1 /*
2 * VP8 compatible video decoder
3 *
4 * Copyright (C) 2010 David Conrad
5 *
6 * This file is part of FFmpeg.
7 *
8 * FFmpeg is free software; you can redistribute it and/or
9 * modify it under the terms of the GNU Lesser General Public
10 * License as published by the Free Software Foundation; either
11 * version 2.1 of the License, or (at your option) any later version.
12 *
13 * FFmpeg is distributed in the hope that it will be useful,
14 * but WITHOUT ANY WARRANTY; without even the implied warranty of
15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16 * Lesser General Public License for more details.
17 *
18 * You should have received a copy of the GNU Lesser General Public
19 * License along with FFmpeg; if not, write to the Free Software
20 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
21 */
22
23 #include "config.h"
24
25 #include "libavutil/attributes.h"
26 #include "libavutil/cpu.h"
27 #include "libavutil/mem_internal.h"
28 #include "libavutil/ppc/cpu.h"
29 #include "libavutil/ppc/util_altivec.h"
30
31 #include "libavcodec/vp8dsp.h"
32
33 #include "hpeldsp_altivec.h"
34
35 #if HAVE_ALTIVEC
36 #define REPT4(...) { __VA_ARGS__, __VA_ARGS__, __VA_ARGS__, __VA_ARGS__ }
37
38 // h subpel filter uses msum to multiply+add 4 pixel taps at once
39 static const vec_s8 h_subpel_filters_inner[7] =
40 {
41 REPT4( -6, 123, 12, -1),
42 REPT4(-11, 108, 36, -8),
43 REPT4( -9, 93, 50, -6),
44 REPT4(-16, 77, 77, -16),
45 REPT4( -6, 50, 93, -9),
46 REPT4( -8, 36, 108, -11),
47 REPT4( -1, 12, 123, -6),
48 };
49
50 // for 6tap filters, these are the outer two taps
51 // The zeros mask off pixels 4-7 when filtering 0-3
52 // and vice-versa
53 static const vec_s8 h_subpel_filters_outer[3] =
54 {
55 REPT4(0, 0, 2, 1),
56 REPT4(0, 0, 3, 3),
57 REPT4(0, 0, 1, 2),
58 };
59
60 #define LOAD_H_SUBPEL_FILTER(i) \
61 vec_s8 filter_inner = h_subpel_filters_inner[i]; \
62 vec_s8 filter_outerh = h_subpel_filters_outer[(i)>>1]; \
63 vec_s8 filter_outerl = vec_sld(filter_outerh, filter_outerh, 2)
64
65 #if HAVE_BIGENDIAN
66 #define GET_PIXHL(offset) \
67 a = vec_ld((offset)-is6tap-1, src); \
68 b = vec_ld((offset)-is6tap-1+15, src); \
69 pixh = vec_perm(a, b, permh##offset); \
70 pixl = vec_perm(a, b, perml##offset)
71
72 #define GET_OUTER(offset) outer = vec_perm(a, b, perm_6tap##offset)
73 #else
74 #define GET_PIXHL(offset) \
75 a = vec_vsx_ld((offset)-is6tap-1, src); \
76 pixh = vec_perm(a, a, perm_inner); \
77 pixl = vec_perm(a, a, vec_add(perm_inner, vec_splat_u8(4)))
78
79 #define GET_OUTER(offset) outer = vec_perm(a, a, perm_outer)
80 #endif
81
82 #define FILTER_H(dstv, off) \
83 GET_PIXHL(off); \
84 filth = vec_msum(filter_inner, pixh, c64); \
85 filtl = vec_msum(filter_inner, pixl, c64); \
86 \
87 if (is6tap) { \
88 GET_OUTER(off); \
89 filth = vec_msum(filter_outerh, outer, filth); \
90 filtl = vec_msum(filter_outerl, outer, filtl); \
91 } \
92 if (w == 4) \
93 filtl = filth; /* discard pixels 4-7 */ \
94 dstv = vec_packs(filth, filtl); \
95 dstv = vec_sra(dstv, c7)
96
97 static av_always_inline
put_vp8_epel_h_altivec_core(uint8_t *dst, ptrdiff_t dst_stride, uint8_t *src, ptrdiff_t src_stride, int h, int mx, int w, int is6tap)98 void put_vp8_epel_h_altivec_core(uint8_t *dst, ptrdiff_t dst_stride,
99 uint8_t *src, ptrdiff_t src_stride,
100 int h, int mx, int w, int is6tap)
101 {
102 LOAD_H_SUBPEL_FILTER(mx-1);
103 #if HAVE_BIGENDIAN
104 vec_u8 align_vec0, align_vec8, permh0, permh8;
105 vec_u8 perm_6tap0, perm_6tap8, perml0, perml8;
106 vec_u8 b;
107 #endif
108 vec_u8 filt, a, pixh, pixl, outer;
109 vec_s16 f16h, f16l;
110 vec_s32 filth, filtl;
111
112 vec_u8 perm_inner6 = { 1,2,3,4, 2,3,4,5, 3,4,5,6, 4,5,6,7 };
113 vec_u8 perm_inner4 = { 0,1,2,3, 1,2,3,4, 2,3,4,5, 3,4,5,6 };
114 vec_u8 perm_inner = is6tap ? perm_inner6 : perm_inner4;
115 vec_u8 perm_outer = { 4,9, 0,5, 5,10, 1,6, 6,11, 2,7, 7,12, 3,8 };
116 vec_s32 c64 = vec_sl(vec_splat_s32(1), vec_splat_u32(6));
117 vec_u16 c7 = vec_splat_u16(7);
118
119 #if HAVE_BIGENDIAN
120 align_vec0 = vec_lvsl( -is6tap-1, src);
121 align_vec8 = vec_lvsl(8-is6tap-1, src);
122
123 permh0 = vec_perm(align_vec0, align_vec0, perm_inner);
124 permh8 = vec_perm(align_vec8, align_vec8, perm_inner);
125 perm_inner = vec_add(perm_inner, vec_splat_u8(4));
126 perml0 = vec_perm(align_vec0, align_vec0, perm_inner);
127 perml8 = vec_perm(align_vec8, align_vec8, perm_inner);
128 perm_6tap0 = vec_perm(align_vec0, align_vec0, perm_outer);
129 perm_6tap8 = vec_perm(align_vec8, align_vec8, perm_outer);
130 #endif
131
132 while (h --> 0) {
133 FILTER_H(f16h, 0);
134
135 if (w == 16) {
136 FILTER_H(f16l, 8);
137 filt = vec_packsu(f16h, f16l);
138 vec_st(filt, 0, dst);
139 } else {
140 filt = vec_packsu(f16h, f16h);
141 vec_ste((vec_u32)filt, 0, (uint32_t*)dst);
142 if (w == 8)
143 vec_ste((vec_u32)filt, 4, (uint32_t*)dst);
144 }
145 src += src_stride;
146 dst += dst_stride;
147 }
148 }
149
150 // v subpel filter does a simple vertical multiply + add
151 static const vec_u8 v_subpel_filters[7] =
152 {
153 { 0, 6, 123, 12, 1, 0 },
154 { 2, 11, 108, 36, 8, 1 },
155 { 0, 9, 93, 50, 6, 0 },
156 { 3, 16, 77, 77, 16, 3 },
157 { 0, 6, 50, 93, 9, 0 },
158 { 1, 8, 36, 108, 11, 2 },
159 { 0, 1, 12, 123, 6, 0 },
160 };
161
162 #define LOAD_V_SUBPEL_FILTER(i) \
163 vec_u8 subpel_filter = v_subpel_filters[i]; \
164 vec_u8 f0 = vec_splat(subpel_filter, 0); \
165 vec_u8 f1 = vec_splat(subpel_filter, 1); \
166 vec_u8 f2 = vec_splat(subpel_filter, 2); \
167 vec_u8 f3 = vec_splat(subpel_filter, 3); \
168 vec_u8 f4 = vec_splat(subpel_filter, 4); \
169 vec_u8 f5 = vec_splat(subpel_filter, 5)
170
171 #define FILTER_V(dstv, vec_mul) \
172 s1f = (vec_s16)vec_mul(s1, f1); \
173 s2f = (vec_s16)vec_mul(s2, f2); \
174 s3f = (vec_s16)vec_mul(s3, f3); \
175 s4f = (vec_s16)vec_mul(s4, f4); \
176 s2f = vec_subs(s2f, s1f); \
177 s3f = vec_subs(s3f, s4f); \
178 if (is6tap) { \
179 s0f = (vec_s16)vec_mul(s0, f0); \
180 s5f = (vec_s16)vec_mul(s5, f5); \
181 s2f = vec_adds(s2f, s0f); \
182 s3f = vec_adds(s3f, s5f); \
183 } \
184 dstv = vec_adds(s2f, s3f); \
185 dstv = vec_adds(dstv, c64); \
186 dstv = vec_sra(dstv, c7)
187
188 #if HAVE_BIGENDIAN
189 #define LOAD_HL(off, s, perm) load_with_perm_vec(off, s, perm)
190 #else
191 #define LOAD_HL(off, s, perm) vec_mergeh(vec_vsx_ld(off,s), vec_vsx_ld(off+8,s))
192 #endif
193
194 static av_always_inline
put_vp8_epel_v_altivec_core(uint8_t *dst, ptrdiff_t dst_stride, uint8_t *src, ptrdiff_t src_stride, int h, int my, int w, int is6tap)195 void put_vp8_epel_v_altivec_core(uint8_t *dst, ptrdiff_t dst_stride,
196 uint8_t *src, ptrdiff_t src_stride,
197 int h, int my, int w, int is6tap)
198 {
199 LOAD_V_SUBPEL_FILTER(my-1);
200 vec_u8 s0, s1, s2, s3, s4, s5, filt, align_vech, perm_vec, align_vecl;
201 vec_s16 s0f, s1f, s2f, s3f, s4f, s5f, f16h, f16l;
202 vec_s16 c64 = vec_sl(vec_splat_s16(1), vec_splat_u16(6));
203 vec_u16 c7 = vec_splat_u16(7);
204
205 #if HAVE_BIGENDIAN
206 // we want pixels 0-7 to be in the even positions and 8-15 in the odd,
207 // so combine this permute with the alignment permute vector
208 align_vech = vec_lvsl(0, src);
209 align_vecl = vec_sld(align_vech, align_vech, 8);
210 if (w ==16)
211 perm_vec = vec_mergeh(align_vech, align_vecl);
212 else
213 perm_vec = vec_mergeh(align_vech, align_vech);
214 #endif
215
216 if (is6tap)
217 s0 = LOAD_HL(-2*src_stride, src, perm_vec);
218 s1 = LOAD_HL(-1*src_stride, src, perm_vec);
219 s2 = LOAD_HL( 0*src_stride, src, perm_vec);
220 s3 = LOAD_HL( 1*src_stride, src, perm_vec);
221 if (is6tap)
222 s4 = LOAD_HL( 2*src_stride, src, perm_vec);
223
224 src += (2+is6tap)*src_stride;
225
226 while (h --> 0) {
227 if (is6tap)
228 s5 = LOAD_HL(0, src, perm_vec);
229 else
230 s4 = LOAD_HL(0, src, perm_vec);
231
232 FILTER_V(f16h, vec_mule);
233
234 if (w == 16) {
235 FILTER_V(f16l, vec_mulo);
236 filt = vec_packsu(f16h, f16l);
237 vec_st(filt, 0, dst);
238 } else {
239 filt = vec_packsu(f16h, f16h);
240 if (w == 4)
241 filt = (vec_u8)vec_splat((vec_u32)filt, 0);
242 else
243 vec_ste((vec_u32)filt, 4, (uint32_t*)dst);
244 vec_ste((vec_u32)filt, 0, (uint32_t*)dst);
245 }
246
247 if (is6tap)
248 s0 = s1;
249 s1 = s2;
250 s2 = s3;
251 s3 = s4;
252 if (is6tap)
253 s4 = s5;
254
255 dst += dst_stride;
256 src += src_stride;
257 }
258 }
259
260 #define EPEL_FUNCS(WIDTH, TAPS) \
261 static av_noinline \
262 void put_vp8_epel ## WIDTH ## _h ## TAPS ## _altivec(uint8_t *dst, ptrdiff_t dst_stride, uint8_t *src, ptrdiff_t src_stride, int h, int mx, int my) \
263 { \
264 put_vp8_epel_h_altivec_core(dst, dst_stride, src, src_stride, h, mx, WIDTH, TAPS == 6); \
265 } \
266 \
267 static av_noinline \
268 void put_vp8_epel ## WIDTH ## _v ## TAPS ## _altivec(uint8_t *dst, ptrdiff_t dst_stride, uint8_t *src, ptrdiff_t src_stride, int h, int mx, int my) \
269 { \
270 put_vp8_epel_v_altivec_core(dst, dst_stride, src, src_stride, h, my, WIDTH, TAPS == 6); \
271 }
272
273 #define EPEL_HV(WIDTH, HTAPS, VTAPS) \
274 static void put_vp8_epel ## WIDTH ## _h ## HTAPS ## v ## VTAPS ## _altivec(uint8_t *dst, ptrdiff_t dstride, uint8_t *src, ptrdiff_t sstride, int h, int mx, int my) \
275 { \
276 DECLARE_ALIGNED(16, uint8_t, tmp)[(2*WIDTH+5)*16]; \
277 if (VTAPS == 6) { \
278 put_vp8_epel ## WIDTH ## _h ## HTAPS ## _altivec(tmp, 16, src-2*sstride, sstride, h+5, mx, my); \
279 put_vp8_epel ## WIDTH ## _v ## VTAPS ## _altivec(dst, dstride, tmp+2*16, 16, h, mx, my); \
280 } else { \
281 put_vp8_epel ## WIDTH ## _h ## HTAPS ## _altivec(tmp, 16, src-sstride, sstride, h+4, mx, my); \
282 put_vp8_epel ## WIDTH ## _v ## VTAPS ## _altivec(dst, dstride, tmp+16, 16, h, mx, my); \
283 } \
284 }
285
286 EPEL_FUNCS(16,6)
287 EPEL_FUNCS(8, 6)
288 EPEL_FUNCS(8, 4)
289 EPEL_FUNCS(4, 6)
290 EPEL_FUNCS(4, 4)
291
292 EPEL_HV(16, 6,6)
293 EPEL_HV(8, 6,6)
294 EPEL_HV(8, 4,6)
295 EPEL_HV(8, 6,4)
296 EPEL_HV(8, 4,4)
297 EPEL_HV(4, 6,6)
298 EPEL_HV(4, 4,6)
299 EPEL_HV(4, 6,4)
300 EPEL_HV(4, 4,4)
301
put_vp8_pixels16_altivec(uint8_t *dst, ptrdiff_t dstride, uint8_t *src, ptrdiff_t sstride, int h, int mx, int my)302 static void put_vp8_pixels16_altivec(uint8_t *dst, ptrdiff_t dstride, uint8_t *src, ptrdiff_t sstride, int h, int mx, int my)
303 {
304 register vector unsigned char perm;
305 int i;
306 register ptrdiff_t dstride2 = dstride << 1, sstride2 = sstride << 1;
307 register ptrdiff_t dstride3 = dstride2 + dstride, sstride3 = sstride + sstride2;
308 register ptrdiff_t dstride4 = dstride << 2, sstride4 = sstride << 2;
309
310 #if HAVE_BIGENDIAN
311 perm = vec_lvsl(0, src);
312 #endif
313 // hand-unrolling the loop by 4 gains about 15%
314 // mininum execution time goes from 74 to 60 cycles
315 // it's faster than -funroll-loops, but using
316 // -funroll-loops w/ this is bad - 74 cycles again.
317 // all this is on a 7450, tuning for the 7450
318 for (i = 0; i < h; i += 4) {
319 vec_st(load_with_perm_vec(0, src, perm), 0, dst);
320 vec_st(load_with_perm_vec(sstride, src, perm), dstride, dst);
321 vec_st(load_with_perm_vec(sstride2, src, perm), dstride2, dst);
322 vec_st(load_with_perm_vec(sstride3, src, perm), dstride3, dst);
323 src += sstride4;
324 dst += dstride4;
325 }
326 }
327
328 #endif /* HAVE_ALTIVEC */
329
330
ff_vp78dsp_init_ppc(VP8DSPContext *c)331 av_cold void ff_vp78dsp_init_ppc(VP8DSPContext *c)
332 {
333 #if HAVE_ALTIVEC
334 if (!PPC_ALTIVEC(av_get_cpu_flags()))
335 return;
336
337 c->put_vp8_epel_pixels_tab[0][0][0] = put_vp8_pixels16_altivec;
338 c->put_vp8_epel_pixels_tab[0][0][2] = put_vp8_epel16_h6_altivec;
339 c->put_vp8_epel_pixels_tab[0][2][0] = put_vp8_epel16_v6_altivec;
340 c->put_vp8_epel_pixels_tab[0][2][2] = put_vp8_epel16_h6v6_altivec;
341
342 c->put_vp8_epel_pixels_tab[1][0][2] = put_vp8_epel8_h6_altivec;
343 c->put_vp8_epel_pixels_tab[1][2][0] = put_vp8_epel8_v6_altivec;
344 c->put_vp8_epel_pixels_tab[1][0][1] = put_vp8_epel8_h4_altivec;
345 c->put_vp8_epel_pixels_tab[1][1][0] = put_vp8_epel8_v4_altivec;
346
347 c->put_vp8_epel_pixels_tab[1][2][2] = put_vp8_epel8_h6v6_altivec;
348 c->put_vp8_epel_pixels_tab[1][1][1] = put_vp8_epel8_h4v4_altivec;
349 c->put_vp8_epel_pixels_tab[1][1][2] = put_vp8_epel8_h6v4_altivec;
350 c->put_vp8_epel_pixels_tab[1][2][1] = put_vp8_epel8_h4v6_altivec;
351
352 c->put_vp8_epel_pixels_tab[2][0][2] = put_vp8_epel4_h6_altivec;
353 c->put_vp8_epel_pixels_tab[2][2][0] = put_vp8_epel4_v6_altivec;
354 c->put_vp8_epel_pixels_tab[2][0][1] = put_vp8_epel4_h4_altivec;
355 c->put_vp8_epel_pixels_tab[2][1][0] = put_vp8_epel4_v4_altivec;
356
357 c->put_vp8_epel_pixels_tab[2][2][2] = put_vp8_epel4_h6v6_altivec;
358 c->put_vp8_epel_pixels_tab[2][1][1] = put_vp8_epel4_h4v4_altivec;
359 c->put_vp8_epel_pixels_tab[2][1][2] = put_vp8_epel4_h6v4_altivec;
360 c->put_vp8_epel_pixels_tab[2][2][1] = put_vp8_epel4_h4v6_altivec;
361 #endif /* HAVE_ALTIVEC */
362 }
363