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
|
#------------------------------------------------------------------------------
#
# Copyright (c) 2016, Linaro Ltd. All rights reserved.<BR>
#
# SPDX-License-Identifier: BSD-2-Clause-Patent
#
#------------------------------------------------------------------------------
.text
.thumb
.syntax unified
.align 5
.type ASM_PFX(InternalMemSetMem16), %function
ASM_GLOBAL ASM_PFX(InternalMemSetMem16)
ASM_PFX(InternalMemSetMem16):
uxth r2, r2
lsl r1, r1, #1
orr r2, r2, r2, lsl #16
b 0f
.type ASM_PFX(InternalMemSetMem32), %function
ASM_GLOBAL ASM_PFX(InternalMemSetMem32)
ASM_PFX(InternalMemSetMem32):
lsl r1, r1, #2
b 0f
.type ASM_PFX(InternalMemSetMem64), %function
ASM_GLOBAL ASM_PFX(InternalMemSetMem64)
ASM_PFX(InternalMemSetMem64):
lsl r1, r1, #3
b 1f
.align 5
.type ASM_PFX(InternalMemSetMem), %function
ASM_GLOBAL ASM_PFX(InternalMemSetMem)
ASM_PFX(InternalMemSetMem):
uxtb r2, r2
orr r2, r2, r2, lsl #8
orr r2, r2, r2, lsl #16
b 0f
.type ASM_PFX(InternalMemZeroMem), %function
ASM_GLOBAL ASM_PFX(InternalMemZeroMem)
ASM_PFX(InternalMemZeroMem):
movs r2, #0
0: mov r3, r2
1: push {r4, lr}
cmp r1, #16 // fewer than 16 bytes of input?
add r1, r1, r0 // r1 := dst + length
add lr, r0, #16
blt 2f
bic lr, lr, #15 // align output pointer
str r2, [r0] // potentially unaligned store of 4 bytes
str r3, [r0, #4] // potentially unaligned store of 4 bytes
str r2, [r0, #8] // potentially unaligned store of 4 bytes
str r3, [r0, #12] // potentially unaligned store of 4 bytes
beq 1f
0: add lr, lr, #16 // advance the output pointer by 16 bytes
subs r4, r1, lr // past the output?
blt 3f // break out of the loop
strd r2, r3, [lr, #-16] // aligned store of 16 bytes
strd r2, r3, [lr, #-8]
bne 0b // goto beginning of loop
1: pop {r4, pc}
2: subs r4, r1, lr
3: adds r4, r4, #16
subs r1, r1, #8
cmp r4, #4 // between 4 and 15 bytes?
blt 4f
cmp r4, #8 // between 8 and 15 bytes?
sub r4, lr, #16
str r2, [r4] // overlapping store of 4 + (4 + 4) + 4 bytes
it gt
strgt.n r3, [r4, #4]
it gt
strgt.n r2, [r1]
str r3, [r1, #4]
pop {r4, pc}
4: cmp r4, #2 // 2 or 3 bytes?
strb r2, [lr, #-16] // store 1 byte
it ge
strhge.n r2, [r1, #6] // store 2 bytes
pop {r4, pc}
|
