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
261
262
263
264
265
266
|
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -DLAMBDA -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -check-prefix=LAMBDA %s
// RUN: %clang_cc1 -verify -fopenmp -x c++ -fblocks -DBLOCKS -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -check-prefix=BLOCKS %s
// expected-no-diagnostics
// REQUIRES: x86-registered-target
#ifndef HEADER
#define HEADER
template <class T>
struct S {
T f;
S(T a) : f(a) {}
S() : f() {}
S<T> &operator=(const S<T> &);
operator T() { return T(); }
~S() {}
};
volatile int g = 1212;
volatile int &g1 = g;
float f;
char cnt;
// CHECK: [[S_FLOAT_TY:%.+]] = type { float }
// CHECK: [[S_INT_TY:%.+]] = type { i32 }
// CHECK-DAG: [[IMPLICIT_BARRIER_LOC:@.+]] = private unnamed_addr constant %{{.+}} { i32 0, i32 66, i32 0, i32 0, i8*
// CHECK-DAG: [[F:@.+]] = global float 0.0
// CHECK-DAG: [[CNT:@.+]] = global i8 0
template <typename T>
T tmain() {
S<T> test;
T *pvar = &test.f;
T &lvar = test.f;
#pragma omp parallel
#pragma omp for linear(pvar, lvar)
for (int i = 0; i < 2; ++i) {
++pvar, ++lvar;
}
return T();
}
int main() {
#ifdef LAMBDA
// LAMBDA: [[G:@.+]] = global i{{[0-9]+}} 1212,
// LAMBDA-LABEL: @main
// LAMBDA: call void [[OUTER_LAMBDA:@.+]](
[&]() {
// LAMBDA: define{{.*}} internal{{.*}} void [[OUTER_LAMBDA]](
// LAMBDA: call void {{.+}} @__kmpc_fork_call({{.+}}, i32 0, {{.+}}* [[OMP_REGION:@.+]] to {{.+}})
#pragma omp parallel
#pragma omp for linear(g, g1:5)
for (int i = 0; i < 2; ++i) {
// LAMBDA: define{{.*}} internal{{.*}} void [[OMP_REGION]](i32* noalias %{{.+}}, i32* noalias %{{.+}})
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: [[G_START_ADDR:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: [[G_PRIVATE_ADDR:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[GTID_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** %{{.+}}
// LAMBDA: [[GTID:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[GTID_REF]]
// LAMBDA: call {{.+}} @__kmpc_for_static_init_4(%{{.+}}* @{{.+}}, i32 [[GTID]], i32 34, i32* [[IS_LAST_ADDR:%.+]], i32* %{{.+}}, i32* %{{.+}}, i32* %{{.+}}, i32 1, i32 1)
// LAMBDA: [[VAL:%.+]] = load i32, i32* [[G_START_ADDR]]
// LAMBDA: [[CNT:%.+]] = load i32, i32*
// LAMBDA: [[MUL:%.+]] = mul nsw i32 [[CNT]], 5
// LAMBDA: [[ADD:%.+]] = add nsw i32 [[VAL]], [[MUL]]
// LAMBDA: store i32 [[ADD]], i32* [[G_PRIVATE_ADDR]],
// LAMBDA: [[VAL:%.+]] = load i32, i32* [[G_PRIVATE_ADDR]],
// LAMBDA: [[ADD:%.+]] = add nsw i32 [[VAL]], 5
// LAMBDA: store i32 [[ADD]], i32* [[G_PRIVATE_ADDR]],
// LAMBDA: [[G_PRIVATE_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// LAMBDA: store i{{[0-9]+}}* [[G_PRIVATE_ADDR]], i{{[0-9]+}}** [[G_PRIVATE_ADDR_REF]]
// LAMBDA: call void [[INNER_LAMBDA:@.+]](%{{.+}}* [[ARG]])
// LAMBDA: call void @__kmpc_for_static_fini(%{{.+}}* @{{.+}}, i32 [[GTID]])
g += 5;
g1 += 5;
// LAMBDA: call void @__kmpc_barrier(%{{.+}}* @{{.+}}, i{{[0-9]+}} [[GTID]])
[&]() {
// LAMBDA: define {{.+}} void [[INNER_LAMBDA]](%{{.+}}* [[ARG_PTR:%.+]])
// LAMBDA: store %{{.+}}* [[ARG_PTR]], %{{.+}}** [[ARG_PTR_REF:%.+]],
g = 2;
g1 = 2;
// LAMBDA: [[ARG_PTR:%.+]] = load %{{.+}}*, %{{.+}}** [[ARG_PTR_REF]]
// LAMBDA: [[G_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// LAMBDA: [[G_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[G_PTR_REF]]
// LAMBDA: store i{{[0-9]+}} 2, i{{[0-9]+}}* [[G_REF]]
}();
}
}();
return 0;
#elif defined(BLOCKS)
// BLOCKS: [[G:@.+]] = global i{{[0-9]+}} 1212,
// BLOCKS-LABEL: @main
// BLOCKS: call void {{%.+}}(i8
^{
// BLOCKS: define{{.*}} internal{{.*}} void {{.+}}(i8*
// BLOCKS: call void {{.+}} @__kmpc_fork_call({{.+}}, i32 0, {{.+}}* [[OMP_REGION:@.+]] to {{.+}})
#pragma omp parallel
#pragma omp for linear(g, g1:5)
for (int i = 0; i < 2; ++i) {
// BLOCKS: define{{.*}} internal{{.*}} void [[OMP_REGION]](i32* noalias %{{.+}}, i32* noalias %{{.+}})
// BLOCKS: alloca i{{[0-9]+}},
// BLOCKS: [[G_START_ADDR:%.+]] = alloca i{{[0-9]+}},
// BLOCKS: alloca i{{[0-9]+}},
// BLOCKS: alloca i{{[0-9]+}},
// BLOCKS: alloca i{{[0-9]+}},
// BLOCKS: alloca i{{[0-9]+}},
// BLOCKS: alloca i{{[0-9]+}},
// BLOCKS: alloca i{{[0-9]+}},
// BLOCKS: [[G_PRIVATE_ADDR:%.+]] = alloca i{{[0-9]+}},
// BLOCKS: [[GTID_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** %{{.+}}
// BLOCKS: [[GTID:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[GTID_REF]]
// BLOCKS: call {{.+}} @__kmpc_for_static_init_4(%{{.+}}* @{{.+}}, i32 [[GTID]], i32 34, i32* [[IS_LAST_ADDR:%.+]], i32* %{{.+}}, i32* %{{.+}}, i32* %{{.+}}, i32 1, i32 1)
// BLOCKS: [[VAL:%.+]] = load i32, i32* [[G_START_ADDR]]
// BLOCKS: [[CNT:%.+]] = load i32, i32*
// BLOCKS: [[MUL:%.+]] = mul nsw i32 [[CNT]], 5
// BLOCKS: [[ADD:%.+]] = add nsw i32 [[VAL]], [[MUL]]
// BLOCKS: store i32 [[ADD]], i32* [[G_PRIVATE_ADDR]],
// BLOCKS: [[VAL:%.+]] = load i32, i32* [[G_PRIVATE_ADDR]],
// BLOCKS: [[ADD:%.+]] = add nsw i32 [[VAL]], 5
// BLOCKS: store i32 [[ADD]], i32* [[G_PRIVATE_ADDR]],
// BLOCKS-NOT: [[G]]{{[[^:word:]]}}
// BLOCKS: i{{[0-9]+}}* [[G_PRIVATE_ADDR]]
// BLOCKS-NOT: [[G]]{{[[^:word:]]}}
// BLOCKS: call void {{%.+}}(i8
// BLOCKS: call void @__kmpc_for_static_fini(%{{.+}}* @{{.+}}, i32 [[GTID]])
g += 5;
g1 += 5;
// BLOCKS: call void @__kmpc_barrier(%{{.+}}* @{{.+}}, i{{[0-9]+}} [[GTID]])
g = 1;
g1 = 5;
^{
// BLOCKS: define {{.+}} void {{@.+}}(i8*
g = 2;
g1 = 2;
// BLOCKS-NOT: [[G]]{{[[^:word:]]}}
// BLOCKS: store i{{[0-9]+}} 2, i{{[0-9]+}}*
// BLOCKS-NOT: [[G]]{{[[^:word:]]}}
// BLOCKS: ret
}();
}
}();
return 0;
#else
S<float> test;
float *pvar = &test.f;
long long lvar = 0;
#pragma omp parallel
#pragma omp for linear(pvar, lvar : 3)
for (int i = 0; i < 2; ++i) {
pvar += 3, lvar += 3;
}
return tmain<int>();
#endif
}
// CHECK: define i{{[0-9]+}} @main()
// CHECK: [[TEST:%.+]] = alloca [[S_FLOAT_TY]],
// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_CONSTR:@.+]]([[S_FLOAT_TY]]* [[TEST]])
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 2, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, float**, i64*)* [[MAIN_MICROTASK:@.+]] to void
// CHECK: = call {{.+}} [[TMAIN_INT:@.+]]()
// CHECK: call void [[S_FLOAT_TY_DESTR:@.+]]([[S_FLOAT_TY]]*
// CHECK: ret
// CHECK: define internal void [[MAIN_MICROTASK]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, float** dereferenceable(8) %{{.+}}, i64* dereferenceable(8) %{{.+}})
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[PVAR_START:%.+]] = alloca float*,
// CHECK: [[LVAR_START:%.+]] = alloca i64,
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[PVAR_PRIV:%.+]] = alloca float*,
// CHECK: [[LVAR_PRIV:%.+]] = alloca i64,
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_REF:%.+]]
// Check for default initialization.
// CHECK: [[PVAR_REF:%.+]] = load float**, float*** %
// CHECK: [[LVAR_REF:%.+]] = load i64*, i64** %
// CHECK: [[PVAR_VAL:%.+]] = load float*, float** [[PVAR_REF]],
// CHECK: store float* [[PVAR_VAL]], float** [[PVAR_START]],
// CHECK: [[LVAR_VAL:%.+]] = load i64, i64* [[LVAR_REF]],
// CHECK: store i64 [[LVAR_VAL]], i64* [[LVAR_START]],
// CHECK: call {{.+}} @__kmpc_for_static_init_4(%{{.+}}* @{{.+}}, i32 [[GTID:%.+]], i32 34, i32* [[IS_LAST_ADDR:%.+]], i32* %{{.+}}, i32* %{{.+}}, i32* %{{.+}}, i32 1, i32 1)
// CHECK: [[PVAR_VAL:%.+]] = load float*, float** [[PVAR_START]],
// CHECK: [[CNT:%.+]] = load i32, i32*
// CHECK: [[MUL:%.+]] = mul nsw i32 [[CNT]], 3
// CHECK: [[IDX:%.+]] = sext i32 [[MUL]] to i64
// CHECK: [[PTR:%.+]] = getelementptr inbounds float, float* [[PVAR_VAL]], i64 [[IDX]]
// CHECK: store float* [[PTR]], float** [[PVAR_PRIV]],
// CHECK: [[LVAR_VAL:%.+]] = load i64, i64* [[LVAR_START]],
// CHECK: [[CNT:%.+]] = load i32, i32*
// CHECK: [[MUL:%.+]] = mul nsw i32 [[CNT]], 3
// CHECK: [[CONV:%.+]] = sext i32 [[MUL]] to i64
// CHECK: [[VAL:%.+]] = add nsw i64 [[LVAR_VAL]], [[CONV]]
// CHECK: store i64 [[VAL]], i64* [[LVAR_PRIV]],
// CHECK: [[PVAR_VAL:%.+]] = load float*, float** [[PVAR_PRIV]]
// CHECK: [[PTR:%.+]] = getelementptr inbounds float, float* [[PVAR_VAL]], i64 3
// CHECK: store float* [[PTR]], float** [[PVAR_PRIV]],
// CHECK: [[LVAR_VAL:%.+]] = load i64, i64* [[LVAR_PRIV]],
// CHECK: [[ADD:%.+]] = add nsw i64 [[LVAR_VAL]], 3
// CHECK: store i64 [[ADD]], i64* [[LVAR_PRIV]],
// CHECK: call void @__kmpc_for_static_fini(%{{.+}}* @{{.+}}, i32 %{{.+}})
// CHECK: call void @__kmpc_barrier(%{{.+}}* [[IMPLICIT_BARRIER_LOC]], i{{[0-9]+}} [[GTID]])
// CHECK: ret void
// CHECK: define {{.*}} i{{[0-9]+}} [[TMAIN_INT]]()
// CHECK: [[TEST:%.+]] = alloca [[S_INT_TY]],
// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR:@.+]]([[S_INT_TY]]* [[TEST]])
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 2, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, i32**, i32*)* [[TMAIN_MICROTASK:@.+]] to void
// CHECK: call void [[S_INT_TY_DESTR:@.+]]([[S_INT_TY]]*
// CHECK: ret
//
// CHECK: define internal void [[TMAIN_MICROTASK]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, i32** dereferenceable(8) %{{.+}}, i32* dereferenceable(4) %{{.+}})
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[PVAR_START:%.+]] = alloca i32*,
// CHECK: [[LVAR_START:%.+]] = alloca i32,
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[PVAR_PRIV:%.+]] = alloca i32*,
// CHECK: [[LVAR_PRIV:%.+]] = alloca i32,
// CHECK: [[LVAR_PRIV_REF:%.+]] = alloca i32*,
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_REF:%.+]]
// Check for default initialization.
// CHECK: [[PVAR_REF:%.+]] = load i32**, i32*** %
// CHECK: [[PVAR_VAL:%.+]] = load i32*, i32** [[PVAR_REF]],
// CHECK: store i32* [[PVAR_VAL]], i32** [[PVAR_START]],
// CHECK: [[LVAR_REF:%.+]] = load i32*, i32** %
// CHECK: [[LVAR_VAL:%.+]] = load i32, i32* [[LVAR_REF]],
// CHECK: store i32 [[LVAR_VAL]], i32* [[LVAR_START]],
// CHECK: store i32* [[LVAR_PRIV]], i32** [[LVAR_PRIV_REF]],
// CHECK: call {{.+}} @__kmpc_for_static_init_4(%{{.+}}* @{{.+}}, i32 [[GTID:%.+]], i32 34, i32* [[IS_LAST_ADDR:%.+]], i32* %{{.+}}, i32* %{{.+}}, i32* %{{.+}}, i32 1, i32 1)
// CHECK: [[PVAR_VAL:%.+]] = load i32*, i32** [[PVAR_START]],
// CHECK: [[CNT:%.+]] = load i32, i32*
// CHECK: [[MUL:%.+]] = mul nsw i32 [[CNT]], 1
// CHECK: [[IDX:%.+]] = sext i32 [[MUL]] to i64
// CHECK: [[PTR:%.+]] = getelementptr inbounds i32, i32* [[PVAR_VAL]], i64 [[IDX]]
// CHECK: store i32* [[PTR]], i32** [[PVAR_PRIV]],
// CHECK: [[LVAR_VAL:%.+]] = load i32, i32* [[LVAR_START]],
// CHECK: [[CNT:%.+]] = load i32, i32*
// CHECK: [[MUL:%.+]] = mul nsw i32 [[CNT]], 1
// CHECK: [[VAL:%.+]] = add nsw i32 [[LVAR_VAL]], [[MUL]]
// CHECK: store i32 [[VAL]], i32* [[LVAR_PRIV]],
// CHECK: [[PVAR_VAL:%.+]] = load i32*, i32** [[PVAR_PRIV]]
// CHECK: [[PTR:%.+]] = getelementptr inbounds i32, i32* [[PVAR_VAL]], i32 1
// CHECK: store i32* [[PTR]], i32** [[PVAR_PRIV]],
// CHECK: [[LVAR_PRIV:%.+]] = load i32*, i32** [[LVAR_PRIV_REF]],
// CHECK: [[LVAR_VAL:%.+]] = load i32, i32* [[LVAR_PRIV]],
// CHECK: [[ADD:%.+]] = add nsw i32 [[LVAR_VAL]], 1
// CHECK: store i32 [[ADD]], i32* [[LVAR_PRIV]],
// CHECK: call void @__kmpc_for_static_fini(%{{.+}}* @{{.+}}, i32 %{{.+}})
// CHECK: call void @__kmpc_barrier(%{{.+}}* [[IMPLICIT_BARRIER_LOC]], i{{[0-9]+}} [[GTID]])
// CHECK: ret void
#endif
|
