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
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs
// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm -o - -fopenmp \
// RUN: -triple i386-unknown-unknown -fopenmp-version=51 %s | \
// RUN: FileCheck %s --check-prefix=CHECK-32
// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm -o - -fopenmp \
// RUN: -triple x86_64-unknown-linux-gnu -fopenmp-version=51 %s | FileCheck %s
// RUN: %clang_cc1 -no-opaque-pointers -fopenmp \
// RUN: -triple x86_64-unknown-linux-gnu -fopenmp-version=51 \
// RUN: -emit-pch %s -o %t
// RUN: %clang_cc1 -no-opaque-pointers -fopenmp \
// RUN: -triple x86_64-unknown-linux-gnu -fopenmp-version=51 \
// RUN: -include-pch %t -emit-llvm %s -o - | FileCheck %s
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
typedef enum omp_allocator_handle_t {
omp_null_allocator = 0,
omp_default_mem_alloc = 1,
omp_large_cap_mem_alloc = 2,
omp_const_mem_alloc = 3,
omp_high_bw_mem_alloc = 4,
omp_low_lat_mem_alloc = 5,
omp_cgroup_mem_alloc = 6,
omp_pteam_mem_alloc = 7,
omp_thread_mem_alloc = 8,
KMP_ALLOCATOR_MAX_HANDLE = __UINTPTR_MAX__
} omp_allocator_handle_t;
int main() {
int foo0[5];
int foo1[10];
int foo2[20];
int foo3[30];
int foo4[40];
int foo5[50];
int foo6[60];
int foo7[70];
int foo8[80];
omp_allocator_handle_t MyAlloc = omp_large_cap_mem_alloc;
#pragma omp allocate(foo0) align(1)
#pragma omp allocate(foo1) allocator(omp_pteam_mem_alloc) align(2)
#pragma omp allocate(foo2) align(4) allocator(omp_cgroup_mem_alloc)
#pragma omp allocate(foo3) align(8) allocator(omp_low_lat_mem_alloc)
#pragma omp allocate(foo4) align(16) allocator(omp_high_bw_mem_alloc)
#pragma omp allocate(foo5) align(32) allocator(omp_const_mem_alloc)
#pragma omp allocate(foo6) align(64) allocator(omp_large_cap_mem_alloc)
#pragma omp allocate(foo7) align(32) allocator(omp_thread_mem_alloc)
#pragma omp allocate(foo8) align(16) allocator(omp_null_allocator)
{
double foo9[80];
double foo10[90];
#pragma omp allocate(foo9) align(8) allocator(omp_thread_mem_alloc)
#pragma omp allocate(foo10) align(128)
}
{
int bar1;
int bar2[10];
int bar3[20];
int *bar4;
float bar5;
double bar6[30];
#pragma omp allocate(bar1, bar2, bar3) align(2) allocator(MyAlloc)
#pragma omp allocate(bar4, bar5, bar6) align(16)
}
}
// Verify align clause in template with non-type template parameter.
template <typename T, unsigned size, unsigned align>
T run() {
T foo[size];
#pragma omp allocate(foo) align(align) allocator(omp_cgroup_mem_alloc)
return foo[0];
}
int template_test() {
double result;
result = run<double, 1000, 16>();
return 0;
}
#endif
// CHECK-32-LABEL: define {{[^@]+}}@main
// CHECK-32-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK-32-NEXT: entry:
// CHECK-32-NEXT: [[MYALLOC:%.*]] = alloca i32, align 4
// CHECK-32-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK-32-NEXT: [[DOTFOO0__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 4, i32 20, i8* null)
// CHECK-32-NEXT: [[DOTFOO0__ADDR:%.*]] = bitcast i8* [[DOTFOO0__VOID_ADDR]] to [5 x i32]*
// CHECK-32-NEXT: [[DOTFOO1__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 4, i32 40, i8* inttoptr (i32 7 to i8*))
// CHECK-32-NEXT: [[DOTFOO1__ADDR:%.*]] = bitcast i8* [[DOTFOO1__VOID_ADDR]] to [10 x i32]*
// CHECK-32-NEXT: [[DOTFOO2__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 4, i32 80, i8* inttoptr (i32 6 to i8*))
// CHECK-32-NEXT: [[DOTFOO2__ADDR:%.*]] = bitcast i8* [[DOTFOO2__VOID_ADDR]] to [20 x i32]*
// CHECK-32-NEXT: [[DOTFOO3__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 8, i32 120, i8* inttoptr (i32 5 to i8*))
// CHECK-32-NEXT: [[DOTFOO3__ADDR:%.*]] = bitcast i8* [[DOTFOO3__VOID_ADDR]] to [30 x i32]*
// CHECK-32-NEXT: [[DOTFOO4__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 16, i32 160, i8* inttoptr (i32 4 to i8*))
// CHECK-32-NEXT: [[DOTFOO4__ADDR:%.*]] = bitcast i8* [[DOTFOO4__VOID_ADDR]] to [40 x i32]*
// CHECK-32-NEXT: [[DOTFOO5__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 32, i32 200, i8* inttoptr (i32 3 to i8*))
// CHECK-32-NEXT: [[DOTFOO5__ADDR:%.*]] = bitcast i8* [[DOTFOO5__VOID_ADDR]] to [50 x i32]*
// CHECK-32-NEXT: [[DOTFOO6__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 64, i32 240, i8* inttoptr (i32 2 to i8*))
// CHECK-32-NEXT: [[DOTFOO6__ADDR:%.*]] = bitcast i8* [[DOTFOO6__VOID_ADDR]] to [60 x i32]*
// CHECK-32-NEXT: [[DOTFOO7__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 32, i32 280, i8* inttoptr (i32 8 to i8*))
// CHECK-32-NEXT: [[DOTFOO7__ADDR:%.*]] = bitcast i8* [[DOTFOO7__VOID_ADDR]] to [70 x i32]*
// CHECK-32-NEXT: [[DOTFOO8__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 16, i32 320, i8* null)
// CHECK-32-NEXT: [[DOTFOO8__ADDR:%.*]] = bitcast i8* [[DOTFOO8__VOID_ADDR]] to [80 x i32]*
// CHECK-32-NEXT: store i32 2, i32* [[MYALLOC]], align 4
// CHECK-32-NEXT: [[DOTFOO9__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 8, i32 640, i8* inttoptr (i32 8 to i8*))
// CHECK-32-NEXT: [[DOTFOO9__ADDR:%.*]] = bitcast i8* [[DOTFOO9__VOID_ADDR]] to [80 x double]*
// CHECK-32-NEXT: [[DOTFOO10__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 128, i32 720, i8* null)
// CHECK-32-NEXT: [[DOTFOO10__ADDR:%.*]] = bitcast i8* [[DOTFOO10__VOID_ADDR]] to [90 x double]*
// CHECK-32-NEXT: [[TMP1:%.*]] = bitcast [90 x double]* [[DOTFOO10__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP1]], i8* null)
// CHECK-32-NEXT: [[TMP2:%.*]] = bitcast [80 x double]* [[DOTFOO9__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP2]], i8* inttoptr (i32 8 to i8*))
// CHECK-32-NEXT: [[TMP3:%.*]] = load i32, i32* [[MYALLOC]], align 4
// CHECK-32-NEXT: [[CONV:%.*]] = inttoptr i32 [[TMP3]] to i8*
// CHECK-32-NEXT: [[DOTBAR1__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 4, i32 4, i8* [[CONV]])
// CHECK-32-NEXT: [[DOTBAR1__ADDR:%.*]] = bitcast i8* [[DOTBAR1__VOID_ADDR]] to i32*
// CHECK-32-NEXT: [[TMP4:%.*]] = load i32, i32* [[MYALLOC]], align 4
// CHECK-32-NEXT: [[CONV1:%.*]] = inttoptr i32 [[TMP4]] to i8*
// CHECK-32-NEXT: [[DOTBAR2__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 4, i32 40, i8* [[CONV1]])
// CHECK-32-NEXT: [[DOTBAR2__ADDR:%.*]] = bitcast i8* [[DOTBAR2__VOID_ADDR]] to [10 x i32]*
// CHECK-32-NEXT: [[TMP5:%.*]] = load i32, i32* [[MYALLOC]], align 4
// CHECK-32-NEXT: [[CONV2:%.*]] = inttoptr i32 [[TMP5]] to i8*
// CHECK-32-NEXT: [[DOTBAR3__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 4, i32 80, i8* [[CONV2]])
// CHECK-32-NEXT: [[DOTBAR3__ADDR:%.*]] = bitcast i8* [[DOTBAR3__VOID_ADDR]] to [20 x i32]*
// CHECK-32-NEXT: [[DOTBAR4__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 16, i32 4, i8* null)
// CHECK-32-NEXT: [[DOTBAR4__ADDR:%.*]] = bitcast i8* [[DOTBAR4__VOID_ADDR]] to i32**
// CHECK-32-NEXT: [[DOTBAR5__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 16, i32 4, i8* null)
// CHECK-32-NEXT: [[DOTBAR5__ADDR:%.*]] = bitcast i8* [[DOTBAR5__VOID_ADDR]] to float*
// CHECK-32-NEXT: [[DOTBAR6__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 16, i32 240, i8* null)
// CHECK-32-NEXT: [[DOTBAR6__ADDR:%.*]] = bitcast i8* [[DOTBAR6__VOID_ADDR]] to [30 x double]*
// CHECK-32-NEXT: [[TMP6:%.*]] = bitcast [30 x double]* [[DOTBAR6__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP6]], i8* null)
// CHECK-32-NEXT: [[TMP7:%.*]] = bitcast float* [[DOTBAR5__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP7]], i8* null)
// CHECK-32-NEXT: [[TMP8:%.*]] = bitcast i32** [[DOTBAR4__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP8]], i8* null)
// CHECK-32-NEXT: [[TMP9:%.*]] = bitcast [20 x i32]* [[DOTBAR3__ADDR]] to i8*
// CHECK-32-NEXT: [[TMP10:%.*]] = load i32, i32* [[MYALLOC]], align 4
// CHECK-32-NEXT: [[CONV3:%.*]] = inttoptr i32 [[TMP10]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP9]], i8* [[CONV3]])
// CHECK-32-NEXT: [[TMP11:%.*]] = bitcast [10 x i32]* [[DOTBAR2__ADDR]] to i8*
// CHECK-32-NEXT: [[TMP12:%.*]] = load i32, i32* [[MYALLOC]], align 4
// CHECK-32-NEXT: [[CONV4:%.*]] = inttoptr i32 [[TMP12]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP11]], i8* [[CONV4]])
// CHECK-32-NEXT: [[TMP13:%.*]] = bitcast i32* [[DOTBAR1__ADDR]] to i8*
// CHECK-32-NEXT: [[TMP14:%.*]] = load i32, i32* [[MYALLOC]], align 4
// CHECK-32-NEXT: [[CONV5:%.*]] = inttoptr i32 [[TMP14]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP13]], i8* [[CONV5]])
// CHECK-32-NEXT: [[TMP15:%.*]] = bitcast [80 x i32]* [[DOTFOO8__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP15]], i8* null)
// CHECK-32-NEXT: [[TMP16:%.*]] = bitcast [70 x i32]* [[DOTFOO7__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP16]], i8* inttoptr (i32 8 to i8*))
// CHECK-32-NEXT: [[TMP17:%.*]] = bitcast [60 x i32]* [[DOTFOO6__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP17]], i8* inttoptr (i32 2 to i8*))
// CHECK-32-NEXT: [[TMP18:%.*]] = bitcast [50 x i32]* [[DOTFOO5__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP18]], i8* inttoptr (i32 3 to i8*))
// CHECK-32-NEXT: [[TMP19:%.*]] = bitcast [40 x i32]* [[DOTFOO4__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP19]], i8* inttoptr (i32 4 to i8*))
// CHECK-32-NEXT: [[TMP20:%.*]] = bitcast [30 x i32]* [[DOTFOO3__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP20]], i8* inttoptr (i32 5 to i8*))
// CHECK-32-NEXT: [[TMP21:%.*]] = bitcast [20 x i32]* [[DOTFOO2__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP21]], i8* inttoptr (i32 6 to i8*))
// CHECK-32-NEXT: [[TMP22:%.*]] = bitcast [10 x i32]* [[DOTFOO1__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP22]], i8* inttoptr (i32 7 to i8*))
// CHECK-32-NEXT: [[TMP23:%.*]] = bitcast [5 x i32]* [[DOTFOO0__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP23]], i8* null)
// CHECK-32-NEXT: ret i32 0
//
//
// CHECK-32-LABEL: define {{[^@]+}}@_Z13template_testv
// CHECK-32-SAME: () #[[ATTR2:[0-9]+]] {
// CHECK-32-NEXT: entry:
// CHECK-32-NEXT: [[RESULT:%.*]] = alloca double, align 8
// CHECK-32-NEXT: [[CALL:%.*]] = call noundef double @_Z3runIdLj1000ELj16EET_v()
// CHECK-32-NEXT: store double [[CALL]], double* [[RESULT]], align 8
// CHECK-32-NEXT: ret i32 0
//
//
// CHECK-32-LABEL: define {{[^@]+}}@_Z3runIdLj1000ELj16EET_v
// CHECK-32-SAME: () #[[ATTR2]] comdat {
// CHECK-32-NEXT: entry:
// CHECK-32-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]])
// CHECK-32-NEXT: [[DOTFOO__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i32 16, i32 8000, i8* inttoptr (i32 6 to i8*))
// CHECK-32-NEXT: [[DOTFOO__ADDR:%.*]] = bitcast i8* [[DOTFOO__VOID_ADDR]] to [1000 x double]*
// CHECK-32-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [1000 x double], [1000 x double]* [[DOTFOO__ADDR]], i32 0, i32 0
// CHECK-32-NEXT: [[TMP1:%.*]] = load double, double* [[ARRAYIDX]], align 8
// CHECK-32-NEXT: [[TMP2:%.*]] = bitcast [1000 x double]* [[DOTFOO__ADDR]] to i8*
// CHECK-32-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP2]], i8* inttoptr (i32 6 to i8*))
// CHECK-32-NEXT: ret double [[TMP1]]
//
//
// CHECK-LABEL: define {{[^@]+}}@main
// CHECK-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[MYALLOC:%.*]] = alloca i64, align 8
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK-NEXT: [[DOTFOO0__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 4, i64 32, i8* null)
// CHECK-NEXT: [[DOTFOO0__ADDR:%.*]] = bitcast i8* [[DOTFOO0__VOID_ADDR]] to [5 x i32]*
// CHECK-NEXT: [[DOTFOO1__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 4, i64 48, i8* inttoptr (i64 7 to i8*))
// CHECK-NEXT: [[DOTFOO1__ADDR:%.*]] = bitcast i8* [[DOTFOO1__VOID_ADDR]] to [10 x i32]*
// CHECK-NEXT: [[DOTFOO2__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 4, i64 80, i8* inttoptr (i64 6 to i8*))
// CHECK-NEXT: [[DOTFOO2__ADDR:%.*]] = bitcast i8* [[DOTFOO2__VOID_ADDR]] to [20 x i32]*
// CHECK-NEXT: [[DOTFOO3__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 8, i64 128, i8* inttoptr (i64 5 to i8*))
// CHECK-NEXT: [[DOTFOO3__ADDR:%.*]] = bitcast i8* [[DOTFOO3__VOID_ADDR]] to [30 x i32]*
// CHECK-NEXT: [[DOTFOO4__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 16, i64 160, i8* inttoptr (i64 4 to i8*))
// CHECK-NEXT: [[DOTFOO4__ADDR:%.*]] = bitcast i8* [[DOTFOO4__VOID_ADDR]] to [40 x i32]*
// CHECK-NEXT: [[DOTFOO5__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 32, i64 208, i8* inttoptr (i64 3 to i8*))
// CHECK-NEXT: [[DOTFOO5__ADDR:%.*]] = bitcast i8* [[DOTFOO5__VOID_ADDR]] to [50 x i32]*
// CHECK-NEXT: [[DOTFOO6__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 64, i64 240, i8* inttoptr (i64 2 to i8*))
// CHECK-NEXT: [[DOTFOO6__ADDR:%.*]] = bitcast i8* [[DOTFOO6__VOID_ADDR]] to [60 x i32]*
// CHECK-NEXT: [[DOTFOO7__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 32, i64 288, i8* inttoptr (i64 8 to i8*))
// CHECK-NEXT: [[DOTFOO7__ADDR:%.*]] = bitcast i8* [[DOTFOO7__VOID_ADDR]] to [70 x i32]*
// CHECK-NEXT: [[DOTFOO8__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 16, i64 320, i8* null)
// CHECK-NEXT: [[DOTFOO8__ADDR:%.*]] = bitcast i8* [[DOTFOO8__VOID_ADDR]] to [80 x i32]*
// CHECK-NEXT: store i64 2, i64* [[MYALLOC]], align 8
// CHECK-NEXT: [[DOTFOO9__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 8, i64 640, i8* inttoptr (i64 8 to i8*))
// CHECK-NEXT: [[DOTFOO9__ADDR:%.*]] = bitcast i8* [[DOTFOO9__VOID_ADDR]] to [80 x double]*
// CHECK-NEXT: [[DOTFOO10__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 128, i64 720, i8* null)
// CHECK-NEXT: [[DOTFOO10__ADDR:%.*]] = bitcast i8* [[DOTFOO10__VOID_ADDR]] to [90 x double]*
// CHECK-NEXT: [[TMP1:%.*]] = bitcast [90 x double]* [[DOTFOO10__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP1]], i8* null)
// CHECK-NEXT: [[TMP2:%.*]] = bitcast [80 x double]* [[DOTFOO9__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP2]], i8* inttoptr (i64 8 to i8*))
// CHECK-NEXT: [[TMP3:%.*]] = load i64, i64* [[MYALLOC]], align 8
// CHECK-NEXT: [[CONV:%.*]] = inttoptr i64 [[TMP3]] to i8*
// CHECK-NEXT: [[DOTBAR1__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 4, i64 4, i8* [[CONV]])
// CHECK-NEXT: [[DOTBAR1__ADDR:%.*]] = bitcast i8* [[DOTBAR1__VOID_ADDR]] to i32*
// CHECK-NEXT: [[TMP4:%.*]] = load i64, i64* [[MYALLOC]], align 8
// CHECK-NEXT: [[CONV1:%.*]] = inttoptr i64 [[TMP4]] to i8*
// CHECK-NEXT: [[DOTBAR2__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 4, i64 48, i8* [[CONV1]])
// CHECK-NEXT: [[DOTBAR2__ADDR:%.*]] = bitcast i8* [[DOTBAR2__VOID_ADDR]] to [10 x i32]*
// CHECK-NEXT: [[TMP5:%.*]] = load i64, i64* [[MYALLOC]], align 8
// CHECK-NEXT: [[CONV2:%.*]] = inttoptr i64 [[TMP5]] to i8*
// CHECK-NEXT: [[DOTBAR3__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 4, i64 80, i8* [[CONV2]])
// CHECK-NEXT: [[DOTBAR3__ADDR:%.*]] = bitcast i8* [[DOTBAR3__VOID_ADDR]] to [20 x i32]*
// CHECK-NEXT: [[DOTBAR4__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 16, i64 8, i8* null)
// CHECK-NEXT: [[DOTBAR4__ADDR:%.*]] = bitcast i8* [[DOTBAR4__VOID_ADDR]] to i32**
// CHECK-NEXT: [[DOTBAR5__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 16, i64 4, i8* null)
// CHECK-NEXT: [[DOTBAR5__ADDR:%.*]] = bitcast i8* [[DOTBAR5__VOID_ADDR]] to float*
// CHECK-NEXT: [[DOTBAR6__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 16, i64 240, i8* null)
// CHECK-NEXT: [[DOTBAR6__ADDR:%.*]] = bitcast i8* [[DOTBAR6__VOID_ADDR]] to [30 x double]*
// CHECK-NEXT: [[TMP6:%.*]] = bitcast [30 x double]* [[DOTBAR6__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP6]], i8* null)
// CHECK-NEXT: [[TMP7:%.*]] = bitcast float* [[DOTBAR5__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP7]], i8* null)
// CHECK-NEXT: [[TMP8:%.*]] = bitcast i32** [[DOTBAR4__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP8]], i8* null)
// CHECK-NEXT: [[TMP9:%.*]] = bitcast [20 x i32]* [[DOTBAR3__ADDR]] to i8*
// CHECK-NEXT: [[TMP10:%.*]] = load i64, i64* [[MYALLOC]], align 8
// CHECK-NEXT: [[CONV3:%.*]] = inttoptr i64 [[TMP10]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP9]], i8* [[CONV3]])
// CHECK-NEXT: [[TMP11:%.*]] = bitcast [10 x i32]* [[DOTBAR2__ADDR]] to i8*
// CHECK-NEXT: [[TMP12:%.*]] = load i64, i64* [[MYALLOC]], align 8
// CHECK-NEXT: [[CONV4:%.*]] = inttoptr i64 [[TMP12]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP11]], i8* [[CONV4]])
// CHECK-NEXT: [[TMP13:%.*]] = bitcast i32* [[DOTBAR1__ADDR]] to i8*
// CHECK-NEXT: [[TMP14:%.*]] = load i64, i64* [[MYALLOC]], align 8
// CHECK-NEXT: [[CONV5:%.*]] = inttoptr i64 [[TMP14]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP13]], i8* [[CONV5]])
// CHECK-NEXT: [[TMP15:%.*]] = bitcast [80 x i32]* [[DOTFOO8__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP15]], i8* null)
// CHECK-NEXT: [[TMP16:%.*]] = bitcast [70 x i32]* [[DOTFOO7__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP16]], i8* inttoptr (i64 8 to i8*))
// CHECK-NEXT: [[TMP17:%.*]] = bitcast [60 x i32]* [[DOTFOO6__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP17]], i8* inttoptr (i64 2 to i8*))
// CHECK-NEXT: [[TMP18:%.*]] = bitcast [50 x i32]* [[DOTFOO5__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP18]], i8* inttoptr (i64 3 to i8*))
// CHECK-NEXT: [[TMP19:%.*]] = bitcast [40 x i32]* [[DOTFOO4__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP19]], i8* inttoptr (i64 4 to i8*))
// CHECK-NEXT: [[TMP20:%.*]] = bitcast [30 x i32]* [[DOTFOO3__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP20]], i8* inttoptr (i64 5 to i8*))
// CHECK-NEXT: [[TMP21:%.*]] = bitcast [20 x i32]* [[DOTFOO2__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP21]], i8* inttoptr (i64 6 to i8*))
// CHECK-NEXT: [[TMP22:%.*]] = bitcast [10 x i32]* [[DOTFOO1__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP22]], i8* inttoptr (i64 7 to i8*))
// CHECK-NEXT: [[TMP23:%.*]] = bitcast [5 x i32]* [[DOTFOO0__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP23]], i8* null)
// CHECK-NEXT: ret i32 0
//
//
// CHECK-LABEL: define {{[^@]+}}@_Z13template_testv
// CHECK-SAME: () #[[ATTR2:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RESULT:%.*]] = alloca double, align 8
// CHECK-NEXT: [[CALL:%.*]] = call noundef double @_Z3runIdLj1000ELj16EET_v()
// CHECK-NEXT: store double [[CALL]], double* [[RESULT]], align 8
// CHECK-NEXT: ret i32 0
//
//
// CHECK-LABEL: define {{[^@]+}}@_Z3runIdLj1000ELj16EET_v
// CHECK-SAME: () #[[ATTR2]] comdat {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]])
// CHECK-NEXT: [[DOTFOO__VOID_ADDR:%.*]] = call i8* @__kmpc_aligned_alloc(i32 [[TMP0]], i64 16, i64 8000, i8* inttoptr (i64 6 to i8*))
// CHECK-NEXT: [[DOTFOO__ADDR:%.*]] = bitcast i8* [[DOTFOO__VOID_ADDR]] to [1000 x double]*
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [1000 x double], [1000 x double]* [[DOTFOO__ADDR]], i64 0, i64 0
// CHECK-NEXT: [[TMP1:%.*]] = load double, double* [[ARRAYIDX]], align 16
// CHECK-NEXT: [[TMP2:%.*]] = bitcast [1000 x double]* [[DOTFOO__ADDR]] to i8*
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], i8* [[TMP2]], i8* inttoptr (i64 6 to i8*))
// CHECK-NEXT: ret double [[TMP1]]
//
|
