1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
|
/*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "config.h"
#include "libavutil/attributes.h"
#include "huffyuvencdsp.h"
#include "mathops.h"
// 0x7f7f7f7f or 0x7f7f7f7f7f7f7f7f or whatever, depending on the cpu's native arithmetic size
#define pb_7f (~0UL / 255 * 0x7f)
#define pb_80 (~0UL / 255 * 0x80)
static void diff_bytes_c(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, intptr_t w)
{
long i;
#if !HAVE_FAST_UNALIGNED
if (((long)src1 | (long)src2) & (sizeof(long) - 1)) {
for (i = 0; i + 7 < w; i += 8) {
dst[i + 0] = src1[i + 0] - src2[i + 0];
dst[i + 1] = src1[i + 1] - src2[i + 1];
dst[i + 2] = src1[i + 2] - src2[i + 2];
dst[i + 3] = src1[i + 3] - src2[i + 3];
dst[i + 4] = src1[i + 4] - src2[i + 4];
dst[i + 5] = src1[i + 5] - src2[i + 5];
dst[i + 6] = src1[i + 6] - src2[i + 6];
dst[i + 7] = src1[i + 7] - src2[i + 7];
}
} else
#endif
for (i = 0; i <= w - (int) sizeof(long); i += sizeof(long)) {
long a = *(long *) (src1 + i);
long b = *(long *) (src2 + i);
*(long *) (dst + i) = ((a | pb_80) - (b & pb_7f)) ^
((a ^ b ^ pb_80) & pb_80);
}
for (; i < w; i++)
dst[i + 0] = src1[i + 0] - src2[i + 0];
}
static void diff_int16_c(uint16_t *dst, const uint16_t *src1, const uint16_t *src2, unsigned mask, int w){
long i;
#if !HAVE_FAST_UNALIGNED
if((long)src2 & (sizeof(long)-1)){
for(i=0; i+3<w; i+=4){
dst[i+0] = (src1[i+0]-src2[i+0]) & mask;
dst[i+1] = (src1[i+1]-src2[i+1]) & mask;
dst[i+2] = (src1[i+2]-src2[i+2]) & mask;
dst[i+3] = (src1[i+3]-src2[i+3]) & mask;
}
}else
#endif
{
unsigned long pw_lsb = (mask >> 1) * 0x0001000100010001ULL;
unsigned long pw_msb = pw_lsb + 0x0001000100010001ULL;
for (i = 0; i <= w - (int)sizeof(long)/2; i += sizeof(long)/2) {
long a = *(long*)(src1+i);
long b = *(long*)(src2+i);
*(long*)(dst+i) = ((a|pw_msb) - (b&pw_lsb)) ^ ((a^b^pw_msb)&pw_msb);
}
}
for (; i<w; i++)
dst[i] = (src1[i] - src2[i]) & mask;
}
static void sub_hfyu_median_pred_c(uint8_t *dst, const uint8_t *src1,
const uint8_t *src2, intptr_t w,
int *left, int *left_top)
{
int i;
uint8_t l, lt;
l = *left;
lt = *left_top;
for (i = 0; i < w; i++) {
const int pred = mid_pred(l, src1[i], (l + src1[i] - lt) & 0xFF);
lt = src1[i];
l = src2[i];
dst[i] = l - pred;
}
*left = l;
*left_top = lt;
}
static void sub_hfyu_median_pred_int16_c(uint16_t *dst, const uint16_t *src1, const uint16_t *src2, unsigned mask, int w, int *left, int *left_top){
int i;
uint16_t l, lt;
l = *left;
lt = *left_top;
for(i=0; i<w; i++){
const int pred = mid_pred(l, src1[i], (l + src1[i] - lt) & mask);
lt = src1[i];
l = src2[i];
dst[i] = (l - pred) & mask;
}
*left = l;
*left_top = lt;
}
av_cold void ff_huffyuvencdsp_init(HuffYUVEncDSPContext *c, AVCodecContext *avctx)
{
c->diff_bytes = diff_bytes_c;
c->diff_int16 = diff_int16_c;
c->sub_hfyu_median_pred = sub_hfyu_median_pred_c;
c->sub_hfyu_median_pred_int16 = sub_hfyu_median_pred_int16_c;
if (ARCH_X86)
ff_huffyuvencdsp_init_x86(c, avctx);
}
|
