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
|
// Test target codegen - host bc file has to be created first.
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -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 -fopenmp-cuda-mode -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 -fopenmp-cuda-mode -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 -fopenmp-cuda-mode -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 -fopenmp-cuda-mode -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 4 target regions on the gpu is set to SPMD Mode.
// CHECK-DAG: {{@__omp_offloading_.+l30}}_exec_mode = weak constant i8 0
// CHECK-DAG: {{@__omp_offloading_.+l36}}_exec_mode = weak constant i8 0
// CHECK-DAG: {{@__omp_offloading_.+l41}}_exec_mode = weak constant i8 0
// CHECK-DAG: {{@__omp_offloading_.+l46}}_exec_mode = weak constant i8 0
#define N 1000
#define M 10
template<typename tx>
tx ftemplate(int n) {
tx a[N];
short aa[N];
tx b[10];
tx c[M][M];
tx f = n;
tx l;
int k;
#pragma omp target teams distribute parallel for simd lastprivate(l) dist_schedule(static,128) schedule(static,32)
for(int i = 0; i < n; i++) {
a[i] = 1;
l = i;
}
#pragma omp target teams distribute parallel for simd map(tofrom: aa) num_teams(M) thread_limit(64)
for(int i = 0; i < n; i++) {
aa[i] += 1;
}
#pragma omp target teams distribute parallel for simd map(tofrom:a, aa, b) if(target: n>40) proc_bind(spread)
for(int i = 0; i < 10; i++) {
b[i] += 1;
}
#pragma omp target teams distribute parallel for simd collapse(2) firstprivate(f) private(k)
for(int i = 0; i < M; i++) {
for(int j = 0; j < M; j++) {
k = M;
c[i][j] = i+j*f+k;
}
}
return a[0];
}
int bar(int n){
int a = 0;
a += ftemplate<int>(n);
return a;
}
// CHECK-DAG: [[MEM_TY:%.+]] = type { [128 x i8] }
// CHECK-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
// CHECK-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
// CHECK-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
// CHECK-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}_l30(
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]], i16 0, i16 0)
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
// CHECK: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
// CHECK: call void @__kmpc_get_team_static_memory(i16 1, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
// CHECK: [[TEAM_ALLOC:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
// CHECK: [[PTR:%.+]] = getelementptr inbounds i8, i8* [[TEAM_ALLOC]], i{{64|32}} 0
// CHECK: [[BC:%.+]] = bitcast i8* [[PTR]] to [[REC:%.+]]*
// CHECK: getelementptr inbounds [[REC]], [[REC]]* [[BC]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
// CHECK: {{call|invoke}} void [[OUTL1:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
// CHECK: call void @__kmpc_restore_team_static_memory(i16 1, i16 [[SHARED]])
// CHECK: ret void
// CHECK: define internal void [[OUTL1]](
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]], i16 0, i16 0)
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
// CHECK: {{call|invoke}} void [[OUTL2:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define internal void [[OUTL2]](
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]], i16 0, i16 0)
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
// CHECK: {{call|invoke}} void [[OUTL3:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define internal void [[OUTL3]](
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define {{.*}}void {{@__omp_offloading_.+}}({{.+}}, i{{32|64}} [[F_IN:%.+]])
// CHECK: store {{.+}} [[F_IN]], {{.+}}* {{.+}},
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]], i16 0, i16 0)
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: store {{.+}} 99, {{.+}}* [[COMB_UB:%.+]], align
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91, {{.+}}, {{.+}}, {{.+}}* [[COMB_UB]],
// CHECK: {{call|invoke}} void [[OUTL4:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define internal void [[OUTL4]](
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
#endif
|
