FFmpeg
lossless_videoencdsp.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 "config.h"
20 #include "libavutil/attributes.h"
21 #include "libavutil/intreadwrite.h"
22 #include "lossless_videoencdsp.h"
23 #include "mathops.h"
24 
25 #if HAVE_FAST_64BIT
26 typedef uint64_t uint_native;
27 #define READ AV_RN64
28 #define WRITE AV_WN64
29 #else
30 typedef uint32_t uint_native;
31 #define READ AV_RN32
32 #define WRITE AV_WN32
33 #endif
34 // 0x7f7f7f7f or 0x7f7f7f7f7f7f7f7f or whatever, depending on the cpu's native arithmetic size
35 #define pb_7f (~(uint_native)0 / 255 * 0x7f)
36 #define pb_80 (~(uint_native)0 / 255 * 0x80)
37 
38 static void diff_bytes_c(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, intptr_t w)
39 {
40  long i;
41 
42 #if !HAVE_FAST_UNALIGNED
43  if (((uintptr_t)src1 | (uintptr_t)src2) & (sizeof(uint_native) - 1)) {
44  for (i = 0; i + 7 < w; i += 8) {
45  dst[i + 0] = src1[i + 0] - src2[i + 0];
46  dst[i + 1] = src1[i + 1] - src2[i + 1];
47  dst[i + 2] = src1[i + 2] - src2[i + 2];
48  dst[i + 3] = src1[i + 3] - src2[i + 3];
49  dst[i + 4] = src1[i + 4] - src2[i + 4];
50  dst[i + 5] = src1[i + 5] - src2[i + 5];
51  dst[i + 6] = src1[i + 6] - src2[i + 6];
52  dst[i + 7] = src1[i + 7] - src2[i + 7];
53  }
54  } else
55 #endif
56  for (i = 0; i <= w - (int) sizeof(uint_native); i += sizeof(uint_native)) {
57  uint_native a = READ(src1 + i);
58  uint_native b = READ(src2 + i);
59  WRITE(dst + i, ((a | pb_80) - (b & pb_7f)) ^ ((a ^ b ^ pb_80) & pb_80));
60  }
61  for (; i < w; i++)
62  dst[i + 0] = src1[i + 0] - src2[i + 0];
63 }
64 
65 static void sub_median_pred_c(uint8_t *dst, const uint8_t *src1,
66  const uint8_t *src2, intptr_t w,
67  int *left, int *left_top)
68 {
69  int i;
70  uint8_t l, lt;
71 
72  l = *left;
73  lt = *left_top;
74 
75  for (i = 0; i < w; i++) {
76  const int pred = mid_pred(l, src1[i], (l + src1[i] - lt) & 0xFF);
77  lt = src1[i];
78  l = src2[i];
79  dst[i] = l - pred;
80  }
81 
82  *left = l;
83  *left_top = lt;
84 }
85 
86 static void sub_left_predict_c(uint8_t *dst, const uint8_t *src,
87  ptrdiff_t stride, ptrdiff_t width, int height)
88 {
89  int i, j;
90  uint8_t prev = 0x80; /* Set the initial value */
91  for (j = 0; j < height; j++) {
92  for (i = 0; i < width; i++) {
93  *dst++ = src[i] - prev;
94  prev = src[i];
95  }
96  src += stride;
97  }
98 }
99 
101 {
102  c->diff_bytes = diff_bytes_c;
103  c->sub_median_pred = sub_median_pred_c;
104  c->sub_left_predict = sub_left_predict_c;
105 
106 #if ARCH_RISCV
108 #elif ARCH_X86
110 #endif
111 }
WRITE
#define WRITE
Definition: lossless_videoencdsp.c:32
src1
const pixel * src1
Definition: h264pred_template.c:421
w
uint8_t w
Definition: llviddspenc.c:38
b
#define b
Definition: input.c:41
pb_7f
#define pb_7f
Definition: lossless_videoencdsp.c:35
READ
#define READ
Definition: lossless_videoencdsp.c:31
sub_median_pred_c
static void sub_median_pred_c(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, intptr_t w, int *left, int *left_top)
Definition: lossless_videoencdsp.c:65
uint_native
uint32_t uint_native
Definition: lossless_videoencdsp.c:30
av_cold
#define av_cold
Definition: attributes.h:90
intreadwrite.h
ff_llvidencdsp_init_x86
void ff_llvidencdsp_init_x86(LLVidEncDSPContext *c)
Definition: lossless_videoencdsp_init.c:84
pb_80
#define pb_80
Definition: lossless_videoencdsp.c:36
diff_bytes_c
static void diff_bytes_c(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, intptr_t w)
Definition: lossless_videoencdsp.c:38
ff_llvidencdsp_init_riscv
void ff_llvidencdsp_init_riscv(LLVidEncDSPContext *c)
Definition: llvidencdsp_init.c:30
mathops.h
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
ff_llvidencdsp_init
av_cold void ff_llvidencdsp_init(LLVidEncDSPContext *c)
Definition: lossless_videoencdsp.c:100
height
#define height
Definition: dsp.h:85
dst
uint8_t ptrdiff_t const uint8_t ptrdiff_t int intptr_t intptr_t int int16_t * dst
Definition: dsp.h:83
a
The reader does not expect b to be semantically here and if the code is changed by maybe adding a a division or other the signedness will almost certainly be mistaken To avoid this confusion a new type was SUINT is the C unsigned type but it holds a signed int to use the same example SUINT a
Definition: undefined.txt:41
attributes.h
lossless_videoencdsp.h
i
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:256
src2
const pixel * src2
Definition: h264pred_template.c:422
sub_left_predict_c
static void sub_left_predict_c(uint8_t *dst, const uint8_t *src, ptrdiff_t stride, ptrdiff_t width, int height)
Definition: lossless_videoencdsp.c:86
LLVidEncDSPContext
Definition: lossless_videoencdsp.h:25
stride
#define stride
Definition: h264pred_template.c:537
mid_pred
#define mid_pred
Definition: mathops.h:96
pred
static const float pred[4]
Definition: siprdata.h:259
left
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 left
Definition: snow.txt:386
width
#define width
Definition: dsp.h:85
uint_native
uint32_t uint_native
Definition: huffyuvencdsp.c:30
src
#define src
Definition: vp8dsp.c:248