mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-09-23 23:06:41 +00:00
9c8bc74c2b
This work is sponsored by, and copyright, Google.
Previously all subpartitions except the eob=1 (DC) case ran with
the same runtime:
Cortex A7 A8 A9 A53
vp9_inv_dct_dct_16x16_sub16_add_neon: 3188.1 2435.4 2499.0 1969.0
vp9_inv_dct_dct_32x32_sub32_add_neon: 18531.7 16582.3 14207.6 12000.3
By skipping individual 4x16 or 4x32 pixel slices in the first pass,
we reduce the runtime of these functions like this:
vp9_inv_dct_dct_16x16_sub1_add_neon: 274.6 189.5 211.7 235.8
vp9_inv_dct_dct_16x16_sub2_add_neon: 2064.0 1534.8 1719.4 1248.7
vp9_inv_dct_dct_16x16_sub4_add_neon: 2135.0 1477.2 1736.3 1249.5
vp9_inv_dct_dct_16x16_sub8_add_neon: 2446.7 1828.7 1993.6 1494.7
vp9_inv_dct_dct_16x16_sub12_add_neon: 2832.4 2118.3 2266.5 1735.1
vp9_inv_dct_dct_16x16_sub16_add_neon: 3211.7 2475.3 2523.5 1983.1
vp9_inv_dct_dct_32x32_sub1_add_neon: 756.2 456.7 862.0 553.9
vp9_inv_dct_dct_32x32_sub2_add_neon: 10682.2 8190.4 8539.2 6762.5
vp9_inv_dct_dct_32x32_sub4_add_neon: 10813.5 8014.9 8518.3 6762.8
vp9_inv_dct_dct_32x32_sub8_add_neon: 11859.6 9313.0 9347.4 7514.5
vp9_inv_dct_dct_32x32_sub12_add_neon: 12946.6 10752.4 10192.2 8280.2
vp9_inv_dct_dct_32x32_sub16_add_neon: 14074.6 11946.5 11001.4 9008.6
vp9_inv_dct_dct_32x32_sub20_add_neon: 15269.9 13662.7 11816.1 9762.6
vp9_inv_dct_dct_32x32_sub24_add_neon: 16327.9 14940.1 12626.7 10516.0
vp9_inv_dct_dct_32x32_sub28_add_neon: 17462.7 15776.1 13446.2 11264.7
vp9_inv_dct_dct_32x32_sub32_add_neon: 18575.5 17157.0 14249.3 12015.1
I.e. in general a very minor overhead for the full subpartition case due
to the additional loads and cmps, but a significant speedup for the cases
when we only need to process a small part of the actual input data.
In common VP9 content in a few inspected clips, 70-90% of the non-dc-only
16x16 and 32x32 IDCTs only have nonzero coefficients in the upper left
8x8 or 16x16 subpartitions respectively.
Signed-off-by: Martin Storsjö <martin@martin.st>
|
||
|---|---|---|
| .. | ||
| aac.h | ||
| aacpsdsp_init_arm.c | ||
| aacpsdsp_neon.S | ||
| ac3dsp_arm.S | ||
| ac3dsp_armv6.S | ||
| ac3dsp_init_arm.c | ||
| ac3dsp_neon.S | ||
| apedsp_init_arm.c | ||
| apedsp_neon.S | ||
| asm-offsets.h | ||
| audiodsp_arm.h | ||
| audiodsp_init_arm.c | ||
| audiodsp_init_neon.c | ||
| audiodsp_neon.S | ||
| blockdsp_arm.h | ||
| blockdsp_init_arm.c | ||
| blockdsp_init_neon.c | ||
| blockdsp_neon.S | ||
| cabac.h | ||
| dca.h | ||
| dcadsp_init_arm.c | ||
| dcadsp_neon.S | ||
| dcadsp_vfp.S | ||
| fft_fixed_init_arm.c | ||
| fft_fixed_neon.S | ||
| fft_init_arm.c | ||
| fft_neon.S | ||
| fft_vfp.S | ||
| flacdsp_arm.S | ||
| flacdsp_init_arm.c | ||
| fmtconvert_init_arm.c | ||
| fmtconvert_neon.S | ||
| fmtconvert_vfp.S | ||
| g722dsp_init_arm.c | ||
| g722dsp_neon.S | ||
| h264chroma_init_arm.c | ||
| h264cmc_neon.S | ||
| h264dsp_init_arm.c | ||
| h264dsp_neon.S | ||
| h264idct_neon.S | ||
| h264pred_init_arm.c | ||
| h264pred_neon.S | ||
| h264qpel_init_arm.c | ||
| h264qpel_neon.S | ||
| hpeldsp_arm.h | ||
| hpeldsp_arm.S | ||
| hpeldsp_armv6.S | ||
| hpeldsp_init_arm.c | ||
| hpeldsp_init_armv6.c | ||
| hpeldsp_init_neon.c | ||
| hpeldsp_neon.S | ||
| idct.h | ||
| idctdsp_arm.h | ||
| idctdsp_arm.S | ||
| idctdsp_armv6.S | ||
| idctdsp_init_arm.c | ||
| idctdsp_init_armv5te.c | ||
| idctdsp_init_armv6.c | ||
| idctdsp_init_neon.c | ||
| idctdsp_neon.S | ||
| int_neon.S | ||
| jrevdct_arm.S | ||
| Makefile | ||
| mathops.h | ||
| mdct_fixed_init_arm.c | ||
| mdct_fixed_neon.S | ||
| mdct_init_arm.c | ||
| mdct_neon.S | ||
| mdct_vfp.S | ||
| me_cmp_armv6.S | ||
| me_cmp_init_arm.c | ||
| mlpdsp_armv5te.S | ||
| mlpdsp_armv6.S | ||
| mlpdsp_init_arm.c | ||
| mpegaudiodsp_fixed_armv6.S | ||
| mpegaudiodsp_init_arm.c | ||
| mpegvideo_arm.c | ||
| mpegvideo_arm.h | ||
| mpegvideo_armv5te_s.S | ||
| mpegvideo_armv5te.c | ||
| mpegvideo_neon.S | ||
| mpegvideoencdsp_armv6.S | ||
| mpegvideoencdsp_init_arm.c | ||
| neon.S | ||
| neontest.c | ||
| pixblockdsp_armv6.S | ||
| pixblockdsp_init_arm.c | ||
| rdft_init_arm.c | ||
| rdft_neon.S | ||
| rv34dsp_init_arm.c | ||
| rv34dsp_neon.S | ||
| rv40dsp_init_arm.c | ||
| rv40dsp_neon.S | ||
| sbrdsp_init_arm.c | ||
| sbrdsp_neon.S | ||
| simple_idct_arm.S | ||
| simple_idct_armv5te.S | ||
| simple_idct_armv6.S | ||
| simple_idct_neon.S | ||
| startcode_armv6.S | ||
| startcode.h | ||
| synth_filter_neon.S | ||
| synth_filter_vfp.S | ||
| vc1dsp_init_arm.c | ||
| vc1dsp_init_neon.c | ||
| vc1dsp_neon.S | ||
| vc1dsp.h | ||
| videodsp_arm.h | ||
| videodsp_armv5te.S | ||
| videodsp_init_arm.c | ||
| videodsp_init_armv5te.c | ||
| vorbisdsp_init_arm.c | ||
| vorbisdsp_neon.S | ||
| vp3dsp_init_arm.c | ||
| vp3dsp_neon.S | ||
| vp6dsp_init_arm.c | ||
| vp6dsp_neon.S | ||
| vp8_armv6.S | ||
| vp8.h | ||
| vp8dsp_armv6.S | ||
| vp8dsp_init_arm.c | ||
| vp8dsp_init_armv6.c | ||
| vp8dsp_init_neon.c | ||
| vp8dsp_neon.S | ||
| vp8dsp.h | ||
| vp9dsp_init_arm.c | ||
| vp9itxfm_neon.S | ||
| vp9lpf_neon.S | ||
| vp9mc_neon.S | ||
| vp56_arith.h | ||