aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/vp3dsp.c
blob: 9b0b5d0a9c01653719453767535051f16dde4381 (plain) (blame)
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
/*
 * Copyright (C) 2004 the ffmpeg project
 *
 * This file is part of Libav.
 *
 * Libav 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.
 *
 * Libav 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 Libav; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

/**
 * @file
 * Standard C DSP-oriented functions cribbed from the original VP3
 * source code.
 */

#include "libavutil/attributes.h"
#include "libavutil/common.h"
#include "avcodec.h"
#include "dsputil.h"
#include "vp3dsp.h"

#define IdctAdjustBeforeShift 8
#define xC1S7 64277
#define xC2S6 60547
#define xC3S5 54491
#define xC4S4 46341
#define xC5S3 36410
#define xC6S2 25080
#define xC7S1 12785

#define M(a,b) (((a) * (b))>>16)

static av_always_inline void idct(uint8_t *dst, int stride, int16_t *input, int type)
{
    int16_t *ip = input;

    int A, B, C, D, Ad, Bd, Cd, Dd, E, F, G, H;
    int Ed, Gd, Add, Bdd, Fd, Hd;

    int i;

    /* Inverse DCT on the rows now */
    for (i = 0; i < 8; i++) {
        /* Check for non-zero values */
        if ( ip[0] | ip[1] | ip[2] | ip[3] | ip[4] | ip[5] | ip[6] | ip[7] ) {
            A = M(xC1S7, ip[1]) + M(xC7S1, ip[7]);
            B = M(xC7S1, ip[1]) - M(xC1S7, ip[7]);
            C = M(xC3S5, ip[3]) + M(xC5S3, ip[5]);
            D = M(xC3S5, ip[5]) - M(xC5S3, ip[3]);

            Ad = M(xC4S4, (A - C));
            Bd = M(xC4S4, (B - D));

            Cd = A + C;
            Dd = B + D;

            E = M(xC4S4, (ip[0] + ip[4]));
            F = M(xC4S4, (ip[0] - ip[4]));

            G = M(xC2S6, ip[2]) + M(xC6S2, ip[6]);
            H = M(xC6S2, ip[2]) - M(xC2S6, ip[6]);

            Ed = E - G;
            Gd = E + G;

            Add = F + Ad;
            Bdd = Bd - H;

            Fd = F - Ad;
            Hd = Bd + H;

            /*  Final sequence of operations over-write original inputs. */
            ip[0] = Gd + Cd ;
            ip[7] = Gd - Cd ;

            ip[1] = Add + Hd;
            ip[2] = Add - Hd;

            ip[3] = Ed + Dd ;
            ip[4] = Ed - Dd ;

            ip[5] = Fd + Bdd;
            ip[6] = Fd - Bdd;
        }

        ip += 8;            /* next row */
    }

    ip = input;

    for ( i = 0; i < 8; i++) {
        /* Check for non-zero values (bitwise or faster than ||) */
        if ( ip[1 * 8] | ip[2 * 8] | ip[3 * 8] |
             ip[4 * 8] | ip[5 * 8] | ip[6 * 8] | ip[7 * 8] ) {

            A = M(xC1S7, ip[1*8]) + M(xC7S1, ip[7*8]);
            B = M(xC7S1, ip[1*8]) - M(xC1S7, ip[7*8]);
            C = M(xC3S5, ip[3*8]) + M(xC5S3, ip[5*8]);
            D = M(xC3S5, ip[5*8]) - M(xC5S3, ip[3*8]);

            Ad = M(xC4S4, (A - C));
            Bd = M(xC4S4, (B - D));

            Cd = A + C;
            Dd = B + D;

            E = M(xC4S4, (ip[0*8] + ip[4*8])) + 8;
            F = M(xC4S4, (ip[0*8] - ip[4*8])) + 8;

            if(type==1){  //HACK
                E += 16*128;
                F += 16*128;
            }

            G = M(xC2S6, ip[2*8]) + M(xC6S2, ip[6*8]);
            H = M(xC6S2, ip[2*8]) - M(xC2S6, ip[6*8]);

            Ed = E - G;
            Gd = E + G;

            Add = F + Ad;
            Bdd = Bd - H;

            Fd = F - Ad;
            Hd = Bd + H;

            /* Final sequence of operations over-write original inputs. */
            if(type==0){
                ip[0*8] = (Gd + Cd )  >> 4;
                ip[7*8] = (Gd - Cd )  >> 4;

                ip[1*8] = (Add + Hd ) >> 4;
                ip[2*8] = (Add - Hd ) >> 4;

                ip[3*8] = (Ed + Dd )  >> 4;
                ip[4*8] = (Ed - Dd )  >> 4;

                ip[5*8] = (Fd + Bdd ) >> 4;
                ip[6*8] = (Fd - Bdd ) >> 4;
            }else if(type==1){
                dst[0*stride] = av_clip_uint8((Gd + Cd )  >> 4);
                dst[7*stride] = av_clip_uint8((Gd - Cd )  >> 4);

                dst[1*stride] = av_clip_uint8((Add + Hd ) >> 4);
                dst[2*stride] = av_clip_uint8((Add - Hd ) >> 4);

                dst[3*stride] = av_clip_uint8((Ed + Dd )  >> 4);
                dst[4*stride] = av_clip_uint8((Ed - Dd )  >> 4);

                dst[5*stride] = av_clip_uint8((Fd + Bdd ) >> 4);
                dst[6*stride] = av_clip_uint8((Fd - Bdd ) >> 4);
            }else{
                dst[0*stride] = av_clip_uint8(dst[0*stride] + ((Gd + Cd )  >> 4));
                dst[7*stride] = av_clip_uint8(dst[7*stride] + ((Gd - Cd )  >> 4));

                dst[1*stride] = av_clip_uint8(dst[1*stride] + ((Add + Hd ) >> 4));
                dst[2*stride] = av_clip_uint8(dst[2*stride] + ((Add - Hd ) >> 4));

                dst[3*stride] = av_clip_uint8(dst[3*stride] + ((Ed + Dd )  >> 4));
                dst[4*stride] = av_clip_uint8(dst[4*stride] + ((Ed - Dd )  >> 4));

                dst[5*stride] = av_clip_uint8(dst[5*stride] + ((Fd + Bdd ) >> 4));
                dst[6*stride] = av_clip_uint8(dst[6*stride] + ((Fd - Bdd ) >> 4));
            }

        } else {
            if(type==0){
                ip[0*8] =
                ip[1*8] =
                ip[2*8] =
                ip[3*8] =
                ip[4*8] =
                ip[5*8] =
                ip[6*8] =
                ip[7*8] = ((xC4S4 * ip[0*8] + (IdctAdjustBeforeShift<<16))>>20);
            }else if(type==1){
                dst[0*stride]=
                dst[1*stride]=
                dst[2*stride]=
                dst[3*stride]=
                dst[4*stride]=
                dst[5*stride]=
                dst[6*stride]=
                dst[7*stride]= av_clip_uint8(128 + ((xC4S4 * ip[0*8] + (IdctAdjustBeforeShift<<16))>>20));
            }else{
                if(ip[0*8]){
                    int v= ((xC4S4 * ip[0*8] + (IdctAdjustBeforeShift<<16))>>20);
                    dst[0*stride] = av_clip_uint8(dst[0*stride] + v);
                    dst[1*stride] = av_clip_uint8(dst[1*stride] + v);
                    dst[2*stride] = av_clip_uint8(dst[2*stride] + v);
                    dst[3*stride] = av_clip_uint8(dst[3*stride] + v);
                    dst[4*stride] = av_clip_uint8(dst[4*stride] + v);
                    dst[5*stride] = av_clip_uint8(dst[5*stride] + v);
                    dst[6*stride] = av_clip_uint8(dst[6*stride] + v);
                    dst[7*stride] = av_clip_uint8(dst[7*stride] + v);
                }
            }
        }

        ip++;            /* next column */
        dst++;
    }
}

static void vp3_idct_put_c(uint8_t *dest/*align 8*/, int line_size, DCTELEM *block/*align 16*/){
    idct(dest, line_size, block, 1);
}

static void vp3_idct_add_c(uint8_t *dest/*align 8*/, int line_size, DCTELEM *block/*align 16*/){
    idct(dest, line_size, block, 2);
}

static void vp3_idct_dc_add_c(uint8_t *dest/*align 8*/, int line_size,
                              const DCTELEM *block/*align 16*/){
    int i, dc = (block[0] + 15) >> 5;

    for(i = 0; i < 8; i++){
        dest[0] = av_clip_uint8(dest[0] + dc);
        dest[1] = av_clip_uint8(dest[1] + dc);
        dest[2] = av_clip_uint8(dest[2] + dc);
        dest[3] = av_clip_uint8(dest[3] + dc);
        dest[4] = av_clip_uint8(dest[4] + dc);
        dest[5] = av_clip_uint8(dest[5] + dc);
        dest[6] = av_clip_uint8(dest[6] + dc);
        dest[7] = av_clip_uint8(dest[7] + dc);
        dest += line_size;
    }
}

static void vp3_v_loop_filter_c(uint8_t *first_pixel, int stride,
                                int *bounding_values)
{
    unsigned char *end;
    int filter_value;
    const int nstride= -stride;

    for (end= first_pixel + 8; first_pixel < end; first_pixel++) {
        filter_value =
            (first_pixel[2 * nstride] - first_pixel[ stride])
         +3*(first_pixel[0          ] - first_pixel[nstride]);
        filter_value = bounding_values[(filter_value + 4) >> 3];
        first_pixel[nstride] = av_clip_uint8(first_pixel[nstride] + filter_value);
        first_pixel[0] = av_clip_uint8(first_pixel[0] - filter_value);
    }
}

static void vp3_h_loop_filter_c(uint8_t *first_pixel, int stride,
                                int *bounding_values)
{
    unsigned char *end;
    int filter_value;

    for (end= first_pixel + 8*stride; first_pixel != end; first_pixel += stride) {
        filter_value =
            (first_pixel[-2] - first_pixel[ 1])
         +3*(first_pixel[ 0] - first_pixel[-1]);
        filter_value = bounding_values[(filter_value + 4) >> 3];
        first_pixel[-1] = av_clip_uint8(first_pixel[-1] + filter_value);
        first_pixel[ 0] = av_clip_uint8(first_pixel[ 0] - filter_value);
    }
}

av_cold void ff_vp3dsp_init(VP3DSPContext *c, int flags)
{
    c->idct_put      = vp3_idct_put_c;
    c->idct_add      = vp3_idct_add_c;
    c->idct_dc_add   = vp3_idct_dc_add_c;
    c->v_loop_filter = vp3_v_loop_filter_c;
    c->h_loop_filter = vp3_h_loop_filter_c;

    c->idct_perm = FF_NO_IDCT_PERM;

    if (ARCH_ARM)
        ff_vp3dsp_init_arm(c, flags);
    if (ARCH_PPC)
        ff_vp3dsp_init_ppc(c, flags);
    if (ARCH_X86)
        ff_vp3dsp_init_x86(c, flags);
}