/
compositororc.orc
433 lines (375 loc) · 8.57 KB
/
compositororc.orc
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
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
.function compositor_orc_splat_u32
.dest 4 d1 guint32
.param 4 p1 guint32
copyl d1, p1
.function compositor_orc_memcpy_u32
.dest 4 d1 guint32
.source 4 s1 guint32
copyl d1, s1
.function compositor_orc_blend_u8
.flags 2d
.dest 1 d1 guint8
.source 1 s1 guint8
.param 2 p1
.temp 2 t1
.temp 2 t2
.const 1 c1 8
convubw t1, d1
convubw t2, s1
subw t2, t2, t1
mullw t2, t2, p1
shlw t1, t1, c1
addw t2, t1, t2
shruw t2, t2, c1
convsuswb d1, t2
.function compositor_orc_blend_argb
.flags 2d
.dest 4 d guint8
.source 4 s guint8
.param 2 alpha
.temp 4 t
.temp 2 tw
.temp 1 tb
.temp 4 a
.temp 8 d_wide
.temp 8 s_wide
.temp 8 a_wide
.const 4 a_alpha 0x000000ff
loadl t, s
convlw tw, t
convwb tb, tw
splatbl a, tb
x4 convubw a_wide, a
x4 mullw a_wide, a_wide, alpha
x4 div255w a_wide, a_wide
x4 convubw s_wide, t
x4 mullw s_wide, s_wide, a_wide
# calc 255-alpha
x4 subw a_wide, 0xff, a_wide
loadl t, d
x4 convubw d_wide, t
x4 mullw d_wide, d_wide, a_wide
x4 addw d_wide, d_wide, s_wide
x4 div255w d_wide, d_wide
x4 convwb t, d_wide
orl t, t, a_alpha
storel d, t
.function compositor_orc_source_argb
.flags 2d
.dest 4 d guint8
.source 4 s guint8
.param 2 alpha
.temp 4 t
.temp 4 t2
.temp 2 tw
.temp 1 tb
.temp 4 a
.temp 8 a_wide
.const 4 a_alpha 0x000000ff
.const 4 a_not_alpha 0xffffff00
loadl t, s
convlw tw, t
convwb tb, tw
splatbl a, tb
x4 convubw a_wide, a
x4 mullw a_wide, a_wide, alpha
x4 div255w a_wide, a_wide
andl t, t, a_not_alpha
x4 convwb t2, a_wide
andl t2, t2, a_alpha
orl t, t, t2
storel d, t
.function compositor_orc_blend_bgra
.flags 2d
.dest 4 d guint8
.source 4 s guint8
.param 2 alpha
.temp 4 t
.temp 4 t2
.temp 2 tw
.temp 1 tb
.temp 4 a
.temp 8 d_wide
.temp 8 s_wide
.temp 8 a_wide
.const 4 a_alpha 0xff000000
loadl t, s
shrul t2, t, 24
convlw tw, t2
convwb tb, tw
splatbl a, tb
x4 convubw a_wide, a
x4 mullw a_wide, a_wide, alpha
x4 div255w a_wide, a_wide
x4 convubw s_wide, t
x4 mullw s_wide, s_wide, a_wide
# calc 255-alpha
x4 subw a_wide, 0xff, a_wide
loadl t, d
x4 convubw d_wide, t
x4 mullw d_wide, d_wide, a_wide
x4 addw d_wide, d_wide, s_wide
x4 div255w d_wide, d_wide
x4 convwb t, d_wide
orl t, t, a_alpha
storel d, t
.function compositor_orc_source_bgra
.flags 2d
.dest 4 d guint8
.source 4 s guint8
.param 2 alpha
.temp 4 t
.temp 4 t2
.temp 2 tw
.temp 1 tb
.temp 4 a
.temp 8 a_wide
.const 4 a_alpha 0xff000000
.const 4 a_not_alpha 0x00ffffff
loadl t, s
convhlw tw, t
convhwb tb, tw
splatbl a, tb
x4 convubw a_wide, a
x4 mullw a_wide, a_wide, alpha
x4 div255w a_wide, a_wide
andl t, t, a_not_alpha
x4 convwb t2, a_wide
andl t2, t2, a_alpha
orl t, t, t2
storel d, t
.function compositor_orc_overlay_argb
.flags 2d
.dest 4 d guint8
.source 4 s guint8
.param 2 alpha
.temp 4 t
.temp 2 tw
.temp 1 tb
.temp 8 alpha_s
.temp 8 alpha_s_inv
.temp 8 alpha_d
.temp 4 a
.temp 8 d_wide
.temp 8 s_wide
.const 4 xfs 0xffffffff
.const 4 a_alpha 0x000000ff
.const 4 a_alpha_inv 0xffffff00
# calc source alpha as alpha_s = alpha_s * alpha / 255
loadl t, s
convlw tw, t
convwb tb, tw
splatbl a, tb
x4 convubw alpha_s, a
x4 mullw alpha_s, alpha_s, alpha
x4 div255w alpha_s, alpha_s
x4 convubw s_wide, t
x4 mullw s_wide, s_wide, alpha_s
# calc destination alpha as alpha_d = (255-alpha_s) * alpha_d / 255
loadpl a, xfs
x4 convubw alpha_s_inv, a
x4 subw alpha_s_inv, alpha_s_inv, alpha_s
loadl t, d
convlw tw, t
convwb tb, tw
splatbl a, tb
x4 convubw alpha_d, a
x4 mullw alpha_d, alpha_d, alpha_s_inv
x4 div255w alpha_d, alpha_d
x4 convubw d_wide, t
x4 mullw d_wide, d_wide, alpha_d
# calc final pixel as pix_d = pix_s*alpha_s + pix_d*alpha_d*(255-alpha_s)/255
x4 addw d_wide, d_wide, s_wide
# calc the final destination alpha_d = alpha_s + alpha_d * (255-alpha_s)/255
x4 addw alpha_d, alpha_d, alpha_s
# now normalize the pix_d by the final alpha to make it associative
x4 divluw, d_wide, d_wide, alpha_d
# pack the new alpha into the correct spot
x4 convwb t, d_wide
andl t, t, a_alpha_inv
x4 convwb a, alpha_d
andl a, a, a_alpha
orl t, t, a
storel d, t
.function compositor_orc_overlay_argb_addition
.flags 2d
.dest 4 d guint8
.source 4 s guint8
.param 2 alpha
.temp 4 t
.temp 2 tw
.temp 1 tb
.temp 8 alpha_s
.temp 8 alpha_s_inv
.temp 8 alpha_factor
.temp 8 alpha_d
.temp 4 a
.temp 8 d_wide
.temp 8 s_wide
.const 4 xfs 0xffffffff
.const 4 a_alpha 0x000000ff
.const 4 a_alpha_inv 0xffffff00
# calc source alpha as alpha_s = alpha_s * alpha / 255
loadl t, s
convlw tw, t
convwb tb, tw
splatbl a, tb
x4 convubw alpha_s, a
x4 mullw alpha_s, alpha_s, alpha
x4 div255w alpha_s, alpha_s
x4 convubw s_wide, t
x4 mullw s_wide, s_wide, alpha_s
# calc destination alpha as alpha_factor = (255-alpha_s) * alpha_factor / factor
loadpl a, xfs
x4 convubw alpha_s_inv, a
x4 subw alpha_s_inv, alpha_s_inv, alpha_s
loadl t, d
convlw tw, t
convwb tb, tw
splatbl a, tb
x4 convubw alpha_factor, a
x4 mullw alpha_factor, alpha_factor, alpha_s_inv
x4 div255w alpha_factor, alpha_factor
x4 convubw d_wide, t
x4 mullw d_wide, d_wide, alpha_factor
# calc final pixel as pix_d = pix_s*alpha_s + pix_d*alpha_factor*(255-alpha_s)/255
x4 addw d_wide, d_wide, s_wide
# calc the alpha factor alpha_factor = alpha_s + alpha_factor * (255-alpha_s)/255
x4 addw alpha_factor, alpha_factor, alpha_s
# now normalize the pix_d by the final alpha to make it associative
x4 divluw, d_wide, d_wide, alpha_factor
# calc the final global alpha_d = alpha_d + (alpha_s * (alpha / 255))
loadl t, d
convlw tw, t
convwb tb, tw
splatbl a, tb
x4 convubw alpha_d, a
x4 addw alpha_d, alpha_d, alpha_s
# pack the new alpha into the correct spot
x4 convwb t, d_wide
andl t, t, a_alpha_inv
x4 convwb a, alpha_d
andl a, a, a_alpha
orl t, t, a
storel d, t
.function compositor_orc_overlay_bgra
.flags 2d
.dest 4 d guint8
.source 4 s guint8
.param 2 alpha
.temp 4 t
.temp 4 t2
.temp 2 tw
.temp 1 tb
.temp 8 alpha_s
.temp 8 alpha_s_inv
.temp 8 alpha_d
.temp 4 a
.temp 8 d_wide
.temp 8 s_wide
.const 4 xfs 0xffffffff
.const 4 a_alpha 0xff000000
.const 4 a_alpha_inv 0x00ffffff
# calc source alpha as alpha_s = alpha_s * alpha / 255
loadl t, s
shrul t2, t, 24
convlw tw, t2
convwb tb, tw
splatbl a, tb
x4 convubw alpha_s, a
x4 mullw alpha_s, alpha_s, alpha
x4 div255w alpha_s, alpha_s
x4 convubw s_wide, t
x4 mullw s_wide, s_wide, alpha_s
# calc destination alpha as alpha_d = (255-alpha_s) * alpha_d / 255
loadpl a, xfs
x4 convubw alpha_s_inv, a
x4 subw alpha_s_inv, alpha_s_inv, alpha_s
loadl t, d
shrul t2, t, 24
convlw tw, t2
convwb tb, tw
splatbl a, tb
x4 convubw alpha_d, a
x4 mullw alpha_d, alpha_d, alpha_s_inv
x4 div255w alpha_d, alpha_d
x4 convubw d_wide, t
x4 mullw d_wide, d_wide, alpha_d
# calc final pixel as pix_d = pix_s*alpha_s + pix_d*alpha_d*(255-alpha_s)/255
x4 addw d_wide, d_wide, s_wide
# calc the final destination alpha_d = alpha_s + alpha_d * (255-alpha_s)/255
x4 addw alpha_d, alpha_d, alpha_s
# now normalize the pix_d by the final alpha to make it associative
x4 divluw, d_wide, d_wide, alpha_d
# pack the new alpha into the correct spot
x4 convwb t, d_wide
andl t, t, a_alpha_inv
x4 convwb a, alpha_d
andl a, a, a_alpha
orl t, t, a
storel d, t
.function compositor_orc_overlay_bgra_addition
.flags 2d
.dest 4 d guint8
.source 4 s guint8
.param 2 alpha
.temp 4 t
.temp 4 t2
.temp 2 tw
.temp 1 tb
.temp 8 alpha_s
.temp 8 alpha_s_inv
.temp 8 alpha_factor
.temp 8 alpha_d
.temp 4 a
.temp 8 d_wide
.temp 8 s_wide
.const 4 xfs 0xffffffff
.const 4 a_alpha 0xff000000
.const 4 a_alpha_inv 0x00ffffff
# calc source alpha as alpha_s = alpha_s * alpha / 255
loadl t, s
shrul t2, t, 24
convlw tw, t2
convwb tb, tw
splatbl a, tb
x4 convubw alpha_s, a
x4 mullw alpha_s, alpha_s, alpha
x4 div255w alpha_s, alpha_s
x4 convubw s_wide, t
x4 mullw s_wide, s_wide, alpha_s
# calc destination alpha as alpha_factor = (255-alpha_s) * alpha_factor / 255
loadpl a, xfs
x4 convubw alpha_s_inv, a
x4 subw alpha_s_inv, alpha_s_inv, alpha_s
loadl t, d
shrul t2, t, 24
convlw tw, t2
convwb tb, tw
splatbl a, tb
x4 convubw alpha_factor, a
x4 mullw alpha_factor, alpha_factor, alpha_s_inv
x4 div255w alpha_factor, alpha_factor
x4 convubw d_wide, t
x4 mullw d_wide, d_wide, alpha_factor
# calc final pixel as pix_d = pix_s*alpha_s + pix_d*alpha_factor*(255-alpha_s)/255
x4 addw d_wide, d_wide, s_wide
# calc the final destination alpha_factor = alpha_s + alpha_factor * (255-alpha_s)/255
x4 addw alpha_factor, alpha_factor, alpha_s
# now normalize the pix_d by the final alpha to make it associative
x4 divluw, d_wide, d_wide, alpha_factor
# calc the final global alpha_d = alpha_d + (alpha_s * (alpha / 255))
loadl t, d
shrul t2, t, 24
convlw tw, t2
convwb tb, tw
splatbl a, tb
x4 convubw alpha_d, a
x4 addw alpha_d, alpha_d, alpha_s
# pack the new alpha into the correct spot
x4 convwb t, d_wide
andl t, t, a_alpha_inv
x4 convwb a, alpha_d
andl a, a, a_alpha
orl t, t, a
storel d, t