-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathdistribute_parallel_for_simd_ast_print.cpp
158 lines (144 loc) · 5.9 KB
/
distribute_parallel_for_simd_ast_print.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
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -ast-print %s -Wno-openmp-target | FileCheck %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-target | FileCheck %s
// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -ast-print %s -Wno-openmp-target | FileCheck %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-target | FileCheck %s
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
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
#pragma omp 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
#pragma omp distribute parallel for simd private(a) private(this->a) linear(k)
for (k = 0; k < s.a.a; ++k)
++s.a.a;
return *this;
}
};
// CHECK: #pragma omp distribute parallel for simd private(this->a) private(this->a) private(T::a){{$}}
// CHECK: #pragma omp distribute parallel for simd private(this->a) private(this->a) linear(k)
// CHECK: #pragma omp distribute parallel for simd private(this->a) private(this->a) private(this->S::a)
class S8 : public S7<S> {
S8() {}
public:
S8(int v) : S7<S>(v){
#pragma omp target
#pragma omp teams
#pragma omp 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
#pragma omp distribute parallel for simd private(a) private(this->a)
for (int k = 0; k < s.a.a; ++k)
++s.a.a;
return *this;
}
};
// CHECK: #pragma omp distribute parallel for simd private(this->a) private(this->a) private(this->S7<S>::a)
// CHECK: #pragma omp distribute parallel for simd private(this->a) private(this->a)
template <class T, int N>
T tmain(T argc) {
T b = argc, c, d, e, f, h;
static T a;
// CHECK: static T a;
static T g;
#pragma omp threadprivate(g)
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for simd dist_schedule(static, a) schedule(dynamic) default(none) copyin(g) firstprivate(a) allocate(a)
// CHECK: #pragma omp distribute parallel for simd dist_schedule(static, a) schedule(dynamic) default(none) copyin(g) firstprivate(a) allocate(a)
for (int i = 0; i < 2; ++i)
a = 2;
// CHECK-NEXT: for (int i = 0; i < 2; ++i)
// CHECK-NEXT: a = 2;
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for simd allocate(argc) private(argc, b), firstprivate(c, d), lastprivate(f) collapse(N) schedule(static, N) if (parallel :argc) num_threads(N) default(shared) shared(e) reduction(+ : h) dist_schedule(static,N)
for (int i = 0; i < 2; ++i)
for (int j = 0; j < 2; ++j)
for (int j = 0; j < 2; ++j)
for (int j = 0; j < 2; ++j)
for (int j = 0; j < 2; ++j)
for (int i = 0; i < 2; ++i)
for (int j = 0; j < 2; ++j)
for (int j = 0; j < 2; ++j)
for (int j = 0; j < 2; ++j)
for (int j = 0; j < 2; ++j)
a++;
// CHECK: #pragma omp distribute parallel for simd allocate(argc) private(argc,b) firstprivate(c,d) lastprivate(f) collapse(N) schedule(static, N) if(parallel: argc) num_threads(N) default(shared) shared(e) reduction(+: h) dist_schedule(static, N)
// CHECK-NEXT: for (int i = 0; i < 2; ++i)
// CHECK-NEXT: for (int j = 0; j < 2; ++j)
// CHECK-NEXT: for (int j = 0; j < 2; ++j)
// CHECK-NEXT: for (int j = 0; j < 2; ++j)
// CHECK-NEXT: for (int j = 0; j < 2; ++j)
// CHECK-NEXT: for (int i = 0; i < 2; ++i)
// CHECK-NEXT: for (int j = 0; j < 2; ++j)
// CHECK-NEXT: for (int j = 0; j < 2; ++j)
// CHECK-NEXT: for (int j = 0; j < 2; ++j)
// CHECK-NEXT: for (int j = 0; j < 2; ++j)
// CHECK-NEXT: a++;
return T();
}
int main(int argc, char **argv) {
int b = argc, c, d, e, f, h;
int x[200];
static int a;
// CHECK: static int a;
static float g;
#pragma omp threadprivate(g)
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for simd schedule(guided, argc) default(none) copyin(g) dist_schedule(static, a) private(a) shared(argc)
// CHECK: #pragma omp distribute parallel for simd schedule(guided, argc) default(none) copyin(g) dist_schedule(static, a) private(a) shared(argc)
for (int i = 0; i < 2; ++i)
a = 2;
// CHECK-NEXT: for (int i = 0; i < 2; ++i)
// CHECK-NEXT: a = 2;
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for simd private(argc, b), firstprivate(argv, c), lastprivate(d, f) collapse(2) schedule(auto) if (argc) num_threads(a) default(shared) shared(e) reduction(+ : h) dist_schedule(static, b)
for (int i = 0; i < 10; ++i)
for (int j = 0; j < 10; ++j)
a++;
// CHECK: #pragma omp distribute parallel for simd private(argc,b) firstprivate(argv,c) lastprivate(d,f) collapse(2) schedule(auto) if(argc) num_threads(a) default(shared) shared(e) reduction(+: h) dist_schedule(static, b)
// CHECK-NEXT: for (int i = 0; i < 10; ++i)
// CHECK-NEXT: for (int j = 0; j < 10; ++j)
// CHECK-NEXT: a++;
int i;
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for simd aligned(x:8) linear(i:2) safelen(8) simdlen(8)
for (i = 0; i < 100; i++)
for (int j = 0; j < 200; j++)
a += h + x[j];
// CHECK: #pragma omp distribute parallel for simd aligned(x: 8) linear(i: 2) safelen(8) simdlen(8)
// CHECK-NEXT: for (i = 0; i < 100; i++)
// CHECK-NEXT: for (int j = 0; j < 200; j++)
// CHECK-NEXT: a += h + x[j];
return (tmain<int, 5>(argc) + tmain<char, 1>(argv[0][0]));
}
#endif