Coverage Report

Created: 2024-09-06 07:53

/src/ffmpeg/libavcodec/x86/vc1dsp_mmx.c
Line
Count
Source (jump to first uncovered line)
1
/*
2
 * VC-1 and WMV3 - DSP functions MMX-optimized
3
 * Copyright (c) 2007 Christophe GISQUET <christophe.gisquet@free.fr>
4
 *
5
 * Permission is hereby granted, free of charge, to any person
6
 * obtaining a copy of this software and associated documentation
7
 * files (the "Software"), to deal in the Software without
8
 * restriction, including without limitation the rights to use,
9
 * copy, modify, merge, publish, distribute, sublicense, and/or sell
10
 * copies of the Software, and to permit persons to whom the
11
 * Software is furnished to do so, subject to the following
12
 * conditions:
13
 *
14
 * The above copyright notice and this permission notice shall be
15
 * included in all copies or substantial portions of the Software.
16
 *
17
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
18
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
19
 * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
20
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
21
 * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
22
 * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
23
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
24
 * OTHER DEALINGS IN THE SOFTWARE.
25
 */
26
27
#include "libavutil/attributes.h"
28
#include "libavutil/mem_internal.h"
29
#include "libavutil/x86/asm.h"
30
#include "libavutil/x86/cpu.h"
31
#include "libavcodec/vc1dsp.h"
32
#include "constants.h"
33
#include "fpel.h"
34
#include "vc1dsp.h"
35
36
#if HAVE_6REGS && HAVE_INLINE_ASM && HAVE_MMX_EXTERNAL
37
38
void ff_vc1_put_ver_16b_shift2_mmx(int16_t *dst,
39
                                   const uint8_t *src, x86_reg stride,
40
                                   int rnd, int64_t shift);
41
void ff_vc1_put_hor_16b_shift2_mmx(uint8_t *dst, x86_reg stride,
42
                                   const int16_t *src, int rnd);
43
void ff_vc1_avg_hor_16b_shift2_mmxext(uint8_t *dst, x86_reg stride,
44
                                      const int16_t *src, int rnd);
45
46
#define OP_PUT(S,D)
47
#define OP_AVG(S,D) "pavgb " #S ", " #D " \n\t"
48
49
/** Add rounder from mm7 to mm3 and pack result at destination */
50
#define NORMALIZE_MMX(SHIFT)                                    \
51
     "paddw     %%mm7, %%mm3           \n\t" /* +bias-r */      \
52
     "paddw     %%mm7, %%mm4           \n\t" /* +bias-r */      \
53
     "psraw     "SHIFT", %%mm3         \n\t"                    \
54
     "psraw     "SHIFT", %%mm4         \n\t"
55
56
#define TRANSFER_DO_PACK(OP)                    \
57
     "packuswb  %%mm4, %%mm3           \n\t"    \
58
     OP((%2), %%mm3)                            \
59
     "movq      %%mm3, (%2)            \n\t"
60
61
#define TRANSFER_DONT_PACK(OP)                  \
62
     OP(0(%2), %%mm3)                           \
63
     OP(8(%2), %%mm4)                           \
64
     "movq      %%mm3, 0(%2)           \n\t"    \
65
     "movq      %%mm4, 8(%2)           \n\t"
66
67
/** @see MSPEL_FILTER13_CORE for use as UNPACK macro */
68
#define DO_UNPACK(reg)  "punpcklbw %%mm0, " reg "\n\t"
69
#define DONT_UNPACK(reg)
70
71
/** Compute the rounder 32-r or 8-r and unpacks it to mm7 */
72
#define LOAD_ROUNDER_MMX(ROUND)                 \
73
     "movd      "ROUND", %%mm7         \n\t"    \
74
     "punpcklwd %%mm7, %%mm7           \n\t"    \
75
     "punpckldq %%mm7, %%mm7           \n\t"
76
77
/**
78
 * Purely vertical or horizontal 1/2 shift interpolation.
79
 * Sacrifice mm6 for *9 factor.
80
 */
81
#define VC1_SHIFT2(OP, OPNAME)\
82
static void OPNAME ## vc1_shift2_mmx(uint8_t *dst, const uint8_t *src,\
83
0
                                     x86_reg stride, int rnd, x86_reg offset)\
84
0
{\
85
0
    rnd = 8-rnd;\
86
0
    __asm__ volatile(\
87
0
        "mov       $8, %%"FF_REG_c"        \n\t"\
88
0
        LOAD_ROUNDER_MMX("%5")\
89
0
        "movq      "MANGLE(ff_pw_9)", %%mm6\n\t"\
90
0
        "1:                                \n\t"\
91
0
        "movd      0(%0   ), %%mm3         \n\t"\
92
0
        "movd      4(%0   ), %%mm4         \n\t"\
93
0
        "movd      0(%0,%2), %%mm1         \n\t"\
94
0
        "movd      4(%0,%2), %%mm2         \n\t"\
95
0
        "add       %2, %0                  \n\t"\
96
0
        "punpcklbw %%mm0, %%mm3            \n\t"\
97
0
        "punpcklbw %%mm0, %%mm4            \n\t"\
98
0
        "punpcklbw %%mm0, %%mm1            \n\t"\
99
0
        "punpcklbw %%mm0, %%mm2            \n\t"\
100
0
        "paddw     %%mm1, %%mm3            \n\t"\
101
0
        "paddw     %%mm2, %%mm4            \n\t"\
102
0
        "movd      0(%0,%3), %%mm1         \n\t"\
103
0
        "movd      4(%0,%3), %%mm2         \n\t"\
104
0
        "pmullw    %%mm6, %%mm3            \n\t" /* 0,9,9,0*/\
105
0
        "pmullw    %%mm6, %%mm4            \n\t" /* 0,9,9,0*/\
106
0
        "punpcklbw %%mm0, %%mm1            \n\t"\
107
0
        "punpcklbw %%mm0, %%mm2            \n\t"\
108
0
        "psubw     %%mm1, %%mm3            \n\t" /*-1,9,9,0*/\
109
0
        "psubw     %%mm2, %%mm4            \n\t" /*-1,9,9,0*/\
110
0
        "movd      0(%0,%2), %%mm1         \n\t"\
111
0
        "movd      4(%0,%2), %%mm2         \n\t"\
112
0
        "punpcklbw %%mm0, %%mm1            \n\t"\
113
0
        "punpcklbw %%mm0, %%mm2            \n\t"\
114
0
        "psubw     %%mm1, %%mm3            \n\t" /*-1,9,9,-1*/\
115
0
        "psubw     %%mm2, %%mm4            \n\t" /*-1,9,9,-1*/\
116
0
        NORMALIZE_MMX("$4")\
117
0
        "packuswb  %%mm4, %%mm3            \n\t"\
118
0
        OP((%1), %%mm3)\
119
0
        "movq      %%mm3, (%1)             \n\t"\
120
0
        "add       %6, %0                  \n\t"\
121
0
        "add       %4, %1                  \n\t"\
122
0
        "dec       %%"FF_REG_c"            \n\t"\
123
0
        "jnz 1b                            \n\t"\
124
0
        : "+r"(src),  "+r"(dst)\
125
0
        : "r"(offset), "r"(-2*offset), "g"(stride), "m"(rnd),\
126
0
          "g"(stride-offset)\
127
0
          NAMED_CONSTRAINTS_ADD(ff_pw_9)\
128
0
        : "%"FF_REG_c, "memory"\
129
0
    );\
130
0
}
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_shift2_mmx
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_shift2_mmx
131
132
VC1_SHIFT2(OP_PUT, put_)
133
VC1_SHIFT2(OP_AVG, avg_)
134
135
/**
136
 * Core of the 1/4 and 3/4 shift bicubic interpolation.
137
 *
138
 * @param UNPACK  Macro unpacking arguments from 8 to 16 bits (can be empty).
139
 * @param MOVQ    "movd 1" or "movq 2", if data read is already unpacked.
140
 * @param A1      Address of 1st tap (beware of unpacked/packed).
141
 * @param A2      Address of 2nd tap
142
 * @param A3      Address of 3rd tap
143
 * @param A4      Address of 4th tap
144
 */
145
#define MSPEL_FILTER13_CORE(UNPACK, MOVQ, A1, A2, A3, A4)       \
146
     MOVQ "*0+"A1", %%mm1       \n\t"                           \
147
     MOVQ "*4+"A1", %%mm2       \n\t"                           \
148
     UNPACK("%%mm1")                                            \
149
     UNPACK("%%mm2")                                            \
150
     "pmullw    "MANGLE(ff_pw_3)", %%mm1\n\t"                   \
151
     "pmullw    "MANGLE(ff_pw_3)", %%mm2\n\t"                   \
152
     MOVQ "*0+"A2", %%mm3       \n\t"                           \
153
     MOVQ "*4+"A2", %%mm4       \n\t"                           \
154
     UNPACK("%%mm3")                                            \
155
     UNPACK("%%mm4")                                            \
156
     "pmullw    %%mm6, %%mm3    \n\t" /* *18 */                 \
157
     "pmullw    %%mm6, %%mm4    \n\t" /* *18 */                 \
158
     "psubw     %%mm1, %%mm3    \n\t" /* 18,-3 */               \
159
     "psubw     %%mm2, %%mm4    \n\t" /* 18,-3 */               \
160
     MOVQ "*0+"A4", %%mm1       \n\t"                           \
161
     MOVQ "*4+"A4", %%mm2       \n\t"                           \
162
     UNPACK("%%mm1")                                            \
163
     UNPACK("%%mm2")                                            \
164
     "psllw     $2, %%mm1       \n\t" /* 4* */                  \
165
     "psllw     $2, %%mm2       \n\t" /* 4* */                  \
166
     "psubw     %%mm1, %%mm3    \n\t" /* -4,18,-3 */            \
167
     "psubw     %%mm2, %%mm4    \n\t" /* -4,18,-3 */            \
168
     MOVQ "*0+"A3", %%mm1       \n\t"                           \
169
     MOVQ "*4+"A3", %%mm2       \n\t"                           \
170
     UNPACK("%%mm1")                                            \
171
     UNPACK("%%mm2")                                            \
172
     "pmullw    %%mm5, %%mm1    \n\t" /* *53 */                 \
173
     "pmullw    %%mm5, %%mm2    \n\t" /* *53 */                 \
174
     "paddw     %%mm1, %%mm3    \n\t" /* 4,53,18,-3 */          \
175
     "paddw     %%mm2, %%mm4    \n\t" /* 4,53,18,-3 */
176
177
/**
178
 * Macro to build the vertical 16 bits version of vc1_put_shift[13].
179
 * Here, offset=src_stride. Parameters passed A1 to A4 must use
180
 * %3 (src_stride) and %4 (3*src_stride).
181
 *
182
 * @param  NAME   Either 1 or 3
183
 * @see MSPEL_FILTER13_CORE for information on A1->A4
184
 */
185
#define MSPEL_FILTER13_VER_16B(NAME, A1, A2, A3, A4)                    \
186
static void                                                             \
187
vc1_put_ver_16b_ ## NAME ## _mmx(int16_t *dst, const uint8_t *src,      \
188
                                 x86_reg src_stride,                   \
189
0
                                 int rnd, int64_t shift)                \
190
0
{                                                                       \
191
0
    int h = 8;                                                          \
192
0
    src -= src_stride;                                                  \
193
0
    __asm__ volatile(                                                       \
194
0
        LOAD_ROUNDER_MMX("%5")                                          \
195
0
        "movq      "MANGLE(ff_pw_53)", %%mm5\n\t"                       \
196
0
        "movq      "MANGLE(ff_pw_18)", %%mm6\n\t"                       \
197
0
        ".p2align 3                \n\t"                                \
198
0
        "1:                        \n\t"                                \
199
0
        MSPEL_FILTER13_CORE(DO_UNPACK, "movd  1", A1, A2, A3, A4)       \
200
0
        NORMALIZE_MMX("%6")                                             \
201
0
        TRANSFER_DONT_PACK(OP_PUT)                                      \
202
0
        /* Last 3 (in fact 4) bytes on the line */                      \
203
0
        "movd      8+"A1", %%mm1   \n\t"                                \
204
0
        DO_UNPACK("%%mm1")                                              \
205
0
        "movq      %%mm1, %%mm3    \n\t"                                \
206
0
        "paddw     %%mm1, %%mm1    \n\t"                                \
207
0
        "paddw     %%mm3, %%mm1    \n\t" /* 3* */                       \
208
0
        "movd      8+"A2", %%mm3   \n\t"                                \
209
0
        DO_UNPACK("%%mm3")                                              \
210
0
        "pmullw    %%mm6, %%mm3    \n\t" /* *18 */                      \
211
0
        "psubw     %%mm1, %%mm3    \n\t" /*18,-3 */                     \
212
0
        "movd      8+"A3", %%mm1   \n\t"                                \
213
0
        DO_UNPACK("%%mm1")                                              \
214
0
        "pmullw    %%mm5, %%mm1    \n\t" /* *53 */                      \
215
0
        "paddw     %%mm1, %%mm3    \n\t" /*53,18,-3 */                  \
216
0
        "movd      8+"A4", %%mm1   \n\t"                                \
217
0
        DO_UNPACK("%%mm1")                                              \
218
0
        "psllw     $2, %%mm1       \n\t" /* 4* */                       \
219
0
        "psubw     %%mm1, %%mm3    \n\t"                                \
220
0
        "paddw     %%mm7, %%mm3    \n\t"                                \
221
0
        "psraw     %6, %%mm3       \n\t"                                \
222
0
        "movq      %%mm3, 16(%2)   \n\t"                                \
223
0
        "add       %3, %1          \n\t"                                \
224
0
        "add       $24, %2         \n\t"                                \
225
0
        "decl      %0              \n\t"                                \
226
0
        "jnz 1b                    \n\t"                                \
227
0
        : "+r"(h), "+r" (src),  "+r" (dst)                              \
228
0
        : "r"(src_stride), "r"(3*src_stride),                           \
229
0
          "m"(rnd), "m"(shift)                                          \
230
0
          NAMED_CONSTRAINTS_ADD(ff_pw_3,ff_pw_53,ff_pw_18)              \
231
0
        : "memory"                                                      \
232
0
    );                                                                  \
233
0
}
Unexecuted instantiation: vc1dsp_mmx.c:vc1_put_ver_16b_shift1_mmx
Unexecuted instantiation: vc1dsp_mmx.c:vc1_put_ver_16b_shift3_mmx
234
235
/**
236
 * Macro to build the horizontal 16 bits version of vc1_put_shift[13].
237
 * Here, offset=16 bits, so parameters passed A1 to A4 should be simple.
238
 *
239
 * @param  NAME   Either 1 or 3
240
 * @see MSPEL_FILTER13_CORE for information on A1->A4
241
 */
242
#define MSPEL_FILTER13_HOR_16B(NAME, A1, A2, A3, A4, OP, OPNAME)        \
243
static void                                                             \
244
OPNAME ## vc1_hor_16b_ ## NAME ## _mmx(uint8_t *dst, x86_reg stride,    \
245
0
                                 const int16_t *src, int rnd)           \
246
0
{                                                                       \
247
0
    int h = 8;                                                          \
248
0
    src -= 1;                                                           \
249
0
    rnd -= (-4+58+13-3)*256; /* Add -256 bias */                        \
250
0
    __asm__ volatile(                                                       \
251
0
        LOAD_ROUNDER_MMX("%4")                                          \
252
0
        "movq      "MANGLE(ff_pw_18)", %%mm6   \n\t"                    \
253
0
        "movq      "MANGLE(ff_pw_53)", %%mm5   \n\t"                    \
254
0
        ".p2align 3                \n\t"                                \
255
0
        "1:                        \n\t"                                \
256
0
        MSPEL_FILTER13_CORE(DONT_UNPACK, "movq 2", A1, A2, A3, A4)      \
257
0
        NORMALIZE_MMX("$7")                                             \
258
0
        /* Remove bias */                                               \
259
0
        "paddw     "MANGLE(ff_pw_128)", %%mm3  \n\t"                    \
260
0
        "paddw     "MANGLE(ff_pw_128)", %%mm4  \n\t"                    \
261
0
        TRANSFER_DO_PACK(OP)                                            \
262
0
        "add       $24, %1         \n\t"                                \
263
0
        "add       %3, %2          \n\t"                                \
264
0
        "decl      %0              \n\t"                                \
265
0
        "jnz 1b                    \n\t"                                \
266
0
        : "+r"(h), "+r" (src),  "+r" (dst)                              \
267
0
        : "r"(stride), "m"(rnd)                                         \
268
0
          NAMED_CONSTRAINTS_ADD(ff_pw_3,ff_pw_18,ff_pw_53,ff_pw_128)    \
269
0
        : "memory"                                                      \
270
0
    );                                                                  \
271
0
}
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_hor_16b_shift1_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_hor_16b_shift3_mmx
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_hor_16b_shift1_mmx
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_hor_16b_shift3_mmx
272
273
/**
274
 * Macro to build the 8 bits, any direction, version of vc1_put_shift[13].
275
 * Here, offset=src_stride. Parameters passed A1 to A4 must use
276
 * %3 (offset) and %4 (3*offset).
277
 *
278
 * @param  NAME   Either 1 or 3
279
 * @see MSPEL_FILTER13_CORE for information on A1->A4
280
 */
281
#define MSPEL_FILTER13_8B(NAME, A1, A2, A3, A4, OP, OPNAME)             \
282
static void                                                             \
283
OPNAME ## vc1_## NAME ## _mmx(uint8_t *dst, const uint8_t *src,         \
284
0
                        x86_reg stride, int rnd, x86_reg offset)      \
285
0
{                                                                       \
286
0
    int h = 8;                                                          \
287
0
    src -= offset;                                                      \
288
0
    rnd = 32-rnd;                                                       \
289
0
    __asm__ volatile (                                                      \
290
0
        LOAD_ROUNDER_MMX("%6")                                          \
291
0
        "movq      "MANGLE(ff_pw_53)", %%mm5       \n\t"                \
292
0
        "movq      "MANGLE(ff_pw_18)", %%mm6       \n\t"                \
293
0
        ".p2align 3                \n\t"                                \
294
0
        "1:                        \n\t"                                \
295
0
        MSPEL_FILTER13_CORE(DO_UNPACK, "movd   1", A1, A2, A3, A4)      \
296
0
        NORMALIZE_MMX("$6")                                             \
297
0
        TRANSFER_DO_PACK(OP)                                            \
298
0
        "add       %5, %1          \n\t"                                \
299
0
        "add       %5, %2          \n\t"                                \
300
0
        "decl      %0              \n\t"                                \
301
0
        "jnz 1b                    \n\t"                                \
302
0
        : "+r"(h), "+r" (src),  "+r" (dst)                              \
303
0
        : "r"(offset), "r"(3*offset), "g"(stride), "m"(rnd)             \
304
0
          NAMED_CONSTRAINTS_ADD(ff_pw_53,ff_pw_18,ff_pw_3)              \
305
0
        : "memory"                                                      \
306
0
    );                                                                  \
307
0
}
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_shift1_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_shift3_mmx
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_shift1_mmx
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_shift3_mmx
308
309
/** 1/4 shift bicubic interpolation */
310
MSPEL_FILTER13_8B     (shift1, "0(%1,%4  )", "0(%1,%3,2)", "0(%1,%3  )", "0(%1     )", OP_PUT, put_)
311
MSPEL_FILTER13_8B     (shift1, "0(%1,%4  )", "0(%1,%3,2)", "0(%1,%3  )", "0(%1     )", OP_AVG, avg_)
312
MSPEL_FILTER13_VER_16B(shift1, "0(%1,%4  )", "0(%1,%3,2)", "0(%1,%3  )", "0(%1     )")
313
MSPEL_FILTER13_HOR_16B(shift1, "2*3(%1)", "2*2(%1)", "2*1(%1)", "2*0(%1)", OP_PUT, put_)
314
MSPEL_FILTER13_HOR_16B(shift1, "2*3(%1)", "2*2(%1)", "2*1(%1)", "2*0(%1)", OP_AVG, avg_)
315
316
/** 3/4 shift bicubic interpolation */
317
MSPEL_FILTER13_8B     (shift3, "0(%1     )", "0(%1,%3  )", "0(%1,%3,2)", "0(%1,%4  )", OP_PUT, put_)
318
MSPEL_FILTER13_8B     (shift3, "0(%1     )", "0(%1,%3  )", "0(%1,%3,2)", "0(%1,%4  )", OP_AVG, avg_)
319
MSPEL_FILTER13_VER_16B(shift3, "0(%1     )", "0(%1,%3  )", "0(%1,%3,2)", "0(%1,%4  )")
320
MSPEL_FILTER13_HOR_16B(shift3, "2*0(%1)", "2*1(%1)", "2*2(%1)", "2*3(%1)", OP_PUT, put_)
321
MSPEL_FILTER13_HOR_16B(shift3, "2*0(%1)", "2*1(%1)", "2*2(%1)", "2*3(%1)", OP_AVG, avg_)
322
323
typedef void (*vc1_mspel_mc_filter_ver_16bits)(int16_t *dst, const uint8_t *src, x86_reg src_stride, int rnd, int64_t shift);
324
typedef void (*vc1_mspel_mc_filter_hor_16bits)(uint8_t *dst, x86_reg dst_stride, const int16_t *src, int rnd);
325
typedef void (*vc1_mspel_mc_filter_8bits)(uint8_t *dst, const uint8_t *src, x86_reg stride, int rnd, x86_reg offset);
326
327
/**
328
 * Interpolate fractional pel values by applying proper vertical then
329
 * horizontal filter.
330
 *
331
 * @param  dst     Destination buffer for interpolated pels.
332
 * @param  src     Source buffer.
333
 * @param  stride  Stride for both src and dst buffers.
334
 * @param  hmode   Horizontal filter (expressed in quarter pixels shift).
335
 * @param  hmode   Vertical filter.
336
 * @param  rnd     Rounding bias.
337
 */
338
#define VC1_MSPEL_MC(OP, INSTR)\
339
static void OP ## vc1_mspel_mc(uint8_t *dst, const uint8_t *src, int stride,\
340
0
                               int hmode, int vmode, int rnd)\
341
0
{\
342
0
    static const vc1_mspel_mc_filter_ver_16bits vc1_put_shift_ver_16bits[] =\
343
0
         { NULL, vc1_put_ver_16b_shift1_mmx, ff_vc1_put_ver_16b_shift2_mmx, vc1_put_ver_16b_shift3_mmx };\
344
0
    static const vc1_mspel_mc_filter_hor_16bits vc1_put_shift_hor_16bits[] =\
345
0
         { NULL, OP ## vc1_hor_16b_shift1_mmx, ff_vc1_ ## OP ## hor_16b_shift2_ ## INSTR, OP ## vc1_hor_16b_shift3_mmx };\
346
0
    static const vc1_mspel_mc_filter_8bits vc1_put_shift_8bits[] =\
347
0
         { NULL, OP ## vc1_shift1_mmx, OP ## vc1_shift2_mmx, OP ## vc1_shift3_mmx };\
348
0
\
349
0
    __asm__ volatile(\
350
0
        "pxor %%mm0, %%mm0         \n\t"\
351
0
        ::: "memory"\
352
0
    );\
353
0
\
354
0
    if (vmode) { /* Vertical filter to apply */\
355
0
        if (hmode) { /* Horizontal filter to apply, output to tmp */\
356
0
            static const int shift_value[] = { 0, 5, 1, 5 };\
357
0
            int              shift = (shift_value[hmode]+shift_value[vmode])>>1;\
358
0
            int              r;\
359
0
            LOCAL_ALIGNED(16, int16_t, tmp, [12*8]);\
360
0
\
361
0
            r = (1<<(shift-1)) + rnd-1;\
362
0
            vc1_put_shift_ver_16bits[vmode](tmp, src-1, stride, r, shift);\
363
0
\
364
0
            vc1_put_shift_hor_16bits[hmode](dst, stride, tmp+1, 64-rnd);\
365
0
            return;\
366
0
        }\
367
0
        else { /* No horizontal filter, output 8 lines to dst */\
368
0
            vc1_put_shift_8bits[vmode](dst, src, stride, 1-rnd, stride);\
369
0
            return;\
370
0
        }\
371
0
    }\
372
0
\
373
0
    /* Horizontal mode with no vertical mode */\
374
0
    vc1_put_shift_8bits[hmode](dst, src, stride, rnd, 1);\
375
0
} \
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc
376
static void OP ## vc1_mspel_mc_16(uint8_t *dst, const uint8_t *src, \
377
0
                                  int stride, int hmode, int vmode, int rnd)\
378
0
{ \
379
0
    OP ## vc1_mspel_mc(dst + 0, src + 0, stride, hmode, vmode, rnd); \
380
0
    OP ## vc1_mspel_mc(dst + 8, src + 8, stride, hmode, vmode, rnd); \
381
0
    dst += 8*stride; src += 8*stride; \
382
0
    OP ## vc1_mspel_mc(dst + 0, src + 0, stride, hmode, vmode, rnd); \
383
0
    OP ## vc1_mspel_mc(dst + 8, src + 8, stride, hmode, vmode, rnd); \
384
0
}
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc_16
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc_16
385
386
VC1_MSPEL_MC(put_, mmx)
387
VC1_MSPEL_MC(avg_, mmxext)
388
389
/** Macro to ease bicubic filter interpolation functions declarations */
390
#define DECLARE_FUNCTION(a, b)                                          \
391
static void put_vc1_mspel_mc ## a ## b ## _mmx(uint8_t *dst,            \
392
                                               const uint8_t *src,      \
393
                                               ptrdiff_t stride,        \
394
0
                                               int rnd)                 \
395
0
{                                                                       \
396
0
     put_vc1_mspel_mc(dst, src, stride, a, b, rnd);                     \
397
0
}\
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc01_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc02_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc03_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc10_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc11_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc12_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc13_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc20_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc21_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc22_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc23_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc30_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc31_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc32_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc33_mmx
398
static void avg_vc1_mspel_mc ## a ## b ## _mmxext(uint8_t *dst,         \
399
                                                  const uint8_t *src,   \
400
                                                  ptrdiff_t stride,     \
401
0
                                                  int rnd)              \
402
0
{                                                                       \
403
0
     avg_vc1_mspel_mc(dst, src, stride, a, b, rnd);                     \
404
0
}\
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc01_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc02_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc03_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc10_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc11_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc12_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc13_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc20_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc21_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc22_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc23_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc30_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc31_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc32_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc33_mmxext
405
static void put_vc1_mspel_mc ## a ## b ## _16_mmx(uint8_t *dst,         \
406
                                                  const uint8_t *src,   \
407
                                                  ptrdiff_t stride,     \
408
0
                                                  int rnd)              \
409
0
{                                                                       \
410
0
     put_vc1_mspel_mc_16(dst, src, stride, a, b, rnd);                  \
411
0
}\
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc01_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc02_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc03_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc10_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc11_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc12_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc13_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc20_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc21_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc22_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc23_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc30_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc31_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc32_16_mmx
Unexecuted instantiation: vc1dsp_mmx.c:put_vc1_mspel_mc33_16_mmx
412
static void avg_vc1_mspel_mc ## a ## b ## _16_mmxext(uint8_t *dst,      \
413
                                                     const uint8_t *src,\
414
                                                     ptrdiff_t stride,  \
415
0
                                                     int rnd)           \
416
0
{                                                                       \
417
0
     avg_vc1_mspel_mc_16(dst, src, stride, a, b, rnd);                  \
418
0
}
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc01_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc02_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc03_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc10_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc11_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc12_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc13_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc20_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc21_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc22_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc23_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc30_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc31_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc32_16_mmxext
Unexecuted instantiation: vc1dsp_mmx.c:avg_vc1_mspel_mc33_16_mmxext
419
420
DECLARE_FUNCTION(0, 1)
421
DECLARE_FUNCTION(0, 2)
422
DECLARE_FUNCTION(0, 3)
423
424
DECLARE_FUNCTION(1, 0)
425
DECLARE_FUNCTION(1, 1)
426
DECLARE_FUNCTION(1, 2)
427
DECLARE_FUNCTION(1, 3)
428
429
DECLARE_FUNCTION(2, 0)
430
DECLARE_FUNCTION(2, 1)
431
DECLARE_FUNCTION(2, 2)
432
DECLARE_FUNCTION(2, 3)
433
434
DECLARE_FUNCTION(3, 0)
435
DECLARE_FUNCTION(3, 1)
436
DECLARE_FUNCTION(3, 2)
437
DECLARE_FUNCTION(3, 3)
438
439
#define FN_ASSIGN(OP, X, Y, INSN) \
440
5.76k
    dsp->OP##vc1_mspel_pixels_tab[1][X+4*Y] = OP##vc1_mspel_mc##X##Y##INSN; \
441
5.76k
    dsp->OP##vc1_mspel_pixels_tab[0][X+4*Y] = OP##vc1_mspel_mc##X##Y##_16##INSN
442
443
av_cold void ff_vc1dsp_init_mmx(VC1DSPContext *dsp)
444
192
{
445
192
    FN_ASSIGN(put_, 0, 1, _mmx);
446
192
    FN_ASSIGN(put_, 0, 2, _mmx);
447
192
    FN_ASSIGN(put_, 0, 3, _mmx);
448
449
192
    FN_ASSIGN(put_, 1, 0, _mmx);
450
192
    FN_ASSIGN(put_, 1, 1, _mmx);
451
192
    FN_ASSIGN(put_, 1, 2, _mmx);
452
192
    FN_ASSIGN(put_, 1, 3, _mmx);
453
454
192
    FN_ASSIGN(put_, 2, 0, _mmx);
455
192
    FN_ASSIGN(put_, 2, 1, _mmx);
456
192
    FN_ASSIGN(put_, 2, 2, _mmx);
457
192
    FN_ASSIGN(put_, 2, 3, _mmx);
458
459
192
    FN_ASSIGN(put_, 3, 0, _mmx);
460
192
    FN_ASSIGN(put_, 3, 1, _mmx);
461
192
    FN_ASSIGN(put_, 3, 2, _mmx);
462
192
    FN_ASSIGN(put_, 3, 3, _mmx);
463
192
}
464
465
av_cold void ff_vc1dsp_init_mmxext(VC1DSPContext *dsp)
466
192
{
467
192
    FN_ASSIGN(avg_, 0, 1, _mmxext);
468
192
    FN_ASSIGN(avg_, 0, 2, _mmxext);
469
192
    FN_ASSIGN(avg_, 0, 3, _mmxext);
470
471
192
    FN_ASSIGN(avg_, 1, 0, _mmxext);
472
192
    FN_ASSIGN(avg_, 1, 1, _mmxext);
473
192
    FN_ASSIGN(avg_, 1, 2, _mmxext);
474
192
    FN_ASSIGN(avg_, 1, 3, _mmxext);
475
476
192
    FN_ASSIGN(avg_, 2, 0, _mmxext);
477
192
    FN_ASSIGN(avg_, 2, 1, _mmxext);
478
192
    FN_ASSIGN(avg_, 2, 2, _mmxext);
479
192
    FN_ASSIGN(avg_, 2, 3, _mmxext);
480
481
192
    FN_ASSIGN(avg_, 3, 0, _mmxext);
482
192
    FN_ASSIGN(avg_, 3, 1, _mmxext);
483
192
    FN_ASSIGN(avg_, 3, 2, _mmxext);
484
192
    FN_ASSIGN(avg_, 3, 3, _mmxext);
485
192
}
486
#endif /* HAVE_6REGS && HAVE_INLINE_ASM && HAVE_MMX_EXTERNAL */