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
|
.function video_mixer_orc_splat_u32
.dest 4 d1 guint32
.param 4 p1 guint32
copyl d1, p1
.function video_mixer_orc_memcpy_u32
.dest 4 d1 guint32
.source 4 s1 guint32
copyl d1, s1
.function video_mixer_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 video_mixer_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 shruw a_wide, a_wide, 8
x4 convubw s_wide, t
loadl t, d
x4 convubw d_wide, t
x4 subw s_wide, s_wide, d_wide
x4 mullw s_wide, s_wide, a_wide
x4 div255w s_wide, s_wide
x4 addw d_wide, d_wide, s_wide
x4 convwb t, d_wide
orl t, t, a_alpha
storel d, t
.function video_mixer_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 shruw a_wide, a_wide, 8
x4 convubw s_wide, t
loadl t, d
x4 convubw d_wide, t
x4 subw s_wide, s_wide, d_wide
x4 mullw s_wide, s_wide, a_wide
x4 div255w s_wide, s_wide
x4 addw d_wide, d_wide, s_wide
x4 convwb t, d_wide
orl t, t, a_alpha
storel d, t
.function video_mixer_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 / 256
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 shruw alpha_s, alpha_s, 8
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 video_mixer_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 / 256
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 shruw alpha_s, alpha_s, 8
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
|
