nvptx_target_teams_codegen.cpp
10.9 KB
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
// Test target codegen - host bc file has to be created first.
// RUN: %clang_cc1 -verify -fopenmp -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 -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 -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 -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 -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 2 target regions is set to Generic Mode.
// CHECK-DAG: {{@__omp_offloading_.+l27}}_exec_mode = weak constant i8 1
// CHECK-DAG: {{@__omp_offloading_.+l32}}_exec_mode = weak constant i8 1
// CHECK-DAG: {{@__omp_offloading_.+l37}}_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 teams if(0)
{
b[2] += 1;
}
#pragma omp target teams if(1)
{
a = '1';
}
#pragma omp target teams if(n>40)
{
aa = 1;
}
#pragma omp target teams
{
#pragma omp parallel
#pragma omp parallel
aa = 1;
}
return a;
}
int bar(int n){
int a = 0;
a += ftemplate<char>(n);
return a;
}
// CHECK-NOT: define {{.*}}void {{@__omp_offloading_.+template.+l22}}_worker()
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l27}}_worker()
// CHECK-DAG: [[OMP_EXEC_STATUS:%.+]] = alloca i8,
// CHECK-DAG: [[OMP_WORK_FN:%.+]] = alloca i8*,
// CHECK: store i8* null, i8** [[OMP_WORK_FN]],
// CHECK: store i8 0, i8* [[OMP_EXEC_STATUS]],
// CHECK: br label {{%?}}[[AWAIT_WORK:.+]]
//
// CHECK: [[AWAIT_WORK]]
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]], i16 1)
// CHECK: [[KPRB:%.+]] = zext i1 [[KPR]] to i8
// store i8 [[KPRB]], i8* [[OMP_EXEC_STATUS]], align 1
// CHECK: [[WORK:%.+]] = load i8*, i8** [[OMP_WORK_FN]],
// CHECK: [[SHOULD_EXIT:%.+]] = icmp eq i8* [[WORK]], null
// CHECK: br i1 [[SHOULD_EXIT]], label {{%?}}[[EXIT:.+]], label {{%?}}[[SEL_WORKERS:.+]]
//
// CHECK: [[SEL_WORKERS]]
// CHECK: [[ST:%.+]] = load i8, i8* [[OMP_EXEC_STATUS]]
// CHECK: [[IS_ACTIVE:%.+]] = icmp ne i8 [[ST]], 0
// CHECK: br i1 [[IS_ACTIVE]], label {{%?}}[[EXEC_PARALLEL:.+]], label {{%?}}[[BAR_PARALLEL:.+]]
//
// CHECK: [[EXEC_PARALLEL]]
// CHECK: br label {{%?}}[[TERM_PARALLEL:.+]]
//
// CHECK: [[TERM_PARALLEL]]
// CHECK: call void @__kmpc_kernel_end_parallel()
// CHECK: br label {{%?}}[[BAR_PARALLEL]]
//
// CHECK: [[BAR_PARALLEL]]
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: br label {{%?}}[[AWAIT_WORK]]
//
// CHECK: [[EXIT]]
// CHECK: ret void
// CHECK: define {{.*}}void [[T1:@__omp_offloading_.+template.+l27]](i[[SZ:32|64]] [[A:%[^)]+]])
// CHECK: store i[[SZ]] [[A]], i[[SZ]]* [[A_ADDR:%.+]], align
// CHECK: [[CONV:%.+]] = bitcast i[[SZ]]* [[A_ADDR]] to i8*
// CHECK-DAG: [[TID:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK-DAG: [[NTH:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK-DAG: [[WS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK-DAG: [[TH_LIMIT:%.+]] = sub nuw i32 [[NTH]], [[WS]]
// CHECK: [[IS_WORKER:%.+]] = icmp ult i32 [[TID]], [[TH_LIMIT]]
// CHECK: br i1 [[IS_WORKER]], label {{%?}}[[WORKER:.+]], label {{%?}}[[CHECK_MASTER:.+]]
//
// CHECK: [[WORKER]]
// CHECK: {{call|invoke}} void [[T1]]_worker()
// CHECK: br label {{%?}}[[EXIT:.+]]
//
// CHECK: [[CHECK_MASTER]]
// CHECK-DAG: [[CMTID:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK-DAG: [[CMNTH:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK-DAG: [[CMWS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK: [[IS_MASTER:%.+]] = icmp eq i32 [[CMTID]],
// CHECK: br i1 [[IS_MASTER]], label {{%?}}[[MASTER:.+]], label {{%?}}[[EXIT]]
//
// CHECK: [[MASTER]]
// CHECK-DAG: [[MNTH:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK-DAG: [[MWS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK: [[MTMP1:%.+]] = sub nuw i32 [[MNTH]], [[MWS]]
// CHECK: call void @__kmpc_kernel_init(i32 [[MTMP1]]
//
// CHECK-NOT: kmpc_fork_teams
// CHECK: [[A_VAL:%.+]] = load i8, i8* [[CONV]], align
// CHECK: [[ACP:%.+]] = bitcast i[[SZ]]* [[AC:%.+]] to i8*
// CHECK: store i8 [[A_VAL]], i8* [[ACP]], align
// CHECK: [[ACV:%.+]] = load i[[SZ]], i[[SZ]]* [[AC]], align
// CHECK: call void [[PARALLEL:@.+]](i32* %{{.+}}, i32* %{{.+}}, i[[SZ]] [[ACV]])
// CHECK: br label {{%?}}[[TERMINATE:.+]]
//
// CHECK: [[TERMINATE]]
// CHECK: call void @__kmpc_kernel_deinit(
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: br label {{%?}}[[EXIT]]
//
// CHECK: [[EXIT]]
// CHECK: ret void
// CHECK: define internal void [[PARALLEL]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i[[SZ]] [[A_VAL:%.+]])
// CHECK: [[A_ADDR:%.+]] = alloca i[[SZ]],
// CHECK: store i[[SZ]] [[A_VAL]], i[[SZ]]* [[A_ADDR]],
// CHECK: [[CONV:%.+]] = bitcast i[[SZ]]* [[A_ADDR]] to i8*
// CHECK: store i8 49, i8* [[CONV]],
// CHECK: ret void
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l32}}_worker()
// CHECK-DAG: [[OMP_EXEC_STATUS:%.+]] = alloca i8,
// CHECK-DAG: [[OMP_WORK_FN:%.+]] = alloca i8*,
// CHECK: store i8* null, i8** [[OMP_WORK_FN]],
// CHECK: store i8 0, i8* [[OMP_EXEC_STATUS]],
// CHECK: br label {{%?}}[[AWAIT_WORK:.+]]
//
// CHECK: [[AWAIT_WORK]]
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]], i16 1)
// CHECK: [[KPRB:%.+]] = zext i1 [[KPR]] to i8
// store i8 [[KPRB]], i8* [[OMP_EXEC_STATUS]], align 1
// CHECK: [[WORK:%.+]] = load i8*, i8** [[OMP_WORK_FN]],
// CHECK: [[SHOULD_EXIT:%.+]] = icmp eq i8* [[WORK]], null
// CHECK: br i1 [[SHOULD_EXIT]], label {{%?}}[[EXIT:.+]], label {{%?}}[[SEL_WORKERS:.+]]
//
// CHECK: [[SEL_WORKERS]]
// CHECK: [[ST:%.+]] = load i8, i8* [[OMP_EXEC_STATUS]]
// CHECK: [[IS_ACTIVE:%.+]] = icmp ne i8 [[ST]], 0
// CHECK: br i1 [[IS_ACTIVE]], label {{%?}}[[EXEC_PARALLEL:.+]], label {{%?}}[[BAR_PARALLEL:.+]]
//
// CHECK: [[EXEC_PARALLEL]]
// CHECK: br label {{%?}}[[TERM_PARALLEL:.+]]
//
// CHECK: [[TERM_PARALLEL]]
// CHECK: call void @__kmpc_kernel_end_parallel()
// CHECK: br label {{%?}}[[BAR_PARALLEL]]
//
// CHECK: [[BAR_PARALLEL]]
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: br label {{%?}}[[AWAIT_WORK]]
//
// CHECK: [[EXIT]]
// CHECK: ret void
// CHECK: define {{.*}}void [[T2:@__omp_offloading_.+template.+l32]](i[[SZ:32|64]] [[AA:%[^)]+]])
// CHECK: store i[[SZ]] [[AA]], i[[SZ]]* [[AA_ADDR:%.+]], align
// CHECK: [[CONV:%.+]] = bitcast i[[SZ]]* [[AA_ADDR]] to i16*
// CHECK-DAG: [[TID:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK-DAG: [[NTH:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK-DAG: [[WS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK-DAG: [[TH_LIMIT:%.+]] = sub nuw i32 [[NTH]], [[WS]]
// CHECK: [[IS_WORKER:%.+]] = icmp ult i32 [[TID]], [[TH_LIMIT]]
// CHECK: br i1 [[IS_WORKER]], label {{%?}}[[WORKER:.+]], label {{%?}}[[CHECK_MASTER:.+]]
//
// CHECK: [[WORKER]]
// CHECK: {{call|invoke}} void [[T2]]_worker()
// CHECK: br label {{%?}}[[EXIT:.+]]
//
// CHECK: [[CHECK_MASTER]]
// CHECK-DAG: [[CMTID:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK-DAG: [[CMNTH:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK-DAG: [[CMWS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK: [[IS_MASTER:%.+]] = icmp eq i32 [[CMTID]],
// CHECK: br i1 [[IS_MASTER]], label {{%?}}[[MASTER:.+]], label {{%?}}[[EXIT]]
//
// CHECK: [[MASTER]]
// CHECK-DAG: [[MNTH:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK-DAG: [[MWS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK: [[MTMP1:%.+]] = sub nuw i32 [[MNTH]], [[MWS]]
// CHECK: call void @__kmpc_kernel_init(i32 [[MTMP1]]
//
// CHECK-NOT: kmpc_fork_teams
// CHECK: [[AA_VAL:%.+]] = load i16, i16* [[CONV]], align
// CHECK: [[ACP:%.+]] = bitcast i[[SZ]]* [[AC:%.+]] to i16*
// CHECK: store i16 [[AA_VAL]], i16* [[ACP]], align
// CHECK: [[ACV:%.+]] = load i[[SZ]], i[[SZ]]* [[AC]], align
// CHECK: call void [[PARALLEL:@.+]](i32* %{{.+}}, i32* %{{.+}}, i[[SZ]] [[ACV]])
// CHECK: br label {{%?}}[[TERMINATE:.+]]
//
// CHECK: [[TERMINATE]]
// CHECK: call void @__kmpc_kernel_deinit(
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: br label {{%?}}[[EXIT]]
//
// CHECK: [[EXIT]]
// CHECK: ret void
// CHECK: define internal void [[PARALLEL]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i[[SZ]] [[A_VAL:%.+]])
// CHECK: [[A_ADDR:%.+]] = alloca i[[SZ]],
// CHECK: store i[[SZ]] [[A_VAL]], i[[SZ]]* [[A_ADDR]],
// CHECK: [[CONV:%.+]] = bitcast i[[SZ]]* [[A_ADDR]] to i16*
// CHECK: store i16 1, i16* [[CONV]],
// CHECK: ret void
// CHECK: define weak void @__omp_offloading_{{.*}}ftemplate{{.*}}_l37(
// CHECK: call void @__kmpc_spmd_kernel_init(i32 {{.+}}, i16 1, i16 0)
// CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK-NOT: call i8* @__kmpc_data_sharing_push_stack(
// CHECK-NOT: call void @__kmpc_serialized_parallel(
// CHECK: call void [[L0:@.+]](i32* %{{.+}}, i32* %{{.+}}, i[[SZ]] %{{.+}})
// CHECK-NOT: call void @__kmpc_end_serialized_parallel(
// CHECK-NOT: call void @__kmpc_data_sharing_pop_stack(
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK: ret
// CHECK: define internal void [[L0]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i[[SZ]] %{{.+}})
// CHECK: call void [[L1:@.+]](i32* %{{.+}}, i32* %{{.+}}, i16* %{{.+}})
// CHECK: ret void
// CHECK: define internal void [[L1]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i16* dereferenceable
// CHECK: call void @__kmpc_serialized_parallel(
// CHECK: call void [[L2:@.+]](i32* %{{.+}}, i32* %{{.+}}, i16* %{{.+}})
// CHECK: call void @__kmpc_end_serialized_parallel(
// CHECK: ret void
// CHECK: define internal void [[L2]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i16* dereferenceable
// CHECK: store i16 1, i16* %
// CHECK: ret void
#endif