|
|
|
|
ARCH_HEADERS = mathops.h
|
|
|
|
|
|
|
|
|
|
# subsystems
|
|
|
|
|
OBJS-$(CONFIG_AC3DSP) += arm/ac3dsp_init_arm.o \
|
|
|
|
|
arm/ac3dsp_arm.o
|
|
|
|
|
OBJS-$(CONFIG_AUDIODSP) += arm/audiodsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_BLOCKDSP) += arm/blockdsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_FFT) += arm/fft_init_arm.o \
|
|
|
|
|
arm/fft_fixed_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_FLACDSP) += arm/flacdsp_init_arm.o \
|
|
|
|
|
arm/flacdsp_arm.o
|
|
|
|
|
OBJS-$(CONFIG_FMTCONVERT) += arm/fmtconvert_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_G722DSP) += arm/g722dsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_H264CHROMA) += arm/h264chroma_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_H264DSP) += arm/h264dsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_H264PRED) += arm/h264pred_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_H264QPEL) += arm/h264qpel_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_HPELDSP) += arm/hpeldsp_init_arm.o \
|
|
|
|
|
arm/hpeldsp_arm.o
|
|
|
|
|
OBJS-$(CONFIG_IDCTDSP) += arm/idctdsp_init_arm.o \
|
|
|
|
|
arm/idctdsp_arm.o \
|
|
|
|
|
arm/jrevdct_arm.o \
|
|
|
|
|
arm/simple_idct_arm.o
|
|
|
|
|
OBJS-$(CONFIG_LLAUDDSP) += arm/lossless_audiodsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_ME_CMP) += arm/me_cmp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_MPEGAUDIODSP) += arm/mpegaudiodsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_MPEGVIDEO) += arm/mpegvideo_arm.o
|
|
|
|
|
OBJS-$(CONFIG_MPEGVIDEOENC) += arm/mpegvideoencdsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_NEON_CLOBBER_TEST) += arm/neontest.o
|
|
|
|
|
OBJS-$(CONFIG_PIXBLOCKDSP) += arm/pixblockdsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_RDFT) += arm/rdft_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_RV34DSP) += arm/rv34dsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_VC1DSP) += arm/vc1dsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_VIDEODSP) += arm/videodsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_VP3DSP) += arm/vp3dsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_VP8DSP) += arm/vp8dsp_init_arm.o
|
|
|
|
|
|
|
|
|
|
# decoders/encoders
|
|
|
|
|
OBJS-$(CONFIG_AAC_DECODER) += arm/aacpsdsp_init_arm.o \
|
|
|
|
|
arm/sbrdsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_DCA_DECODER) += arm/synth_filter_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_HEVC_DECODER) += arm/hevcdsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_MLP_DECODER) += arm/mlpdsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_RV40_DECODER) += arm/rv40dsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_SBC_ENCODER) += arm/sbcdsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_VORBIS_DECODER) += arm/vorbisdsp_init_arm.o
|
|
|
|
|
OBJS-$(CONFIG_VP6_DECODER) += arm/vp6dsp_init_arm.o
|
arm: Add NEON optimizations for 10 and 12 bit vp9 MC
This work is sponsored by, and copyright, Google.
The plain pixel put/copy functions are used from the 8 bit version,
for the double size (e.g. put16 uses ff_vp9_copy32_neon), and a new
copy128 is added.
Compared with the 8 bit version, the filters can no longer use the
trick to accumulate in 16 bit with only saturation at the end, but now
the accumulators need to be 32 bit. This avoids the need to keep track
of which filter index is the largest though, reducing the size of the
executable code for these filters.
For the horizontal filters, we only do 4 or 8 pixels wide in parallel
(while doing two rows at a time), since we don't have enough register
space to filter 16 pixels wide.
For the vertical filters, we still do 4 and 8 pixels in parallel just
as in the 8 bit case, but we need to store the output after every 2
rows instead of after every 4 rows.
Examples of relative speedup compared to the C version, from checkasm:
Cortex A7 A8 A9 A53
vp9_avg4_10bpp_neon: 2.25 2.44 3.05 2.16
vp9_avg8_10bpp_neon: 3.66 8.48 3.86 3.50
vp9_avg16_10bpp_neon: 3.39 8.26 3.37 2.72
vp9_avg32_10bpp_neon: 4.03 10.20 4.07 3.42
vp9_avg64_10bpp_neon: 4.15 10.01 4.13 3.70
vp9_avg_8tap_smooth_4h_10bpp_neon: 3.38 6.22 3.41 4.75
vp9_avg_8tap_smooth_4hv_10bpp_neon: 3.89 6.39 4.30 5.32
vp9_avg_8tap_smooth_4v_10bpp_neon: 5.32 9.73 6.34 7.31
vp9_avg_8tap_smooth_8h_10bpp_neon: 4.45 9.40 4.68 6.87
vp9_avg_8tap_smooth_8hv_10bpp_neon: 4.64 8.91 5.44 6.47
vp9_avg_8tap_smooth_8v_10bpp_neon: 6.44 13.42 8.68 8.79
vp9_avg_8tap_smooth_64h_10bpp_neon: 4.66 9.02 4.84 7.71
vp9_avg_8tap_smooth_64hv_10bpp_neon: 4.61 9.14 4.92 7.10
vp9_avg_8tap_smooth_64v_10bpp_neon: 6.90 14.13 9.57 10.41
vp9_put4_10bpp_neon: 1.33 1.46 2.09 1.33
vp9_put8_10bpp_neon: 1.57 3.42 1.83 1.84
vp9_put16_10bpp_neon: 1.55 4.78 2.17 1.89
vp9_put32_10bpp_neon: 2.06 5.35 2.14 2.30
vp9_put64_10bpp_neon: 3.00 2.41 1.95 1.66
vp9_put_8tap_smooth_4h_10bpp_neon: 3.19 5.81 3.31 4.63
vp9_put_8tap_smooth_4hv_10bpp_neon: 3.86 6.22 4.32 5.21
vp9_put_8tap_smooth_4v_10bpp_neon: 5.40 9.77 6.08 7.21
vp9_put_8tap_smooth_8h_10bpp_neon: 4.22 8.41 4.46 6.63
vp9_put_8tap_smooth_8hv_10bpp_neon: 4.56 8.51 5.39 6.25
vp9_put_8tap_smooth_8v_10bpp_neon: 6.60 12.43 8.17 8.89
vp9_put_8tap_smooth_64h_10bpp_neon: 4.41 8.59 4.54 7.49
vp9_put_8tap_smooth_64hv_10bpp_neon: 4.43 8.58 5.34 6.63
vp9_put_8tap_smooth_64v_10bpp_neon: 7.26 13.92 9.27 10.92
For the larger 8tap filters, the speedup vs C code is around 4-14x.
Signed-off-by: Martin Storsjö <martin@martin.st>
8 years ago
|
|
|
OBJS-$(CONFIG_VP9_DECODER) += arm/vp9dsp_init_10bpp_arm.o \
|
|
|
|
|
arm/vp9dsp_init_12bpp_arm.o \
|
|
|
|
|
arm/vp9dsp_init_arm.o
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ARMv5 optimizations
|
|
|
|
|
# subsystems
|
|
|
|
|
ARMV5TE-OBJS-$(CONFIG_IDCTDSP) += arm/idctdsp_init_armv5te.o \
|
|
|
|
|
arm/simple_idct_armv5te.o
|
|
|
|
|
ARMV5TE-OBJS-$(CONFIG_MPEGVIDEO) += arm/mpegvideo_armv5te.o \
|
|
|
|
|
arm/mpegvideo_armv5te_s.o
|
|
|
|
|
ARMV5TE-OBJS-$(CONFIG_VIDEODSP) += arm/videodsp_init_armv5te.o \
|
|
|
|
|
arm/videodsp_armv5te.o
|
|
|
|
|
|
|
|
|
|
# decoders/encoders
|
|
|
|
|
ARMV5TE-OBJS-$(CONFIG_MLP_DECODER) += arm/mlpdsp_armv5te.o
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ARMv6 optimizations
|
|
|
|
|
# subsystems
|
|
|
|
|
ARMV6-OBJS-$(CONFIG_AC3DSP) += arm/ac3dsp_armv6.o
|
|
|
|
|
ARMV6-OBJS-$(CONFIG_HPELDSP) += arm/hpeldsp_init_armv6.o \
|
|
|
|
|
arm/hpeldsp_armv6.o
|
|
|
|
|
ARMV6-OBJS-$(CONFIG_IDCTDSP) += arm/idctdsp_init_armv6.o \
|
|
|
|
|
arm/idctdsp_armv6.o \
|
|
|
|
|
arm/simple_idct_armv6.o
|
|
|
|
|
ARMV6-OBJS-$(CONFIG_ME_CMP) += arm/me_cmp_armv6.o
|
|
|
|
|
ARMV6-OBJS-$(CONFIG_MPEGAUDIODSP) += arm/mpegaudiodsp_fixed_armv6.o
|
|
|
|
|
ARMV6-OBJS-$(CONFIG_MPEGVIDEOENC) += arm/mpegvideoencdsp_armv6.o
|
|
|
|
|
ARMV6-OBJS-$(CONFIG_PIXBLOCKDSP) += arm/pixblockdsp_armv6.o
|
|
|
|
|
ARMV6-OBJS-$(CONFIG_STARTCODE) += arm/startcode_armv6.o
|
|
|
|
|
ARMV6-OBJS-$(CONFIG_VP8DSP) += arm/vp8_armv6.o \
|
|
|
|
|
arm/vp8dsp_init_armv6.o \
|
|
|
|
|
arm/vp8dsp_armv6.o
|
|
|
|
|
|
|
|
|
|
# decoders/encoders
|
|
|
|
|
ARMV6-OBJS-$(CONFIG_MLP_DECODER) += arm/mlpdsp_armv6.o
|
|
|
|
|
ARMV6-OBJS-$(CONFIG_SBC_ENCODER) += arm/sbcdsp_armv6.o
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# VFP optimizations
|
|
|
|
|
|
|
|
|
|
# subsystems
|
|
|
|
|
VFP-OBJS-$(CONFIG_FFT) += arm/fft_vfp.o
|
|
|
|
|
VFP-OBJS-$(CONFIG_FMTCONVERT) += arm/fmtconvert_vfp.o
|
|
|
|
|
VFP-OBJS-$(CONFIG_MDCT) += arm/mdct_vfp.o
|
|
|
|
|
|
|
|
|
|
# decoders/encoders
|
|
|
|
|
VFP-OBJS-$(CONFIG_DCA_DECODER) += arm/synth_filter_vfp.o
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# NEON optimizations
|
|
|
|
|
|
|
|
|
|
# subsystems
|
|
|
|
|
NEON-OBJS-$(CONFIG_AC3DSP) += arm/ac3dsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_AUDIODSP) += arm/audiodsp_init_neon.o \
|
|
|
|
|
arm/audiodsp_neon.o \
|
|
|
|
|
arm/int_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_BLOCKDSP) += arm/blockdsp_init_neon.o \
|
|
|
|
|
arm/blockdsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_FFT) += arm/fft_neon.o \
|
|
|
|
|
arm/fft_fixed_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_FMTCONVERT) += arm/fmtconvert_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_G722DSP) += arm/g722dsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_H264CHROMA) += arm/h264cmc_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_H264DSP) += arm/h264dsp_neon.o \
|
|
|
|
|
arm/h264idct_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_H264PRED) += arm/h264pred_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_H264QPEL) += arm/h264qpel_neon.o \
|
|
|
|
|
arm/hpeldsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_HPELDSP) += arm/hpeldsp_init_neon.o \
|
|
|
|
|
arm/hpeldsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_IDCTDSP) += arm/idctdsp_init_neon.o \
|
|
|
|
|
arm/idctdsp_neon.o \
|
|
|
|
|
arm/simple_idct_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_MDCT) += arm/mdct_neon.o \
|
|
|
|
|
arm/mdct_fixed_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_MPEGVIDEO) += arm/mpegvideo_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_RDFT) += arm/rdft_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_VC1DSP) += arm/vc1dsp_init_neon.o \
|
|
|
|
|
arm/vc1dsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_VP3DSP) += arm/vp3dsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_VP8DSP) += arm/vp8dsp_init_neon.o \
|
|
|
|
|
arm/vp8dsp_neon.o
|
|
|
|
|
|
|
|
|
|
# decoders/encoders
|
|
|
|
|
NEON-OBJS-$(CONFIG_AAC_DECODER) += arm/aacpsdsp_neon.o \
|
|
|
|
|
arm/sbrdsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_LLAUDDSP) += arm/lossless_audiodsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_DCA_DECODER) += arm/synth_filter_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_HEVC_DECODER) += arm/hevcdsp_init_neon.o \
|
|
|
|
|
arm/hevcdsp_deblock_neon.o \
|
|
|
|
|
arm/hevcdsp_idct_neon.o \
|
|
|
|
|
arm/hevcdsp_qpel_neon.o \
|
|
|
|
|
arm/hevcdsp_sao_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_RV30_DECODER) += arm/rv34dsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_RV40_DECODER) += arm/rv34dsp_neon.o \
|
|
|
|
|
arm/rv40dsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_SBC_ENCODER) += arm/sbcdsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_VORBIS_DECODER) += arm/vorbisdsp_neon.o
|
|
|
|
|
NEON-OBJS-$(CONFIG_VP6_DECODER) += arm/vp6dsp_neon.o
|
arm: Add NEON optimizations for 10 and 12 bit vp9 itxfm
This work is sponsored by, and copyright, Google.
This is structured similarly to the 8 bit version. In the 8 bit
version, the coefficients are 16 bits, and intermediates are 32 bits.
Here, the coefficients are 32 bit. For the 4x4 transforms for 10 bit
content, the intermediates also fit in 32 bits, but for all other
transforms (4x4 for 12 bit content, and 8x8 and larger for both 10
and 12 bit) the intermediates are 64 bit.
For the existing 8 bit case, the 8x8 transform fit all coefficients in
registers; for 10/12 bit, when the coefficients are 32 bit, the 8x8
transform also has to be done in slices of 4 pixels (just as 16x16 and
32x32 for 8 bit).
The slice width also shrinks from 4 elements to 2 elements in parallel
for the 16x16 and 32x32 cases.
The 16 bit coefficients from idct_coeffs and similar tables also need
to be lenghtened to 32 bit in order to be used in multiplication with
vectors with 32 bit elements. This leads to the fixed coefficient
vectors needing more space, leading to more cases where they have to
be reloaded within the transform (in iadst16).
This technically would need testing in checkasm for subpartitions
in increments of 2, but that slows down normal checkasm runs
excessively.
Examples of relative speedup compared to the C version, from checkasm:
Cortex A7 A8 A9 A53
vp9_inv_adst_adst_4x4_sub4_add_10_neon: 4.83 11.36 5.22 6.77
vp9_inv_adst_adst_8x8_sub8_add_10_neon: 4.12 7.60 4.06 4.84
vp9_inv_adst_adst_16x16_sub16_add_10_neon: 3.93 8.16 4.52 5.35
vp9_inv_dct_dct_4x4_sub1_add_10_neon: 1.36 2.57 1.41 1.61
vp9_inv_dct_dct_4x4_sub4_add_10_neon: 4.24 8.66 5.06 5.81
vp9_inv_dct_dct_8x8_sub1_add_10_neon: 2.63 4.18 1.68 2.87
vp9_inv_dct_dct_8x8_sub4_add_10_neon: 4.52 9.47 4.24 5.39
vp9_inv_dct_dct_8x8_sub8_add_10_neon: 3.45 7.34 3.45 4.30
vp9_inv_dct_dct_16x16_sub1_add_10_neon: 3.56 6.21 2.47 4.32
vp9_inv_dct_dct_16x16_sub2_add_10_neon: 5.68 12.73 5.28 7.07
vp9_inv_dct_dct_16x16_sub8_add_10_neon: 4.42 9.28 4.24 5.45
vp9_inv_dct_dct_16x16_sub16_add_10_neon: 3.41 7.29 3.35 4.19
vp9_inv_dct_dct_32x32_sub1_add_10_neon: 4.52 8.35 3.83 6.40
vp9_inv_dct_dct_32x32_sub2_add_10_neon: 5.86 13.19 6.14 7.04
vp9_inv_dct_dct_32x32_sub16_add_10_neon: 4.29 8.11 4.59 5.06
vp9_inv_dct_dct_32x32_sub32_add_10_neon: 3.31 5.70 3.56 3.84
vp9_inv_wht_wht_4x4_sub4_add_10_neon: 1.89 2.80 1.82 1.97
The speedup compared to the C functions is around 1.3 to 7x for the
full transforms, even higher for the smaller subpartitions.
Signed-off-by: Martin Storsjö <martin@martin.st>
8 years ago
|
|
|
NEON-OBJS-$(CONFIG_VP9_DECODER) += arm/vp9itxfm_16bpp_neon.o \
|
|
|
|
|
arm/vp9itxfm_neon.o \
|
arm: Add NEON optimizations for 10 and 12 bit vp9 loop filter
This work is sponsored by, and copyright, Google.
This is pretty much similar to the 8 bpp version, but in some senses
simpler. All input pixels are 16 bits, and all intermediates also fit
in 16 bits, so there's no lengthening/narrowing in the filter at all.
For the full 16 pixel wide filter, we can only process 4 pixels at a time
(using an implementation very much similar to the one for 8 bpp),
but we can do 8 pixels at a time for the 4 and 8 pixel wide filters with
a different implementation of the core filter.
Examples of relative speedup compared to the C version, from checkasm:
Cortex A7 A8 A9 A53
vp9_loop_filter_h_4_8_10bpp_neon: 1.83 2.16 1.40 2.09
vp9_loop_filter_h_8_8_10bpp_neon: 1.39 1.67 1.24 1.70
vp9_loop_filter_h_16_8_10bpp_neon: 1.56 1.47 1.10 1.81
vp9_loop_filter_h_16_16_10bpp_neon: 1.94 1.69 1.33 2.24
vp9_loop_filter_mix2_h_44_16_10bpp_neon: 2.01 2.27 1.67 2.39
vp9_loop_filter_mix2_h_48_16_10bpp_neon: 1.84 2.06 1.45 2.19
vp9_loop_filter_mix2_h_84_16_10bpp_neon: 1.89 2.20 1.47 2.29
vp9_loop_filter_mix2_h_88_16_10bpp_neon: 1.69 2.12 1.47 2.08
vp9_loop_filter_mix2_v_44_16_10bpp_neon: 3.16 3.98 2.50 4.05
vp9_loop_filter_mix2_v_48_16_10bpp_neon: 2.84 3.64 2.25 3.77
vp9_loop_filter_mix2_v_84_16_10bpp_neon: 2.65 3.45 2.16 3.54
vp9_loop_filter_mix2_v_88_16_10bpp_neon: 2.55 3.30 2.16 3.55
vp9_loop_filter_v_4_8_10bpp_neon: 2.85 3.97 2.24 3.68
vp9_loop_filter_v_8_8_10bpp_neon: 2.27 3.19 1.96 3.08
vp9_loop_filter_v_16_8_10bpp_neon: 3.42 2.74 2.26 4.40
vp9_loop_filter_v_16_16_10bpp_neon: 2.86 2.44 1.93 3.88
The speedup vs C code measured in checkasm is around 1.1-4x.
These numbers are quite inconclusive though, since the checkasm test
runs multiple filterings on top of each other, so later rounds might
end up with different codepaths (different decisions on which filter
to apply, based on input pixel differences).
Based on START_TIMER/STOP_TIMER wrapping around a few individual
functions, the speedup vs C code is around 2-4x.
Signed-off-by: Martin Storsjö <martin@martin.st>
8 years ago
|
|
|
arm/vp9lpf_16bpp_neon.o \
|
arm: vp9: Add NEON loop filters
This work is sponsored by, and copyright, Google.
The implementation tries to have smart handling of cases
where no pixels need the full filtering for the 8/16 width
filters, skipping both calculation and writeback of the
unmodified pixels in those cases. The actual effect of this
is hard to test with checkasm though, since it tests the
full filtering, and the benefit depends on how many filtered
blocks use the shortcut.
Examples of relative speedup compared to the C version, from checkasm:
Cortex A7 A8 A9 A53
vp9_loop_filter_h_4_8_neon: 2.72 2.68 1.78 3.15
vp9_loop_filter_h_8_8_neon: 2.36 2.38 1.70 2.91
vp9_loop_filter_h_16_8_neon: 1.80 1.89 1.45 2.01
vp9_loop_filter_h_16_16_neon: 2.81 2.78 2.18 3.16
vp9_loop_filter_mix2_h_44_16_neon: 2.65 2.67 1.93 3.05
vp9_loop_filter_mix2_h_48_16_neon: 2.46 2.38 1.81 2.85
vp9_loop_filter_mix2_h_84_16_neon: 2.50 2.41 1.73 2.85
vp9_loop_filter_mix2_h_88_16_neon: 2.77 2.66 1.96 3.23
vp9_loop_filter_mix2_v_44_16_neon: 4.28 4.46 3.22 5.70
vp9_loop_filter_mix2_v_48_16_neon: 3.92 4.00 3.03 5.19
vp9_loop_filter_mix2_v_84_16_neon: 3.97 4.31 2.98 5.33
vp9_loop_filter_mix2_v_88_16_neon: 3.91 4.19 3.06 5.18
vp9_loop_filter_v_4_8_neon: 4.53 4.47 3.31 6.05
vp9_loop_filter_v_8_8_neon: 3.58 3.99 2.92 5.17
vp9_loop_filter_v_16_8_neon: 3.40 3.50 2.81 4.68
vp9_loop_filter_v_16_16_neon: 4.66 4.41 3.74 6.02
The speedup vs C code is around 2-6x. The numbers are quite
inconclusive though, since the checkasm test runs multiple filterings
on top of each other, so later rounds might end up with different
codepaths (different decisions on which filter to apply, based
on input pixel differences). Disabling the early-exit in the asm
doesn't give a fair comparison either though, since the C code
only does the necessary calcuations for each row.
Based on START_TIMER/STOP_TIMER wrapping around a few individual
functions, the speedup vs C code is around 4-9x.
This is pretty similar in runtime to the corresponding routines
in libvpx. (This is comparing vpx_lpf_vertical_16_neon,
vpx_lpf_horizontal_edge_8_neon and vpx_lpf_horizontal_edge_16_neon
to vp9_loop_filter_h_16_8_neon, vp9_loop_filter_v_16_8_neon
and vp9_loop_filter_v_16_16_neon - note that the naming of horizonal
and vertical is flipped between the libraries.)
In order to have stable, comparable numbers, the early exits in both
asm versions were disabled, forcing the full filtering codepath.
Cortex A7 A8 A9 A53
vp9_loop_filter_h_16_8_neon: 597.2 472.0 482.4 415.0
libvpx vpx_lpf_vertical_16_neon: 626.0 464.5 470.7 445.0
vp9_loop_filter_v_16_8_neon: 500.2 422.5 429.7 295.0
libvpx vpx_lpf_horizontal_edge_8_neon: 586.5 414.5 415.6 383.2
vp9_loop_filter_v_16_16_neon: 905.0 784.7 791.5 546.0
libvpx vpx_lpf_horizontal_edge_16_neon: 1060.2 751.7 743.5 685.2
Our version is consistently faster on on A7 and A53, marginally slower on
A8, and sometimes faster, sometimes slower on A9 (marginally slower in all
three tests in this particular test run).
This is an adapted cherry-pick from libav commit
dd299a2d6d4d1af9528ed35a8131c35946be5973.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
8 years ago
|
|
|
arm/vp9lpf_neon.o \
|
arm: Add NEON optimizations for 10 and 12 bit vp9 MC
This work is sponsored by, and copyright, Google.
The plain pixel put/copy functions are used from the 8 bit version,
for the double size (e.g. put16 uses ff_vp9_copy32_neon), and a new
copy128 is added.
Compared with the 8 bit version, the filters can no longer use the
trick to accumulate in 16 bit with only saturation at the end, but now
the accumulators need to be 32 bit. This avoids the need to keep track
of which filter index is the largest though, reducing the size of the
executable code for these filters.
For the horizontal filters, we only do 4 or 8 pixels wide in parallel
(while doing two rows at a time), since we don't have enough register
space to filter 16 pixels wide.
For the vertical filters, we still do 4 and 8 pixels in parallel just
as in the 8 bit case, but we need to store the output after every 2
rows instead of after every 4 rows.
Examples of relative speedup compared to the C version, from checkasm:
Cortex A7 A8 A9 A53
vp9_avg4_10bpp_neon: 2.25 2.44 3.05 2.16
vp9_avg8_10bpp_neon: 3.66 8.48 3.86 3.50
vp9_avg16_10bpp_neon: 3.39 8.26 3.37 2.72
vp9_avg32_10bpp_neon: 4.03 10.20 4.07 3.42
vp9_avg64_10bpp_neon: 4.15 10.01 4.13 3.70
vp9_avg_8tap_smooth_4h_10bpp_neon: 3.38 6.22 3.41 4.75
vp9_avg_8tap_smooth_4hv_10bpp_neon: 3.89 6.39 4.30 5.32
vp9_avg_8tap_smooth_4v_10bpp_neon: 5.32 9.73 6.34 7.31
vp9_avg_8tap_smooth_8h_10bpp_neon: 4.45 9.40 4.68 6.87
vp9_avg_8tap_smooth_8hv_10bpp_neon: 4.64 8.91 5.44 6.47
vp9_avg_8tap_smooth_8v_10bpp_neon: 6.44 13.42 8.68 8.79
vp9_avg_8tap_smooth_64h_10bpp_neon: 4.66 9.02 4.84 7.71
vp9_avg_8tap_smooth_64hv_10bpp_neon: 4.61 9.14 4.92 7.10
vp9_avg_8tap_smooth_64v_10bpp_neon: 6.90 14.13 9.57 10.41
vp9_put4_10bpp_neon: 1.33 1.46 2.09 1.33
vp9_put8_10bpp_neon: 1.57 3.42 1.83 1.84
vp9_put16_10bpp_neon: 1.55 4.78 2.17 1.89
vp9_put32_10bpp_neon: 2.06 5.35 2.14 2.30
vp9_put64_10bpp_neon: 3.00 2.41 1.95 1.66
vp9_put_8tap_smooth_4h_10bpp_neon: 3.19 5.81 3.31 4.63
vp9_put_8tap_smooth_4hv_10bpp_neon: 3.86 6.22 4.32 5.21
vp9_put_8tap_smooth_4v_10bpp_neon: 5.40 9.77 6.08 7.21
vp9_put_8tap_smooth_8h_10bpp_neon: 4.22 8.41 4.46 6.63
vp9_put_8tap_smooth_8hv_10bpp_neon: 4.56 8.51 5.39 6.25
vp9_put_8tap_smooth_8v_10bpp_neon: 6.60 12.43 8.17 8.89
vp9_put_8tap_smooth_64h_10bpp_neon: 4.41 8.59 4.54 7.49
vp9_put_8tap_smooth_64hv_10bpp_neon: 4.43 8.58 5.34 6.63
vp9_put_8tap_smooth_64v_10bpp_neon: 7.26 13.92 9.27 10.92
For the larger 8tap filters, the speedup vs C code is around 4-14x.
Signed-off-by: Martin Storsjö <martin@martin.st>
8 years ago
|
|
|
arm/vp9mc_16bpp_neon.o \
|
arm: vp9: Add NEON itxfm routines
This work is sponsored by, and copyright, Google.
For the transforms up to 8x8, we can fit all the data (including
temporaries) in registers and just do a straightforward transform
of all the data. For 16x16, we do a transform of 4x16 pixels in
4 slices, using a temporary buffer. For 32x32, we transform 4x32
pixels at a time, in two steps of 4x16 pixels each.
Examples of relative speedup compared to the C version, from checkasm:
Cortex A7 A8 A9 A53
vp9_inv_adst_adst_4x4_add_neon: 3.39 5.83 4.17 4.01
vp9_inv_adst_adst_8x8_add_neon: 3.79 4.86 4.23 3.98
vp9_inv_adst_adst_16x16_add_neon: 3.33 4.36 4.11 4.16
vp9_inv_dct_dct_4x4_add_neon: 4.06 6.16 4.59 4.46
vp9_inv_dct_dct_8x8_add_neon: 4.61 6.01 4.98 4.86
vp9_inv_dct_dct_16x16_add_neon: 3.35 3.44 3.36 3.79
vp9_inv_dct_dct_32x32_add_neon: 3.89 3.50 3.79 4.42
vp9_inv_wht_wht_4x4_add_neon: 3.22 5.13 3.53 3.77
Thus, the speedup vs C code is around 3-6x.
This is mostly marginally faster than the corresponding routines
in libvpx on most cores, tested with their 32x32 idct (compared to
vpx_idct32x32_1024_add_neon). These numbers are slightly in libvpx's
favour since their version doesn't clear the input buffer like ours
do (although the effect of that on the total runtime probably is
negligible.)
Cortex A7 A8 A9 A53
vp9_inv_dct_dct_32x32_add_neon: 18436.8 16874.1 14235.1 11988.9
libvpx vpx_idct32x32_1024_add_neon 20789.0 13344.3 15049.9 13030.5
Only on the Cortex A8, the libvpx function is faster. On the other cores,
ours is slightly faster even though ours has got source block clearing
integrated.
This is an adapted cherry-pick from libav commits
a67ae67083151f2f9595a1f2d17b601da19b939e and
52d196fb30fb6628921b5f1b31e7bd11eb7e1d9a.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
8 years ago
|
|
|
arm/vp9mc_neon.o
|
