Line | Branch | Exec | Source |
---|---|---|---|
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 "huffyuvencdsp.h" | ||
23 | #include "mathops.h" | ||
24 | |||
25 | #if HAVE_FAST_64BIT | ||
26 | #define BITS 64 | ||
27 | typedef uint64_t uint_native; | ||
28 | #else | ||
29 | #define BITS 32 | ||
30 | typedef uint32_t uint_native; | ||
31 | #endif | ||
32 | #define RN AV_JOIN(AV_RN, BITS) | ||
33 | #define RNA AV_JOIN(AV_JOIN(AV_RN, BITS), A) | ||
34 | #define WNA AV_JOIN(AV_JOIN(AV_WN, BITS), A) | ||
35 | |||
36 | // 0x7f7f7f7f or 0x7f7f7f7f7f7f7f7f or whatever, depending on the cpu's native arithmetic size | ||
37 | #define pb_7f (~(uint_native)0 / 255 * 0x7f) | ||
38 | #define pb_80 (~(uint_native)0 / 255 * 0x80) | ||
39 | |||
40 | // 0x00010001 or 0x0001000100010001 or whatever, depending on the cpu's native arithmetic size | ||
41 | #define pw_1 ((uint_native)-1 / UINT16_MAX) | ||
42 | |||
43 | 488200 | static void diff_int16_c(uint16_t *dst, const uint16_t *src1, const uint16_t *src2, unsigned mask, int w){ | |
44 | long i; | ||
45 | #if !HAVE_FAST_UNALIGNED | ||
46 | if ((uintptr_t)src2 & (sizeof(uint_native) - 1)) { | ||
47 | for(i=0; i+3<w; i+=4){ | ||
48 | dst[i+0] = (src1[i+0]-src2[i+0]) & mask; | ||
49 | dst[i+1] = (src1[i+1]-src2[i+1]) & mask; | ||
50 | dst[i+2] = (src1[i+2]-src2[i+2]) & mask; | ||
51 | dst[i+3] = (src1[i+3]-src2[i+3]) & mask; | ||
52 | } | ||
53 | }else | ||
54 | #endif | ||
55 | { | ||
56 | 488200 | uint_native pw_lsb = (mask >> 1) * pw_1; | |
57 | 488200 | uint_native pw_msb = pw_lsb + pw_1; | |
58 | |||
59 |
2/2✓ Branch 0 taken 33350400 times.
✓ Branch 1 taken 488200 times.
|
33838600 | for (i = 0; i <= w - (int)sizeof(uint_native)/2; i += sizeof(uint_native)/2) { |
60 | 33350400 | uint_native a = RNA(src1 + i); | |
61 | 33350400 | uint_native b = RN (src2 + i); | |
62 | 33350400 | WNA(dst + i, ((a | pw_msb) - (b & pw_lsb)) ^ ((a^b^pw_msb) & pw_msb)); | |
63 | } | ||
64 | } | ||
65 |
2/2✓ Branch 0 taken 26900 times.
✓ Branch 1 taken 488200 times.
|
515100 | for (; i<w; i++) |
66 | 26900 | dst[i] = (src1[i] - src2[i]) & mask; | |
67 | 488200 | } | |
68 | |||
69 | ✗ | 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){ | |
70 | int i; | ||
71 | uint16_t l, lt; | ||
72 | |||
73 | ✗ | l = *left; | |
74 | ✗ | lt = *left_top; | |
75 | |||
76 | ✗ | for(i=0; i<w; i++){ | |
77 | ✗ | const int pred = mid_pred(l, src1[i], (l + src1[i] - lt) & mask); | |
78 | ✗ | lt = src1[i]; | |
79 | ✗ | l = src2[i]; | |
80 | ✗ | dst[i] = (l - pred) & mask; | |
81 | } | ||
82 | |||
83 | ✗ | *left = l; | |
84 | ✗ | *left_top = lt; | |
85 | ✗ | } | |
86 | |||
87 | 32 | av_cold void ff_huffyuvencdsp_init(HuffYUVEncDSPContext *c, enum AVPixelFormat pix_fmt) | |
88 | { | ||
89 | 32 | c->diff_int16 = diff_int16_c; | |
90 | 32 | c->sub_hfyu_median_pred_int16 = sub_hfyu_median_pred_int16_c; | |
91 | |||
92 | #if ARCH_X86 | ||
93 | 32 | ff_huffyuvencdsp_init_x86(c, pix_fmt); | |
94 | #endif | ||
95 | 32 | } | |
96 |