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
|
// RUN: %clang_cc1 -verify -fopenmp -ast-print %s -Wno-openmp-mapping | FileCheck %s --check-prefix CHECK --check-prefix OMP45
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-mapping | FileCheck %s --check-prefix CHECK --check-prefix OMP45
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -DOMP5 -ast-print %s -Wno-openmp-mapping | FileCheck %s --check-prefix CHECK --check-prefix OMP50
// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-mapping | FileCheck %s --check-prefix CHECK --check-prefix OMP50
// RUN: %clang_cc1 -verify -fopenmp-simd -ast-print %s -Wno-openmp-mapping | FileCheck %s --check-prefix CHECK --check-prefix OMP45
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-mapping | FileCheck %s --check-prefix CHECK --check-prefix OMP45
// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -DOMP5 -ast-print %s -Wno-openmp-mapping | FileCheck %s --check-prefix CHECK --check-prefix OMP50
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-mapping | FileCheck %s --check-prefix CHECK --check-prefix OMP50
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
void foo() {}
struct S {
S(): a(0) {}
S(int v) : a(v) {}
int a;
typedef int type;
};
template <typename T>
class S7 : public T {
protected:
T a;
S7() : a(0) {}
public:
S7(typename T::type v) : a(v) {
#pragma omp target
#pragma omp teams distribute parallel for simd private(a) private(this->a) private(T::a)
for (int k = 0; k < a.a; ++k)
++this->a.a;
}
S7 &operator=(S7 &s) {
int k;
#pragma omp target
#pragma omp teams distribute parallel for simd private(a) private(this->a) linear(k)
for (k = 0; k < s.a.a; ++k)
++s.a.a;
foo();
bar();
return *this;
}
void foo() {
int b, argv, d, c, e, f;
#pragma omp target
#pragma omp teams distribute parallel for simd default(none), private(b) firstprivate(argv) shared(d) reduction(+:c) reduction(max:e) num_teams(f) thread_limit(d)
for (int k = 0; k < a.a; ++k)
++a.a;
}
void bar() {
int arr[10];
const int alen = 16;
const int slen1 = 8;
const int slen2 = 8;
#pragma omp target
#pragma omp teams distribute parallel for simd simdlen(slen1) safelen(slen2) aligned(arr:alen)
for (int k = 0; k < a.a; ++k)
++a.a;
}
};
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd private(this->a) private(this->a) private(T::a)
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd private(this->a) private(this->a) linear(k)
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd default(none) private(b) firstprivate(argv) shared(d) reduction(+: c) reduction(max: e) num_teams(f) thread_limit(d)
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd simdlen(slen1) safelen(slen2) aligned(arr: alen)
class S8 : public S7<S> {
S8() {}
public:
S8(int v) : S7<S>(v){
#pragma omp target
#pragma omp teams distribute parallel for simd private(a) private(this->a) private(S7<S>::a)
for (int k = 0; k < a.a; ++k)
++this->a.a;
}
S8 &operator=(S8 &s) {
#pragma omp target
#pragma omp teams distribute parallel for simd private(a) private(this->a)
for (int k = 0; k < s.a.a; ++k)
++s.a.a;
foo();
bar();
return *this;
}
void bar() {
int b, argv, d, c, e, f8;
#pragma omp target
#pragma omp teams distribute parallel for simd default(none), private(b) firstprivate(argv) shared(d) reduction(+:c) reduction(max:e) num_teams(f8) thread_limit(d)
for (int k = 0; k < a.a; ++k)
++a.a;
}
void foo() {
const int alen = 16;
const int slen1 = 8;
const int slen2 = 8;
int arr[10];
#pragma omp target
#pragma omp teams distribute parallel for simd simdlen(slen1) safelen(slen2) aligned(arr:alen)
for (int k = 0; k < a.a; ++k)
++a.a;
}
};
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd private(this->a) private(this->a) private(this->S::a)
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd private(this->a) private(this->a) private(this->S7<S>::a)
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd private(this->a) private(this->a)
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd default(none) private(b) firstprivate(argv) shared(d) reduction(+: c) reduction(max: e) num_teams(f8) thread_limit(d)
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd simdlen(slen1) safelen(slen2) aligned(arr: alen)
template <class T, int N>
T tmain(T argc) {
T b = argc, c, d, e, f, g;
static T a;
// CHECK: static T a;
const T clen = 5;
const T alen = 16;
int arr[10];
#pragma omp target
#pragma omp teams distribute parallel for simd
for (int i=0; i < 2; ++i)
a = 2;
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd{{$}}
// CHECK-NEXT: for (int i = 0; i < 2; ++i)
// CHECK-NEXT: a = 2;
#pragma omp target
#pragma omp teams distribute parallel for simd allocate(b) private(argc, b), firstprivate(c, d), collapse(2) allocate(d)
for (int i = 0; i < 10; ++i)
for (int j = 0; j < 10; ++j)
foo();
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd allocate(b) private(argc,b) firstprivate(c,d) collapse(2) allocate(d)
// CHECK-NEXT: for (int i = 0; i < 10; ++i)
// CHECK-NEXT: for (int j = 0; j < 10; ++j)
// CHECK-NEXT: foo();
for (int i = 0; i < 10; ++i)
foo();
// CHECK: for (int i = 0; i < 10; ++i)
// CHECK-NEXT: foo();
#pragma omp target
#ifdef OMP5
#pragma omp teams distribute parallel for simd if(simd:argc) nontemporal(argc, c, d) order(concurrent)
#else
#pragma omp teams distribute parallel for simd
#endif // OMP5
for (int i = 0; i < 10; ++i)
foo();
// CHECK: #pragma omp target
// OMP45-NEXT: #pragma omp teams distribute parallel for simd
// OMP50-NEXT: #pragma omp teams distribute parallel for simd if(simd: argc) nontemporal(argc,c,d) order(concurrent)
// CHECK-NEXT: for (int i = 0; i < 10; ++i)
// CHECK-NEXT: foo();
#pragma omp target
#pragma omp teams distribute parallel for simd default(none), private(b) firstprivate(argc) shared(d) reduction(+:c) reduction(max:e) num_teams(f) thread_limit(d)
for (int k = 0; k < 10; ++k)
e += d + argc;
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd default(none) private(b) firstprivate(argc) shared(d) reduction(+: c) reduction(max: e) num_teams(f) thread_limit(d)
// CHECK-NEXT: for (int k = 0; k < 10; ++k)
// CHECK-NEXT: e += d + argc;
#pragma omp target
#pragma omp teams distribute parallel for simd simdlen(clen-1)
for (int k = 0; k < 10; ++k)
e += d + argc;
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd simdlen(clen - 1)
// CHECK-NEXT: for (int k = 0; k < 10; ++k)
// CHECK-NEXT: e += d + argc;
#pragma omp target
#pragma omp teams distribute parallel for simd safelen(clen-1) aligned(arr:alen)
for (int k = 0; k < 10; ++k)
e += d + argc + arr[k];
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd safelen(clen - 1) aligned(arr: alen)
// CHECK-NEXT: for (int k = 0; k < 10; ++k)
// CHECK-NEXT: e += d + argc + arr[k];
return T();
}
int main (int argc, char **argv) {
int b = argc, c, d, e, f, g;
static int a;
// CHECK: static int a;
const int clen = 5;
const int N = 10;
int arr[10];
#pragma omp target
#pragma omp teams distribute parallel for simd
for (int i=0; i < 2; ++i)
a = 2;
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd
// CHECK-NEXT: for (int i = 0; i < 2; ++i)
// CHECK-NEXT: a = 2;
#pragma omp target
#pragma omp teams distribute parallel for simd private(argc,b),firstprivate(argv, c), collapse(2)
for (int i = 0; i < 10; ++i)
for (int j = 0; j < 10; ++j)
foo();
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd private(argc,b) firstprivate(argv,c) collapse(2)
// CHECK-NEXT: for (int i = 0; i < 10; ++i)
// CHECK-NEXT: for (int j = 0; j < 10; ++j)
// CHECK-NEXT: foo();
for (int i = 0; i < 10; ++i)
foo();
// CHECK: for (int i = 0; i < 10; ++i)
// CHECK-NEXT: foo();
#pragma omp target
#pragma omp teams distribute parallel for simd
for (int i = 0; i < 10; ++i)foo();
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd
// CHECK-NEXT: for (int i = 0; i < 10; ++i)
// CHECK-NEXT: foo();
#pragma omp target
#pragma omp teams distribute parallel for simd default(none), private(b) firstprivate(argc) shared(d) reduction(+:c) reduction(max:e) num_teams(f) thread_limit(d)
for (int k = 0; k < 10; ++k)
e += d + argc;
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd default(none) private(b) firstprivate(argc) shared(d) reduction(+: c) reduction(max: e) num_teams(f) thread_limit(d)
// CHECK-NEXT: for (int k = 0; k < 10; ++k)
// CHECK-NEXT: e += d + argc;
#pragma omp target
#pragma omp teams distribute parallel for simd simdlen(clen-1)
for (int k = 0; k < 10; ++k)
e += d + argc;
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd simdlen(clen - 1)
// CHECK-NEXT: for (int k = 0; k < 10; ++k)
// CHECK-NEXT: e += d + argc;
#pragma omp target
#pragma omp teams distribute parallel for simd safelen(clen-1) aligned(arr:N+6)
for (int k = 0; k < 10; ++k)
e += d + argc + arr[k];
// CHECK: #pragma omp target
// CHECK-NEXT: #pragma omp teams distribute parallel for simd safelen(clen - 1) aligned(arr: N + 6)
// CHECK-NEXT: for (int k = 0; k < 10; ++k)
// CHECK-NEXT: e += d + argc + arr[k];
return (0);
}
#endif
|
