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
|
Index: libavcodec/aarch64/vp9lpf_neon.S
--- libavcodec/aarch64/vp9lpf_neon.S.orig
+++ libavcodec/aarch64/vp9lpf_neon.S
@@ -399,7 +399,7 @@
.endif
// If no pixels needed flat8in nor flat8out, jump to a
// writeout of the inner 4 pixels
- br x14
+ ret x14
1:
mov x5, v7.d[0]
@@ -411,7 +411,7 @@
cbnz x5, 1f
.endif
// If no pixels need flat8out, jump to a writeout of the inner 6 pixels
- br x15
+ ret x15
1:
// flat8out
@@ -532,32 +532,32 @@ function vp9_loop_filter_4
loop_filter 4, .8b, 0, v16, v17, v18, v19, v28, v29, v30, v31
ret
9:
- br x10
+ ret x10
endfunc
function vp9_loop_filter_4_16b_mix_44
loop_filter 4, .16b, 44, v16, v17, v18, v19, v28, v29, v30, v31
ret
9:
- br x10
+ ret x10
endfunc
function vp9_loop_filter_8
loop_filter 8, .8b, 0, v16, v17, v18, v19, v28, v29, v30, v31
ret
6:
- br x13
+ ret x13
9:
- br x10
+ ret x10
endfunc
function vp9_loop_filter_8_16b_mix
loop_filter 8, .16b, 88, v16, v17, v18, v19, v28, v29, v30, v31
ret
6:
- br x13
+ ret x13
9:
- br x10
+ ret x10
endfunc
function vp9_loop_filter_16
@@ -568,7 +568,7 @@ function vp9_loop_filter_16
ldp d10, d11, [sp], 0x10
ldp d12, d13, [sp], 0x10
ldp d14, d15, [sp], 0x10
- br x10
+ ret x10
endfunc
function vp9_loop_filter_16_16b
@@ -579,7 +579,7 @@ function vp9_loop_filter_16_16b
ldp d10, d11, [sp], 0x10
ldp d12, d13, [sp], 0x10
ldp d14, d15, [sp], 0x10
- br x10
+ ret x10
endfunc
.macro loop_filter_4
@@ -648,7 +648,7 @@ function ff_vp9_loop_filter_v_4_8_neon, export=1
st1 {v23.8b}, [x9], x1
st1 {v25.8b}, [x0], x1
- br x10
+ ret x10
endfunc
function ff_vp9_loop_filter_v_44_16_neon, export=1
@@ -672,7 +672,7 @@ function ff_vp9_loop_filter_v_44_16_neon, export=1
st1 {v23.16b}, [x9], x1
st1 {v25.16b}, [x0], x1
- br x10
+ ret x10
endfunc
function ff_vp9_loop_filter_h_4_8_neon, export=1
@@ -714,7 +714,7 @@ function ff_vp9_loop_filter_h_4_8_neon, export=1
st1 {v25.s}[0], [x9], x1
st1 {v25.s}[1], [x0], x1
- br x10
+ ret x10
endfunc
function ff_vp9_loop_filter_h_44_16_neon, export=1
@@ -766,7 +766,7 @@ function ff_vp9_loop_filter_h_44_16_neon, export=1
st1 {v25.s}[1], [x9], x1
st1 {v25.s}[3], [x0], x1
- br x10
+ ret x10
endfunc
function ff_vp9_loop_filter_v_8_8_neon, export=1
@@ -793,14 +793,14 @@ function ff_vp9_loop_filter_v_8_8_neon, export=1
st1 {v23.8b}, [x9], x1
st1 {v26.8b}, [x0], x1
- br x10
+ ret x10
6:
sub x9, x0, x1, lsl #1
st1 {v22.8b}, [x9], x1
st1 {v24.8b}, [x0], x1
st1 {v23.8b}, [x9], x1
st1 {v25.8b}, [x0], x1
- br x10
+ ret x10
endfunc
.macro mix_v_16 mix
@@ -828,14 +828,14 @@ function ff_vp9_loop_filter_v_\mix\()_16_neon, export=
st1 {v23.16b}, [x9], x1
st1 {v26.16b}, [x0], x1
- br x10
+ ret x10
6:
sub x9, x0, x1, lsl #1
st1 {v22.16b}, [x9], x1
st1 {v24.16b}, [x0], x1
st1 {v23.16b}, [x9], x1
st1 {v25.16b}, [x0], x1
- br x10
+ ret x10
endfunc
.endm
@@ -876,7 +876,7 @@ function ff_vp9_loop_filter_h_8_8_neon, export=1
st1 {v23.8b}, [x9], x1
st1 {v27.8b}, [x0], x1
- br x10
+ ret x10
6:
// If we didn't need to do the flat8in part, we use the same writeback
// as in loop_filter_h_4_8.
@@ -891,7 +891,7 @@ function ff_vp9_loop_filter_h_8_8_neon, export=1
st1 {v24.s}[1], [x0], x1
st1 {v25.s}[0], [x9], x1
st1 {v25.s}[1], [x0], x1
- br x10
+ ret x10
endfunc
.macro mix_h_16 mix
@@ -942,7 +942,7 @@ function ff_vp9_loop_filter_h_\mix\()_16_neon, export=
st1 {v27.8b}, [x9], x1
st1 {v27.d}[1], [x0], x1
- br x10
+ ret x10
6:
add x9, x9, #2
add x0, x0, #2
@@ -963,7 +963,7 @@ function ff_vp9_loop_filter_h_\mix\()_16_neon, export=
st1 {v24.s}[3], [x0], x1
st1 {v25.s}[1], [x9], x1
st1 {v25.s}[3], [x0], x1
- br x10
+ ret x10
endfunc
.endm
@@ -1022,7 +1022,7 @@ function ff_vp9_loop_filter_v_16_8_neon, export=1
ldp d10, d11, [sp], 0x10
ldp d12, d13, [sp], 0x10
ldp d14, d15, [sp], 0x10
- br x10
+ ret x10
8:
add x9, x9, x1, lsl #2
// If we didn't do the flat8out part, the output is left in the
@@ -1091,7 +1091,7 @@ function ff_vp9_loop_filter_v_16_16_neon, export=1
ldp d10, d11, [sp], 0x10
ldp d12, d13, [sp], 0x10
ldp d14, d15, [sp], 0x10
- br x10
+ ret x10
8:
add x9, x9, x1, lsl #2
st1 {v21.16b}, [x9], x1
@@ -1168,7 +1168,7 @@ function ff_vp9_loop_filter_h_16_8_neon, export=1
ldp d10, d11, [sp], 0x10
ldp d12, d13, [sp], 0x10
ldp d14, d15, [sp], 0x10
- br x10
+ ret x10
8:
// The same writeback as in loop_filter_h_8_8
sub x9, x0, #4
@@ -1287,7 +1287,7 @@ function ff_vp9_loop_filter_h_16_16_neon, export=1
ldp d10, d11, [sp], 0x10
ldp d12, d13, [sp], 0x10
ldp d14, d15, [sp], 0x10
- br x10
+ ret x10
8:
sub x9, x0, #4
add x0, x9, x1, lsl #3
|
