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
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
// RUN: %clang_cc1 -fopenmp-enable-irbuilder -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
struct MyIterator {
MyIterator(unsigned pos);
MyIterator(const MyIterator &other);
const MyIterator &operator=(const MyIterator &that);
MyIterator &operator++();
int operator-(const MyIterator &that) const;
MyIterator &operator+=(unsigned a);
MyIterator operator+(unsigned a) const;
bool operator==(const MyIterator &that) const;
bool operator!=(const MyIterator &that) const;
unsigned operator*() const;
};
struct MyRange {
MyRange(int n);
MyIterator begin();
MyIterator end();
};
extern "C" void workshareloop_rangefor(float *a, float *b, float *c) {
#pragma omp for
for (unsigned i : MyRange(42)) {
a[i] = b[i] * c[i];
}
}
#endif // HEADER
// CHECK-LABEL: define {{[^@]+}}@workshareloop_rangefor
// CHECK-SAME: (ptr noundef [[A:%.*]], ptr noundef [[B:%.*]], ptr noundef [[C:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[C_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[__RANGE2:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_MYRANGE:%.*]], align 1
// CHECK-NEXT: [[__BEGIN2:%.*]] = alloca [[STRUCT_MYITERATOR:%.*]], align 1
// CHECK-NEXT: [[__END2:%.*]] = alloca [[STRUCT_MYITERATOR]], align 1
// CHECK-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 8
// CHECK-NEXT: [[AGG_CAPTURED1:%.*]] = alloca [[STRUCT_ANON_0:%.*]], align 1
// CHECK-NEXT: [[DOTCOUNT_ADDR:%.*]] = alloca i64, align 8
// CHECK-NEXT: [[P_LASTITER:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[P_LOWERBOUND:%.*]] = alloca i64, align 8
// CHECK-NEXT: [[P_UPPERBOUND:%.*]] = alloca i64, align 8
// CHECK-NEXT: [[P_STRIDE:%.*]] = alloca i64, align 8
// CHECK-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK-NEXT: store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK-NEXT: store ptr [[C]], ptr [[C_ADDR]], align 8
// CHECK-NEXT: call void @_ZN7MyRangeC1Ei(ptr noundef nonnull align 1 dereferenceable(1) [[REF_TMP]], i32 noundef 42)
// CHECK-NEXT: store ptr [[REF_TMP]], ptr [[__RANGE2]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[__RANGE2]], align 8
// CHECK-NEXT: call void @_ZN7MyRange5beginEv(ptr dead_on_unwind writable sret([[STRUCT_MYITERATOR]]) align 1 [[__BEGIN2]], ptr noundef nonnull align 1 dereferenceable(1) [[TMP0]])
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[__RANGE2]], align 8
// CHECK-NEXT: call void @_ZN7MyRange3endEv(ptr dead_on_unwind writable sret([[STRUCT_MYITERATOR]]) align 1 [[__END2]], ptr noundef nonnull align 1 dereferenceable(1) [[TMP1]])
// CHECK-NEXT: [[CALL:%.*]] = call noundef i32 @_ZNK10MyIteratordeEv(ptr noundef nonnull align 1 dereferenceable(1) [[__BEGIN2]])
// CHECK-NEXT: store i32 [[CALL]], ptr [[I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_ANON]], ptr [[AGG_CAPTURED]], i32 0, i32 0
// CHECK-NEXT: store ptr [[__BEGIN2]], ptr [[TMP2]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON]], ptr [[AGG_CAPTURED]], i32 0, i32 1
// CHECK-NEXT: store ptr [[__END2]], ptr [[TMP3]], align 8
// CHECK-NEXT: call void @_ZN10MyIteratorC1ERKS_(ptr noundef nonnull align 1 dereferenceable(1) [[AGG_CAPTURED1]], ptr noundef nonnull align 1 dereferenceable(1) [[__BEGIN2]])
// CHECK-NEXT: call void @__captured_stmt(ptr [[DOTCOUNT_ADDR]], ptr [[AGG_CAPTURED]])
// CHECK-NEXT: [[DOTCOUNT:%.*]] = load i64, ptr [[DOTCOUNT_ADDR]], align 8
// CHECK-NEXT: br label [[OMP_LOOP_PREHEADER:%.*]]
// CHECK: omp_loop.preheader:
// CHECK-NEXT: store i64 0, ptr [[P_LOWERBOUND]], align 8
// CHECK-NEXT: [[TMP5:%.*]] = sub i64 [[DOTCOUNT]], 1
// CHECK-NEXT: store i64 [[TMP5]], ptr [[P_UPPERBOUND]], align 8
// CHECK-NEXT: store i64 1, ptr [[P_STRIDE]], align 8
// CHECK-NEXT: [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
// CHECK-NEXT: call void @__kmpc_for_static_init_8u(ptr @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM]], i32 34, ptr [[P_LASTITER]], ptr [[P_LOWERBOUND]], ptr [[P_UPPERBOUND]], ptr [[P_STRIDE]], i64 1, i64 0)
// CHECK-NEXT: [[TMP6:%.*]] = load i64, ptr [[P_LOWERBOUND]], align 8
// CHECK-NEXT: [[TMP7:%.*]] = load i64, ptr [[P_UPPERBOUND]], align 8
// CHECK-NEXT: [[TMP8:%.*]] = sub i64 [[TMP7]], [[TMP6]]
// CHECK-NEXT: [[TMP9:%.*]] = add i64 [[TMP8]], 1
// CHECK-NEXT: br label [[OMP_LOOP_HEADER:%.*]]
// CHECK: omp_loop.header:
// CHECK-NEXT: [[OMP_LOOP_IV:%.*]] = phi i64 [ 0, [[OMP_LOOP_PREHEADER]] ], [ [[OMP_LOOP_NEXT:%.*]], [[OMP_LOOP_INC:%.*]] ]
// CHECK-NEXT: br label [[OMP_LOOP_COND:%.*]]
// CHECK: omp_loop.cond:
// CHECK-NEXT: [[OMP_LOOP_CMP:%.*]] = icmp ult i64 [[OMP_LOOP_IV]], [[TMP9]]
// CHECK-NEXT: br i1 [[OMP_LOOP_CMP]], label [[OMP_LOOP_BODY:%.*]], label [[OMP_LOOP_EXIT:%.*]]
// CHECK: omp_loop.body:
// CHECK-NEXT: [[TMP10:%.*]] = add i64 [[OMP_LOOP_IV]], [[TMP6]]
// CHECK-NEXT: call void @__captured_stmt.1(ptr [[I]], i64 [[TMP10]], ptr [[AGG_CAPTURED1]])
// CHECK-NEXT: [[TMP11:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK-NEXT: [[TMP12:%.*]] = load i32, ptr [[I]], align 4
// CHECK-NEXT: [[IDXPROM:%.*]] = zext i32 [[TMP12]] to i64
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[TMP11]], i64 [[IDXPROM]]
// CHECK-NEXT: [[TMP13:%.*]] = load float, ptr [[ARRAYIDX]], align 4
// CHECK-NEXT: [[TMP14:%.*]] = load ptr, ptr [[C_ADDR]], align 8
// CHECK-NEXT: [[TMP15:%.*]] = load i32, ptr [[I]], align 4
// CHECK-NEXT: [[IDXPROM2:%.*]] = zext i32 [[TMP15]] to i64
// CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i64 [[IDXPROM2]]
// CHECK-NEXT: [[TMP16:%.*]] = load float, ptr [[ARRAYIDX3]], align 4
// CHECK-NEXT: [[MUL:%.*]] = fmul float [[TMP13]], [[TMP16]]
// CHECK-NEXT: [[TMP17:%.*]] = load ptr, ptr [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP18:%.*]] = load i32, ptr [[I]], align 4
// CHECK-NEXT: [[IDXPROM4:%.*]] = zext i32 [[TMP18]] to i64
// CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i64 [[IDXPROM4]]
// CHECK-NEXT: store float [[MUL]], ptr [[ARRAYIDX5]], align 4
// CHECK-NEXT: br label [[OMP_LOOP_INC]]
// CHECK: omp_loop.inc:
// CHECK-NEXT: [[OMP_LOOP_NEXT]] = add nuw i64 [[OMP_LOOP_IV]], 1
// CHECK-NEXT: br label [[OMP_LOOP_HEADER]]
// CHECK: omp_loop.exit:
// CHECK-NEXT: call void @__kmpc_for_static_fini(ptr @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM]])
// CHECK-NEXT: [[OMP_GLOBAL_THREAD_NUM6:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
// CHECK-NEXT: call void @__kmpc_barrier(ptr @[[GLOB2:[0-9]+]], i32 [[OMP_GLOBAL_THREAD_NUM6]])
// CHECK-NEXT: br label [[OMP_LOOP_AFTER:%.*]]
// CHECK: omp_loop.after:
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@__captured_stmt
// CHECK-SAME: (ptr noundef nonnull align 8 dereferenceable(8) [[DISTANCE:%.*]], ptr noalias noundef [[__CONTEXT:%.*]]) #[[ATTR2:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DISTANCE_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[DOTSTART:%.*]] = alloca [[STRUCT_MYITERATOR:%.*]], align 1
// CHECK-NEXT: [[DOTSTOP:%.*]] = alloca [[STRUCT_MYITERATOR]], align 1
// CHECK-NEXT: [[DOTSTEP:%.*]] = alloca i64, align 8
// CHECK-NEXT: store ptr [[DISTANCE]], ptr [[DISTANCE_ADDR]], align 8
// CHECK-NEXT: store ptr [[__CONTEXT]], ptr [[__CONTEXT_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[__CONTEXT_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON:%.*]], ptr [[TMP0]], i32 0, i32 0
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TMP1]], align 8
// CHECK-NEXT: call void @_ZN10MyIteratorC1ERKS_(ptr noundef nonnull align 1 dereferenceable(1) [[DOTSTART]], ptr noundef nonnull align 1 dereferenceable(1) [[TMP2]])
// CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON]], ptr [[TMP0]], i32 0, i32 1
// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TMP3]], align 8
// CHECK-NEXT: call void @_ZN10MyIteratorC1ERKS_(ptr noundef nonnull align 1 dereferenceable(1) [[DOTSTOP]], ptr noundef nonnull align 1 dereferenceable(1) [[TMP4]])
// CHECK-NEXT: store i64 1, ptr [[DOTSTEP]], align 8
// CHECK-NEXT: [[TMP5:%.*]] = load i64, ptr [[DOTSTEP]], align 8
// CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[TMP5]], 0
// CHECK-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK: cond.true:
// CHECK-NEXT: [[CALL:%.*]] = call noundef i32 @_ZNK10MyIteratormiERKS_(ptr noundef nonnull align 1 dereferenceable(1) [[DOTSTART]], ptr noundef nonnull align 1 dereferenceable(1) [[DOTSTOP]])
// CHECK-NEXT: [[CONV:%.*]] = sext i32 [[CALL]] to i64
// CHECK-NEXT: [[TMP6:%.*]] = load i64, ptr [[DOTSTEP]], align 8
// CHECK-NEXT: [[SUB:%.*]] = sub i64 0, [[TMP6]]
// CHECK-NEXT: [[DIV:%.*]] = udiv i64 [[CONV]], [[SUB]]
// CHECK-NEXT: br label [[COND_END:%.*]]
// CHECK: cond.false:
// CHECK-NEXT: [[CALL1:%.*]] = call noundef i32 @_ZNK10MyIteratormiERKS_(ptr noundef nonnull align 1 dereferenceable(1) [[DOTSTOP]], ptr noundef nonnull align 1 dereferenceable(1) [[DOTSTART]])
// CHECK-NEXT: [[CONV2:%.*]] = sext i32 [[CALL1]] to i64
// CHECK-NEXT: [[TMP7:%.*]] = load i64, ptr [[DOTSTEP]], align 8
// CHECK-NEXT: [[DIV3:%.*]] = udiv i64 [[CONV2]], [[TMP7]]
// CHECK-NEXT: br label [[COND_END]]
// CHECK: cond.end:
// CHECK-NEXT: [[COND:%.*]] = phi i64 [ [[DIV]], [[COND_TRUE]] ], [ [[DIV3]], [[COND_FALSE]] ]
// CHECK-NEXT: [[TMP8:%.*]] = load ptr, ptr [[DISTANCE_ADDR]], align 8
// CHECK-NEXT: store i64 [[COND]], ptr [[TMP8]], align 8
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@__captured_stmt.1
// CHECK-SAME: (ptr noundef nonnull align 4 dereferenceable(4) [[LOOPVAR:%.*]], i64 noundef [[LOGICAL:%.*]], ptr noalias noundef [[__CONTEXT:%.*]]) #[[ATTR2]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LOOPVAR_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[LOGICAL_ADDR:%.*]] = alloca i64, align 8
// CHECK-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_MYITERATOR:%.*]], align 1
// CHECK-NEXT: store ptr [[LOOPVAR]], ptr [[LOOPVAR_ADDR]], align 8
// CHECK-NEXT: store i64 [[LOGICAL]], ptr [[LOGICAL_ADDR]], align 8
// CHECK-NEXT: store ptr [[__CONTEXT]], ptr [[__CONTEXT_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[__CONTEXT_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load i64, ptr [[LOGICAL_ADDR]], align 8
// CHECK-NEXT: [[MUL:%.*]] = mul i64 1, [[TMP1]]
// CHECK-NEXT: [[CONV:%.*]] = trunc i64 [[MUL]] to i32
// CHECK-NEXT: call void @_ZNK10MyIteratorplEj(ptr dead_on_unwind writable sret([[STRUCT_MYITERATOR]]) align 1 [[REF_TMP]], ptr noundef nonnull align 1 dereferenceable(1) [[TMP0]], i32 noundef [[CONV]])
// CHECK-NEXT: [[CALL:%.*]] = call noundef i32 @_ZNK10MyIteratordeEv(ptr noundef nonnull align 1 dereferenceable(1) [[REF_TMP]])
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[LOOPVAR_ADDR]], align 8
// CHECK-NEXT: store i32 [[CALL]], ptr [[TMP2]], align 4
// CHECK-NEXT: ret void
//
|
