blob: 5cc4934c0ef6a19e0a62f25d3c99da12e19ebde5
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 "lossless_videoencdsp.h" |
22 | #include "mathops.h" |
23 | |
24 | // 0x7f7f7f7f or 0x7f7f7f7f7f7f7f7f or whatever, depending on the cpu's native arithmetic size |
25 | #define pb_7f (~0UL / 255 * 0x7f) |
26 | #define pb_80 (~0UL / 255 * 0x80) |
27 | |
28 | static void diff_bytes_c(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, intptr_t w) |
29 | { |
30 | long i; |
31 | |
32 | #if !HAVE_FAST_UNALIGNED |
33 | if (((long)src1 | (long)src2) & (sizeof(long) - 1)) { |
34 | for (i = 0; i + 7 < w; i += 8) { |
35 | dst[i + 0] = src1[i + 0] - src2[i + 0]; |
36 | dst[i + 1] = src1[i + 1] - src2[i + 1]; |
37 | dst[i + 2] = src1[i + 2] - src2[i + 2]; |
38 | dst[i + 3] = src1[i + 3] - src2[i + 3]; |
39 | dst[i + 4] = src1[i + 4] - src2[i + 4]; |
40 | dst[i + 5] = src1[i + 5] - src2[i + 5]; |
41 | dst[i + 6] = src1[i + 6] - src2[i + 6]; |
42 | dst[i + 7] = src1[i + 7] - src2[i + 7]; |
43 | } |
44 | } else |
45 | #endif |
46 | for (i = 0; i <= w - (int) sizeof(long); i += sizeof(long)) { |
47 | long a = *(long *) (src1 + i); |
48 | long b = *(long *) (src2 + i); |
49 | *(long *) (dst + i) = ((a | pb_80) - (b & pb_7f)) ^ |
50 | ((a ^ b ^ pb_80) & pb_80); |
51 | } |
52 | for (; i < w; i++) |
53 | dst[i + 0] = src1[i + 0] - src2[i + 0]; |
54 | } |
55 | |
56 | static void sub_median_pred_c(uint8_t *dst, const uint8_t *src1, |
57 | const uint8_t *src2, intptr_t w, |
58 | int *left, int *left_top) |
59 | { |
60 | int i; |
61 | uint8_t l, lt; |
62 | |
63 | l = *left; |
64 | lt = *left_top; |
65 | |
66 | for (i = 0; i < w; i++) { |
67 | const int pred = mid_pred(l, src1[i], (l + src1[i] - lt) & 0xFF); |
68 | lt = src1[i]; |
69 | l = src2[i]; |
70 | dst[i] = l - pred; |
71 | } |
72 | |
73 | *left = l; |
74 | *left_top = lt; |
75 | } |
76 | |
77 | av_cold void ff_llvidencdsp_init(LLVidEncDSPContext *c) |
78 | { |
79 | c->diff_bytes = diff_bytes_c; |
80 | c->sub_median_pred = sub_median_pred_c; |
81 | |
82 | if (ARCH_X86) |
83 | ff_llvidencdsp_init_x86(c); |
84 | } |
85 |