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
|
;
; Copyright (c) 2010 The VP8 project authors. All Rights Reserved.
;
; Use of this source code is governed by a BSD-style license and patent
; grant that can be found in the LICENSE file in the root of the source
; tree. All contributing project authors may be found in the AUTHORS
; file in the root of the source tree.
;
EXPORT |vp8_sad8x8_neon|
EXPORT |vp8_sad8x16_neon|
EXPORT |vp8_sad4x4_neon|
ARM
REQUIRE8
PRESERVE8
AREA ||.text||, CODE, READONLY, ALIGN=2
; unsigned int vp8_sad8x8_c(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride)
|vp8_sad8x8_neon| PROC
vld1.8 {d0}, [r0], r1
vld1.8 {d8}, [r2], r3
vld1.8 {d2}, [r0], r1
vld1.8 {d10}, [r2], r3
vabdl.u8 q12, d0, d8
vld1.8 {d4}, [r0], r1
vld1.8 {d12}, [r2], r3
vabal.u8 q12, d2, d10
vld1.8 {d6}, [r0], r1
vld1.8 {d14}, [r2], r3
vabal.u8 q12, d4, d12
vld1.8 {d0}, [r0], r1
vld1.8 {d8}, [r2], r3
vabal.u8 q12, d6, d14
vld1.8 {d2}, [r0], r1
vld1.8 {d10}, [r2], r3
vabal.u8 q12, d0, d8
vld1.8 {d4}, [r0], r1
vld1.8 {d12}, [r2], r3
vabal.u8 q12, d2, d10
vld1.8 {d6}, [r0], r1
vld1.8 {d14}, [r2], r3
vabal.u8 q12, d4, d12
vabal.u8 q12, d6, d14
vpaddl.u16 q1, q12
vpaddl.u32 q0, q1
vadd.u32 d0, d0, d1
vmov.32 r0, d0[0]
bx lr
ENDP
;============================
;unsigned int vp8_sad8x16_c(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride)
|vp8_sad8x16_neon| PROC
vld1.8 {d0}, [r0], r1
vld1.8 {d8}, [r2], r3
vld1.8 {d2}, [r0], r1
vld1.8 {d10}, [r2], r3
vabdl.u8 q12, d0, d8
vld1.8 {d4}, [r0], r1
vld1.8 {d12}, [r2], r3
vabal.u8 q12, d2, d10
vld1.8 {d6}, [r0], r1
vld1.8 {d14}, [r2], r3
vabal.u8 q12, d4, d12
vld1.8 {d0}, [r0], r1
vld1.8 {d8}, [r2], r3
vabal.u8 q12, d6, d14
vld1.8 {d2}, [r0], r1
vld1.8 {d10}, [r2], r3
vabal.u8 q12, d0, d8
vld1.8 {d4}, [r0], r1
vld1.8 {d12}, [r2], r3
vabal.u8 q12, d2, d10
vld1.8 {d6}, [r0], r1
vld1.8 {d14}, [r2], r3
vabal.u8 q12, d4, d12
vld1.8 {d0}, [r0], r1
vld1.8 {d8}, [r2], r3
vabal.u8 q12, d6, d14
vld1.8 {d2}, [r0], r1
vld1.8 {d10}, [r2], r3
vabal.u8 q12, d0, d8
vld1.8 {d4}, [r0], r1
vld1.8 {d12}, [r2], r3
vabal.u8 q12, d2, d10
vld1.8 {d6}, [r0], r1
vld1.8 {d14}, [r2], r3
vabal.u8 q12, d4, d12
vld1.8 {d0}, [r0], r1
vld1.8 {d8}, [r2], r3
vabal.u8 q12, d6, d14
vld1.8 {d2}, [r0], r1
vld1.8 {d10}, [r2], r3
vabal.u8 q12, d0, d8
vld1.8 {d4}, [r0], r1
vld1.8 {d12}, [r2], r3
vabal.u8 q12, d2, d10
vld1.8 {d6}, [r0], r1
vld1.8 {d14}, [r2], r3
vabal.u8 q12, d4, d12
vabal.u8 q12, d6, d14
vpaddl.u16 q1, q12
vpaddl.u32 q0, q1
vadd.u32 d0, d0, d1
vmov.32 r0, d0[0]
bx lr
ENDP
;===========================
;unsigned int vp8_sad4x4_c(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride)
|vp8_sad4x4_neon| PROC
vld1.8 {d0}, [r0], r1
vld1.8 {d8}, [r2], r3
vld1.8 {d2}, [r0], r1
vld1.8 {d10}, [r2], r3
vabdl.u8 q12, d0, d8
vld1.8 {d4}, [r0], r1
vld1.8 {d12}, [r2], r3
vabal.u8 q12, d2, d10
vld1.8 {d6}, [r0], r1
vld1.8 {d14}, [r2], r3
vabal.u8 q12, d4, d12
vabal.u8 q12, d6, d14
vpaddl.u16 d1, d24
vpaddl.u32 d0, d1
vmov.32 r0, d0[0]
bx lr
ENDP
END
|
