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
|
; RUN: llc < %s -O0 -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=armv7-apple-ios -verify-machineinstrs | FileCheck %s --check-prefix=ARM --check-prefix=ARM-MACHO
; RUN: llc < %s -O0 -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=armv7-linux-gnueabi -verify-machineinstrs | FileCheck %s --check-prefix=ARM --check-prefix=ARM-ELF
; RUN: llc < %s -O0 -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=thumbv7-apple-ios -verify-machineinstrs | FileCheck %s --check-prefix=THUMB
; Very basic fast-isel functionality.
define i32 @test0(i32 %a, i32 %b) nounwind {
entry:
%a.addr = alloca i32, align 4
%b.addr = alloca i32, align 4
store i32 %a, ptr %a.addr
store i32 %b, ptr %b.addr
%tmp = load i32, ptr %a.addr
%tmp1 = load i32, ptr %b.addr
%add = add nsw i32 %tmp, %tmp1
ret i32 %add
}
; Check truncate to bool
define void @test1(i32 %tmp) nounwind {
entry:
%tobool = trunc i32 %tmp to i1
br i1 %tobool, label %if.then, label %if.end
if.then: ; preds = %entry
call void @test1(i32 0)
br label %if.end
if.end: ; preds = %if.then, %entry
ret void
; ARM-LABEL: test1:
; ARM: tst r0, #1
; THUMB-LABEL: test1:
; THUMB: tst.w r0, #1
}
; Check some simple operations with immediates
define void @test2(i32 %tmp, ptr %ptr) nounwind {
; THUMB-LABEL: test2:
; ARM-LABEL: test2:
b1:
%a = add i32 %tmp, 4096
store i32 %a, ptr %ptr
br label %b2
; THUMB: add.w {{.*}} #4096
; ARM: add {{.*}} #4096
b2:
%b = add i32 %tmp, 4095
store i32 %b, ptr %ptr
br label %b3
; THUMB: addw {{.*}} #4095
; ARM: movw {{.*}} #4095
; ARM: add
b3:
%c = or i32 %tmp, 4
store i32 %c, ptr %ptr
ret void
; THUMB: orr {{.*}} #4
; ARM: orr {{.*}} #4
}
define void @test3(i32 %tmp, ptr %ptr1, ptr %ptr2, ptr %ptr3) nounwind {
; THUMB-LABEL: test3:
; ARM-LABEL: test3:
bb1:
%a1 = trunc i32 %tmp to i16
%a2 = trunc i16 %a1 to i8
%a3 = trunc i8 %a2 to i1
%a4 = zext i1 %a3 to i8
store i8 %a4, ptr %ptr3
%a5 = zext i8 %a4 to i16
store i16 %a5, ptr %ptr2
%a6 = zext i16 %a5 to i32
store i32 %a6, ptr %ptr1
br label %bb2
; THUMB: and
; THUMB: strb
; THUMB: and{{.*}}, #255
; THUMB: strh
; THUMB: uxth
; ARM: and
; ARM: strb
; ARM: and{{.*}}, #255
; ARM: strh
; ARM: uxth
bb2:
%b1 = trunc i32 %tmp to i16
%b2 = trunc i16 %b1 to i8
store i8 %b2, ptr %ptr3
%b3 = sext i8 %b2 to i16
store i16 %b3, ptr %ptr2
%b4 = sext i16 %b3 to i32
store i32 %b4, ptr %ptr1
br label %bb3
; THUMB: strb
; THUMB: sxtb
; THUMB: strh
; THUMB: sxth
; ARM: strb
; ARM: sxtb
; ARM: strh
; ARM: sxth
bb3:
%c1 = load i8, ptr %ptr3
%c2 = load i16, ptr %ptr2
%c3 = load i32, ptr %ptr1
%c4 = zext i8 %c1 to i32
%c5 = sext i16 %c2 to i32
%c6 = add i32 %c4, %c5
%c7 = sub i32 %c3, %c6
store i32 %c7, ptr %ptr1
ret void
; THUMB: ldrb
; THUMB: ldrh
; THUMB: and{{.*}}, #255
; THUMB: sxth
; THUMB: add
; THUMB: sub
; ARM: ldrb
; ARM: ldrh
; ARM: and{{.*}}, #255
; ARM: sxth
; ARM: add
; ARM: sub
}
; Check loads/stores with globals
@test4g = external global i32
define void @test4() {
%a = load i32, ptr @test4g
%b = add i32 %a, 1
store i32 %b, ptr @test4g
ret void
; Note that relocations are either movw/movt or constant pool
; loads. Different platforms will select different approaches.
; THUMB: {{(movw r0, :lower16:L_test4g\$non_lazy_ptr)|(ldr.n r0, .LCPI)}}
; THUMB: {{(movt r0, :upper16:L_test4g\$non_lazy_ptr)?}}
; THUMB: ldr [[REG:r[0-9]+]], [r0]
; THUMB: ldr [[REG1:r[0-9]+]], [[[REG]]]
; THUMB: adds [[REG1]], #1
; THUMB: {{(movw r1, :lower16:L_test4g\$non_lazy_ptr)|(ldr.n r0, .LCPI)}}
; THUMB: {{(movt r1, :upper16:L_test4g\$non_lazy_ptr)?}}
; THUMB: ldr [[REG2:r[0-9]+]], [r1]
; THUMB: str [[REG1]], [[[REG2]]]
; ARM-MACHO: {{(movw r0, :lower16:L_test4g\$non_lazy_ptr)|(ldr r0, .LCPI)}}
; ARM-MACHO: {{(movt r0, :upper16:L_test4g\$non_lazy_ptr)?}}
; ARM-MACHO: ldr [[REG:r[0-9]+]], [r0]
; ARM-ELF: movw [[REG:r[0-9]+]], :lower16:test4g
; ARM-ELF: movt [[REG]], :upper16:test4g
; ARM: ldr [[REG1:r[0-9]+]], [[[REG]]]
; ARM: add [[REG2:r[0-9]+]], [[REG1]], #1
; ARM-MACHO: {{(movw r1, :lower16:L_test4g\$non_lazy_ptr)|(ldr r0, .LCPI)}}
; ARM-MACHO: {{(movt r1, :upper16:L_test4g\$non_lazy_ptr)?}}
; ARM-MACHO: ldr [[REG3:r[0-9]+]], [r1]
; ARM-ELF: movw [[REG3:r[0-9]+]], :lower16:test4g
; ARM-ELF: movt [[REG3]], :upper16:test4g
; ARM: str [[REG2]], [[[REG3]]]
}
; ARM: @urem_fold
; THUMB: @urem_fold
; ARM: and r0, r0, #31
; THUMB: and r0, r0, #31
define i32 @urem_fold(i32 %a) nounwind {
%rem = urem i32 %a, 32
ret i32 %rem
}
define i32 @trap_intrinsic() noreturn nounwind {
entry:
; ARM: @trap_intrinsic
; THUMB: @trap_intrinsic
; ARM: trap
; THUMB: trap
tail call void @llvm.trap( )
unreachable
}
declare void @llvm.trap() nounwind
|
