blob: 91c6de1b85d34ebbfcd04b148207b9c45670c4db (
plain)
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
|
// Test target codegen - host bc file has to be created first.
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
// Check that the execution mode of all 3 target regions on the gpu is set to SPMD Mode.
// CHECK-DAG: {{@__omp_offloading_.+l22}}_exec_mode = weak constant i8 0
// CHECK-DAG: {{@__omp_offloading_.+l26}}_exec_mode = weak constant i8 0
// CHECK-DAG: {{@__omp_offloading_.+l31}}_exec_mode = weak constant i8 0
template<typename tx>
tx ftemplate(int n) {
tx a = 0;
short aa = 0;
tx b[10];
#pragma omp target parallel proc_bind(master)
{
}
#pragma omp target parallel proc_bind(spread)
{
aa += 1;
}
#pragma omp target parallel proc_bind(close)
{
a += 1;
aa += 1;
b[2] += 1;
}
return a;
}
int bar(int n){
int a = 0;
a += ftemplate<int>(n);
return a;
}
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l22}}(
// CHECK: call void @__kmpc_spmd_kernel_init(
// CHECK: br label {{%?}}[[EXEC:.+]]
//
// CHECK: [[EXEC]]
// CHECK-NOT: call void @__kmpc_push_proc_bind
// CHECK: {{call|invoke}} void [[OP1:@.+]](i32* null, i32* null
// CHECK: br label {{%?}}[[DONE:.+]]
//
// CHECK: [[DONE]]
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: br label {{%?}}[[EXIT:.+]]
//
// CHECK: [[EXIT]]
// CHECK: ret void
// CHECK: }
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l26}}(
// CHECK: call void @__kmpc_spmd_kernel_init(
// CHECK: br label {{%?}}[[EXEC:.+]]
//
// CHECK: [[EXEC]]
// CHECK-NOT: call void @__kmpc_push_proc_bind
// CHECK: {{call|invoke}} void [[OP1:@.+]](i32* null, i32* null
// CHECK: br label {{%?}}[[DONE:.+]]
//
// CHECK: [[DONE]]
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: br label {{%?}}[[EXIT:.+]]
//
// CHECK: [[EXIT]]
// CHECK: ret void
// CHECK: }
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l31}}(
// CHECK: call void @__kmpc_spmd_kernel_init(
// CHECK: br label {{%?}}[[EXEC:.+]]
//
// CHECK: [[EXEC]]
// CHECK-NOT: call void @__kmpc_push_proc_bind
// CHECK: {{call|invoke}} void [[OP1:@.+]](i32* null, i32* null
// CHECK: br label {{%?}}[[DONE:.+]]
//
// CHECK: [[DONE]]
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: br label {{%?}}[[EXIT:.+]]
//
// CHECK: [[EXIT]]
// CHECK: ret void
// CHECK: }
#endif
|
