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
|
/*
* Copyright (C) 2007-2008 ARM Limited
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*
*/
/*
*
*/
.eabi_attribute 24, 1
.eabi_attribute 25, 1
.arm
.fpu neon
.text
.global omxVCM4P10_FilterDeblockingChroma_HorEdge_I
omxVCM4P10_FilterDeblockingChroma_HorEdge_I:
PUSH {r4-r10,lr}
VPUSH {d8-d15}
VLD1.8 {d0[]},[r2]!
SUB r0,r0,r1,LSL #1
SUB r0,r0,r1
VLD1.8 {d2[]},[r3]!
LDR r4,[sp,#0x64]
LDR r5,[sp,#0x60]
LDR r9, =0x3030303
LDR r8, =0x4040404
VMOV.I8 d14,#0
VMOV.I8 d15,#0x1
VMOV.I16 d1,#0x4
MOV r7,#0x40000000
L0x38:
LDR r6,[r4],#8
VLD1.8 {d6},[r0],r1
VLD1.8 {d5},[r0],r1
CMP r6,#0
VLD1.8 {d4},[r0],r1
VLD1.8 {d8},[r0],r1
VABD.U8 d19,d6,d4
VLD1.8 {d9},[r0],r1
VABD.U8 d13,d4,d8
VLD1.8 {d10},[r0],r1
BEQ L0xe4
VABD.U8 d12,d5,d4
VABD.U8 d18,d9,d8
VCGT.U8 d16,d0,d13
VMOV.32 d26[0],r6
VMAX.U8 d12,d18,d12
VMOVL.U8 q13,d26
VABD.U8 d17,d10,d8
VCGT.S16 d27,d26,#0
VCGT.U8 d12,d2,d12
VCGT.U8 d19,d2,d19
VAND d16,d16,d27
TST r6,r9
VCGT.U8 d17,d2,d17
VAND d16,d16,d12
VAND d12,d16,d17
VAND d17,d16,d19
BLNE armVCM4P10_DeblockingChromabSLT4_unsafe
TST r6,r8
SUB r0,r0,r1,LSL #2
VTST.16 d26,d26,d1
BLNE armVCM4P10_DeblockingChromabSGE4_unsafe
VBIT d29,d13,d26
VBIT d24,d31,d26
VBIF d29,d4,d16
VBIF d24,d8,d16
VST1.8 {d29},[r0],r1
ADDS r7,r7,r7
VST1.8 {d24},[r0],r1
BNE L0x38
MOV r0,#0
VPOP {d8-d15}
POP {r4-r10,pc}
L0xe4:
VLD1.8 {d0[]},[r2]
SUB r0,r0,r1,LSL #1
ADDS r7,r7,r7
VLD1.8 {d2[]},[r3]
ADD r5,r5,#4
BNE L0x38
MOV r0,#0
VPOP {d8-d15}
POP {r4-r10,pc}
.end
|
