forked from llvm/llvm-project
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdistribute_parallel_for_private_codegen.cpp
313 lines (283 loc) · 16.6 KB
/
distribute_parallel_for_private_codegen.cpp
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
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-32
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-32
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// SIMD-ONLY1-NOT: {{__kmpc|__tgt}}
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
template <class T>
struct S {
T f;
S(T a) : f(a) {}
S() : f() {}
operator T() { return T(); }
~S() {}
};
// CHECK: [[S_FLOAT_TY:%.+]] = type { float }
// CHECK: [[S_INT_TY:%.+]] = type { i{{[0-9]+}} }
template <typename T>
T tmain() {
S<T> test;
T t_var = T();
T vec[] = {1, 2};
S<T> s_arr[] = {1, 2};
S<T> &var = test;
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for private(t_var, vec, s_arr, s_arr, var, var)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
}
return T();
}
int main() {
static int svar;
volatile double g;
volatile double &g1 = g;
#ifdef LAMBDA
// LAMBDA-LABEL: @main
// LAMBDA: call{{.*}} void [[OUTER_LAMBDA:@.+]](
[&]() {
static float sfvar;
// LAMBDA: define{{.*}} internal{{.*}} void [[OUTER_LAMBDA]](
// LAMBDA: call i{{[0-9]+}} @__tgt_target_teams(
// LAMBDA: call void [[OFFLOADING_FUN:@.+]](
// LAMBDA: define{{.+}} void [[OFFLOADING_FUN]]()
// LAMBDA: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[OMP_OUTLINED:@.+]] to {{.+}})
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for private(g, g1, svar, sfvar)
for (int i = 0; i < 2; ++i) {
// LAMBDA: define{{.*}} internal{{.*}} void [[OMP_OUTLINED]](i32* noalias %{{.+}}, i32* noalias %{{.+}})
// LAMBDA: [[G_PRIVATE_ADDR:%.+]] = alloca double,
// LAMBDA: [[G1_PRIVATE_ADDR:%.+]] = alloca double,
// LAMBDA: [[TMP_PRIVATE_ADDR:%.+]] = alloca double*,
// LAMBDA: [[SVAR_PRIVATE_ADDR:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[SFVAR_PRIVATE_ADDR:%.+]] = alloca float,
// LAMBDA: store double* [[G1_PRIVATE_ADDR]], double** [[TMP_PRIVATE_ADDR]],
// LAMBDA: call {{.*}}void @__kmpc_for_static_init_4(
// LAMBDA: call{{.+}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}}[[OMP_PARFOR_OUTLINED:@.+]] to {{.+}},
// LAMBDA: call {{.*}}void @__kmpc_for_static_fini(
// LAMBDA: ret void
// LAMBDA: define{{.+}} void [[OMP_PARFOR_OUTLINED]](
// LAMBDA: [[G_PRIVATE_ADDR:%.+]] = alloca double,
// LAMBDA: [[G1_PRIVATE_ADDR:%.+]] = alloca double,
// LAMBDA: [[TMP_PRIVATE_ADDR:%.+]] = alloca double*,
// LAMBDA: [[SVAR_PRIVATE_ADDR:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[SFVAR_PRIVATE_ADDR:%.+]] = alloca float,
g = 1;
g1 = 1;
svar = 3;
sfvar = 4.0;
// LAMBDA: store double* [[G1_PRIVATE_ADDR]], double** [[TMP_PRIVATE_ADDR]],
// LAMBDA: store double 1.0{{.+}}, double* [[G_PRIVATE_ADDR]],
// LAMBDA: store i{{[0-9]+}} 3, i{{[0-9]+}}* [[SVAR_PRIVATE_ADDR]],
// LAMBDA: store float 4.0{{.+}}, float* [[SFVAR_PRIVATE_ADDR]],
// LAMBDA: [[G_PRIVATE_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// LAMBDA: store double* [[G_PRIVATE_ADDR]], double** [[G_PRIVATE_ADDR_REF]],
// LAMBDA: [[TMP_PRIVATE_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 1
// LAMBDA: [[G1_PRIVATE_ADDR_FROM_TMP:%.+]] = load double*, double** [[TMP_PRIVATE_ADDR]],
// LAMBDA: store double* [[G1_PRIVATE_ADDR_FROM_TMP]], double** [[TMP_PRIVATE_ADDR_REF]],
// LAMBDA: [[SVAR_PRIVATE_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 2
// LAMBDA: store i{{[0-9]+}}* [[SVAR_PRIVATE_ADDR]], i{{[0-9]+}}** [[SVAR_PRIVATE_ADDR_REF]]
// LAMBDA: [[SFVAR_PRIVATE_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 3
// LAMBDA: store float* [[SFVAR_PRIVATE_ADDR]], float** [[SFVAR_PRIVATE_ADDR_REF]]
// LAMBDA: call{{.*}} void [[INNER_LAMBDA:@.+]](%{{.+}}* [[ARG]])
// LAMBDA: call {{.*}}void @__kmpc_for_static_fini(
// LAMBDA: ret void
[&]() {
// LAMBDA: define {{.+}} void [[INNER_LAMBDA]](%{{.+}}* [[ARG_PTR:%.+]])
// LAMBDA: store %{{.+}}* [[ARG_PTR]], %{{.+}}** [[ARG_PTR_REF:%.+]],
g = 2;
g1 = 2;
svar = 4;
sfvar = 8.0;
// 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 double*, double** [[G_PTR_REF]]
// LAMBDA: store double 2.0{{.+}}, double* [[G_REF]]
// LAMBDA: [[TMP_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 1
// LAMBDA: [[G1_REF:%.+]] = load double*, double** [[TMP_PTR_REF]]
// LAMBDA: store double 2.0{{.+}}, double* [[G1_REF]],
// LAMBDA: [[SVAR_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 2
// LAMBDA: [[SVAR_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[SVAR_PTR_REF]]
// LAMBDA: store i{{[0-9]+}} 4, i{{[0-9]+}}* [[SVAR_REF]]
// LAMBDA: [[SFVAR_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 3
// LAMBDA: [[SFVAR_REF:%.+]] = load float*, float** [[SFVAR_PTR_REF]]
// LAMBDA: store float 8.0{{.+}}, float* [[SFVAR_REF]]
}();
}
}();
return 0;
#else
S<float> test;
int t_var = 0;
int vec[] = {1, 2};
S<float> s_arr[] = {1, 2};
S<float> &var = test;
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for private(t_var, vec, s_arr, s_arr, var, var, svar)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
}
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 i{{[0-9]+}} @__tgt_target_teams(
// CHECK: call void [[OFFLOAD_FUN_0:@.+]](
// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_DESTR:@.+]]([[S_FLOAT_TY]]* [[TEST]])
// CHECK: ret
// CHECK: define{{.+}} [[OFFLOAD_FUN_0]]()
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_teams(%{{.+}}* @{{.+}}, i{{[0-9]+}} 0, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*)* [[OMP_OUTLINED_0:@.+]] to void
// CHECK: ret
//
// CHECK: define internal void [[OMP_OUTLINED_0]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}})
// CHECK: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_FLOAT_TY]]],
// CHECK-NOT: alloca [2 x [[S_FLOAT_TY]]],
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_FLOAT_TY]],
// CHECK-NOT: alloca [[S_FLOAT_TY]],
// CHECK: [[S_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_REF:%.+]]
// CHECK-NOT: [[T_VAR_PRIV]]
// CHECK-NOT: [[VEC_PRIV]]
// this is the ctor loop
// CHECK: {{.+}}:
// CHECK: [[S_ARR_PRIV_ITEM:%.+]] = phi [[S_FLOAT_TY]]*
// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_CONSTR]]([[S_FLOAT_TY]]* [[S_ARR_PRIV_ITEM]])
// CHECK-NOT: [[T_VAR_PRIV]]
// CHECK-NOT: [[VEC_PRIV]]
// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_CONSTR]]([[S_FLOAT_TY]]* [[VAR_PRIV]])
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call{{.+}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}}[[OMP_PARFOR_OUTLINED_0:@.+]] to {{.+}},
// CHECK: call void @__kmpc_for_static_fini(
// call destructors: var..
// CHECK-DAG: call {{.+}} [[S_FLOAT_TY_DEF_DESTR]]([[S_FLOAT_TY]]* [[VAR_PRIV]])
// ..and s_arr
// CHECK: {{.+}}:
// CHECK: [[S_ARR_EL_PAST:%.+]] = phi [[S_FLOAT_TY]]*
// CHECK: [[S_ARR_PRIV_ITEM:%.+]] = getelementptr {{.+}}, {{.+}} [[S_ARR_EL_PAST]],
// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_DESTR]]([[S_FLOAT_TY]]* [[S_ARR_PRIV_ITEM]])
// CHECK: ret void
// By OpenMP specifications, private applies to both distribute and parallel for.
// However, the support for 'private' of 'parallel' is only used when 'parallel'
// is found alone. Therefore we only have one 'private' support for 'parallel for'
// in combination
// CHECK: define{{.+}} void [[OMP_PARFOR_OUTLINED_0]](
// CHECK: [[T_VAR_PRIV:%t_var+]] = alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%vec+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%s_arr+]] = alloca [2 x [[S_FLOAT_TY]]],
// CHECK-NOT: alloca [2 x [[S_FLOAT_TY]]],
// CHECK: [[VAR_PRIV:%var+]] = alloca [[S_FLOAT_TY]],
// CHECK-NOT: alloca [[S_FLOAT_TY]],
// CHECK: [[S_VAR_PRIV:%svar+]] = alloca i{{[0-9]+}},
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_REF:%.+]]
// CHECK-NOT: [[T_VAR_PRIV]]
// CHECK-NOT: [[VEC_PRIV]]
// this is the ctor loop
// CHECK: {{.+}}:
// CHECK: [[S_ARR_PRIV_ITEM:%.+]] = phi [[S_FLOAT_TY]]*
// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_CONSTR]]([[S_FLOAT_TY]]* [[S_ARR_PRIV_ITEM]])
// CHECK-NOT: [[T_VAR_PRIV]]
// CHECK-NOT: [[VEC_PRIV]]
// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_CONSTR]]([[S_FLOAT_TY]]* [[VAR_PRIV]])
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void @__kmpc_for_static_fini(
// call destructors: var..
// CHECK-DAG: call {{.+}} [[S_FLOAT_TY_DEF_DESTR]]([[S_FLOAT_TY]]* [[VAR_PRIV]])
// ..and s_arr
// CHECK: {{.+}}:
// CHECK: [[S_ARR_EL_PAST:%.+]] = phi [[S_FLOAT_TY]]*
// CHECK: [[S_ARR_PRIV_ITEM:%.+]] = getelementptr {{.+}}, {{.+}} [[S_ARR_EL_PAST]],
// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_DESTR]]([[S_FLOAT_TY]]* [[S_ARR_PRIV_ITEM]])
// CHECK: ret void
// template tmain with S_INT_TY
// 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 i{{[0-9]+}} @__tgt_target_teams(
// CHECK: call void [[OFFLOAD_FUN_1:@.+]](
// CHECK: call {{.*}} [[S_INT_TY_DEF_DESTR:@.+]]([[S_INT_TY]]* [[TEST]])
// CHECK: ret
// CHECK: ret
// CHECK: define internal void [[OFFLOAD_FUN_1]]()
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_teams(%{{.+}}* @{{.+}}, i{{[0-9]+}} 0, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*)* [[OMP_OUTLINED_1:@.+]] to void
// CHECK: ret
//
// CHECK: define internal void [[OMP_OUTLINED_1]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}})
// CHECK: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_INT_TY]]],
// CHECK-NOT: alloca [2 x [[S_INT_TY]]],
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_INT_TY]],
// CHECK-NOT: alloca [[S_INT_TY]],
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_REF:%.+]]
// CHECK-NOT: [[T_VAR_PRIV]]
// CHECK-NOT: [[VEC_PRIV]]
// CHECK: {{.+}}:
// CHECK: [[S_ARR_PRIV_ITEM:%.+]] = phi [[S_INT_TY]]*
// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR]]([[S_INT_TY]]* [[S_ARR_PRIV_ITEM]])
// CHECK-NOT: [[T_VAR_PRIV]]
// CHECK-NOT: [[VEC_PRIV]]
// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR]]([[S_INT_TY]]* [[VAR_PRIV]])
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call{{.+}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}}[[OMP_PARFOR_OUTLINED_1:@.+]] to {{.+}},
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define{{.+}} void [[OMP_PARFOR_OUTLINED_1]](
// CHECK: [[T_VAR_PRIV:%t_var+]] = alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%vec+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%s_arr+]] = alloca [2 x [[S_INT_TY]]],
// CHECK-NOT: alloca [2 x [[S_INT_TY]]],
// CHECK: [[VAR_PRIV:%var+]] = alloca [[S_INT_TY]],
// CHECK-NOT: alloca [[S_INT_TY]],
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_REF:%.+]]
// CHECK-NOT: [[T_VAR_PRIV]]
// CHECK-NOT: [[VEC_PRIV]]
// this is the ctor loop
// CHECK: {{.+}}:
// CHECK: [[S_ARR_PRIV_ITEM:%.+]] = phi [[S_INT_TY]]*
// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR]]([[S_INT_TY]]* [[S_ARR_PRIV_ITEM]])
// CHECK-NOT: [[T_VAR_PRIV]]
// CHECK-NOT: [[VEC_PRIV]]
// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR]]([[S_INT_TY]]* [[VAR_PRIV]])
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void @__kmpc_for_static_fini(
// call destructors: var..
// CHECK-DAG: call {{.+}} [[S_INT_TY_DEF_DESTR]]([[S_INT_TY]]* [[VAR_PRIV]])
// ..and s_arr
// CHECK: {{.+}}:
// CHECK: [[S_ARR_EL_PAST:%.+]] = phi [[S_INT_TY]]*
// CHECK: [[S_ARR_PRIV_ITEM:%.+]] = getelementptr {{.+}}, {{.+}} [[S_ARR_EL_PAST]],
// CHECK: call {{.*}} [[S_INT_TY_DEF_DESTR]]([[S_INT_TY]]* [[S_ARR_PRIV_ITEM]])
// CHECK: ret void
#endif