FFmpeg
vp8dsp_init.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2024 Institue of Software Chinese Academy of Sciences (ISCAS).
3  *
4  * This file is part of FFmpeg.
5  *
6  * FFmpeg is free software; you can redistribute it and/or
7  * modify it under the terms of the GNU Lesser General Public
8  * License as published by the Free Software Foundation; either
9  * version 2.1 of the License, or (at your option) any later version.
10  *
11  * FFmpeg is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14  * Lesser General Public License for more details.
15  *
16  * You should have received a copy of the GNU Lesser General Public
17  * License along with FFmpeg; if not, write to the Free Software
18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19  */
20 
21 #include "config.h"
22 
23 #include "libavutil/attributes.h"
24 #include "libavutil/cpu.h"
25 #include "libavutil/riscv/cpu.h"
26 #include "libavcodec/vp8dsp.h"
27 #include "vp8dsp.h"
28 
29 void ff_vp8_luma_dc_wht_rvv(int16_t block[4][4][16], int16_t dc[16]);
30 void ff_vp8_idct_add_rvv(uint8_t *dst, int16_t block[16], ptrdiff_t stride);
31 void ff_vp8_idct_dc_add_rvv(uint8_t *dst, int16_t block[16], ptrdiff_t stride);
32 void ff_vp8_idct_dc_add4y_rvv(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride);
33 void ff_vp8_idct_dc_add4uv_rvv(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride);
34 
35 VP8_EPEL(16, rvi);
36 VP8_EPEL(8, rvi);
37 VP8_EPEL(4, rvi);
38 VP8_EPEL(16, rvv);
39 VP8_EPEL(8, rvv);
40 VP8_EPEL(4, rvv);
41 
42 VP8_BILIN(16, rvv);
43 VP8_BILIN(8, rvv);
44 VP8_BILIN(4, rvv);
45 
47 {
48 #if HAVE_RV
49  int flags = av_get_cpu_flags();
51 #if __riscv_xlen >= 64
52  c->put_vp8_epel_pixels_tab[0][0][0] = ff_put_vp8_pixels16_rvi;
53  c->put_vp8_epel_pixels_tab[1][0][0] = ff_put_vp8_pixels8_rvi;
54  c->put_vp8_bilinear_pixels_tab[0][0][0] = ff_put_vp8_pixels16_rvi;
55  c->put_vp8_bilinear_pixels_tab[1][0][0] = ff_put_vp8_pixels8_rvi;
56 #endif
57  c->put_vp8_epel_pixels_tab[2][0][0] = ff_put_vp8_pixels4_rvi;
58  c->put_vp8_bilinear_pixels_tab[2][0][0] = ff_put_vp8_pixels4_rvi;
59  }
60 #if HAVE_RVV
62  c->put_vp8_bilinear_pixels_tab[0][0][1] = ff_put_vp8_bilin16_h_rvv;
63  c->put_vp8_bilinear_pixels_tab[0][0][2] = ff_put_vp8_bilin16_h_rvv;
64  c->put_vp8_bilinear_pixels_tab[1][0][1] = ff_put_vp8_bilin8_h_rvv;
65  c->put_vp8_bilinear_pixels_tab[1][0][2] = ff_put_vp8_bilin8_h_rvv;
66  c->put_vp8_bilinear_pixels_tab[2][0][1] = ff_put_vp8_bilin4_h_rvv;
67  c->put_vp8_bilinear_pixels_tab[2][0][2] = ff_put_vp8_bilin4_h_rvv;
68 
69  c->put_vp8_bilinear_pixels_tab[0][1][0] = ff_put_vp8_bilin16_v_rvv;
70  c->put_vp8_bilinear_pixels_tab[0][2][0] = ff_put_vp8_bilin16_v_rvv;
71  c->put_vp8_bilinear_pixels_tab[1][1][0] = ff_put_vp8_bilin8_v_rvv;
72  c->put_vp8_bilinear_pixels_tab[1][2][0] = ff_put_vp8_bilin8_v_rvv;
73  c->put_vp8_bilinear_pixels_tab[2][1][0] = ff_put_vp8_bilin4_v_rvv;
74  c->put_vp8_bilinear_pixels_tab[2][2][0] = ff_put_vp8_bilin4_v_rvv;
75 
76  c->put_vp8_bilinear_pixels_tab[0][1][1] = ff_put_vp8_bilin16_hv_rvv;
77  c->put_vp8_bilinear_pixels_tab[0][1][2] = ff_put_vp8_bilin16_hv_rvv;
78  c->put_vp8_bilinear_pixels_tab[0][2][1] = ff_put_vp8_bilin16_hv_rvv;
79  c->put_vp8_bilinear_pixels_tab[0][2][2] = ff_put_vp8_bilin16_hv_rvv;
80  c->put_vp8_bilinear_pixels_tab[1][1][1] = ff_put_vp8_bilin8_hv_rvv;
81  c->put_vp8_bilinear_pixels_tab[1][1][2] = ff_put_vp8_bilin8_hv_rvv;
82  c->put_vp8_bilinear_pixels_tab[1][2][1] = ff_put_vp8_bilin8_hv_rvv;
83  c->put_vp8_bilinear_pixels_tab[1][2][2] = ff_put_vp8_bilin8_hv_rvv;
84  c->put_vp8_bilinear_pixels_tab[2][1][1] = ff_put_vp8_bilin4_hv_rvv;
85  c->put_vp8_bilinear_pixels_tab[2][1][2] = ff_put_vp8_bilin4_hv_rvv;
86  c->put_vp8_bilinear_pixels_tab[2][2][1] = ff_put_vp8_bilin4_hv_rvv;
87  c->put_vp8_bilinear_pixels_tab[2][2][2] = ff_put_vp8_bilin4_hv_rvv;
88 
89  if (flags & AV_CPU_FLAG_RVB) {
90  c->put_vp8_epel_pixels_tab[0][0][2] = ff_put_vp8_epel16_h6_rvv;
91  c->put_vp8_epel_pixels_tab[1][0][2] = ff_put_vp8_epel8_h6_rvv;
92  c->put_vp8_epel_pixels_tab[2][0][2] = ff_put_vp8_epel4_h6_rvv;
93  c->put_vp8_epel_pixels_tab[0][0][1] = ff_put_vp8_epel16_h4_rvv;
94  c->put_vp8_epel_pixels_tab[1][0][1] = ff_put_vp8_epel8_h4_rvv;
95  c->put_vp8_epel_pixels_tab[2][0][1] = ff_put_vp8_epel4_h4_rvv;
96 
97  c->put_vp8_epel_pixels_tab[0][2][0] = ff_put_vp8_epel16_v6_rvv;
98  c->put_vp8_epel_pixels_tab[1][2][0] = ff_put_vp8_epel8_v6_rvv;
99  c->put_vp8_epel_pixels_tab[2][2][0] = ff_put_vp8_epel4_v6_rvv;
100  c->put_vp8_epel_pixels_tab[0][1][0] = ff_put_vp8_epel16_v4_rvv;
101  c->put_vp8_epel_pixels_tab[1][1][0] = ff_put_vp8_epel8_v4_rvv;
102  c->put_vp8_epel_pixels_tab[2][1][0] = ff_put_vp8_epel4_v4_rvv;
103 #if __riscv_xlen <= 64
104  c->put_vp8_epel_pixels_tab[0][2][2] = ff_put_vp8_epel16_h6v6_rvv;
105  c->put_vp8_epel_pixels_tab[1][2][2] = ff_put_vp8_epel8_h6v6_rvv;
106  c->put_vp8_epel_pixels_tab[2][2][2] = ff_put_vp8_epel4_h6v6_rvv;
107  c->put_vp8_epel_pixels_tab[0][2][1] = ff_put_vp8_epel16_h4v6_rvv;
108  c->put_vp8_epel_pixels_tab[1][2][1] = ff_put_vp8_epel8_h4v6_rvv;
109  c->put_vp8_epel_pixels_tab[2][2][1] = ff_put_vp8_epel4_h4v6_rvv;
110  c->put_vp8_epel_pixels_tab[0][1][1] = ff_put_vp8_epel16_h4v4_rvv;
111  c->put_vp8_epel_pixels_tab[1][1][1] = ff_put_vp8_epel8_h4v4_rvv;
112  c->put_vp8_epel_pixels_tab[2][1][1] = ff_put_vp8_epel4_h4v4_rvv;
113  c->put_vp8_epel_pixels_tab[0][1][2] = ff_put_vp8_epel16_h6v4_rvv;
114  c->put_vp8_epel_pixels_tab[1][1][2] = ff_put_vp8_epel8_h6v4_rvv;
115  c->put_vp8_epel_pixels_tab[2][1][2] = ff_put_vp8_epel4_h6v4_rvv;
116 #endif
117  }
118  }
119 #endif
120 #endif
121 }
122 
124 {
125 #if HAVE_RVV
126  int flags = av_get_cpu_flags();
127 
129 #if __riscv_xlen >= 64
131  c->vp8_luma_dc_wht = ff_vp8_luma_dc_wht_rvv;
132 #endif
133  c->vp8_idct_add = ff_vp8_idct_add_rvv;
134  c->vp8_idct_dc_add = ff_vp8_idct_dc_add_rvv;
135  c->vp8_idct_dc_add4y = ff_vp8_idct_dc_add4y_rvv;
137  c->vp8_idct_dc_add4uv = ff_vp8_idct_dc_add4uv_rvv;
138  }
139 #endif
140 }
ff_vp8dsp_init_riscv
av_cold void ff_vp8dsp_init_riscv(VP8DSPContext *c)
Definition: vp8dsp_init.c:123
av_get_cpu_flags
int av_get_cpu_flags(void)
Return the flags which specify extensions supported by the CPU.
Definition: cpu.c:107
ff_vp78dsp_init_riscv
av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c)
Definition: vp8dsp_init.c:46
AV_CPU_FLAG_RVB
#define AV_CPU_FLAG_RVB
B (bit manipulations)
Definition: cpu.h:102
ff_vp8_idct_add_rvv
void ff_vp8_idct_add_rvv(uint8_t *dst, int16_t block[16], ptrdiff_t stride)
VP8_EPEL
VP8_EPEL(16, rvi)
av_cold
#define av_cold
Definition: attributes.h:90
vp8dsp.h
ff_rv_vlen_least
static bool ff_rv_vlen_least(unsigned int bits)
Checks that the vector bit-size is at least the given value.
Definition: cpu.h:65
cpu.h
ff_vp8_idct_dc_add4y_rvv
void ff_vp8_idct_dc_add4y_rvv(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride)
c
Undefined Behavior In the C some operations are like signed integer dereferencing freed accessing outside allocated Undefined Behavior must not occur in a C it is not safe even if the output of undefined operations is unused The unsafety may seem nit picking but Optimizing compilers have in fact optimized code on the assumption that no undefined Behavior occurs Optimizing code based on wrong assumptions can and has in some cases lead to effects beyond the output of computations The signed integer overflow problem in speed critical code Code which is highly optimized and works with signed integers sometimes has the problem that often the output of the computation does not c
Definition: undefined.txt:32
vp8dsp.h
VP8DSPContext
Definition: vp8dsp.h:37
VP8_BILIN
VP8_BILIN(16, rvv)
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
dst
uint8_t ptrdiff_t const uint8_t ptrdiff_t int intptr_t intptr_t int int16_t * dst
Definition: dsp.h:83
cpu.h
ff_vp8_luma_dc_wht_rvv
void ff_vp8_luma_dc_wht_rvv(int16_t block[4][4][16], int16_t dc[16])
attributes.h
ff_vp8_idct_dc_add_rvv
void ff_vp8_idct_dc_add_rvv(uint8_t *dst, int16_t block[16], ptrdiff_t stride)
AV_CPU_FLAG_RV_MISALIGNED
#define AV_CPU_FLAG_RV_MISALIGNED
Fast misaligned accesses.
Definition: cpu.h:101
AV_CPU_FLAG_RVV_I32
#define AV_CPU_FLAG_RVV_I32
Vectors of 8/16/32-bit int's *‍/.
Definition: cpu.h:92
stride
#define stride
Definition: h264pred_template.c:537
ff_vp8_idct_dc_add4uv_rvv
void ff_vp8_idct_dc_add4uv_rvv(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride)
flags
#define flags(name, subs,...)
Definition: cbs_av1.c:482
block
The exact code depends on how similar the blocks are and how related they are to the block
Definition: filter_design.txt:207
AV_CPU_FLAG_RVV_I64
#define AV_CPU_FLAG_RVV_I64
Vectors of 64-bit int's *‍/.
Definition: cpu.h:94