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
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
// Test target codegen - host bc file has to be created first.
// RUN: %clang_cc1 -no-opaque-pointers -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 -no-opaque-pointers -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 - -disable-llvm-optzns | FileCheck %s --check-prefix=CHECK
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
template<typename tx>
tx ftemplate(int n) {
tx b[10];
#pragma omp target
{
tx d = n;
#pragma omp parallel for
for(int i=0; i<10; i++) {
b[i] += d;
}
b[3] += 1;
}
return b[3];
}
int bar(int n){
int a = 0;
a += ftemplate<int>(n);
return a;
}
#endif
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l13
// CHECK-SAME: (i64 noundef [[N:%.*]], [10 x i32]* noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[N_ADDR:%.*]] = alloca i64, align 8
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 8
// CHECK-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [2 x i8*], align 8
// CHECK-NEXT: store i64 [[N]], i64* [[N_ADDR]], align 8
// CHECK-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 8
// CHECK-NEXT: [[CONV:%.*]] = bitcast i64* [[N_ADDR]] to i32*
// CHECK-NEXT: [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1:[0-9]+]], i8 1, i1 true, i1 true)
// CHECK-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP1]], -1
// CHECK-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
// CHECK: user_code.entry:
// CHECK-NEXT: [[D:%.*]] = call align 8 i8* @__kmpc_alloc_shared(i64 4)
// CHECK-NEXT: [[D_ON_STACK:%.*]] = bitcast i8* [[D]] to i32*
// CHECK-NEXT: [[TMP2:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]])
// CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* [[CONV]], align 4
// CHECK-NEXT: store i32 [[TMP3]], i32* [[D_ON_STACK]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
// CHECK-NEXT: [[TMP5:%.*]] = bitcast [10 x i32]* [[TMP0]] to i8*
// CHECK-NEXT: store i8* [[TMP5]], i8** [[TMP4]], align 8
// CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 1
// CHECK-NEXT: [[TMP7:%.*]] = bitcast i32* [[D_ON_STACK]] to i8*
// CHECK-NEXT: store i8* [[TMP7]], i8** [[TMP6]], align 8
// CHECK-NEXT: [[TMP8:%.*]] = bitcast [2 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP2]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, [10 x i32]*, i32*)* @__omp_outlined__ to i8*), i8* bitcast (void (i16, i32)* @__omp_outlined___wrapper to i8*), i8** [[TMP8]], i64 2)
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP0]], i64 0, i64 3
// CHECK-NEXT: [[TMP9:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP9]], 1
// CHECK-NEXT: store i32 [[ADD]], i32* [[ARRAYIDX]], align 4
// CHECK-NEXT: call void @__kmpc_free_shared(i8* [[D]], i64 4)
// CHECK-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i8 1, i1 true)
// CHECK-NEXT: ret void
// CHECK: worker.exit:
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@__omp_outlined__
// CHECK-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], [10 x i32]* noundef nonnull align 4 dereferenceable(40) [[B:%.*]], i32* noundef nonnull align 4 dereferenceable(4) [[D:%.*]]) #[[ATTR2:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 8
// CHECK-NEXT: [[D_ADDR:%.*]] = alloca i32*, align 8
// CHECK-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[TMP:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 8
// CHECK-NEXT: store i32* [[D]], i32** [[D_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load i32*, i32** [[D_ADDR]], align 8
// CHECK-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
// CHECK-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
// CHECK-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
// CHECK-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
// CHECK-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP3]], i32 33, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK-NEXT: br label [[OMP_DISPATCH_COND:%.*]]
// CHECK: omp.dispatch.cond:
// CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP4]], 9
// CHECK-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK: cond.true:
// CHECK-NEXT: br label [[COND_END:%.*]]
// CHECK: cond.false:
// CHECK-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK-NEXT: br label [[COND_END]]
// CHECK: cond.end:
// CHECK-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP5]], [[COND_FALSE]] ]
// CHECK-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
// CHECK-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK-NEXT: store i32 [[TMP6]], i32* [[DOTOMP_IV]], align 4
// CHECK-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK-NEXT: [[CMP1:%.*]] = icmp sle i32 [[TMP7]], [[TMP8]]
// CHECK-NEXT: br i1 [[CMP1]], label [[OMP_DISPATCH_BODY:%.*]], label [[OMP_DISPATCH_END:%.*]]
// CHECK: omp.dispatch.body:
// CHECK-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK: omp.inner.for.cond:
// CHECK-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK-NEXT: [[CMP2:%.*]] = icmp sle i32 [[TMP9]], [[TMP10]]
// CHECK-NEXT: br i1 [[CMP2]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
// CHECK: omp.inner.for.body:
// CHECK-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP11]], 1
// CHECK-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK-NEXT: store i32 [[ADD]], i32* [[I]], align 4
// CHECK-NEXT: [[TMP12:%.*]] = load i32, i32* [[TMP1]], align 4
// CHECK-NEXT: [[TMP13:%.*]] = load i32, i32* [[I]], align 4
// CHECK-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP13]] to i64
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP0]], i64 0, i64 [[IDXPROM]]
// CHECK-NEXT: [[TMP14:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP14]], [[TMP12]]
// CHECK-NEXT: store i32 [[ADD3]], i32* [[ARRAYIDX]], align 4
// CHECK-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK: omp.body.continue:
// CHECK-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK: omp.inner.for.inc:
// CHECK-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK-NEXT: [[ADD4:%.*]] = add nsw i32 [[TMP15]], 1
// CHECK-NEXT: store i32 [[ADD4]], i32* [[DOTOMP_IV]], align 4
// CHECK-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK: omp.inner.for.end:
// CHECK-NEXT: br label [[OMP_DISPATCH_INC:%.*]]
// CHECK: omp.dispatch.inc:
// CHECK-NEXT: [[TMP16:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_STRIDE]], align 4
// CHECK-NEXT: [[ADD5:%.*]] = add nsw i32 [[TMP16]], [[TMP17]]
// CHECK-NEXT: store i32 [[ADD5]], i32* [[DOTOMP_LB]], align 4
// CHECK-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_STRIDE]], align 4
// CHECK-NEXT: [[ADD6:%.*]] = add nsw i32 [[TMP18]], [[TMP19]]
// CHECK-NEXT: store i32 [[ADD6]], i32* [[DOTOMP_UB]], align 4
// CHECK-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK: omp.dispatch.end:
// CHECK-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB2]], i32 [[TMP3]])
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@__omp_outlined___wrapper
// CHECK-SAME: (i16 noundef zeroext [[TMP0:%.*]], i32 noundef [[TMP1:%.*]]) #[[ATTR4:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
// CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[GLOBAL_ARGS:%.*]] = alloca i8**, align 8
// CHECK-NEXT: store i16 [[TMP0]], i16* [[DOTADDR]], align 2
// CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
// CHECK-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
// CHECK-NEXT: call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
// CHECK-NEXT: [[TMP2:%.*]] = load i8**, i8*** [[GLOBAL_ARGS]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i8*, i8** [[TMP2]], i64 0
// CHECK-NEXT: [[TMP4:%.*]] = bitcast i8** [[TMP3]] to [10 x i32]**
// CHECK-NEXT: [[TMP5:%.*]] = load [10 x i32]*, [10 x i32]** [[TMP4]], align 8
// CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i8*, i8** [[TMP2]], i64 1
// CHECK-NEXT: [[TMP7:%.*]] = bitcast i8** [[TMP6]] to i32**
// CHECK-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP7]], align 8
// CHECK-NEXT: call void @__omp_outlined__(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]], [10 x i32]* [[TMP5]], i32* [[TMP8]]) #[[ATTR3:[0-9]+]]
// CHECK-NEXT: ret void
//
|
