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
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
|
; RUN: llc < %s -mtriple=arm-eabi -mcpu=generic | FileCheck %s
; RUN: llc < %s -mtriple=thumbv6m-eabi | FileCheck %s -check-prefix=CHECK-V6M-THUMB
define i32 @sadd(i32 %a, i32 %b) local_unnamed_addr #0 {
; CHECK-LABEL: sadd:
; CHECK: adds r0, r0, r1
; CHECK-NEXT: movvc pc, lr
entry:
%0 = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 %a, i32 %b)
%1 = extractvalue { i32, i1 } %0, 1
br i1 %1, label %trap, label %cont
trap:
tail call void @llvm.trap() #2
unreachable
cont:
%2 = extractvalue { i32, i1 } %0, 0
ret i32 %2
}
define i32 @uadd(i32 %a, i32 %b) local_unnamed_addr #0 {
; CHECK-LABEL: uadd:
; CHECK: adds r0, r0, r1
; CHECK-NEXT: movlo pc, lr
entry:
%0 = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
%1 = extractvalue { i32, i1 } %0, 1
br i1 %1, label %trap, label %cont
trap:
tail call void @llvm.trap() #2
unreachable
cont:
%2 = extractvalue { i32, i1 } %0, 0
ret i32 %2
}
define i32 @ssub(i32 %a, i32 %b) local_unnamed_addr #0 {
; CHECK-LABEL: ssub:
; CHECK: subs r0, r0, r1
; CHECK-NEXT: movvc pc, lr
entry:
%0 = tail call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 %a, i32 %b)
%1 = extractvalue { i32, i1 } %0, 1
br i1 %1, label %trap, label %cont
trap:
tail call void @llvm.trap() #2
unreachable
cont:
%2 = extractvalue { i32, i1 } %0, 0
ret i32 %2
}
define i32 @usub(i32 %a, i32 %b) local_unnamed_addr #0 {
; CHECK-LABEL: usub:
; CHECK: subs r0, r0, r1
; CHECK-NEXT: movhs pc, lr
entry:
%0 = tail call { i32, i1 } @llvm.usub.with.overflow.i32(i32 %a, i32 %b)
%1 = extractvalue { i32, i1 } %0, 1
br i1 %1, label %trap, label %cont
trap:
tail call void @llvm.trap() #2
unreachable
cont:
%2 = extractvalue { i32, i1 } %0, 0
ret i32 %2
}
define i32 @smul(i32 %a, i32 %b) local_unnamed_addr #0 {
; CHECK-LABEL: smul:
; CHECK: smull r0, r[[RHI:[0-9]+]], {{r[0-9]+}}, {{r[0-9]+}}
; CHECK-NEXT: cmp r[[RHI]], r0, asr #31
; CHECK-NEXT: moveq pc, lr
; CHECK-V6M-THUMB-LABEL: smul:
; CHECK-V6M-THUMB: bl __aeabi_lmul
entry:
%0 = tail call { i32, i1 } @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
%1 = extractvalue { i32, i1 } %0, 1
br i1 %1, label %trap, label %cont
trap:
tail call void @llvm.trap() #2
unreachable
cont:
%2 = extractvalue { i32, i1 } %0, 0
ret i32 %2
}
define i32 @umul(i32 %a, i32 %b) local_unnamed_addr #0 {
; CHECK-LABEL: umul:
; CHECK: umull r0, r[[RHI:[0-9]+]], {{r[0-9]+}}, {{r[0-9]+}}
; CHECK-NEXT: cmp r[[RHI]], #0
; CHECK-NEXT: moveq pc, lr
; CHECK-V6M-THUMB-LABEL: umul:
; CHECK-V6M-THUMB: bl __aeabi_lmul
entry:
%0 = tail call { i32, i1 } @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
%1 = extractvalue { i32, i1 } %0, 1
br i1 %1, label %trap, label %cont
trap:
tail call void @llvm.trap() #2
unreachable
cont:
%2 = extractvalue { i32, i1 } %0, 0
ret i32 %2
}
define void @sum(i32* %a, i32* %b, i32 %n) local_unnamed_addr #0 {
; CHECK-LABEL: sum:
; CHECK: ldr [[R0:r[0-9]+]],
; CHECK-NEXT: ldr [[R1:r[0-9]+|lr]],
; CHECK-NEXT: adds [[R2:r[0-9]+]], [[R1]], [[R0]]
; CHECK-NEXT: strvc [[R2]],
; CHECK-NEXT: addsvc
; CHECK-NEXT: bvs
entry:
%cmp7 = icmp eq i32 %n, 0
br i1 %cmp7, label %for.cond.cleanup, label %for.body
for.cond.cleanup:
ret void
for.body:
%i.08 = phi i32 [ %7, %cont2 ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %b, i32 %i.08
%0 = load i32, i32* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds i32, i32* %a, i32 %i.08
%1 = load i32, i32* %arrayidx1, align 4
%2 = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 %1, i32 %0)
%3 = extractvalue { i32, i1 } %2, 1
br i1 %3, label %trap, label %cont
trap:
tail call void @llvm.trap() #2
unreachable
cont:
%4 = extractvalue { i32, i1 } %2, 0
store i32 %4, i32* %arrayidx1, align 4
%5 = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 %i.08, i32 1)
%6 = extractvalue { i32, i1 } %5, 1
br i1 %6, label %trap, label %cont2
cont2:
%7 = extractvalue { i32, i1 } %5, 0
%cmp = icmp eq i32 %7, %n
br i1 %cmp, label %for.cond.cleanup, label %for.body
}
define void @extern_loop(i32 %n) local_unnamed_addr #0 {
; Do not replace the compare around the clobbering call.
; CHECK: add {{r[0-9]+}}, {{r[0-9]+}}, #1
; CHECK-NEXT: bl external_fn
; CHECK: cmp
entry:
%0 = tail call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 %n, i32 1)
%1 = extractvalue { i32, i1 } %0, 1
br i1 %1, label %trap, label %cont.lr.ph
cont.lr.ph:
%2 = extractvalue { i32, i1 } %0, 0
%cmp5 = icmp sgt i32 %2, 0
br i1 %cmp5, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
br label %for.body
trap:
tail call void @llvm.trap() #2
unreachable
for.cond.cleanup:
ret void
for.body:
%i.046 = phi i32 [ %5, %cont1 ], [ 0, %for.body.preheader ]
tail call void bitcast (void (...)* @external_fn to void ()*)() #4
%3 = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 %i.046, i32 1)
%4 = extractvalue { i32, i1 } %3, 1
br i1 %4, label %trap, label %cont1
cont1:
%5 = extractvalue { i32, i1 } %3, 0
%cmp = icmp slt i32 %5, %2
br i1 %cmp, label %for.body, label %for.cond.cleanup
}
declare void @external_fn(...) local_unnamed_addr #0
define i32 @are_equal(i32* nocapture readonly %a1, i32* nocapture readonly %a2, i32 %n) local_unnamed_addr #0 {
; CHECK-LABEL: are_equal
; CHECK: subs r{{[0-9]+}}, r{{[0-9]+}}, #1
; CHECK-NEXT: bne
entry:
%tobool7 = icmp eq i32 %n, 0
br i1 %tobool7, label %while.end, label %land.rhs.preheader
land.rhs.preheader:
br label %land.rhs
while.cond:
%tobool = icmp eq i32 %dec9, 0
br i1 %tobool, label %while.end, label %land.rhs
land.rhs:
%dec9.in = phi i32 [ %dec9, %while.cond ], [ %n, %land.rhs.preheader ]
%dec9 = add nsw i32 %dec9.in, -1
%arrayidx = getelementptr inbounds i32, i32* %a1, i32 %dec9
%0 = load i32, i32* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds i32, i32* %a2, i32 %dec9
%1 = load i32, i32* %arrayidx1, align 4
%cmp = icmp eq i32 %0, %1
br i1 %cmp, label %while.cond, label %while.end
while.end:
%n.addr.0.lcssa = phi i32 [ 0, %entry ], [ 0, %while.cond ], [ %dec9.in, %land.rhs ]
%cmp2 = icmp slt i32 %n.addr.0.lcssa, 1
%conv = zext i1 %cmp2 to i32
ret i32 %conv
}
define i1 @no__mulodi4(i32 %a, i64 %b, i32* %c) {
; CHECK-LABEL: no__mulodi4
; CHECK-NOT: bl __mulodi4
entry:
%0 = sext i32 %a to i64
%1 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 %0, i64 %b)
%2 = extractvalue { i64, i1 } %1, 1
%3 = extractvalue { i64, i1 } %1, 0
%4 = trunc i64 %3 to i32
%5 = sext i32 %4 to i64
%6 = icmp ne i64 %3, %5
%7 = or i1 %2, %6
store i32 %4, i32* %c, align 4
ret i1 %7
}
declare void @llvm.trap() #2
declare { i32, i1 } @llvm.sadd.with.overflow.i32(i32, i32) #1
declare { i32, i1 } @llvm.uadd.with.overflow.i32(i32, i32) #1
declare { i32, i1 } @llvm.ssub.with.overflow.i32(i32, i32) #1
declare { i32, i1 } @llvm.usub.with.overflow.i32(i32, i32) #1
declare { i32, i1 } @llvm.smul.with.overflow.i32(i32, i32) #1
declare { i32, i1 } @llvm.umul.with.overflow.i32(i32, i32) #1
declare { i64, i1 } @llvm.smul.with.overflow.i64(i64, i64)
|
