1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-18 03:19:31 +02:00
FFmpeg/libavcodec/aarch64
Martin Storsjö f872b19714 aarch64: hevc: Produce plain neon versions of qpel_bi_hv
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>
2024-03-26 09:05:55 +02:00
..
aacpsdsp_init_aarch64.c
aacpsdsp_neon.S aarch64: Reindent all assembly to 8/24 column indentation 2023-10-21 23:25:54 +03:00
cabac.h
fmtconvert_init.c avcodec/fmtconvert: Remove unused AVCodecContext parameter 2022-09-21 20:26:40 +02:00
fmtconvert_neon.S
h264chroma_init_aarch64.c avcodec/h264chroma: Constify src in h264_chroma_mc_func 2022-08-05 03:02:13 +02:00
h264cmc_neon.S aarch64: Lowercase UXTW/SXTW and similar flags 2023-10-21 23:25:23 +03:00
h264dsp_init_aarch64.c
h264dsp_neon.S aarch64: Make the indentation more consistent 2023-10-21 23:25:29 +03:00
h264idct_neon.S aarch64: Lowercase UXTW/SXTW and similar flags 2023-10-21 23:25:23 +03:00
h264pred_init.c
h264pred_neon.S
h264qpel_init_aarch64.c lavc/aarch64: h264qpel, add 10-bit lowpass_8_10 based functions 2023-12-07 23:20:14 +02:00
h264qpel_neon.S lavc/aarch64: h264qpel, add 10-bit lowpass_8_10 based functions 2023-12-07 23:20:14 +02:00
hevcdsp_deblock_neon.S avcodec/aarch64/hevc: add luma deblock NEON 2024-02-28 10:14:58 +01:00
hevcdsp_epel_neon.S aarch64: hevc: Produce epel_bi_hv functions for both neon and i8mm 2024-03-26 09:03:16 +02:00
hevcdsp_idct_neon.S aarch64: Make the indentation more consistent 2023-10-21 23:25:29 +03:00
hevcdsp_init_aarch64.c aarch64: hevc: Produce plain neon versions of qpel_bi_hv 2024-03-26 09:05:55 +02:00
hevcdsp_qpel_neon.S aarch64: hevc: Produce plain neon versions of qpel_bi_hv 2024-03-26 09:05:55 +02:00
hevcdsp_sao_neon.S aarch64: Implement stack spilling in a consistent way. 2022-10-11 09:12:02 +02:00
hpeldsp_init_aarch64.c
hpeldsp_neon.S aarch64: Consistently use lowercase for vector element specifiers 2023-10-21 23:25:18 +03:00
idct.h
idctdsp_init_aarch64.c
idctdsp_neon.S
Makefile avcodec: Remove DCT, FFT, MDCT and RDFT 2023-10-01 02:25:09 +02:00
me_cmp_init_aarch64.c lavc/aarch64: Add neon implementation for vsse_intra8 2022-10-04 13:24:20 +03:00
me_cmp_neon.S aarch64: Consistently use lowercase for vector element specifiers 2023-10-21 23:25:18 +03:00
mpegaudiodsp_init.c
mpegaudiodsp_neon.S lavc/hevcdsp_qpel_neon: using movi.16b instead of movi.2d 2023-11-28 15:54:49 +02:00
neon.S aarch64: Consistently use lowercase for vector element specifiers 2023-10-21 23:25:18 +03:00
neontest.c
opusdsp_init.c
opusdsp_neon.S aarch64: Reindent all assembly to 8/24 column indentation 2023-10-21 23:25:54 +03:00
pixblockdsp_init_aarch64.c
pixblockdsp_neon.S
rv40dsp_init_aarch64.c avcodec/h264chroma: Constify src in h264_chroma_mc_func 2022-08-05 03:02:13 +02:00
sbrdsp_init_aarch64.c
sbrdsp_neon.S aarch64: Consistently use lowercase for vector element specifiers 2023-10-21 23:25:18 +03:00
simple_idct_neon.S aarch64: Consistently use lowercase for vector element specifiers 2023-10-21 23:25:18 +03:00
synth_filter_init.c avcodec: Remove DCT, FFT, MDCT and RDFT 2023-10-01 02:25:09 +02:00
synth_filter_neon.S avcodec: Remove DCT, FFT, MDCT and RDFT 2023-10-01 02:25:09 +02:00
vc1dsp_init_aarch64.c avcodec/h264chroma: Constify src in h264_chroma_mc_func 2022-08-05 03:02:13 +02:00
vc1dsp_neon.S
videodsp_init.c avcodec/videodsp: Constify buf in VideoDSPContext.prefetch 2022-07-31 03:14:34 +02:00
videodsp.S
vorbisdsp_init.c lavc/vorbisdsp: use ptrdiff_t rather than intptr_t 2022-09-19 13:51:00 -03:00
vorbisdsp_neon.S
vp8dsp_init_aarch64.c
vp8dsp_neon.S aarch64: Make the indentation more consistent 2023-10-21 23:25:29 +03:00
vp8dsp.h avcodec/vp8dsp: Constify src in vp8_mc_func 2022-09-11 20:57:51 +02:00
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 aarch64: Implement stack spilling in a consistent way. 2022-10-11 09:12:02 +02:00
vp9lpf_16bpp_neon.S aarch64: Implement stack spilling in a consistent way. 2022-10-11 09:12:02 +02:00
vp9lpf_neon.S aarch64: Implement stack spilling in a consistent way. 2022-10-11 09:12:02 +02:00
vp9mc_16bpp_neon.S
vp9mc_aarch64.S
vp9mc_neon.S