RepoMirrors/ffmpeg
1
0
Fork 0
mirror of https://git.ffmpeg.org/ffmpeg.git synced 2025-01-01 20:42:19 +00:00
Code Issues Projects Releases Wiki Activity
1f7801c2bc
ffmpeg/libavcodec/aarch64/Makefile

46 lines
2.3 KiB
Makefile
Raw Normal View History

build: miscellaneous cosmetics Restore alphabetical order in lists, break overly long lines, do some prettyprinting, add some explanatory section comments, group parts together that belong together logically.
2016-02-16 16:58:50 +00:00
# subsystems
aarch64: NEON float FFT Approximately as fast as the ARM NEON version on Apple's A7.
2014-03-26 14:20:42 +00:00
OBJS-$(CONFIG_FFT) += aarch64/fft_init_aarch64.o
arm64: int32_to_float_fmul neon asm 3% faster dts decoding on a cortex-a57. cortex-a57 cortex-a53 int32_to_float_fmul_array8_c: 1270.9 4475.6 int32_to_float_fmul_array8_neon: 328.6 569.2 int32_to_float_fmul_scalar_c: 928.5 4119.6 int32_to_float_fmul_scalar_neon: 309.1 524.1
2015-12-03 10:04:29 +00:00
OBJS-$(CONFIG_FMTCONVERT) += aarch64/fmtconvert_init.o
aarch64: h264 chroma motion compensation NEON optimizations Since RV40 and VC-1 use almost the same algorithm so optimizations for those two decoders are easy to do and included.
2013-12-10 19:16:08 +00:00
OBJS-$(CONFIG_H264CHROMA) += aarch64/h264chroma_init_aarch64.o
aarch64: h264 idct NEON assembler optimizations Ported from ARMv7 NEON.
2013-12-12 23:33:48 +00:00
OBJS-$(CONFIG_H264DSP) += aarch64/h264dsp_init_aarch64.o
h264: aarch64: intra prediction optimisations
2015-07-12 16:30:09 +00:00
OBJS-$(CONFIG_H264PRED) += aarch64/h264pred_init.o
aarch64: h264 qpel NEON optimizations Ported from ARMv7 NEON.
2013-12-18 14:56:50 +00:00
OBJS-$(CONFIG_H264QPEL) += aarch64/h264qpel_init_aarch64.o
aarch64: hpeldsp NEON optimizations Ported from ARMv7 NEON.
2013-12-20 19:03:58 +00:00
OBJS-$(CONFIG_HPELDSP) += aarch64/hpeldsp_init_aarch64.o
opus: Factor out imdct15 into a standalone component It will be reused by the AAC decoder.
2015-02-01 10:08:17 +00:00
OBJS-$(CONFIG_IMDCT15) += aarch64/imdct15_init.o
aarch64: NEON fixed/floating point MPADSP apply_window 30%/25% (fixed/float) faster mp3 decoding on Apple's A7. The floating point decoder is approximately 7% faster.
2014-04-19 16:17:23 +00:00
OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_init.o
aarch64: port neon clobber test from arm
2014-01-11 16:21:19 +00:00
OBJS-$(CONFIG_NEON_CLOBBER_TEST) += aarch64/neontest.o
aarch64: implement videodsp.prefetch 8% faster h264 decoding on Apple A7.
2014-04-05 09:47:18 +00:00
OBJS-$(CONFIG_VIDEODSP) += aarch64/videodsp_init.o
build: Group general components separate from de/encoders in arch Makefiles This is in line with how the top-level libavcodec Makefile is structured.
2013-12-20 14:28:18 +00:00
build: miscellaneous cosmetics Restore alphabetical order in lists, break overly long lines, do some prettyprinting, add some explanatory section comments, group parts together that belong together logically.
2016-02-16 16:58:50 +00:00
# decoders/encoders
aarch64/synth_filter: fix compilation Signed-off-by: James Almer <jamrial@gmail.com>
2016-05-11 02:33:12 +00:00
OBJS-$(CONFIG_DCA_DECODER) += aarch64/synth_filter_init.o
aarch64: h264 chroma motion compensation NEON optimizations Since RV40 and VC-1 use almost the same algorithm so optimizations for those two decoders are easy to do and included.
2013-12-10 19:16:08 +00:00
OBJS-$(CONFIG_RV40_DECODER) += aarch64/rv40dsp_init_aarch64.o
avcodec: fix vc1dsp dependencies
2016-09-25 10:56:55 +00:00
OBJS-$(CONFIG_VC1DSP) += aarch64/vc1dsp_init_aarch64.o
aarch64: NEON vorbis_inverse_coupling From the ARMv7 NEON version. 16 times faster as the C version, overall more than 12% faster vorbis decoding on Apple's A7.
2014-04-20 15:57:36 +00:00
OBJS-$(CONFIG_VORBIS_DECODER) += aarch64/vorbisdsp_init.o
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. This is an adapted cherry-pick from libav commit 383d96aa2229f644d9bd77b821ed3a309da5e9fc. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2016-11-14 10:32:25 +00:00
OBJS-$(CONFIG_VP9_DECODER) += aarch64/vp9dsp_init_aarch64.o
aarch64: h264 chroma motion compensation NEON optimizations Since RV40 and VC-1 use almost the same algorithm so optimizations for those two decoders are easy to do and included.
2013-12-10 19:16:08 +00:00
build: miscellaneous cosmetics Restore alphabetical order in lists, break overly long lines, do some prettyprinting, add some explanatory section comments, group parts together that belong together logically.
2016-02-16 16:58:50 +00:00
# ARMv8 optimizations
# subsystems
aarch64: implement videodsp.prefetch 8% faster h264 decoding on Apple A7.
2014-04-05 09:47:18 +00:00
ARMV8-OBJS-$(CONFIG_VIDEODSP) += aarch64/videodsp.o
build: miscellaneous cosmetics Restore alphabetical order in lists, break overly long lines, do some prettyprinting, add some explanatory section comments, group parts together that belong together logically.
2016-02-16 16:58:50 +00:00
# NEON optimizations
# subsystems
aarch64: NEON float FFT Approximately as fast as the ARM NEON version on Apple's A7.
2014-03-26 14:20:42 +00:00
NEON-OBJS-$(CONFIG_FFT) += aarch64/fft_neon.o
arm64: int32_to_float_fmul neon asm 3% faster dts decoding on a cortex-a57. cortex-a57 cortex-a53 int32_to_float_fmul_array8_c: 1270.9 4475.6 int32_to_float_fmul_array8_neon: 328.6 569.2 int32_to_float_fmul_scalar_c: 928.5 4119.6 int32_to_float_fmul_scalar_neon: 309.1 524.1
2015-12-03 10:04:29 +00:00
NEON-OBJS-$(CONFIG_FMTCONVERT) += aarch64/fmtconvert_neon.o
aarch64: h264 chroma motion compensation NEON optimizations Since RV40 and VC-1 use almost the same algorithm so optimizations for those two decoders are easy to do and included.
2013-12-10 19:16:08 +00:00
NEON-OBJS-$(CONFIG_H264CHROMA) += aarch64/h264cmc_neon.o
aarch64: h264 loop filter NEON optimizations Ported from ARMv7 NEON.
2013-12-20 20:02:43 +00:00
NEON-OBJS-$(CONFIG_H264DSP) += aarch64/h264dsp_neon.o \
aarch64/h264idct_neon.o
h264: aarch64: intra prediction optimisations
2015-07-12 16:30:09 +00:00
NEON-OBJS-$(CONFIG_H264PRED) += aarch64/h264pred_neon.o
aarch64: hpeldsp NEON optimizations Ported from ARMv7 NEON.
2013-12-20 19:03:58 +00:00
NEON-OBJS-$(CONFIG_H264QPEL) += aarch64/h264qpel_neon.o \
aarch64/hpeldsp_neon.o
NEON-OBJS-$(CONFIG_HPELDSP) += aarch64/hpeldsp_neon.o
opus: Factor out imdct15 into a standalone component It will be reused by the AAC decoder.
2015-02-01 10:08:17 +00:00
NEON-OBJS-$(CONFIG_IMDCT15) += aarch64/imdct15_neon.o
aarch64: NEON float (i)MDCT Approximately as fast as the ARM NEON version on Apple's A7.
2014-04-15 16:35:57 +00:00
NEON-OBJS-$(CONFIG_MDCT) += aarch64/mdct_neon.o
build: miscellaneous cosmetics Restore alphabetical order in lists, break overly long lines, do some prettyprinting, add some explanatory section comments, group parts together that belong together logically.
2016-02-16 16:58:50 +00:00
NEON-OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_neon.o
aarch64: NEON vorbis_inverse_coupling From the ARMv7 NEON version. 16 times faster as the C version, overall more than 12% faster vorbis decoding on Apple's A7.
2014-04-20 15:57:36 +00:00
build: miscellaneous cosmetics Restore alphabetical order in lists, break overly long lines, do some prettyprinting, add some explanatory section comments, group parts together that belong together logically.
2016-02-16 16:58:50 +00:00
# decoders/encoders
Merge commit '01621202aad7e27b2a05c71d9ad7a19dfcbe17ec' * commit '01621202aad7e27b2a05c71d9ad7a19dfcbe17ec': build: miscellaneous cosmetics Merged-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2016-05-09 14:52:05 +00:00
NEON-OBJS-$(CONFIG_DCA_DECODER) += aarch64/synth_filter_neon.o
aarch64: NEON vorbis_inverse_coupling From the ARMv7 NEON version. 16 times faster as the C version, overall more than 12% faster vorbis decoding on Apple's A7.
2014-04-20 15:57:36 +00:00
NEON-OBJS-$(CONFIG_VORBIS_DECODER) += aarch64/vorbisdsp_neon.o
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. This is an adapted cherry-pick from libav commit 383d96aa2229f644d9bd77b821ed3a309da5e9fc. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2016-11-14 10:32:25 +00:00
NEON-OBJS-$(CONFIG_VP9_DECODER) += aarch64/vp9mc_neon.o
Reference in New Issue Copy Permalink