FFmpeg
vf_gradfun_init.c
Go to the documentation of this file.
1 /*
2  * Copyright (C) 2009 Loren Merritt <lorenm@u.washington.edu>
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 #include "libavutil/attributes.h"
23 #include "libavutil/cpu.h"
24 #include "libavutil/x86/cpu.h"
25 #include "libavfilter/gradfun.h"
26 
27 void ff_gradfun_filter_line_mmxext(intptr_t x, uint8_t *dst, const uint8_t *src,
28  const uint16_t *dc, int thresh,
29  const uint16_t *dithers);
30 void ff_gradfun_filter_line_ssse3(intptr_t x, uint8_t *dst, const uint8_t *src,
31  const uint16_t *dc, int thresh,
32  const uint16_t *dithers);
33 
34 void ff_gradfun_blur_line_movdqa_sse2(intptr_t x, uint16_t *buf,
35  const uint16_t *buf1, uint16_t *dc,
36  const uint8_t *src1, const uint8_t *src2);
37 void ff_gradfun_blur_line_movdqu_sse2(intptr_t x, uint16_t *buf,
38  const uint16_t *buf1, uint16_t *dc,
39  const uint8_t *src1, const uint8_t *src2);
40 
41 #if HAVE_X86ASM
42 static void gradfun_filter_line_mmxext(uint8_t *dst, const uint8_t *src,
43  const uint16_t *dc,
44  int width, int thresh,
45  const uint16_t *dithers)
46 {
47  intptr_t x;
48  if (width & 3) {
49  x = width & ~3;
50  ff_gradfun_filter_line_c(dst + x, src + x, dc + x / 2,
51  width - x, thresh, dithers);
52  width = x;
53  }
54  x = -width;
56  thresh, dithers);
57 }
58 
59 static void gradfun_filter_line_ssse3(uint8_t *dst, const uint8_t *src, const uint16_t *dc,
60  int width, int thresh,
61  const uint16_t *dithers)
62 {
63  intptr_t x;
64  if (width & 7) {
65  // could be 10% faster if I somehow eliminated this
66  x = width & ~7;
67  ff_gradfun_filter_line_c(dst + x, src + x, dc + x / 2,
68  width - x, thresh, dithers);
69  width = x;
70  }
71  x = -width;
73  thresh, dithers);
74 }
75 
76 static void gradfun_blur_line_sse2(uint16_t *dc, uint16_t *buf, const uint16_t *buf1,
77  const uint8_t *src, int src_linesize, int width)
78 {
79  intptr_t x = -2 * width;
80  if (((intptr_t) src | src_linesize) & 15)
82  dc + width, src + width * 2,
83  src + width * 2 + src_linesize);
84  else
86  dc + width, src + width * 2,
87  src + width * 2 + src_linesize);
88 }
89 #endif /* HAVE_X86ASM */
90 
92 {
93 #if HAVE_X86ASM
95 
97  gf->filter_line = gradfun_filter_line_mmxext;
99  gf->filter_line = gradfun_filter_line_ssse3;
100 
102  gf->blur_line = gradfun_blur_line_sse2;
103 #endif /* HAVE_X86ASM */
104 }
cpu.h
GradFunContext::filter_line
void(* filter_line)(uint8_t *dst, const uint8_t *src, const uint16_t *dc, int width, int thresh, const uint16_t *dithers)
DSP functions.
Definition: gradfun.h:38
src1
const pixel * src1
Definition: h264pred_template.c:421
av_get_cpu_flags
int av_get_cpu_flags(void)
Return the flags which specify extensions supported by the CPU.
Definition: cpu.c:101
ff_gradfun_filter_line_ssse3
void ff_gradfun_filter_line_ssse3(intptr_t x, uint8_t *dst, const uint8_t *src, const uint16_t *dc, int thresh, const uint16_t *dithers)
cpu_flags
static atomic_int cpu_flags
Definition: cpu.c:52
av_cold
#define av_cold
Definition: attributes.h:90
ff_gradfun_blur_line_movdqu_sse2
void ff_gradfun_blur_line_movdqu_sse2(intptr_t x, uint16_t *buf, const uint16_t *buf1, uint16_t *dc, const uint8_t *src1, const uint8_t *src2)
width
#define width
ff_gradfun_filter_line_c
void ff_gradfun_filter_line_c(uint8_t *dst, const uint8_t *src, const uint16_t *dc, int width, int thresh, const uint16_t *dithers)
Definition: vf_gradfun.c:57
dithers
static const uint8_t dithers[8][8][8]
Definition: swscale_unscaled.c:38
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
ff_gradfun_init_x86
av_cold void ff_gradfun_init_x86(GradFunContext *gf)
Definition: vf_gradfun_init.c:91
GradFunContext::blur_line
void(* blur_line)(uint16_t *dc, uint16_t *buf, const uint16_t *buf1, const uint8_t *src, int src_linesize, int width)
Definition: gradfun.h:39
cpu.h
attributes.h
EXTERNAL_SSE2
#define EXTERNAL_SSE2(flags)
Definition: cpu.h:59
src2
const pixel * src2
Definition: h264pred_template.c:422
ff_gradfun_filter_line_mmxext
void ff_gradfun_filter_line_mmxext(intptr_t x, uint8_t *dst, const uint8_t *src, const uint16_t *dc, int thresh, const uint16_t *dithers)
ff_gradfun_blur_line_movdqa_sse2
void ff_gradfun_blur_line_movdqa_sse2(intptr_t x, uint16_t *buf, const uint16_t *buf1, uint16_t *dc, const uint8_t *src1, const uint8_t *src2)
gradfun.h
src
INIT_CLIP pixel * src
Definition: h264pred_template.c:418
EXTERNAL_SSSE3
#define EXTERNAL_SSSE3(flags)
Definition: cpu.h:65
GradFunContext
Holds instance-specific information for gradfun.
Definition: gradfun.h:28
EXTERNAL_MMXEXT
#define EXTERNAL_MMXEXT(flags)
Definition: cpu.h:57