-4 faster than C on the cortex-a57 and the asm is around 30-50% faster on the a57 compared to the a53. This is an adapted cherry-pick from libav commit 3c9546dfafcdfe8e7860aff9ebbf609318220f29. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2016-11-14 12:32:26 +02:00
aarch64/vp9mc_neon.o
NEON-OBJS-$(CONFIG_HEVC_DECODER) += aarch64/hevcdsp_idct_neon.o \
aarch64/hevcdsp_init_aarch64.o \
aarch64/hevcdsp_sao_neon.o