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
|
; RUN: opt < %s -jump-threading -S | FileCheck %s
; RUN: opt < %s -passes=jump-threading -S | FileCheck %s
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
target triple = "i386-apple-darwin7"
; Test that we can thread through the block with the partially redundant load (%2).
; rdar://6402033
define i32 @test1(i32* %P) nounwind {
; CHECK-LABEL: @test1(
entry:
%0 = tail call i32 (...) @f1() nounwind ; <i32> [#uses=1]
%1 = icmp eq i32 %0, 0 ; <i1> [#uses=1]
br i1 %1, label %bb1, label %bb
bb: ; preds = %entry
; CHECK: bb1.thread:
; CHECK: store
; CHECK: br label %bb3
store i32 42, i32* %P, align 4
br label %bb1
bb1: ; preds = %entry, %bb
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ] ; <i32> [#uses=2]
%2 = load i32, i32* %P, align 4 ; <i32> [#uses=1]
%3 = icmp sgt i32 %2, 36 ; <i1> [#uses=1]
br i1 %3, label %bb3, label %bb2
bb2: ; preds = %bb1
%4 = tail call i32 (...) @f2() nounwind ; <i32> [#uses=0]
ret i32 %res.0
bb3: ; preds = %bb1
; CHECK: bb3:
; CHECK: %res.01 = phi i32 [ 1, %bb1.thread ], [ 0, %bb1 ]
; CHECK: ret i32 %res.01
ret i32 %res.0
}
declare i32 @f1(...)
declare i32 @f2(...)
;; Check that we preserve TBAA information.
; rdar://11039258
define i32 @test2(i32* %P) nounwind {
; CHECK-LABEL: @test2(
entry:
%0 = tail call i32 (...) @f1() nounwind ; <i32> [#uses=1]
%1 = icmp eq i32 %0, 0 ; <i1> [#uses=1]
br i1 %1, label %bb1, label %bb
bb: ; preds = %entry
; CHECK: bb1.thread:
; CHECK: store{{.*}}, !tbaa !0
; CHECK: br label %bb3
store i32 42, i32* %P, align 4, !tbaa !0
br label %bb1
bb1: ; preds = %entry, %bb
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
%2 = load i32, i32* %P, align 4, !tbaa !0
%3 = icmp sgt i32 %2, 36
br i1 %3, label %bb3, label %bb2
bb2: ; preds = %bb1
%4 = tail call i32 (...) @f2() nounwind
ret i32 %res.0
bb3: ; preds = %bb1
; CHECK: bb3:
; CHECK: %res.01 = phi i32 [ 1, %bb1.thread ], [ 0, %bb1 ]
; CHECK: ret i32 %res.01
ret i32 %res.0
}
define i32 @test3(i8** %x, i1 %f) {
; Correctly thread loads of different (but compatible) types, placing bitcasts
; as necessary in the predecessors. This is especially tricky because the same
; predecessor ends up with two entries in the PHI node and they must share
; a single cast.
; CHECK-LABEL: @test3(
entry:
%0 = bitcast i8** %x to i32**
%1 = load i32*, i32** %0, align 8
br i1 %f, label %if.end57, label %if.then56
; CHECK: %[[LOAD:.*]] = load i32*, i32**
; CHECK: %[[CAST:.*]] = bitcast i32* %[[LOAD]] to i8*
if.then56:
br label %if.end57
if.end57:
%2 = load i8*, i8** %x, align 8
%tobool59 = icmp eq i8* %2, null
br i1 %tobool59, label %return, label %if.then60
; CHECK: %[[PHI:.*]] = phi i8* [ %[[CAST]], %[[PRED:[^ ]+]] ], [ %[[CAST]], %[[PRED]] ]
; CHECK-NEXT: %[[CMP:.*]] = icmp eq i8* %[[PHI]], null
; CHECK-NEXT: br i1 %[[CMP]]
if.then60:
ret i32 42
return:
ret i32 13
}
define i32 @test4(i32* %P) {
; CHECK-LABEL: @test4(
entry:
%v0 = tail call i32 (...) @f1()
%v1 = icmp eq i32 %v0, 0
br i1 %v1, label %bb1, label %bb
bb:
; CHECK: bb1.thread:
; CHECK: store atomic
; CHECK: br label %bb3
store atomic i32 42, i32* %P unordered, align 4
br label %bb1
bb1:
; CHECK: bb1:
; CHECK-NOT: phi
; CHECK: load atomic
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
%v2 = load atomic i32, i32* %P unordered, align 4
%v3 = icmp sgt i32 %v2, 36
br i1 %v3, label %bb3, label %bb2
bb2:
%v4 = tail call i32 (...) @f2()
ret i32 %res.0
bb3:
ret i32 %res.0
}
define i32 @test5(i32* %P) {
; Negative test
; CHECK-LABEL: @test5(
entry:
%v0 = tail call i32 (...) @f1()
%v1 = icmp eq i32 %v0, 0
br i1 %v1, label %bb1, label %bb
bb:
; CHECK: bb:
; CHECK-NEXT: store atomic i32 42, i32* %P release, align 4
; CHECK-NEXT: br label %bb1
store atomic i32 42, i32* %P release, align 4
br label %bb1
bb1:
; CHECK: bb1:
; CHECK-NEXT: %res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
; CHECK-NEXT: %v2 = load atomic i32, i32* %P acquire, align 4
; CHECK-NEXT: %v3 = icmp sgt i32 %v2, 36
; CHECK-NEXT: br i1 %v3, label %bb3, label %bb2
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
%v2 = load atomic i32, i32* %P acquire, align 4
%v3 = icmp sgt i32 %v2, 36
br i1 %v3, label %bb3, label %bb2
bb2:
%v4 = tail call i32 (...) @f2()
ret i32 %res.0
bb3:
ret i32 %res.0
}
define i32 @test6(i32* %P) {
; Negative test
; CHECK-LABEL: @test6(
entry:
%v0 = tail call i32 (...) @f1()
%v1 = icmp eq i32 %v0, 0
br i1 %v1, label %bb1, label %bb
bb:
; CHECK: bb:
; CHECK-NEXT: store i32 42, i32* %P
; CHECK-NEXT: br label %bb1
store i32 42, i32* %P
br label %bb1
bb1:
; CHECK: bb1:
; CHECK-NEXT: %res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
; CHECK-NEXT: %v2 = load atomic i32, i32* %P acquire, align 4
; CHECK-NEXT: %v3 = icmp sgt i32 %v2, 36
; CHECK-NEXT: br i1 %v3, label %bb3, label %bb2
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
%v2 = load atomic i32, i32* %P acquire, align 4
%v3 = icmp sgt i32 %v2, 36
br i1 %v3, label %bb3, label %bb2
bb2:
%v4 = tail call i32 (...) @f2()
ret i32 %res.0
bb3:
ret i32 %res.0
}
define i32 @test7(i32* %P) {
; Negative test
; CHECK-LABEL: @test7(
entry:
%v0 = tail call i32 (...) @f1()
%v1 = icmp eq i32 %v0, 0
br i1 %v1, label %bb1, label %bb
bb:
; CHECK: bb:
; CHECK-NEXT: %val = load i32, i32* %P
; CHECK-NEXT: br label %bb1
%val = load i32, i32* %P
br label %bb1
bb1:
; CHECK: bb1:
; CHECK-NEXT: %res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
; CHECK-NEXT: %v2 = load atomic i32, i32* %P acquire, align 4
; CHECK-NEXT: %v3 = icmp sgt i32 %v2, 36
; CHECK-NEXT: br i1 %v3, label %bb3, label %bb2
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
%v2 = load atomic i32, i32* %P acquire, align 4
%v3 = icmp sgt i32 %v2, 36
br i1 %v3, label %bb3, label %bb2
bb2:
%v4 = tail call i32 (...) @f2()
ret i32 %res.0
bb3:
ret i32 %res.0
}
!0 = !{!3, !3, i64 0}
!1 = !{!"omnipotent char", !2}
!2 = !{!"Simple C/C++ TBAA", null}
!3 = !{!"int", !1}
|
