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
|
/*
* Copyright (c) 2024 Zhao Zhili <quinkblack@foxmail.com>
*
* 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/aarch64/asm.S"
.macro rgb_to_yuv_load_rgb src
ld3 { v16.16b, v17.16b, v18.16b }, [\src]
uxtl v19.8h, v16.8b // v19: r
uxtl v20.8h, v17.8b // v20: g
uxtl v21.8h, v18.8b // v21: b
uxtl2 v22.8h, v16.16b // v22: r
uxtl2 v23.8h, v17.16b // v23: g
uxtl2 v24.8h, v18.16b // v24: b
.endm
.macro rgb_to_yuv_product r, g, b, dst1, dst2, dst, coef0, coef1, coef2, right_shift
mov \dst1\().16b, v6.16b // dst1 = const_offset
mov \dst2\().16b, v6.16b // dst2 = const_offset
smlal \dst1\().4s, \coef0\().4h, \r\().4h // dst1 += rx * r
smlal \dst1\().4s, \coef1\().4h, \g\().4h // dst1 += gx * g
smlal \dst1\().4s, \coef2\().4h, \b\().4h // dst1 += bx * b
smlal2 \dst2\().4s, \coef0\().8h, \r\().8h // dst2 += rx * r
smlal2 \dst2\().4s, \coef1\().8h, \g\().8h // dst2 += gx * g
smlal2 \dst2\().4s, \coef2\().8h, \b\().8h // dst2 += bx * b
sqshrn \dst\().4h, \dst1\().4s, \right_shift // dst_lower_half = dst1 >> right_shift
sqshrn2 \dst\().8h, \dst2\().4s, \right_shift // dst_higher_half = dst2 >> right_shift
.endm
function ff_bgr24ToY_neon, export=1
cmp w4, #0 // check width > 0
ldp w12, w11, [x5] // w12: ry, w11: gy
ldr w10, [x5, #8] // w10: by
b.gt 4f
ret
endfunc
function ff_rgb24ToY_neon, export=1
cmp w4, #0 // check width > 0
ldp w10, w11, [x5] // w10: ry, w11: gy
ldr w12, [x5, #8] // w12: by
b.le 3f
4:
mov w9, #256 // w9 = 1 << (RGB2YUV_SHIFT - 7)
movk w9, #8, lsl #16 // w9 += 32 << (RGB2YUV_SHIFT - 1)
dup v6.4s, w9 // w9: const_offset
cmp w4, #16
dup v0.8h, w10
dup v1.8h, w11
dup v2.8h, w12
b.lt 2f
1:
rgb_to_yuv_load_rgb x1
rgb_to_yuv_product v19, v20, v21, v25, v26, v16, v0, v1, v2, #9
rgb_to_yuv_product v22, v23, v24, v27, v28, v17, v0, v1, v2, #9
sub w4, w4, #16 // width -= 16
add x1, x1, #48 // src += 48
cmp w4, #16 // width >= 16 ?
stp q16, q17, [x0], #32 // store to dst
b.ge 1b
cbz x4, 3f
2:
ldrb w13, [x1] // w13: r
ldrb w14, [x1, #1] // w14: g
ldrb w15, [x1, #2] // w15: b
smaddl x13, w13, w10, x9 // x13 = ry * r + const_offset
smaddl x13, w14, w11, x13 // x13 += gy * g
smaddl x13, w15, w12, x13 // x13 += by * b
asr w13, w13, #9 // x13 >>= 9
sub w4, w4, #1 // width--
add x1, x1, #3 // src += 3
strh w13, [x0], #2 // store to dst
cbnz w4, 2b
3:
ret
endfunc
.macro rgb_set_uv_coeff half
.if \half
mov w9, #512
movk w9, #128, lsl #16 // w9: const_offset
.else
mov w9, #256
movk w9, #64, lsl #16 // w9: const_offset
.endif
dup v0.8h, w10
dup v1.8h, w11
dup v2.8h, w12
dup v3.8h, w13
dup v4.8h, w14
dup v5.8h, w15
dup v6.4s, w9
.endm
function ff_bgr24ToUV_half_neon, export=1
cmp w5, #0 // check width > 0
b.le 3f
ldp w12, w11, [x6, #12]
ldp w10, w15, [x6, #20]
ldp w14, w13, [x6, #28]
b 4f
endfunc
function ff_rgb24ToUV_half_neon, export=1
cmp w5, #0 // check width > 0
b.le 3f
ldp w10, w11, [x6, #12] // w10: ru, w11: gu
ldp w12, w13, [x6, #20] // w12: bu, w13: rv
ldp w14, w15, [x6, #28] // w14: gv, w15: bv
4:
cmp w5, #8
rgb_set_uv_coeff half=1
b.lt 2f
1:
ld3 { v16.16b, v17.16b, v18.16b }, [x3]
uaddlp v19.8h, v16.16b // v19: r
uaddlp v20.8h, v17.16b // v20: g
uaddlp v21.8h, v18.16b // v21: b
rgb_to_yuv_product v19, v20, v21, v22, v23, v16, v0, v1, v2, #10
rgb_to_yuv_product v19, v20, v21, v24, v25, v17, v3, v4, v5, #10
sub w5, w5, #8 // width -= 8
add x3, x3, #48 // src += 48
cmp w5, #8 // width >= 8 ?
str q16, [x0], #16 // store dst_u
str q17, [x1], #16 // store dst_v
b.ge 1b
cbz w5, 3f
2:
ldrb w2, [x3] // w2: r1
ldrb w4, [x3, #3] // w4: r2
add w2, w2, w4 // w2 = r1 + r2
ldrb w4, [x3, #1] // w4: g1
ldrb w7, [x3, #4] // w7: g2
add w4, w4, w7 // w4 = g1 + g2
ldrb w7, [x3, #2] // w7: b1
ldrb w8, [x3, #5] // w8: b2
add w7, w7, w8 // w7 = b1 + b2
smaddl x8, w2, w10, x9 // dst_u = ru * r + const_offset
smaddl x8, w4, w11, x8 // dst_u += gu * g
smaddl x8, w7, w12, x8 // dst_u += bu * b
asr x8, x8, #10 // dst_u >>= 10
strh w8, [x0], #2 // store dst_u
smaddl x8, w2, w13, x9 // dst_v = rv * r + const_offset
smaddl x8, w4, w14, x8 // dst_v += gv * g
smaddl x8, w7, w15, x8 // dst_v += bv * b
asr x8, x8, #10 // dst_v >>= 10
sub w5, w5, #1
add x3, x3, #6 // src += 6
strh w8, [x1], #2 // store dst_v
cbnz w5, 2b
3:
ret
endfunc
function ff_bgr24ToUV_neon, export=1
cmp w5, #0 // check width > 0
b.le 3f
ldp w12, w11, [x6, #12]
ldp w10, w15, [x6, #20]
ldp w14, w13, [x6, #28]
b 4f
endfunc
function ff_rgb24ToUV_neon, export=1
cmp w5, #0 // check width > 0
b.le 3f
ldp w10, w11, [x6, #12] // w10: ru, w11: gu
ldp w12, w13, [x6, #20] // w12: bu, w13: rv
ldp w14, w15, [x6, #28] // w14: gv, w15: bv
4:
cmp w5, #16
rgb_set_uv_coeff half=0
b.lt 2f
1:
rgb_to_yuv_load_rgb x3
rgb_to_yuv_product v19, v20, v21, v25, v26, v16, v0, v1, v2, #9
rgb_to_yuv_product v22, v23, v24, v27, v28, v17, v0, v1, v2, #9
rgb_to_yuv_product v19, v20, v21, v25, v26, v18, v3, v4, v5, #9
rgb_to_yuv_product v22, v23, v24, v27, v28, v19, v3, v4, v5, #9
sub w5, w5, #16
add x3, x3, #48 // src += 48
cmp w5, #16
stp q16, q17, [x0], #32 // store to dst_u
stp q18, q19, [x1], #32 // store to dst_v
b.ge 1b
cbz w5, 3f
2:
ldrb w16, [x3] // w16: r
ldrb w17, [x3, #1] // w17: g
ldrb w4, [x3, #2] // w4: b
smaddl x8, w16, w10, x9 // x8 = ru * r + const_offset
smaddl x8, w17, w11, x8 // x8 += gu * g
smaddl x8, w4, w12, x8 // x8 += bu * b
asr w8, w8, #9 // x8 >>= 9
strh w8, [x0], #2 // store to dst_u
smaddl x8, w16, w13, x9 // x8 = rv * r + const_offset
smaddl x8, w17, w14, x8 // x8 += gv * g
smaddl x8, w4, w15, x8 // x8 += bv * b
asr w8, w8, #9 // x8 >>= 9
sub w5, w5, #1 // width--
add x3, x3, #3 // src += 3
strh w8, [x1], #2 // store to dst_v
cbnz w5, 2b
3:
ret
endfunc
|
