1 /*
2 * Chinese AVS video (AVS1-P2, JiZhun profile) decoder.
3 * Copyright (c) 2006 Stefan Gehrer <stefan.gehrer@gmx.de>
4 *
5 * MMX-optimized DSP functions, based on H.264 optimizations by
6 * Michael Niedermayer and Loren Merritt
7 *
8 * This file is part of FFmpeg.
9 *
10 * FFmpeg is free software; you can redistribute it and/or
11 * modify it under the terms of the GNU Lesser General Public
12 * License as published by the Free Software Foundation; either
13 * version 2.1 of the License, or (at your option) any later version.
14 *
15 * FFmpeg is distributed in the hope that it will be useful,
16 * but WITHOUT ANY WARRANTY; without even the implied warranty of
17 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 * Lesser General Public License for more details.
19 *
20 * You should have received a copy of the GNU Lesser General Public
21 * License along with FFmpeg; if not, write to the Free Software
22 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
23 */
24
25 #include "libavutil/attributes.h"
26 #include "libavutil/common.h"
27 #include "libavutil/cpu.h"
28 #include "libavutil/mem_internal.h"
29 #include "libavutil/x86/asm.h"
30 #include "libavutil/x86/cpu.h"
31 #include "libavcodec/cavsdsp.h"
32 #include "libavcodec/idctdsp.h"
33 #include "constants.h"
34 #include "fpel.h"
35 #include "idctdsp.h"
36 #include "config.h"
37
38
39 #if HAVE_SSE2_EXTERNAL
40
41 void ff_cavs_idct8_sse2(int16_t *out, const int16_t *in);
42
cavs_idct8_add_sse2(uint8_t *dst, int16_t *block, ptrdiff_t stride)43 static void cavs_idct8_add_sse2(uint8_t *dst, int16_t *block, ptrdiff_t stride)
44 {
45 LOCAL_ALIGNED(16, int16_t, b2, [64]);
46 ff_cavs_idct8_sse2(b2, block);
47 ff_add_pixels_clamped_sse2(b2, dst, stride);
48 }
49
50 #endif /* HAVE_SSE2_EXTERNAL */
51
52 #if HAVE_MMXEXT_INLINE
53
54 /*****************************************************************************
55 *
56 * motion compensation
57 *
58 ****************************************************************************/
59
60 /* vertical filter [-1 -2 96 42 -7 0] */
61 #define QPEL_CAVSV1(A,B,C,D,E,F,OP,ADD, MUL1, MUL2) \
62 "movd (%0), "#F" \n\t"\
63 "movq "#C", %%mm6 \n\t"\
64 "pmullw "MANGLE(MUL1)", %%mm6\n\t"\
65 "movq "#D", %%mm7 \n\t"\
66 "pmullw "MANGLE(MUL2)", %%mm7\n\t"\
67 "psllw $3, "#E" \n\t"\
68 "psubw "#E", %%mm6 \n\t"\
69 "psraw $3, "#E" \n\t"\
70 "paddw %%mm7, %%mm6 \n\t"\
71 "paddw "#E", %%mm6 \n\t"\
72 "paddw "#B", "#B" \n\t"\
73 "pxor %%mm7, %%mm7 \n\t"\
74 "add %2, %0 \n\t"\
75 "punpcklbw %%mm7, "#F" \n\t"\
76 "psubw "#B", %%mm6 \n\t"\
77 "psraw $1, "#B" \n\t"\
78 "psubw "#A", %%mm6 \n\t"\
79 "paddw "MANGLE(ADD)", %%mm6 \n\t"\
80 "psraw $7, %%mm6 \n\t"\
81 "packuswb %%mm6, %%mm6 \n\t"\
82 OP(%%mm6, (%1), A, d) \
83 "add %3, %1 \n\t"
84
85 /* vertical filter [ 0 -1 5 5 -1 0] */
86 #define QPEL_CAVSV2(A,B,C,D,E,F,OP,ADD, MUL1, MUL2) \
87 "movd (%0), "#F" \n\t"\
88 "movq "#C", %%mm6 \n\t"\
89 "paddw "#D", %%mm6 \n\t"\
90 "pmullw "MANGLE(MUL1)", %%mm6\n\t"\
91 "add %2, %0 \n\t"\
92 "punpcklbw %%mm7, "#F" \n\t"\
93 "psubw "#B", %%mm6 \n\t"\
94 "psubw "#E", %%mm6 \n\t"\
95 "paddw "MANGLE(ADD)", %%mm6 \n\t"\
96 "psraw $3, %%mm6 \n\t"\
97 "packuswb %%mm6, %%mm6 \n\t"\
98 OP(%%mm6, (%1), A, d) \
99 "add %3, %1 \n\t"
100
101 /* vertical filter [ 0 -7 42 96 -2 -1] */
102 #define QPEL_CAVSV3(A,B,C,D,E,F,OP,ADD, MUL1, MUL2) \
103 "movd (%0), "#F" \n\t"\
104 "movq "#C", %%mm6 \n\t"\
105 "pmullw "MANGLE(MUL2)", %%mm6\n\t"\
106 "movq "#D", %%mm7 \n\t"\
107 "pmullw "MANGLE(MUL1)", %%mm7\n\t"\
108 "psllw $3, "#B" \n\t"\
109 "psubw "#B", %%mm6 \n\t"\
110 "psraw $3, "#B" \n\t"\
111 "paddw %%mm7, %%mm6 \n\t"\
112 "paddw "#B", %%mm6 \n\t"\
113 "paddw "#E", "#E" \n\t"\
114 "pxor %%mm7, %%mm7 \n\t"\
115 "add %2, %0 \n\t"\
116 "punpcklbw %%mm7, "#F" \n\t"\
117 "psubw "#E", %%mm6 \n\t"\
118 "psraw $1, "#E" \n\t"\
119 "psubw "#F", %%mm6 \n\t"\
120 "paddw "MANGLE(ADD)", %%mm6 \n\t"\
121 "psraw $7, %%mm6 \n\t"\
122 "packuswb %%mm6, %%mm6 \n\t"\
123 OP(%%mm6, (%1), A, d) \
124 "add %3, %1 \n\t"
125
126
127 #define QPEL_CAVSVNUM(VOP,OP,ADD,MUL1,MUL2)\
128 int w= 2;\
129 src -= 2*srcStride;\
130 \
131 while(w--){\
132 __asm__ volatile(\
133 "pxor %%mm7, %%mm7 \n\t"\
134 "movd (%0), %%mm0 \n\t"\
135 "add %2, %0 \n\t"\
136 "movd (%0), %%mm1 \n\t"\
137 "add %2, %0 \n\t"\
138 "movd (%0), %%mm2 \n\t"\
139 "add %2, %0 \n\t"\
140 "movd (%0), %%mm3 \n\t"\
141 "add %2, %0 \n\t"\
142 "movd (%0), %%mm4 \n\t"\
143 "add %2, %0 \n\t"\
144 "punpcklbw %%mm7, %%mm0 \n\t"\
145 "punpcklbw %%mm7, %%mm1 \n\t"\
146 "punpcklbw %%mm7, %%mm2 \n\t"\
147 "punpcklbw %%mm7, %%mm3 \n\t"\
148 "punpcklbw %%mm7, %%mm4 \n\t"\
149 VOP(%%mm0, %%mm1, %%mm2, %%mm3, %%mm4, %%mm5, OP, ADD, MUL1, MUL2)\
150 VOP(%%mm1, %%mm2, %%mm3, %%mm4, %%mm5, %%mm0, OP, ADD, MUL1, MUL2)\
151 VOP(%%mm2, %%mm3, %%mm4, %%mm5, %%mm0, %%mm1, OP, ADD, MUL1, MUL2)\
152 VOP(%%mm3, %%mm4, %%mm5, %%mm0, %%mm1, %%mm2, OP, ADD, MUL1, MUL2)\
153 VOP(%%mm4, %%mm5, %%mm0, %%mm1, %%mm2, %%mm3, OP, ADD, MUL1, MUL2)\
154 VOP(%%mm5, %%mm0, %%mm1, %%mm2, %%mm3, %%mm4, OP, ADD, MUL1, MUL2)\
155 VOP(%%mm0, %%mm1, %%mm2, %%mm3, %%mm4, %%mm5, OP, ADD, MUL1, MUL2)\
156 VOP(%%mm1, %%mm2, %%mm3, %%mm4, %%mm5, %%mm0, OP, ADD, MUL1, MUL2)\
157 \
158 : "+a"(src), "+c"(dst)\
159 : "S"((x86_reg)srcStride), "r"((x86_reg)dstStride)\
160 NAMED_CONSTRAINTS_ADD(ADD,MUL1,MUL2)\
161 : "memory"\
162 );\
163 if(h==16){\
164 __asm__ volatile(\
165 VOP(%%mm2, %%mm3, %%mm4, %%mm5, %%mm0, %%mm1, OP, ADD, MUL1, MUL2)\
166 VOP(%%mm3, %%mm4, %%mm5, %%mm0, %%mm1, %%mm2, OP, ADD, MUL1, MUL2)\
167 VOP(%%mm4, %%mm5, %%mm0, %%mm1, %%mm2, %%mm3, OP, ADD, MUL1, MUL2)\
168 VOP(%%mm5, %%mm0, %%mm1, %%mm2, %%mm3, %%mm4, OP, ADD, MUL1, MUL2)\
169 VOP(%%mm0, %%mm1, %%mm2, %%mm3, %%mm4, %%mm5, OP, ADD, MUL1, MUL2)\
170 VOP(%%mm1, %%mm2, %%mm3, %%mm4, %%mm5, %%mm0, OP, ADD, MUL1, MUL2)\
171 VOP(%%mm2, %%mm3, %%mm4, %%mm5, %%mm0, %%mm1, OP, ADD, MUL1, MUL2)\
172 VOP(%%mm3, %%mm4, %%mm5, %%mm0, %%mm1, %%mm2, OP, ADD, MUL1, MUL2)\
173 \
174 : "+a"(src), "+c"(dst)\
175 : "S"((x86_reg)srcStride), "r"((x86_reg)dstStride)\
176 NAMED_CONSTRAINTS_ADD(ADD,MUL1,MUL2)\
177 : "memory"\
178 );\
179 }\
180 src += 4-(h+5)*srcStride;\
181 dst += 4-h*dstStride;\
182 }
183
184 #define QPEL_CAVS(OPNAME, OP, MMX)\
185 static void OPNAME ## cavs_qpel8_h_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t dstStride, ptrdiff_t srcStride)\
186 {\
187 int h=8;\
188 __asm__ volatile(\
189 "pxor %%mm7, %%mm7 \n\t"\
190 "movq "MANGLE(ff_pw_5)", %%mm6\n\t"\
191 "1: \n\t"\
192 "movq (%0), %%mm0 \n\t"\
193 "movq 1(%0), %%mm2 \n\t"\
194 "movq %%mm0, %%mm1 \n\t"\
195 "movq %%mm2, %%mm3 \n\t"\
196 "punpcklbw %%mm7, %%mm0 \n\t"\
197 "punpckhbw %%mm7, %%mm1 \n\t"\
198 "punpcklbw %%mm7, %%mm2 \n\t"\
199 "punpckhbw %%mm7, %%mm3 \n\t"\
200 "paddw %%mm2, %%mm0 \n\t"\
201 "paddw %%mm3, %%mm1 \n\t"\
202 "pmullw %%mm6, %%mm0 \n\t"\
203 "pmullw %%mm6, %%mm1 \n\t"\
204 "movq -1(%0), %%mm2 \n\t"\
205 "movq 2(%0), %%mm4 \n\t"\
206 "movq %%mm2, %%mm3 \n\t"\
207 "movq %%mm4, %%mm5 \n\t"\
208 "punpcklbw %%mm7, %%mm2 \n\t"\
209 "punpckhbw %%mm7, %%mm3 \n\t"\
210 "punpcklbw %%mm7, %%mm4 \n\t"\
211 "punpckhbw %%mm7, %%mm5 \n\t"\
212 "paddw %%mm4, %%mm2 \n\t"\
213 "paddw %%mm3, %%mm5 \n\t"\
214 "psubw %%mm2, %%mm0 \n\t"\
215 "psubw %%mm5, %%mm1 \n\t"\
216 "movq "MANGLE(ff_pw_4)", %%mm5\n\t"\
217 "paddw %%mm5, %%mm0 \n\t"\
218 "paddw %%mm5, %%mm1 \n\t"\
219 "psraw $3, %%mm0 \n\t"\
220 "psraw $3, %%mm1 \n\t"\
221 "packuswb %%mm1, %%mm0 \n\t"\
222 OP(%%mm0, (%1),%%mm5, q) \
223 "add %3, %0 \n\t"\
224 "add %4, %1 \n\t"\
225 "decl %2 \n\t"\
226 " jnz 1b \n\t"\
227 : "+a"(src), "+c"(dst), "+m"(h)\
228 : "d"((x86_reg)srcStride), "S"((x86_reg)dstStride)\
229 NAMED_CONSTRAINTS_ADD(ff_pw_4,ff_pw_5)\
230 : "memory"\
231 );\
232 }\
233 \
234 static inline void OPNAME ## cavs_qpel8or16_v1_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t dstStride, ptrdiff_t srcStride, int h)\
235 { \
236 QPEL_CAVSVNUM(QPEL_CAVSV1,OP,ff_pw_64,ff_pw_96,ff_pw_42) \
237 }\
238 \
239 static inline void OPNAME ## cavs_qpel8or16_v2_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t dstStride, ptrdiff_t srcStride, int h)\
240 { \
241 QPEL_CAVSVNUM(QPEL_CAVSV2,OP,ff_pw_4,ff_pw_5,ff_pw_42) \
242 }\
243 \
244 static inline void OPNAME ## cavs_qpel8or16_v3_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t dstStride, ptrdiff_t srcStride, int h)\
245 { \
246 QPEL_CAVSVNUM(QPEL_CAVSV3,OP,ff_pw_64,ff_pw_96,ff_pw_42) \
247 }\
248 \
249 static void OPNAME ## cavs_qpel8_v1_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t dstStride, ptrdiff_t srcStride)\
250 { \
251 OPNAME ## cavs_qpel8or16_v1_ ## MMX(dst , src , dstStride, srcStride, 8);\
252 }\
253 static void OPNAME ## cavs_qpel16_v1_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t dstStride, ptrdiff_t srcStride)\
254 { \
255 OPNAME ## cavs_qpel8or16_v1_ ## MMX(dst , src , dstStride, srcStride, 16);\
256 OPNAME ## cavs_qpel8or16_v1_ ## MMX(dst+8, src+8, dstStride, srcStride, 16);\
257 }\
258 \
259 static void OPNAME ## cavs_qpel8_v2_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t dstStride, ptrdiff_t srcStride)\
260 { \
261 OPNAME ## cavs_qpel8or16_v2_ ## MMX(dst , src , dstStride, srcStride, 8);\
262 }\
263 static void OPNAME ## cavs_qpel16_v2_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t dstStride, ptrdiff_t srcStride)\
264 { \
265 OPNAME ## cavs_qpel8or16_v2_ ## MMX(dst , src , dstStride, srcStride, 16);\
266 OPNAME ## cavs_qpel8or16_v2_ ## MMX(dst+8, src+8, dstStride, srcStride, 16);\
267 }\
268 \
269 static void OPNAME ## cavs_qpel8_v3_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t dstStride, ptrdiff_t srcStride)\
270 { \
271 OPNAME ## cavs_qpel8or16_v3_ ## MMX(dst , src , dstStride, srcStride, 8);\
272 }\
273 static void OPNAME ## cavs_qpel16_v3_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t dstStride, ptrdiff_t srcStride)\
274 { \
275 OPNAME ## cavs_qpel8or16_v3_ ## MMX(dst , src , dstStride, srcStride, 16);\
276 OPNAME ## cavs_qpel8or16_v3_ ## MMX(dst+8, src+8, dstStride, srcStride, 16);\
277 }\
278 \
279 static void OPNAME ## cavs_qpel16_h_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t dstStride, ptrdiff_t srcStride)\
280 { \
281 OPNAME ## cavs_qpel8_h_ ## MMX(dst , src , dstStride, srcStride);\
282 OPNAME ## cavs_qpel8_h_ ## MMX(dst+8, src+8, dstStride, srcStride);\
283 src += 8*srcStride;\
284 dst += 8*dstStride;\
285 OPNAME ## cavs_qpel8_h_ ## MMX(dst , src , dstStride, srcStride);\
286 OPNAME ## cavs_qpel8_h_ ## MMX(dst+8, src+8, dstStride, srcStride);\
287 }\
288
289 #define CAVS_MC(OPNAME, SIZE, MMX) \
290 static void OPNAME ## cavs_qpel ## SIZE ## _mc20_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
291 {\
292 OPNAME ## cavs_qpel ## SIZE ## _h_ ## MMX(dst, src, stride, stride);\
293 }\
294 \
295 static void OPNAME ## cavs_qpel ## SIZE ## _mc01_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
296 {\
297 OPNAME ## cavs_qpel ## SIZE ## _v1_ ## MMX(dst, src, stride, stride);\
298 }\
299 \
300 static void OPNAME ## cavs_qpel ## SIZE ## _mc02_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
301 {\
302 OPNAME ## cavs_qpel ## SIZE ## _v2_ ## MMX(dst, src, stride, stride);\
303 }\
304 \
305 static void OPNAME ## cavs_qpel ## SIZE ## _mc03_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
306 {\
307 OPNAME ## cavs_qpel ## SIZE ## _v3_ ## MMX(dst, src, stride, stride);\
308 }\
309
310 #define PUT_OP(a,b,temp, size) "mov" #size " " #a ", " #b " \n\t"
311 #define AVG_3DNOW_OP(a,b,temp, size) \
312 "mov" #size " " #b ", " #temp " \n\t"\
313 "pavgusb " #temp ", " #a " \n\t"\
314 "mov" #size " " #a ", " #b " \n\t"
315 #define AVG_MMXEXT_OP(a, b, temp, size) \
316 "mov" #size " " #b ", " #temp " \n\t"\
317 "pavgb " #temp ", " #a " \n\t"\
318 "mov" #size " " #a ", " #b " \n\t"
319
320 #endif /* HAVE_MMXEXT_INLINE */
321
322 #if HAVE_MMX_EXTERNAL
put_cavs_qpel8_mc00_mmx(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)323 static void put_cavs_qpel8_mc00_mmx(uint8_t *dst, const uint8_t *src,
324 ptrdiff_t stride)
325 {
326 ff_put_pixels8_mmx(dst, src, stride, 8);
327 }
328
avg_cavs_qpel8_mc00_mmxext(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)329 static void avg_cavs_qpel8_mc00_mmxext(uint8_t *dst, const uint8_t *src,
330 ptrdiff_t stride)
331 {
332 ff_avg_pixels8_mmxext(dst, src, stride, 8);
333 }
334
put_cavs_qpel16_mc00_sse2(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)335 static void put_cavs_qpel16_mc00_sse2(uint8_t *dst, const uint8_t *src,
336 ptrdiff_t stride)
337 {
338 ff_put_pixels16_sse2(dst, src, stride, 16);
339 }
340
avg_cavs_qpel16_mc00_sse2(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)341 static void avg_cavs_qpel16_mc00_sse2(uint8_t *dst, const uint8_t *src,
342 ptrdiff_t stride)
343 {
344 ff_avg_pixels16_sse2(dst, src, stride, 16);
345 }
346 #endif
347
cavsdsp_init_mmx(CAVSDSPContext *c, AVCodecContext *avctx)348 static av_cold void cavsdsp_init_mmx(CAVSDSPContext *c,
349 AVCodecContext *avctx)
350 {
351 #if HAVE_MMX_EXTERNAL
352 c->put_cavs_qpel_pixels_tab[1][0] = put_cavs_qpel8_mc00_mmx;
353 #endif /* HAVE_MMX_EXTERNAL */
354 }
355
356 #define DSPFUNC(PFX, IDX, NUM, EXT) \
357 c->PFX ## _cavs_qpel_pixels_tab[IDX][ 2] = PFX ## _cavs_qpel ## NUM ## _mc20_ ## EXT; \
358 c->PFX ## _cavs_qpel_pixels_tab[IDX][ 4] = PFX ## _cavs_qpel ## NUM ## _mc01_ ## EXT; \
359 c->PFX ## _cavs_qpel_pixels_tab[IDX][ 8] = PFX ## _cavs_qpel ## NUM ## _mc02_ ## EXT; \
360 c->PFX ## _cavs_qpel_pixels_tab[IDX][12] = PFX ## _cavs_qpel ## NUM ## _mc03_ ## EXT; \
361
362 #if HAVE_MMXEXT_INLINE
QPEL_CAVSnull363 QPEL_CAVS(put_, PUT_OP, mmxext)
364 QPEL_CAVS(avg_, AVG_MMXEXT_OP, mmxext)
365
366 CAVS_MC(put_, 8, mmxext)
367 CAVS_MC(put_, 16, mmxext)
368 CAVS_MC(avg_, 8, mmxext)
369 CAVS_MC(avg_, 16, mmxext)
370 #endif /* HAVE_MMXEXT_INLINE */
371
372 av_cold void ff_cavsdsp_init_x86(CAVSDSPContext *c, AVCodecContext *avctx)
373 {
374 av_unused int cpu_flags = av_get_cpu_flags();
375
376 if (X86_MMX(cpu_flags))
377 cavsdsp_init_mmx(c, avctx);
378
379 #if HAVE_MMXEXT_INLINE
380 if (INLINE_MMXEXT(cpu_flags)) {
381 DSPFUNC(put, 0, 16, mmxext);
382 DSPFUNC(put, 1, 8, mmxext);
383 DSPFUNC(avg, 0, 16, mmxext);
384 DSPFUNC(avg, 1, 8, mmxext);
385 }
386 #endif
387 #if HAVE_MMX_EXTERNAL
388 if (EXTERNAL_MMXEXT(cpu_flags)) {
389 c->avg_cavs_qpel_pixels_tab[1][0] = avg_cavs_qpel8_mc00_mmxext;
390 }
391 #endif
392 #if HAVE_SSE2_EXTERNAL
393 if (EXTERNAL_SSE2(cpu_flags)) {
394 c->put_cavs_qpel_pixels_tab[0][0] = put_cavs_qpel16_mc00_sse2;
395 c->avg_cavs_qpel_pixels_tab[0][0] = avg_cavs_qpel16_mc00_sse2;
396
397 c->cavs_idct8_add = cavs_idct8_add_sse2;
398 c->idct_perm = FF_IDCT_PERM_TRANSPOSE;
399 }
400 #endif
401 }
402