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
|
/*
* Copyright (c) 2016 Clément Bœsch <clement stupeflix.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"
function ff_yuv2planeX_8_neon, export=1
// x0 - const int16_t *filter,
// x1 - int filterSize,
// x2 - const int16_t **src,
// x3 - uint8_t *dest,
// w4 - int dstW,
// x5 - const uint8_t *dither,
// w6 - int offset
ld1 {v0.8b}, [x5] // load 8x8-bit dither
and w6, w6, #7
cbz w6, 1f // check if offsetting present
ext v0.8b, v0.8b, v0.8b, #3 // honor offsetting which can be 0 or 3 only
1: uxtl v0.8h, v0.8b // extend dither to 16-bit
ushll v1.4s, v0.4h, #12 // extend dither to 32-bit with left shift by 12 (part 1)
ushll2 v2.4s, v0.8h, #12 // extend dither to 32-bit with left shift by 12 (part 2)
cmp w1, #8 // if filterSize == 8, branch to specialized version
b.eq 6f
cmp w1, #4 // if filterSize == 4, branch to specialized version
b.eq 8f
cmp w1, #2 // if filterSize == 2, branch to specialized version
b.eq 10f
// The filter size does not match of the of specialized implementations. It is either even or odd. If it is even
// then use the first section below.
mov x7, #0 // i = 0
tbnz w1, #0, 4f // if filterSize % 2 != 0 branch to specialized version
// fs % 2 == 0
2: mov v3.16b, v1.16b // initialize accumulator part 1 with dithering value
mov v4.16b, v2.16b // initialize accumulator part 2 with dithering value
mov w8, w1 // tmpfilterSize = filterSize
mov x9, x2 // srcp = src
mov x10, x0 // filterp = filter
3: ldp x11, x12, [x9], #16 // get 2 pointers: src[j] and src[j+1]
ldr s7, [x10], #4 // read 2x16-bit coeff X and Y at filter[j] and filter[j+1]
add x11, x11, x7, lsl #1 // &src[j ][i]
add x12, x12, x7, lsl #1 // &src[j+1][i]
ld1 {v5.8h}, [x11] // read 8x16-bit @ src[j ][i + {0..7}]: A,B,C,D,E,F,G,H
ld1 {v6.8h}, [x12] // read 8x16-bit @ src[j+1][i + {0..7}]: I,J,K,L,M,N,O,P
smlal v3.4s, v5.4h, v7.h[0] // val0 += {A,B,C,D} * X
smlal2 v4.4s, v5.8h, v7.h[0] // val1 += {E,F,G,H} * X
smlal v3.4s, v6.4h, v7.h[1] // val0 += {I,J,K,L} * Y
smlal2 v4.4s, v6.8h, v7.h[1] // val1 += {M,N,O,P} * Y
subs w8, w8, #2 // tmpfilterSize -= 2
b.gt 3b // loop until filterSize consumed
sqshrun v3.4h, v3.4s, #16 // clip16(val0>>16)
sqshrun2 v3.8h, v4.4s, #16 // clip16(val1>>16)
uqshrn v3.8b, v3.8h, #3 // clip8(val>>19)
st1 {v3.8b}, [x3], #8 // write to destination
subs w4, w4, #8 // dstW -= 8
add x7, x7, #8 // i += 8
b.gt 2b // loop until width consumed
ret
// If filter size is odd (most likely == 1), then use this section.
// fs % 2 != 0
4: mov v3.16b, v1.16b // initialize accumulator part 1 with dithering value
mov v4.16b, v2.16b // initialize accumulator part 2 with dithering value
mov w8, w1 // tmpfilterSize = filterSize
mov x9, x2 // srcp = src
mov x10, x0 // filterp = filter
5: ldr x11, [x9], #8 // get 1 pointer: src[j]
ldr h6, [x10], #2 // read 1 16 bit coeff X at filter[j]
add x11, x11, x7, lsl #1 // &src[j ][i]
ld1 {v5.8h}, [x11] // read 8x16-bit @ src[j ][i + {0..7}]: A,B,C,D,E,F,G,H
smlal v3.4s, v5.4h, v6.h[0] // val0 += {A,B,C,D} * X
smlal2 v4.4s, v5.8h, v6.h[0] // val1 += {E,F,G,H} * X
subs w8, w8, #1 // tmpfilterSize -= 2
b.gt 5b // loop until filterSize consumed
sqshrun v3.4h, v3.4s, #16 // clip16(val0>>16)
sqshrun2 v3.8h, v4.4s, #16 // clip16(val1>>16)
uqshrn v3.8b, v3.8h, #3 // clip8(val>>19)
st1 {v3.8b}, [x3], #8 // write to destination
subs w4, w4, #8 // dstW -= 8
add x7, x7, #8 // i += 8
b.gt 4b // loop until width consumed
ret
6: // fs=8
ldp x5, x6, [x2] // load 2 pointers: src[j ] and src[j+1]
ldp x7, x9, [x2, #16] // load 2 pointers: src[j+2] and src[j+3]
ldp x10, x11, [x2, #32] // load 2 pointers: src[j+4] and src[j+5]
ldp x12, x13, [x2, #48] // load 2 pointers: src[j+6] and src[j+7]
// load 8x16-bit values for filter[j], where j=0..7
ld1 {v6.8h}, [x0]
7:
mov v3.16b, v1.16b // initialize accumulator part 1 with dithering value
mov v4.16b, v2.16b // initialize accumulator part 2 with dithering value
ld1 {v24.8h}, [x5], #16 // load 8x16-bit values for src[j + 0][i + {0..7}]
ld1 {v25.8h}, [x6], #16 // load 8x16-bit values for src[j + 1][i + {0..7}]
ld1 {v26.8h}, [x7], #16 // load 8x16-bit values for src[j + 2][i + {0..7}]
ld1 {v27.8h}, [x9], #16 // load 8x16-bit values for src[j + 3][i + {0..7}]
ld1 {v28.8h}, [x10], #16 // load 8x16-bit values for src[j + 4][i + {0..7}]
ld1 {v29.8h}, [x11], #16 // load 8x16-bit values for src[j + 5][i + {0..7}]
ld1 {v30.8h}, [x12], #16 // load 8x16-bit values for src[j + 6][i + {0..7}]
ld1 {v31.8h}, [x13], #16 // load 8x16-bit values for src[j + 7][i + {0..7}]
smlal v3.4s, v24.4h, v6.h[0] // val0 += src[0][i + {0..3}] * filter[0]
smlal2 v4.4s, v24.8h, v6.h[0] // val1 += src[0][i + {4..7}] * filter[0]
smlal v3.4s, v25.4h, v6.h[1] // val0 += src[1][i + {0..3}] * filter[1]
smlal2 v4.4s, v25.8h, v6.h[1] // val1 += src[1][i + {4..7}] * filter[1]
smlal v3.4s, v26.4h, v6.h[2] // val0 += src[2][i + {0..3}] * filter[2]
smlal2 v4.4s, v26.8h, v6.h[2] // val1 += src[2][i + {4..7}] * filter[2]
smlal v3.4s, v27.4h, v6.h[3] // val0 += src[3][i + {0..3}] * filter[3]
smlal2 v4.4s, v27.8h, v6.h[3] // val1 += src[3][i + {4..7}] * filter[3]
smlal v3.4s, v28.4h, v6.h[4] // val0 += src[4][i + {0..3}] * filter[4]
smlal2 v4.4s, v28.8h, v6.h[4] // val1 += src[4][i + {4..7}] * filter[4]
smlal v3.4s, v29.4h, v6.h[5] // val0 += src[5][i + {0..3}] * filter[5]
smlal2 v4.4s, v29.8h, v6.h[5] // val1 += src[5][i + {4..7}] * filter[5]
smlal v3.4s, v30.4h, v6.h[6] // val0 += src[6][i + {0..3}] * filter[6]
smlal2 v4.4s, v30.8h, v6.h[6] // val1 += src[6][i + {4..7}] * filter[6]
smlal v3.4s, v31.4h, v6.h[7] // val0 += src[7][i + {0..3}] * filter[7]
smlal2 v4.4s, v31.8h, v6.h[7] // val1 += src[7][i + {4..7}] * filter[7]
sqshrun v3.4h, v3.4s, #16 // clip16(val0>>16)
sqshrun2 v3.8h, v4.4s, #16 // clip16(val1>>16)
uqshrn v3.8b, v3.8h, #3 // clip8(val>>19)
subs w4, w4, #8 // dstW -= 8
st1 {v3.8b}, [x3], #8 // write to destination
b.gt 7b // loop until width consumed
ret
8: // fs=4
ldp x5, x6, [x2] // load 2 pointers: src[j ] and src[j+1]
ldp x7, x9, [x2, #16] // load 2 pointers: src[j+2] and src[j+3]
// load 4x16-bit values for filter[j], where j=0..3 and replicated across lanes
ld1 {v6.4h}, [x0]
9:
mov v3.16b, v1.16b // initialize accumulator part 1 with dithering value
mov v4.16b, v2.16b // initialize accumulator part 2 with dithering value
ld1 {v24.8h}, [x5], #16 // load 8x16-bit values for src[j + 0][i + {0..7}]
ld1 {v25.8h}, [x6], #16 // load 8x16-bit values for src[j + 1][i + {0..7}]
ld1 {v26.8h}, [x7], #16 // load 8x16-bit values for src[j + 2][i + {0..7}]
ld1 {v27.8h}, [x9], #16 // load 8x16-bit values for src[j + 3][i + {0..7}]
smlal v3.4s, v24.4h, v6.h[0] // val0 += src[0][i + {0..3}] * filter[0]
smlal2 v4.4s, v24.8h, v6.h[0] // val1 += src[0][i + {4..7}] * filter[0]
smlal v3.4s, v25.4h, v6.h[1] // val0 += src[1][i + {0..3}] * filter[1]
smlal2 v4.4s, v25.8h, v6.h[1] // val1 += src[1][i + {4..7}] * filter[1]
smlal v3.4s, v26.4h, v6.h[2] // val0 += src[2][i + {0..3}] * filter[2]
smlal2 v4.4s, v26.8h, v6.h[2] // val1 += src[2][i + {4..7}] * filter[2]
smlal v3.4s, v27.4h, v6.h[3] // val0 += src[3][i + {0..3}] * filter[3]
smlal2 v4.4s, v27.8h, v6.h[3] // val1 += src[3][i + {4..7}] * filter[3]
sqshrun v3.4h, v3.4s, #16 // clip16(val0>>16)
sqshrun2 v3.8h, v4.4s, #16 // clip16(val1>>16)
uqshrn v3.8b, v3.8h, #3 // clip8(val>>19)
st1 {v3.8b}, [x3], #8 // write to destination
subs w4, w4, #8 // dstW -= 8
b.gt 9b // loop until width consumed
ret
10: // fs=2
ldp x5, x6, [x2] // load 2 pointers: src[j ] and src[j+1]
// load 2x16-bit values for filter[j], where j=0..1 and replicated across lanes
ldr s6, [x0]
11:
mov v3.16b, v1.16b // initialize accumulator part 1 with dithering value
mov v4.16b, v2.16b // initialize accumulator part 2 with dithering value
ld1 {v24.8h}, [x5], #16 // load 8x16-bit values for src[j + 0][i + {0..7}]
ld1 {v25.8h}, [x6], #16 // load 8x16-bit values for src[j + 1][i + {0..7}]
smlal v3.4s, v24.4h, v6.h[0] // val0 += src[0][i + {0..3}] * filter[0]
smlal2 v4.4s, v24.8h, v6.h[0] // val1 += src[0][i + {4..7}] * filter[0]
smlal v3.4s, v25.4h, v6.h[1] // val0 += src[1][i + {0..3}] * filter[1]
smlal2 v4.4s, v25.8h, v6.h[1] // val1 += src[1][i + {4..7}] * filter[1]
sqshrun v3.4h, v3.4s, #16 // clip16(val0>>16)
sqshrun2 v3.8h, v4.4s, #16 // clip16(val1>>16)
uqshrn v3.8b, v3.8h, #3 // clip8(val>>19)
st1 {v3.8b}, [x3], #8 // write to destination
subs w4, w4, #8 // dstW -= 8
b.gt 11b // loop until width consumed
ret
endfunc
function ff_yuv2plane1_8_neon, export=1
// x0 - const int16_t *src,
// x1 - uint8_t *dest,
// w2 - int dstW,
// x3 - const uint8_t *dither,
// w4 - int offset
ld1 {v0.8b}, [x3] // load 8x8-bit dither
and w4, w4, #7
cbz w4, 1f // check if offsetting present
ext v0.8b, v0.8b, v0.8b, #3 // honor offsetting which can be 0 or 3 only
1: uxtl v0.8h, v0.8b // extend dither to 32-bit
uxtl v1.4s, v0.4h
uxtl2 v2.4s, v0.8h
2:
ld1 {v3.8h}, [x0], #16 // read 8x16-bit @ src[j ][i + {0..7}]: A,B,C,D,E,F,G,H
sxtl v4.4s, v3.4h
sxtl2 v5.4s, v3.8h
add v4.4s, v4.4s, v1.4s
add v5.4s, v5.4s, v2.4s
sqshrun v4.4h, v4.4s, #6
sqshrun2 v4.8h, v5.4s, #6
uqshrn v3.8b, v4.8h, #1 // clip8(val>>7)
subs w2, w2, #8 // dstW -= 8
st1 {v3.8b}, [x1], #8 // write to destination
b.gt 2b // loop until width consumed
ret
endfunc
|
