mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-23 12:43:46 +02:00
f872b19714
As the plain neon qpel_h functions process two rows at a time, we need to allocate storage for h+8 rows instead of h+7. By allocating storage for h+8 rows, incrementing the stack pointer won't end up at the right spot in the end. Store the intended final stack pointer value in a register x14 which we store on the stack. AWS Graviton 3: put_hevc_qpel_bi_hv4_8_c: 385.7 put_hevc_qpel_bi_hv4_8_neon: 131.0 put_hevc_qpel_bi_hv4_8_i8mm: 92.2 put_hevc_qpel_bi_hv6_8_c: 701.0 put_hevc_qpel_bi_hv6_8_neon: 239.5 put_hevc_qpel_bi_hv6_8_i8mm: 191.0 put_hevc_qpel_bi_hv8_8_c: 1162.0 put_hevc_qpel_bi_hv8_8_neon: 228.0 put_hevc_qpel_bi_hv8_8_i8mm: 225.2 put_hevc_qpel_bi_hv12_8_c: 2305.0 put_hevc_qpel_bi_hv12_8_neon: 558.0 put_hevc_qpel_bi_hv12_8_i8mm: 483.2 put_hevc_qpel_bi_hv16_8_c: 3965.2 put_hevc_qpel_bi_hv16_8_neon: 732.7 put_hevc_qpel_bi_hv16_8_i8mm: 656.5 put_hevc_qpel_bi_hv24_8_c: 8709.7 put_hevc_qpel_bi_hv24_8_neon: 1555.2 put_hevc_qpel_bi_hv24_8_i8mm: 1448.7 put_hevc_qpel_bi_hv32_8_c: 14818.0 put_hevc_qpel_bi_hv32_8_neon: 2763.7 put_hevc_qpel_bi_hv32_8_i8mm: 2468.0 put_hevc_qpel_bi_hv48_8_c: 32855.5 put_hevc_qpel_bi_hv48_8_neon: 6107.2 put_hevc_qpel_bi_hv48_8_i8mm: 5452.7 put_hevc_qpel_bi_hv64_8_c: 57591.5 put_hevc_qpel_bi_hv64_8_neon: 10660.2 put_hevc_qpel_bi_hv64_8_i8mm: 9580.0 Signed-off-by: Martin Storsjö <martin@martin.st> |
||
|---|---|---|
| .. | ||
| aacpsdsp_init_aarch64.c | ||
| aacpsdsp_neon.S | ||
| cabac.h | ||
| 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 | ||
| hevcdsp_deblock_neon.S | ||
| hevcdsp_epel_neon.S | ||
| hevcdsp_idct_neon.S | ||
| hevcdsp_init_aarch64.c | ||
| hevcdsp_qpel_neon.S | ||
| hevcdsp_sao_neon.S | ||
| hpeldsp_init_aarch64.c | ||
| hpeldsp_neon.S | ||
| idct.h | ||
| idctdsp_init_aarch64.c | ||
| idctdsp_neon.S | ||
| Makefile | ||
| me_cmp_init_aarch64.c | ||
| me_cmp_neon.S | ||
| mpegaudiodsp_init.c | ||
| mpegaudiodsp_neon.S | ||
| neon.S | ||
| neontest.c | ||
| opusdsp_init.c | ||
| opusdsp_neon.S | ||
| pixblockdsp_init_aarch64.c | ||
| pixblockdsp_neon.S | ||
| rv40dsp_init_aarch64.c | ||
| sbrdsp_init_aarch64.c | ||
| sbrdsp_neon.S | ||
| simple_idct_neon.S | ||
| synth_filter_init.c | ||
| synth_filter_neon.S | ||
| vc1dsp_init_aarch64.c | ||
| vc1dsp_neon.S | ||
| videodsp_init.c | ||
| videodsp.S | ||
| vorbisdsp_init.c | ||
| vorbisdsp_neon.S | ||
| vp8dsp_init_aarch64.c | ||
| vp8dsp_neon.S | ||
| vp8dsp.h | ||
| vp9dsp_init_10bpp_aarch64.c | ||
| vp9dsp_init_12bpp_aarch64.c | ||
| vp9dsp_init_16bpp_aarch64_template.c | ||
| vp9dsp_init_aarch64.c | ||
| vp9dsp_init.h | ||
| vp9itxfm_16bpp_neon.S | ||
| vp9itxfm_neon.S | ||
| vp9lpf_16bpp_neon.S | ||
| vp9lpf_neon.S | ||
| vp9mc_16bpp_neon.S | ||
| vp9mc_aarch64.S | ||
| vp9mc_neon.S | ||