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
|
.arch armv7-a
.syntax unified
.thumb
.fpu vfpv3-d16
.text
.globl divide
.thumb_func
divide:
eor r12,r3,r4
cmp r4,#0
it lt
neglt r4,r4
cmp r3,#0
it lt
neglt r3,r3
cmp r4,#32
bls divide_by_small_number
clz r1,r4
clz r2,r3
rsb r1,r1,#31-5-11
add r1,r1,r2
mov r2,#0
cmp r1,#32-5-11
bhs divide_large_result
add r1,r1,r1,lsl #1
mov r14,pc
add r14,r14,r1,lsl #2
mov pc,r14
nop
.set shift,32-5-11
.rept 32-5-11
.set shift,shift-1
subs r1,r3,r4,lsl #shift
it cs
movcs r3,r1
it cs
orrcs r2,r2,#1<<shift
.endr
mov r4,r2
cmp r12,#0
it lt
neglt r4,r4
ldr pc,[sp],#4
.thumb_func
divide_large_result:
bpl divide_result_0
vmov s13,r3
vmov s15,r4
vcvt.f64.u32 d6,s13
vcvt.f64.u32 d7,s15
vdiv.f64 d7,d6,d7
vcvt.u32.f64 s15,d7
vmov r4,s15
cmp r12,#0
it lt
neglt r4,r4
ldr pc,[sp],#4
divide_result_0:
mov r4,#0
ldr pc,[sp],#4
.thumb_func
divide_by_small_number:
mov r1,pc
add r1,r1,r4,lsl #3
ldrb r4,[r1,#(div_mod_table+1)-(divide_by_small_number+8)]
ldr r2,[r1,#(div_mod_table+4)-(divide_by_small_number+8)]
ldrb r1,[r1,#div_mod_table-(divide_by_small_number+8)]
adds r3,r3,r4
it cc
umullcc r4,r2,r3,r2
lsr r4,r2,r1
cmp r12,#0
it lt
neglt r4,r4
ldr pc,[sp],#4
.globl modulo
.thumb_func
modulo:
cmp r4,#0
it lt
neglt r4,r4
movs r12,r3
it lt
neglt r3,r3
cmp r4,#32
bls modulo_of_small_number
clz r1,r4
clz r2,r3
rsb r1,r1,#31-5-11
add r1,r1,r2
cmp r1,#32-5-11
bhs modulo_large_divide_result
mov r14,pc
add r14,r14,r1,lsl #3
mov pc,r14
nop
.set shift,32
.rept 32
.set shift,shift-1
subs r1,r3,r4,lsl #shift
it cs
movcs r3,r1
.endr
.thumb_func
modulo_large_divide_result:
bpl modulo_divide_result_0
vmov s13,r3
vmov s15,r4
vcvt.f64.u32 d6,s13
vcvt.f64.u32 d7,s15
vdiv.f64 d7,d6,d7
vcvt.u32.f64 s15,d7
vmov r2,s15
b modulo_from_quotient
modulo_divide_result_0:
mov r4,r3
cmp r12,#0
it lt
neglt r4,r4
ldr pc,[sp],#4
.thumb_func
modulo_of_small_number:
mov r1,pc
add r1,r1,r4,lsl #3
ldrb r0,[r1,#(div_mod_table+1)-(modulo_of_small_number+8)]
ldr r2,[r1,#(div_mod_table+4)-(modulo_of_small_number+8)]
ldrb r1,[r1,#div_mod_table-(modulo_of_small_number+8)]
adds r14,r3,r0
it cc
umullcc r0,r2,r14,r2
lsr r2,r2,r1
.thumb_func
modulo_from_quotient:
@ mls r4,r4,r2,r3
neg r3,r3
mla r4,r4,r2,r3
cmp r12,#0
it lt
neglt r4,r4
ldr pc,[sp],#4
.thumb_func
div_mod_table:
.long 0,0
.long 0x100,0xffffffff
.long 0,0x80000000
.long 1,0xaaaaaaab
.long 0,0x40000000
.long 2,0xcccccccd
.long 2,0xaaaaaaab
.long 0x102,0x92492492
.long 0,0x20000000
.long 1,0x38e38e39
.long 3,0xcccccccd
.long 3,0xba2e8ba3
.long 3,0xaaaaaaab
.long 2,0x4ec4ec4f
.long 0x103,0x92492492
.long 3,0x88888889
.long 0,0x10000000
.long 4,0xf0f0f0f1
.long 2,0x38e38e39
.long 0x104,0xd79435e5
.long 4,0xcccccccd
.long 0x104,0xc30c30c3
.long 4,0xba2e8ba3
.long 4,0xb21642c9
.long 4,0xaaaaaaab
.long 3,0x51eb851f
.long 3,0x4ec4ec4f
.long 0x104,0x97b425ed
.long 0x104,0x92492492
.long 4,0x8d3dcb09
.long 4,0x88888889
.long 0x104,0x84210842
.long 0,0x08000000
|
