mirror of https://git.ffmpeg.org/ffmpeg.git
61b8a9ea29
This work is sponsored by, and copyright, Google. This avoids loading and calculating coefficients that we know will be zero, and avoids filling the temp buffer with zeros in places where we know the second pass won't read. This gives a pretty substantial speedup for the smaller subpartitions. The code size increases from 21512 bytes to 31400 bytes. The idct16/32_end macros are moved above the individual functions; the instructions themselves are unchanged, but since new functions are added at the same place where the code is moved from, the diff looks rather messy. Before: vp9_inv_dct_dct_16x16_sub1_add_10_neon: 284.6 vp9_inv_dct_dct_16x16_sub2_add_10_neon: 1902.7 vp9_inv_dct_dct_16x16_sub4_add_10_neon: 1903.0 vp9_inv_dct_dct_16x16_sub8_add_10_neon: 2201.1 vp9_inv_dct_dct_16x16_sub12_add_10_neon: 2510.0 vp9_inv_dct_dct_16x16_sub16_add_10_neon: 2821.3 vp9_inv_dct_dct_32x32_sub1_add_10_neon: 1011.6 vp9_inv_dct_dct_32x32_sub2_add_10_neon: 9716.5 vp9_inv_dct_dct_32x32_sub4_add_10_neon: 9704.9 vp9_inv_dct_dct_32x32_sub8_add_10_neon: 10641.7 vp9_inv_dct_dct_32x32_sub12_add_10_neon: 11555.7 vp9_inv_dct_dct_32x32_sub16_add_10_neon: 12499.8 vp9_inv_dct_dct_32x32_sub20_add_10_neon: 13403.7 vp9_inv_dct_dct_32x32_sub24_add_10_neon: 14335.8 vp9_inv_dct_dct_32x32_sub28_add_10_neon: 15253.6 vp9_inv_dct_dct_32x32_sub32_add_10_neon: 16179.5 After: vp9_inv_dct_dct_16x16_sub1_add_10_neon: 282.8 vp9_inv_dct_dct_16x16_sub2_add_10_neon: 1142.4 vp9_inv_dct_dct_16x16_sub4_add_10_neon: 1139.0 vp9_inv_dct_dct_16x16_sub8_add_10_neon: 1772.9 vp9_inv_dct_dct_16x16_sub12_add_10_neon: 2515.2 vp9_inv_dct_dct_16x16_sub16_add_10_neon: 2823.5 vp9_inv_dct_dct_32x32_sub1_add_10_neon: 1012.7 vp9_inv_dct_dct_32x32_sub2_add_10_neon: 6944.4 vp9_inv_dct_dct_32x32_sub4_add_10_neon: 6944.2 vp9_inv_dct_dct_32x32_sub8_add_10_neon: 7609.8 vp9_inv_dct_dct_32x32_sub12_add_10_neon: 9953.4 vp9_inv_dct_dct_32x32_sub16_add_10_neon: 10770.1 vp9_inv_dct_dct_32x32_sub20_add_10_neon: 13418.8 vp9_inv_dct_dct_32x32_sub24_add_10_neon: 14330.7 vp9_inv_dct_dct_32x32_sub28_add_10_neon: 15257.1 vp9_inv_dct_dct_32x32_sub32_add_10_neon: 16190.6 Signed-off-by: Martin Storsjö <martin@martin.st> |
||
|---|---|---|
| .. | ||
| Makefile | ||
| asm-offsets.h | ||
| cabac.h | ||
| fft_init_aarch64.c | ||
| fft_neon.S | ||
| fmtconvert_init.c | ||
| fmtconvert_neon.S | ||
| h264chroma_init_aarch64.c | ||
| h264cmc_neon.S | ||
| h264dsp_init_aarch64.c | ||
| h264dsp_neon.S | ||
| h264idct_neon.S | ||
| h264pred_init.c | ||
| h264pred_neon.S | ||
| h264qpel_init_aarch64.c | ||
| h264qpel_neon.S | ||
| hpeldsp_init_aarch64.c | ||
| hpeldsp_neon.S | ||
| idct.h | ||
| idctdsp_init_aarch64.c | ||
| mdct_neon.S | ||
| mpegaudiodsp_init.c | ||
| mpegaudiodsp_neon.S | ||
| neon.S | ||
| neontest.c | ||
| rv40dsp_init_aarch64.c | ||
| simple_idct_neon.S | ||
| synth_filter_init.c | ||
| synth_filter_neon.S | ||
| vc1dsp_init_aarch64.c | ||
| videodsp.S | ||
| videodsp_init.c | ||
| vorbisdsp_init.c | ||
| vorbisdsp_neon.S | ||
| vp9dsp_init.h | ||
| vp9dsp_init_10bpp_aarch64.c | ||
| vp9dsp_init_12bpp_aarch64.c | ||
| vp9dsp_init_16bpp_aarch64_template.c | ||
| vp9dsp_init_aarch64.c | ||
| vp9itxfm_16bpp_neon.S | ||
| vp9itxfm_neon.S | ||
| vp9lpf_16bpp_neon.S | ||
| vp9lpf_neon.S | ||
| vp9mc_16bpp_neon.S | ||
| vp9mc_neon.S | ||