FFmpeg
huffyuvdsp.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2016 Alexandra Hájková
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 <string.h>
22 
23 #include "libavutil/common.h"
24 #include "libavutil/intreadwrite.h"
25 #include "libavutil/mem.h"
26 
27 #include "libavcodec/huffyuvdsp.h"
28 
29 #include "checkasm.h"
30 
31 #define randomize_buffers(buf, size) \
32  do { \
33  int j; \
34  for (j = 0; j < size; j++) \
35  buf[j] = rnd() & 0xFFFF; \
36  } while (0)
37 
38 static void check_add_int16(HuffYUVDSPContext *c, unsigned mask, int width, const char * name)
39 {
40  uint16_t *src0 = av_mallocz(width * sizeof(uint16_t));
41  uint16_t *src1 = av_mallocz(width * sizeof(uint16_t));
42  uint16_t *dst0 = av_mallocz(width * sizeof(uint16_t));
43  uint16_t *dst1 = av_mallocz(width * sizeof(uint16_t));
44 
45  declare_func(void, uint16_t *dst, const uint16_t *src, unsigned mask, int w);
46 
47  if (!src0 || !src1 || !dst0 || !dst1)
48  fail();
49 
51  memcpy(src1, src0, width * sizeof(uint16_t));
52 
53  if (check_func(c->add_int16, "%s", name)) {
54  call_ref(dst0, src0, mask, width);
55  call_new(dst1, src1, mask, width);
56  if (memcmp(dst0, dst1, width * sizeof(uint16_t)))
57  fail();
58  bench_new(dst1, src1, mask, width);
59  }
60 
61  av_free(src0);
62  av_free(src1);
63  av_free(dst0);
64  av_free(dst1);
65 }
66 
68 {
69 #define BUF_SIZE 1080
70  uint8_t src[4 * BUF_SIZE], dst0[4 * BUF_SIZE], dst1[4 * BUF_SIZE];
71  uint8_t left[4], left0[4], left1[4];
72 
73  declare_func(void, uint8_t *d, const uint8_t *s, intptr_t w, uint8_t *l);
74 
75  randomize_buffers(src, sizeof (src));
76  randomize_buffers(left, sizeof (left));
77  memcpy(left0, left, sizeof (left));
78  memcpy(left1, left, sizeof (left));
79 
80  if (check_func(c->add_hfyu_left_pred_bgr32, "add_hfyu_left_pred_bgr32")) {
81  call_ref(dst0, src, BUF_SIZE, left0);
82  call_new(dst1, src, BUF_SIZE, left1);
83 
84  if (memcmp(dst0, dst1, sizeof (dst0)) != 0 ||
85  memcmp(left0, left1, sizeof (left0)) != 0) {
86  fail();
87  }
88 
89  bench_new(dst1, src, BUF_SIZE, left);
90  }
91 
92  report("add_hfyu_left_pred_bgr32");
93 }
94 
96 {
98  int width = 16 * av_clip(rnd(), 16, 128);
99 
101 
102  /*! test width not multiple of mmsize */
103  check_add_int16(&c, 65535, width, "add_int16_rnd_width");
104  report("add_int16_rnd_width");
105 
106  /*! test always with the same size (for perf test) */
107  check_add_int16(&c, 65535, 16*128, "add_int16_128");
108  report("add_int16_128");
109 
111 }
HuffYUVDSPContext
Definition: huffyuvdsp.h:25
name
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf default minimum maximum flags name is the option name
Definition: writing_filters.txt:88
av_clip
#define av_clip
Definition: common.h:99
src1
const pixel * src1
Definition: h264pred_template.c:421
w
uint8_t w
Definition: llviddspenc.c:38
huffyuvdsp.h
check_func
#define check_func(func,...)
Definition: checkasm.h:173
check_add_hfyu_left_pred_bgr32
static void check_add_hfyu_left_pred_bgr32(HuffYUVDSPContext *c)
Definition: huffyuvdsp.c:67
call_ref
#define call_ref(...)
Definition: checkasm.h:188
fail
#define fail()
Definition: checkasm.h:182
checkasm.h
checkasm_check_huffyuvdsp
void checkasm_check_huffyuvdsp(void)
Definition: huffyuvdsp.c:95
rnd
#define rnd()
Definition: checkasm.h:166
mask
static const uint16_t mask[17]
Definition: lzw.c:38
width
#define width
intreadwrite.h
s
#define s(width, name)
Definition: cbs_vp9.c:198
call_new
#define call_new(...)
Definition: checkasm.h:291
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_huffyuvdsp_init
av_cold void ff_huffyuvdsp_init(HuffYUVDSPContext *c, enum AVPixelFormat pix_fmt)
Definition: huffyuvdsp.c:84
randomize_buffers
#define randomize_buffers(buf, size)
Definition: huffyuvdsp.c:31
BUF_SIZE
#define BUF_SIZE
report
#define report
Definition: checkasm.h:185
bench_new
#define bench_new(...)
Definition: checkasm.h:362
common.h
check_add_int16
static void check_add_int16(HuffYUVDSPContext *c, unsigned mask, int width, const char *name)
Definition: huffyuvdsp.c:38
av_mallocz
void * av_mallocz(size_t size)
Allocate a memory block with alignment suitable for all memory accesses (including vectors if availab...
Definition: mem.c:256
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
src0
const pixel *const src0
Definition: h264pred_template.c:420
AV_PIX_FMT_YUV422P
@ AV_PIX_FMT_YUV422P
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
Definition: pixfmt.h:77
mem.h
declare_func
#define declare_func(ret,...)
Definition: checkasm.h:177
av_free
#define av_free(p)
Definition: tableprint_vlc.h:33
src
INIT_CLIP pixel * src
Definition: h264pred_template.c:418
d
d
Definition: ffmpeg_filter.c:424