blob: 427d118be45189ec75cd548ac96957800bd9c574
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 "huffyuvencdsp.h" |
22 | #include "mathops.h" |
23 | |
24 | // 0x00010001 or 0x0001000100010001 or whatever, depending on the cpu's native arithmetic size |
25 | #define pw_1 (ULONG_MAX / UINT16_MAX) |
26 | |
27 | static void diff_int16_c(uint16_t *dst, const uint16_t *src1, const uint16_t *src2, unsigned mask, int w){ |
28 | long i; |
29 | #if !HAVE_FAST_UNALIGNED |
30 | if((long)src2 & (sizeof(long)-1)){ |
31 | for(i=0; i+3<w; i+=4){ |
32 | dst[i+0] = (src1[i+0]-src2[i+0]) & mask; |
33 | dst[i+1] = (src1[i+1]-src2[i+1]) & mask; |
34 | dst[i+2] = (src1[i+2]-src2[i+2]) & mask; |
35 | dst[i+3] = (src1[i+3]-src2[i+3]) & mask; |
36 | } |
37 | }else |
38 | #endif |
39 | { |
40 | unsigned long pw_lsb = (mask >> 1) * pw_1; |
41 | unsigned long pw_msb = pw_lsb + pw_1; |
42 | |
43 | for (i = 0; i <= w - (int)sizeof(long)/2; i += sizeof(long)/2) { |
44 | long a = *(long*)(src1+i); |
45 | long b = *(long*)(src2+i); |
46 | *(long*)(dst+i) = ((a|pw_msb) - (b&pw_lsb)) ^ ((a^b^pw_msb)&pw_msb); |
47 | } |
48 | } |
49 | for (; i<w; i++) |
50 | dst[i] = (src1[i] - src2[i]) & mask; |
51 | } |
52 | |
53 | 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){ |
54 | int i; |
55 | uint16_t l, lt; |
56 | |
57 | l = *left; |
58 | lt = *left_top; |
59 | |
60 | for(i=0; i<w; i++){ |
61 | const int pred = mid_pred(l, src1[i], (l + src1[i] - lt) & mask); |
62 | lt = src1[i]; |
63 | l = src2[i]; |
64 | dst[i] = (l - pred) & mask; |
65 | } |
66 | |
67 | *left = l; |
68 | *left_top = lt; |
69 | } |
70 | |
71 | av_cold void ff_huffyuvencdsp_init(HuffYUVEncDSPContext *c, AVCodecContext *avctx) |
72 | { |
73 | c->diff_int16 = diff_int16_c; |
74 | c->sub_hfyu_median_pred_int16 = sub_hfyu_median_pred_int16_c; |
75 | |
76 | if (ARCH_X86) |
77 | ff_huffyuvencdsp_init_x86(c, avctx); |
78 | } |
79 |