| fdct.h |
AVCODEC_AARCH64_FDCT_H |
920 |
- |
| fdctdsp_init_aarch64.c |
|
1362 |
- |
| fdctdsp_neon.S |
|
17761 |
- |
| h264chroma_init_aarch64.c |
|
2539 |
- |
| h264cmc_neon.S |
|
15575 |
- |
| h264dsp_init_aarch64.c |
|
9661 |
- |
| h264dsp_neon.S |
|
40316 |
- |
| h264idct_neon.S |
|
16269 |
- |
| h264pred_init.c |
|
6899 |
- |
| h264pred_neon.S |
|
26288 |
- |
| hpeldsp_init_aarch64.c |
|
6291 |
- |
| hpeldsp_neon.S |
|
13962 |
- |
| idct.h |
AVCODEC_AARCH64_IDCT_H |
1108 |
- |
| idctdsp_init_aarch64.c |
|
2219 |
- |
| idctdsp_neon.S |
|
5088 |
- |
| moz.build |
|
1642 |
- |
| mpegaudiodsp_init.c |
|
1524 |
- |
| mpegaudiodsp_neon.S |
|
7479 |
- |
| neon.S |
|
7496 |
- |
| simple_idct_neon.S |
|
12659 |
- |
| vc1dsp_init_aarch64.c |
Dealing with starting and stopping, and removing escape bytes, are
comparatively less time-sensitive, so are more clearly expressed using
a C wrapper around the assembly inner loop. Note that we assume a
little-endian machine that supports unaligned loads. |
5602 |
- |
| videodsp.S |
|
1057 |
- |
| videodsp_init.c |
|
1156 |
- |
| vp8dsp.h |
AVCODEC_AARCH64_VP8DSP_H |
3440 |
- |
| vp8dsp_init_aarch64.c |
|
6088 |
- |
| vp8dsp_neon.S |
|
67146 |
- |
| vp9dsp_init.h |
AVCODEC_AARCH64_VP9DSP_INIT_H |
1064 |
- |
| vp9dsp_init_10bpp_aarch64.c |
|
911 |
- |
| vp9dsp_init_12bpp_aarch64.c |
|
911 |
- |
| vp9dsp_init_16bpp_aarch64_template.c |
We only need h + 7 lines, but the horizontal filter assumes an \
even number of rows, so filter h + 8 lines here. |
10805 |
- |
| vp9dsp_init_aarch64.c |
We only need h + 7 lines, but the horizontal filter assumes an \
even number of rows, so filter h + 8 lines here. |
9832 |
- |
| vp9itxfm_16bpp_neon.S |
|
81568 |
- |
| vp9itxfm_neon.S |
|
63534 |
- |
| vp9lpf_16bpp_neon.S |
|
34702 |
- |
| vp9lpf_neon.S |
|
52919 |
- |
| vp9mc_16bpp_neon.S |
|
23422 |
- |
| vp9mc_aarch64.S |
|
2911 |
- |
| vp9mc_neon.S |
|
24513 |
- |