mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-23 12:43:46 +02:00
5cbeefc79e
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_hv4_8_c: 386.0 put_hevc_qpel_hv4_8_neon: 125.7 put_hevc_qpel_hv4_8_i8mm: 83.2 put_hevc_qpel_hv6_8_c: 749.0 put_hevc_qpel_hv6_8_neon: 207.0 put_hevc_qpel_hv6_8_i8mm: 166.0 put_hevc_qpel_hv8_8_c: 1305.2 put_hevc_qpel_hv8_8_neon: 216.5 put_hevc_qpel_hv8_8_i8mm: 213.0 put_hevc_qpel_hv12_8_c: 2570.5 put_hevc_qpel_hv12_8_neon: 480.0 put_hevc_qpel_hv12_8_i8mm: 398.2 put_hevc_qpel_hv16_8_c: 4158.7 put_hevc_qpel_hv16_8_neon: 659.7 put_hevc_qpel_hv16_8_i8mm: 593.5 put_hevc_qpel_hv24_8_c: 8626.7 put_hevc_qpel_hv24_8_neon: 1653.5 put_hevc_qpel_hv24_8_i8mm: 1398.7 put_hevc_qpel_hv32_8_c: 14646.0 put_hevc_qpel_hv32_8_neon: 2566.2 put_hevc_qpel_hv32_8_i8mm: 2287.5 put_hevc_qpel_hv48_8_c: 31072.5 put_hevc_qpel_hv48_8_neon: 6228.5 put_hevc_qpel_hv48_8_i8mm: 5291.0 put_hevc_qpel_hv64_8_c: 53847.2 put_hevc_qpel_hv64_8_neon: 9856.7 put_hevc_qpel_hv64_8_i8mm: 8831.0 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 |