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
|
// RUN: %clang_cc1 -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 \
// RUN: -fsyntax-only -verify %s
// RUN: %clang_cc1 -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 \
// RUN: -ast-print %s | FileCheck %s
// RUN: %clang_cc1 -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 \
// RUN: -emit-pch -o %t %s
// RUN: %clang_cc1 -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 \
// RUN: -include-pch %t -ast-print %s | FileCheck %s
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
typedef void **omp_allocator_handle_t;
extern const omp_allocator_handle_t omp_null_allocator;
extern const omp_allocator_handle_t omp_default_mem_alloc;
extern const omp_allocator_handle_t omp_large_cap_mem_alloc;
extern const omp_allocator_handle_t omp_const_mem_alloc;
extern const omp_allocator_handle_t omp_high_bw_mem_alloc;
extern const omp_allocator_handle_t omp_low_lat_mem_alloc;
extern const omp_allocator_handle_t omp_cgroup_mem_alloc;
extern const omp_allocator_handle_t omp_pteam_mem_alloc;
extern const omp_allocator_handle_t omp_thread_mem_alloc;
//CHECK: template <typename T, int C> void templ_foo(T t) {
//CHECK: T j, z;
//CHECK: #pragma omp parallel loop collapse(C) reduction(+: z) lastprivate(j) bind(thread)
//CHECK: for (T i = 0; i < t; ++i)
//CHECK: for (j = 0; j < t; ++j)
//CHECK: z += i + j;
//CHECK: }
//CHECK: template<> void templ_foo<int, 2>(int t) {
//CHECK: int j, z;
//CHECK: #pragma omp parallel loop collapse(2) reduction(+: z) lastprivate(j) bind(thread)
//CHECK: for (int i = 0; i < t; ++i)
//CHECK: for (j = 0; j < t; ++j)
//CHECK: z += i + j;
//CHECK: }
template <typename T, int C>
void templ_foo(T t) {
T j,z;
#pragma omp parallel loop collapse(C) reduction(+:z) lastprivate(j) bind(thread)
for (T i = 0; i<t; ++i)
for (j = 0; j<t; ++j)
z += i+j;
}
//CHECK: void test() {
void test() {
constexpr int N = 100;
float MTX[N][N];
int aaa[1000];
//CHECK: #pragma omp target teams distribute parallel for map(tofrom: MTX)
//CHECK: #pragma omp parallel loop
#pragma omp target teams distribute parallel for map(MTX)
for (auto i = 0; i < N; ++i) {
#pragma omp parallel loop
for (auto j = 0; j < N; ++j) {
MTX[i][j] = 0;
}
}
//CHECK: #pragma omp target teams
//CHECK: #pragma omp parallel loop
#pragma omp target teams
for (int i=0; i<1000; ++i) {
#pragma omp parallel loop
for (int j=0; j<100; j++) {
aaa[i] += i + j;
}
}
int j, z, z1, z2 = 1, z3 = 2;
//CHECK: #pragma omp parallel loop collapse(2) private(z) lastprivate(j) order(concurrent) firstprivate(z2) num_threads(4) if(1) allocate(omp_default_mem_alloc: z2) shared(z3) reduction(+: z1) bind(parallel) proc_bind(primary)
#pragma omp parallel loop collapse(2) private(z) lastprivate(j) \
order(concurrent) firstprivate(z2) num_threads(4) if(1) \
allocate(omp_default_mem_alloc:z2) shared(z3) \
reduction(+:z1) bind(parallel) proc_bind(primary)
for (auto i = 0; i < N; ++i) {
for (j = 0; j < N; ++j) {
z = i+j;
MTX[i][j] = z;
z1 += z;
}
}
//CHECK: #pragma omp target teams
//CHECK: #pragma omp parallel loop bind(teams)
#pragma omp target teams
#pragma omp parallel loop bind(teams)
for (auto i = 0; i < N; ++i) { }
//CHECK: #pragma omp target
//CHECK: #pragma omp teams
//CHECK: #pragma omp parallel loop bind(teams)
#pragma omp target
#pragma omp teams
#pragma omp parallel loop bind(teams)
for (auto i = 0; i < N; ++i) { }
}
//CHECK: void nobindingfunc() {
void nobindingfunc()
{
//CHECK: #pragma omp parallel loop
#pragma omp parallel loop
for (int i=0; i<10; ++i) { }
}
void bar()
{
templ_foo<int,2>(8);
}
#endif // HEADER
|
