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
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
|
;*****************************************************************************
;* x86-optimized functions for blend filter
;*
;* Copyright (C) 2015 Paul B Mahol
;*
;* This file is part of FFmpeg.
;*
;* FFmpeg 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.
;*
;* FFmpeg 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 FFmpeg; if not, write to the Free Software
;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
;******************************************************************************
%include "libavutil/x86/x86util.asm"
%if ARCH_X86_64
SECTION_RODATA
pw_128: times 8 dw 128
pw_255: times 8 dw 255
SECTION .text
INIT_XMM sse2
cglobal blend_xor, 9, 10, 2, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movu m0, [topq + x]
movu m1, [bottomq + x]
pxor m0, m1
mova [dstq + x], m0
add r10q, mmsize
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
cglobal blend_or, 9, 10, 2, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movu m0, [topq + x]
movu m1, [bottomq + x]
por m0, m1
mova [dstq + x], m0
add r10q, mmsize
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
cglobal blend_and, 9, 10, 2, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movu m0, [topq + x]
movu m1, [bottomq + x]
pand m0, m1
mova [dstq + x], m0
add r10q, mmsize
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
cglobal blend_addition, 9, 10, 2, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movu m0, [topq + x]
movu m1, [bottomq + x]
paddusb m0, m1
mova [dstq + x], m0
add r10q, mmsize
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
cglobal blend_subtract, 9, 10, 2, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movu m0, [topq + x]
movu m1, [bottomq + x]
psubusb m0, m1
mova [dstq + x], m0
add r10q, mmsize
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
cglobal blend_difference128, 9, 10, 4, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
pxor m2, m2
mova m3, [pw_128]
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movh m0, [topq + x]
movh m1, [bottomq + x]
punpcklbw m0, m2
punpcklbw m1, m2
paddw m0, m3
psubw m0, m1
packuswb m0, m0
movh [dstq + x], m0
add r10q, mmsize / 2
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
cglobal blend_average, 9, 10, 3, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
pxor m2, m2
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movh m0, [topq + x]
movh m1, [bottomq + x]
punpcklbw m0, m2
punpcklbw m1, m2
paddw m0, m1
psrlw m0, 1
packuswb m0, m0
movh [dstq + x], m0
add r10q, mmsize / 2
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
cglobal blend_addition128, 9, 10, 4, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
pxor m2, m2
mova m3, [pw_128]
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movh m0, [topq + x]
movh m1, [bottomq + x]
punpcklbw m0, m2
punpcklbw m1, m2
paddw m0, m1
psubw m0, m3
packuswb m0, m0
movh [dstq + x], m0
add r10q, mmsize / 2
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
cglobal blend_darken, 9, 10, 2, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movu m0, [topq + x]
movu m1, [bottomq + x]
pminub m0, m1
mova [dstq + x], m0
add r10q, mmsize
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
cglobal blend_lighten, 9, 10, 2, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movu m0, [topq + x]
movu m1, [bottomq + x]
pmaxub m0, m1
mova [dstq + x], m0
add r10q, mmsize
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
INIT_XMM ssse3
cglobal blend_difference, 9, 10, 3, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
pxor m2, m2
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movh m0, [topq + x]
movh m1, [bottomq + x]
punpcklbw m0, m2
punpcklbw m1, m2
psubw m0, m1
pabsw m0, m0
packuswb m0, m0
movh [dstq + x], m0
add r10q, mmsize / 2
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
cglobal blend_negation, 9, 10, 5, 0, top, top_linesize, bottom, bottom_linesize, dst, dst_linesize, width, start, end
add topq, widthq
add bottomq, widthq
add dstq, widthq
sub endq, startq
pxor m2, m2
mova m4, [pw_255]
neg widthq
.nextrow:
mov r10q, widthq
%define x r10q
.loop:
movh m0, [topq + x]
movh m1, [bottomq + x]
punpcklbw m0, m2
punpcklbw m1, m2
mova m3, m4
psubw m3, m0
psubw m3, m1
pabsw m3, m3
mova m0, m4
psubw m0, m3
packuswb m0, m0
movh [dstq + x], m0
add r10q, mmsize / 2
jl .loop
add topq, top_linesizeq
add bottomq, bottom_linesizeq
add dstq, dst_linesizeq
sub endd, 1
jg .nextrow
REP_RET
%endif
|
