Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
Download
52867 views
1
/*****************************************************************************
2
* bitstream-a.S: arm bitstream functions
3
*****************************************************************************
4
* Copyright (C) 2014-2016 x264 project
5
*
6
* Authors: Janne Grunau <[email protected]>
7
*
8
* This program is free software; you can redistribute it and/or modify
9
* it under the terms of the GNU General Public License as published by
10
* the Free Software Foundation; either version 2 of the License, or
11
* (at your option) any later version.
12
*
13
* This program is distributed in the hope that it will be useful,
14
* but WITHOUT ANY WARRANTY; without even the implied warranty of
15
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16
* GNU General Public License for more details.
17
*
18
* You should have received a copy of the GNU General Public License
19
* along with this program; if not, write to the Free Software
20
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
21
*
22
* This program is also available under a commercial proprietary license.
23
* For more information, contact us at [email protected].
24
*****************************************************************************/
25
26
#include "asm.S"
27
28
function x264_nal_escape_neon
29
push {r4-r5,lr}
30
vmov.u8 q0, #0xff
31
vmov.u8 q8, #4
32
mov r3, #3
33
subs lr, r1, r2
34
beq 99f
35
0:
36
cmn lr, #15
37
blt 16f
38
mov r1, r2
39
b 100f
40
16:
41
vld1.8 {q1}, [r1]!
42
vext.8 q2, q0, q1, #14
43
vext.8 q3, q0, q1, #15
44
vcgt.u8 q11, q8, q1
45
vceq.u8 q9, q2, #0
46
vceq.u8 q10, q3, #0
47
vand q9, q9, q11
48
vand q9, q9, q10
49
vshrn.u16 d22, q9, #4
50
vmov ip, lr, d22
51
orrs ip, ip, lr
52
beq 16f
53
mov lr, #-16
54
100:
55
vmov.u8 r5, d1[6]
56
vmov.u8 r4, d1[7]
57
orr r5, r4, r5, lsl #8
58
101:
59
ldrb r4, [r1, lr]
60
orr ip, r4, r5, lsl #16
61
cmp ip, #3
62
bhi 102f
63
strb r3, [r0], #1
64
orr r5, r3, r5, lsl #8
65
102:
66
adds lr, lr, #1
67
strb r4, [r0], #1
68
orr r5, r4, r5, lsl #8
69
blt 101b
70
subs lr, r1, r2
71
lsr ip, r5, #8
72
vmov.u8 d1[6], ip
73
vmov.u8 d1[7], r5
74
blt 0b
75
76
pop {r4-r5,pc}
77
16:
78
subs lr, r1, r2
79
vst1.8 {q1}, [r0]!
80
vmov q0, q1
81
blt 0b
82
99:
83
pop {r4-r5,pc}
84
endfunc
85
86