mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-23 12:43:46 +02:00
dc47bf3872
This work is sponsored by, and copyright, Google.
This reduces the code size of libavcodec/aarch64/vp9itxfm_neon.o from
19496 to 14740 bytes.
This gives a small slowdown of a couple of tens of cycles, but makes
it more feasible to add more optimized versions of these transforms.
Before:
vp9_inv_dct_dct_16x16_sub4_add_neon: 1036.7
vp9_inv_dct_dct_16x16_sub16_add_neon: 1372.2
vp9_inv_dct_dct_32x32_sub4_add_neon: 5180.0
vp9_inv_dct_dct_32x32_sub32_add_neon: 8095.7
After:
vp9_inv_dct_dct_16x16_sub4_add_neon: 1051.0
vp9_inv_dct_dct_16x16_sub16_add_neon: 1390.1
vp9_inv_dct_dct_32x32_sub4_add_neon: 5199.9
vp9_inv_dct_dct_32x32_sub32_add_neon: 8125.8
This is cherrypicked from libav commit
|
||
---|---|---|
.. | ||
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 | ||
Makefile | ||
mdct_neon.S | ||
mpegaudiodsp_init.c | ||
mpegaudiodsp_neon.S | ||
neon.S | ||
neontest.c | ||
rv40dsp_init_aarch64.c | ||
synth_filter_init.c | ||
synth_filter_neon.S | ||
vc1dsp_init_aarch64.c | ||
videodsp_init.c | ||
videodsp.S | ||
vorbisdsp_init.c | ||
vorbisdsp_neon.S | ||
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_neon.S |