FFmpeg
vp8dsp_init_aarch64.c
Go to the documentation of this file.
1 /*
2  * This file is part of FFmpeg.
3  *
4  * FFmpeg is free software; you can redistribute it and/or
5  * modify it under the terms of the GNU Lesser General Public
6  * License as published by the Free Software Foundation; either
7  * version 2.1 of the License, or (at your option) any later version.
8  *
9  * FFmpeg is distributed in the hope that it will be useful,
10  * but WITHOUT ANY WARRANTY; without even the implied warranty of
11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
12  * Lesser General Public License for more details.
13  *
14  * You should have received a copy of the GNU Lesser General Public
15  * License along with FFmpeg; if not, write to the Free Software
16  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
17  */
18 
19 #include <stdint.h>
20 
21 #include "libavutil/attributes.h"
22 #include "libavutil/aarch64/cpu.h"
23 #include "libavcodec/vp8dsp.h"
24 #include "vp8dsp.h"
25 
26 void ff_vp8_luma_dc_wht_neon(int16_t block[4][4][16], int16_t dc[16]);
27 
28 void ff_vp8_idct_add_neon(uint8_t *dst, int16_t block[16], ptrdiff_t stride);
29 void ff_vp8_idct_dc_add_neon(uint8_t *dst, int16_t block[16], ptrdiff_t stride);
30 void ff_vp8_idct_dc_add4y_neon(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride);
31 void ff_vp8_idct_dc_add4uv_neon(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride);
32 
33 VP8_LF(neon);
34 
35 VP8_EPEL(16, neon);
36 VP8_EPEL(8, neon);
37 VP8_EPEL(4, neon);
38 
39 VP8_BILIN(16, neon);
40 VP8_BILIN(8, neon);
41 VP8_BILIN(4, neon);
42 
44 {
46  return;
47  dsp->put_vp8_epel_pixels_tab[0][0][0] = ff_put_vp8_pixels16_neon;
48  dsp->put_vp8_epel_pixels_tab[0][0][2] = ff_put_vp8_epel16_h6_neon;
49  dsp->put_vp8_epel_pixels_tab[0][2][0] = ff_put_vp8_epel16_v6_neon;
50  dsp->put_vp8_epel_pixels_tab[0][2][2] = ff_put_vp8_epel16_h6v6_neon;
51 
52  dsp->put_vp8_epel_pixels_tab[1][0][0] = ff_put_vp8_pixels8_neon;
53  dsp->put_vp8_epel_pixels_tab[1][0][1] = ff_put_vp8_epel8_h4_neon;
54  dsp->put_vp8_epel_pixels_tab[1][0][2] = ff_put_vp8_epel8_h6_neon;
55  dsp->put_vp8_epel_pixels_tab[1][1][0] = ff_put_vp8_epel8_v4_neon;
56  dsp->put_vp8_epel_pixels_tab[1][1][1] = ff_put_vp8_epel8_h4v4_neon;
57  dsp->put_vp8_epel_pixels_tab[1][1][2] = ff_put_vp8_epel8_h6v4_neon;
58  dsp->put_vp8_epel_pixels_tab[1][2][0] = ff_put_vp8_epel8_v6_neon;
59  dsp->put_vp8_epel_pixels_tab[1][2][1] = ff_put_vp8_epel8_h4v6_neon;
60  dsp->put_vp8_epel_pixels_tab[1][2][2] = ff_put_vp8_epel8_h6v6_neon;
61 
62  dsp->put_vp8_epel_pixels_tab[2][0][1] = ff_put_vp8_epel4_h4_neon;
63  dsp->put_vp8_epel_pixels_tab[2][0][2] = ff_put_vp8_epel4_h6_neon;
64  dsp->put_vp8_epel_pixels_tab[2][1][0] = ff_put_vp8_epel4_v4_neon;
65  dsp->put_vp8_epel_pixels_tab[2][1][1] = ff_put_vp8_epel4_h4v4_neon;
66  dsp->put_vp8_epel_pixels_tab[2][1][2] = ff_put_vp8_epel4_h6v4_neon;
67  dsp->put_vp8_epel_pixels_tab[2][2][0] = ff_put_vp8_epel4_v6_neon;
68  dsp->put_vp8_epel_pixels_tab[2][2][1] = ff_put_vp8_epel4_h4v6_neon;
69  dsp->put_vp8_epel_pixels_tab[2][2][2] = ff_put_vp8_epel4_h6v6_neon;
70 
71  dsp->put_vp8_bilinear_pixels_tab[0][0][0] = ff_put_vp8_pixels16_neon;
72  dsp->put_vp8_bilinear_pixels_tab[0][0][1] = ff_put_vp8_bilin16_h_neon;
73  dsp->put_vp8_bilinear_pixels_tab[0][0][2] = ff_put_vp8_bilin16_h_neon;
74  dsp->put_vp8_bilinear_pixels_tab[0][1][0] = ff_put_vp8_bilin16_v_neon;
75  dsp->put_vp8_bilinear_pixels_tab[0][1][1] = ff_put_vp8_bilin16_hv_neon;
76  dsp->put_vp8_bilinear_pixels_tab[0][1][2] = ff_put_vp8_bilin16_hv_neon;
77  dsp->put_vp8_bilinear_pixels_tab[0][2][0] = ff_put_vp8_bilin16_v_neon;
78  dsp->put_vp8_bilinear_pixels_tab[0][2][1] = ff_put_vp8_bilin16_hv_neon;
79  dsp->put_vp8_bilinear_pixels_tab[0][2][2] = ff_put_vp8_bilin16_hv_neon;
80 
81  dsp->put_vp8_bilinear_pixels_tab[1][0][0] = ff_put_vp8_pixels8_neon;
82  dsp->put_vp8_bilinear_pixels_tab[1][0][1] = ff_put_vp8_bilin8_h_neon;
83  dsp->put_vp8_bilinear_pixels_tab[1][0][2] = ff_put_vp8_bilin8_h_neon;
84  dsp->put_vp8_bilinear_pixels_tab[1][1][0] = ff_put_vp8_bilin8_v_neon;
85  dsp->put_vp8_bilinear_pixels_tab[1][1][1] = ff_put_vp8_bilin8_hv_neon;
86  dsp->put_vp8_bilinear_pixels_tab[1][1][2] = ff_put_vp8_bilin8_hv_neon;
87  dsp->put_vp8_bilinear_pixels_tab[1][2][0] = ff_put_vp8_bilin8_v_neon;
88  dsp->put_vp8_bilinear_pixels_tab[1][2][1] = ff_put_vp8_bilin8_hv_neon;
89  dsp->put_vp8_bilinear_pixels_tab[1][2][2] = ff_put_vp8_bilin8_hv_neon;
90 
91  dsp->put_vp8_bilinear_pixels_tab[2][0][1] = ff_put_vp8_bilin4_h_neon;
92  dsp->put_vp8_bilinear_pixels_tab[2][0][2] = ff_put_vp8_bilin4_h_neon;
93  dsp->put_vp8_bilinear_pixels_tab[2][1][0] = ff_put_vp8_bilin4_v_neon;
94  dsp->put_vp8_bilinear_pixels_tab[2][1][1] = ff_put_vp8_bilin4_hv_neon;
95  dsp->put_vp8_bilinear_pixels_tab[2][1][2] = ff_put_vp8_bilin4_hv_neon;
96  dsp->put_vp8_bilinear_pixels_tab[2][2][0] = ff_put_vp8_bilin4_v_neon;
97  dsp->put_vp8_bilinear_pixels_tab[2][2][1] = ff_put_vp8_bilin4_hv_neon;
98  dsp->put_vp8_bilinear_pixels_tab[2][2][2] = ff_put_vp8_bilin4_hv_neon;
99 }
100 
102 {
103  if (!have_neon(av_get_cpu_flags()))
104  return;
106 
111 
112  dsp->vp8_v_loop_filter16y = ff_vp8_v_loop_filter16_neon;
113  dsp->vp8_h_loop_filter16y = ff_vp8_h_loop_filter16_neon;
114  dsp->vp8_v_loop_filter8uv = ff_vp8_v_loop_filter8uv_neon;
115  dsp->vp8_h_loop_filter8uv = ff_vp8_h_loop_filter8uv_neon;
116 
117  dsp->vp8_v_loop_filter16y_inner = ff_vp8_v_loop_filter16_inner_neon;
118  dsp->vp8_h_loop_filter16y_inner = ff_vp8_h_loop_filter16_inner_neon;
119  dsp->vp8_v_loop_filter8uv_inner = ff_vp8_v_loop_filter8uv_inner_neon;
120  dsp->vp8_h_loop_filter8uv_inner = ff_vp8_h_loop_filter8uv_inner_neon;
121 
122  dsp->vp8_v_loop_filter_simple = ff_vp8_v_loop_filter16_simple_neon;
123  dsp->vp8_h_loop_filter_simple = ff_vp8_h_loop_filter16_simple_neon;
124 }
VP8DSPContext::vp8_h_loop_filter8uv
void(* vp8_h_loop_filter8uv)(uint8_t *dstU, uint8_t *dstV, ptrdiff_t stride, int flim_E, int flim_I, int hev_thresh)
Definition: vp8dsp.h:54
stride
int stride
Definition: mace.c:144
VP8DSPContext::vp8_h_loop_filter8uv_inner
void(* vp8_h_loop_filter8uv_inner)(uint8_t *dstU, uint8_t *dstV, ptrdiff_t stride, int flim_E, int flim_I, int hev_thresh)
Definition: vp8dsp.h:65
VP8DSPContext::vp8_v_loop_filter8uv
void(* vp8_v_loop_filter8uv)(uint8_t *dstU, uint8_t *dstV, ptrdiff_t stride, int flim_E, int flim_I, int hev_thresh)
Definition: vp8dsp.h:52
vp8dsp.h
ff_vp78dsp_init_aarch64
av_cold void ff_vp78dsp_init_aarch64(VP8DSPContext *dsp)
Definition: vp8dsp_init_aarch64.c:43
VP8DSPContext::vp8_v_loop_filter16y
void(* vp8_v_loop_filter16y)(uint8_t *dst, ptrdiff_t stride, int flim_E, int flim_I, int hev_thresh)
Definition: vp8dsp.h:48
ff_vp8_idct_dc_add_neon
void ff_vp8_idct_dc_add_neon(uint8_t *dst, int16_t block[16], ptrdiff_t stride)
av_get_cpu_flags
int av_get_cpu_flags(void)
Return the flags which specify extensions supported by the CPU.
Definition: cpu.c:98
av_cold
#define av_cold
Definition: attributes.h:90
VP8DSPContext::vp8_v_loop_filter16y_inner
void(* vp8_v_loop_filter16y_inner)(uint8_t *dst, ptrdiff_t stride, int flim_E, int flim_I, int hev_thresh)
Definition: vp8dsp.h:58
vp8dsp.h
ff_vp8_idct_add_neon
void ff_vp8_idct_add_neon(uint8_t *dst, int16_t block[16], ptrdiff_t stride)
VP8DSPContext::vp8_h_loop_filter_simple
void(* vp8_h_loop_filter_simple)(uint8_t *dst, ptrdiff_t stride, int flim)
Definition: vp8dsp.h:70
VP8_LF
VP8_LF(neon)
VP8DSPContext::vp8_v_loop_filter_simple
void(* vp8_v_loop_filter_simple)(uint8_t *dst, ptrdiff_t stride, int flim)
Definition: vp8dsp.h:69
VP8DSPContext::vp8_h_loop_filter16y
void(* vp8_h_loop_filter16y)(uint8_t *dst, ptrdiff_t stride, int flim_E, int flim_I, int hev_thresh)
Definition: vp8dsp.h:50
VP8DSPContext::put_vp8_bilinear_pixels_tab
vp8_mc_func put_vp8_bilinear_pixels_tab[3][3][3]
Definition: vp8dsp.h:81
VP8DSPContext::vp8_h_loop_filter16y_inner
void(* vp8_h_loop_filter16y_inner)(uint8_t *dst, ptrdiff_t stride, int flim_E, int flim_I, int hev_thresh)
Definition: vp8dsp.h:60
VP8DSPContext::vp8_luma_dc_wht
void(* vp8_luma_dc_wht)(int16_t block[4][4][16], int16_t dc[16])
Definition: vp8dsp.h:38
ff_vp8_idct_dc_add4uv_neon
void ff_vp8_idct_dc_add4uv_neon(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride)
VP8DSPContext
Definition: vp8dsp.h:37
dc
Tag MUST be and< 10hcoeff half pel interpolation filter coefficients, hcoeff[0] are the 2 middle coefficients[1] are the next outer ones and so on, resulting in a filter like:...eff[2], hcoeff[1], hcoeff[0], hcoeff[0], hcoeff[1], hcoeff[2] ... the sign of the coefficients is not explicitly stored but alternates after each coeff and coeff[0] is positive, so ...,+,-,+,-,+,+,-,+,-,+,... hcoeff[0] is not explicitly stored but found by subtracting the sum of all stored coefficients with signs from 32 hcoeff[0]=32 - hcoeff[1] - hcoeff[2] - ... a good choice for hcoeff and htaps is htaps=6 hcoeff={40,-10, 2} an alternative which requires more computations at both encoder and decoder side and may or may not be better is htaps=8 hcoeff={42,-14, 6,-2}ref_frames minimum of the number of available reference frames and max_ref_frames for example the first frame after a key frame always has ref_frames=1spatial_decomposition_type wavelet type 0 is a 9/7 symmetric compact integer wavelet 1 is a 5/3 symmetric compact integer wavelet others are reserved stored as delta from last, last is reset to 0 if always_reset||keyframeqlog quality(logarithmic quantizer scale) stored as delta from last, last is reset to 0 if always_reset||keyframemv_scale stored as delta from last, last is reset to 0 if always_reset||keyframe FIXME check that everything works fine if this changes between framesqbias dequantization bias stored as delta from last, last is reset to 0 if always_reset||keyframeblock_max_depth maximum depth of the block tree stored as delta from last, last is reset to 0 if always_reset||keyframequant_table quantization tableHighlevel bitstream structure:==============================--------------------------------------------|Header|--------------------------------------------|------------------------------------|||Block0||||split?||||yes no||||......... intra?||||:Block01 :yes no||||:Block02 :....... ..........||||:Block03 ::y DC ::ref index:||||:Block04 ::cb DC ::motion x :||||......... :cr DC ::motion y :||||....... ..........|||------------------------------------||------------------------------------|||Block1|||...|--------------------------------------------|------------ ------------ ------------|||Y subbands||Cb subbands||Cr subbands||||--- ---||--- ---||--- ---|||||LL0||HL0||||LL0||HL0||||LL0||HL0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||LH0||HH0||||LH0||HH0||||LH0||HH0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HL1||LH1||||HL1||LH1||||HL1||LH1|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HH1||HL2||||HH1||HL2||||HH1||HL2|||||...||...||...|||------------ ------------ ------------|--------------------------------------------Decoding process:=================------------|||Subbands|------------||||------------|Intra DC||||LL0 subband prediction ------------|\ Dequantization ------------------- \||Reference frames|\ IDWT|------- -------|Motion \|||Frame 0||Frame 1||Compensation . OBMC v -------|------- -------|--------------. \------> Frame n output Frame Frame<----------------------------------/|...|------------------- Range Coder:============Binary Range Coder:------------------- The implemented range coder is an adapted version based upon "Range encoding: an algorithm for removing redundancy from a digitised message." by G. N. N. Martin. The symbols encoded by the Snow range coder are bits(0|1). The associated probabilities are not fix but change depending on the symbol mix seen so far. bit seen|new state ---------+----------------------------------------------- 0|256 - state_transition_table[256 - old_state];1|state_transition_table[old_state];state_transition_table={ 0, 0, 0, 0, 0, 0, 0, 0, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 190, 191, 192, 194, 194, 195, 196, 197, 198, 199, 200, 201, 202, 202, 204, 205, 206, 207, 208, 209, 209, 210, 211, 212, 213, 215, 215, 216, 217, 218, 219, 220, 220, 222, 223, 224, 225, 226, 227, 227, 229, 229, 230, 231, 232, 234, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 248, 0, 0, 0, 0, 0, 0, 0};FIXME Range Coding of integers:------------------------- FIXME Neighboring Blocks:===================left and top are set to the respective blocks unless they are outside of the image in which case they are set to the Null block top-left is set to the top left block unless it is outside of the image in which case it is set to the left block if this block has no larger parent block or it is at the left side of its parent block and the top right block is not outside of the image then the top right block is used for top-right else the top-left block is used Null block y, cb, cr are 128 level, ref, mx and my are 0 Motion Vector Prediction:=========================1. the motion vectors of all the neighboring blocks are scaled to compensate for the difference of reference frames scaled_mv=(mv *(256 *(current_reference+1)/(mv.reference+1))+128)> the median of the scaled top and top right vectors is used as motion vector prediction the used motion vector is the sum of the predictor and(mvx_diff, mvy_diff) *mv_scale Intra DC Prediction block[y][x] dc[1]
Definition: snow.txt:400
VP8DSPContext::vp8_idct_dc_add
void(* vp8_idct_dc_add)(uint8_t *dst, int16_t block[16], ptrdiff_t stride)
Definition: vp8dsp.h:41
have_neon
#define have_neon(flags)
Definition: cpu.h:26
attributes.h
VP8DSPContext::vp8_v_loop_filter8uv_inner
void(* vp8_v_loop_filter8uv_inner)(uint8_t *dstU, uint8_t *dstV, ptrdiff_t stride, int flim_E, int flim_I, int hev_thresh)
Definition: vp8dsp.h:62
ff_vp8dsp_init_aarch64
av_cold void ff_vp8dsp_init_aarch64(VP8DSPContext *dsp)
Definition: vp8dsp_init_aarch64.c:101
VP8DSPContext::put_vp8_epel_pixels_tab
vp8_mc_func put_vp8_epel_pixels_tab[3][3][3]
first dimension: 4-log2(width) second dimension: 0 if no vertical interpolation is needed; 1 4-tap ve...
Definition: vp8dsp.h:80
VP8_BILIN
VP8_BILIN(16, neon)
VP8DSPContext::vp8_idct_dc_add4uv
void(* vp8_idct_dc_add4uv)(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride)
Definition: vp8dsp.h:44
VP8DSPContext::vp8_idct_dc_add4y
void(* vp8_idct_dc_add4y)(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride)
Definition: vp8dsp.h:42
ff_vp8_idct_dc_add4y_neon
void ff_vp8_idct_dc_add4y_neon(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride)
VP8DSPContext::vp8_idct_add
void(* vp8_idct_add)(uint8_t *dst, int16_t block[16], ptrdiff_t stride)
Definition: vp8dsp.h:40
ff_vp8_luma_dc_wht_neon
void ff_vp8_luma_dc_wht_neon(int16_t block[4][4][16], int16_t dc[16])
block
The exact code depends on how similar the blocks are and how related they are to the block
Definition: filter_design.txt:207
cpu.h
VP8_EPEL
VP8_EPEL(16, neon)