FFmpeg
rv34dsp.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 modify
7  * it under the terms of the GNU General Public License as published by
8  * the Free Software Foundation; either version 2 of the License, or
9  * (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
14  * GNU General Public License for more details.
15  *
16  * You should have received a copy of the GNU General Public License along
17  * with FFmpeg; if not, write to the Free Software Foundation, Inc.,
18  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
19  */
20 
21 #include "libavutil/mem.h"
22 #include "libavutil/mem_internal.h"
23 
24 #include "libavcodec/rv34dsp.h"
25 
26 #include "checkasm.h"
27 
28 #define BUF_SIZE 1024
29 
30 #define randomize(buf, len) \
31  do { \
32  for (int i = 0; i < len; i++) \
33  buf[i] = rnd(); \
34  } while (0)
35 
37  declare_func_emms(AV_CPU_FLAG_MMX, void, int16_t *block);
38 
39  if (check_func(s->rv34_inv_transform_dc, "rv34_inv_transform_dc")) {
40  LOCAL_ALIGNED_16(int16_t, p1, [BUF_SIZE]);
41  LOCAL_ALIGNED_16(int16_t, p2, [BUF_SIZE]);
42 
43  randomize(p1, BUF_SIZE);
44  memcpy(p2, p1, BUF_SIZE * sizeof(*p1));
45 
46  call_ref(p1);
47  call_new(p2);
48 
49  if (memcmp(p1, p2, BUF_SIZE * sizeof (*p1)) != 0) {
50  fail();
51  }
52 
53  bench_new(p1);
54  }
55 
56  report("rv34_inv_transform_dc");
57 }
58 
60  declare_func(void, uint8_t *dst, ptrdiff_t stride, int dc);
61 
62  if (check_func(s->rv34_idct_dc_add, "rv34_idct_dc_add")) {
63  LOCAL_ALIGNED_16(uint8_t, p1, [BUF_SIZE]);
64  LOCAL_ALIGNED_16(uint8_t, p2, [BUF_SIZE]);
65 
66  randomize(p1, BUF_SIZE);
67  memcpy(p2, p1, BUF_SIZE * sizeof(*p1));
68 
69  call_ref(p1, 4, 5);
70  call_new(p2, 4, 5);
71 
72  if (memcmp(p1, p2, BUF_SIZE * sizeof (*p1)) != 0) {
73  fail();
74  }
75 
76  bench_new(p1, 4, 5);
77  }
78 
79  report("rv34_idct_dc_add");
80 }
81 
83 {
84  RV34DSPContext s = { 0 };
86 
89 }
declare_func_emms
#define declare_func_emms(cpu_flags, ret,...)
Definition: checkasm.h:180
mem_internal.h
test_rv34_idct_dc_add
static void test_rv34_idct_dc_add(RV34DSPContext *s)
Definition: rv34dsp.c:59
check_func
#define check_func(func,...)
Definition: checkasm.h:174
ff_rv34dsp_init
av_cold void ff_rv34dsp_init(RV34DSPContext *c)
Definition: rv34dsp.c:131
call_ref
#define call_ref(...)
Definition: checkasm.h:189
fail
#define fail()
Definition: checkasm.h:183
checkasm.h
s
#define s(width, name)
Definition: cbs_vp9.c:198
LOCAL_ALIGNED_16
#define LOCAL_ALIGNED_16(t, v,...)
Definition: mem_internal.h:150
test_rv34_inv_transform_dc
static void test_rv34_inv_transform_dc(RV34DSPContext *s)
Definition: rv34dsp.c:36
call_new
#define call_new(...)
Definition: checkasm.h:292
RV34DSPContext
Definition: rv34dsp.h:57
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
rv34dsp.h
randomize
#define randomize(buf, len)
Definition: rv34dsp.c:30
checkasm_check_rv34dsp
void checkasm_check_rv34dsp(void)
Definition: rv34dsp.c:82
report
#define report
Definition: checkasm.h:186
bench_new
#define bench_new(...)
Definition: checkasm.h:363
stride
#define stride
Definition: h264pred_template.c:537
AV_CPU_FLAG_MMX
#define AV_CPU_FLAG_MMX
standard MMX
Definition: cpu.h:29
BUF_SIZE
#define BUF_SIZE
Definition: rv34dsp.c:28
mem.h
declare_func
#define declare_func(ret,...)
Definition: checkasm.h:178
block
The exact code depends on how similar the blocks are and how related they are to the block
Definition: filter_design.txt:207