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
|
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -fexceptions -fcxx-exceptions -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// REQUIRES: x86-registered-target
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
// CHECK: [[IDENT_T_TY:%.+]] = type { i32, i32, i32, i32, i8* }
// CHECK: [[IMPLICIT_BARRIER_LOC:@.+]] = private unnamed_addr constant %{{.+}} { i32 0, i32 66, i32 0, i32 0, i8*
// CHECK-LABEL: define {{.*void}} @{{.*}}static_not_chunked{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}})
void static_not_chunked(float *a, float *b, float *c, float *d) {
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]])
#pragma omp for schedule(static) ordered
// CHECK: call void @__kmpc_dispatch_init_4([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 66, i32 0, i32 4571423, i32 1, i32 1)
//
// CHECK: [[HASWORK:%.+]] = call i32 @__kmpc_dispatch_next_4([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32* [[OMP_ISLAST:%[^,]+]], i32* [[OMP_LB:%[^,]+]], i32* [[OMP_UB:%[^,]+]], i32* [[OMP_ST:%[^,]+]])
// CHECK-NEXT: [[O_CMP:%.+]] = icmp ne i32 [[HASWORK]], 0
// CHECK-NEXT: br i1 [[O_CMP]], label %[[O_LOOP1_BODY:[^,]+]], label %[[O_LOOP1_END:[^,]+]]
// Loop header
// CHECK: [[O_LOOP1_BODY]]
// CHECK: [[LB:%.+]] = load i32, i32* [[OMP_LB]]
// CHECK-NEXT: store i32 [[LB]], i32* [[OMP_IV:[^,]+]]
// CHECK: [[IV:%.+]] = load i32, i32* [[OMP_IV]]
// CHECK-NEXT: [[UB:%.+]] = load i32, i32* [[OMP_UB]]
// CHECK-NEXT: [[CMP:%.+]] = icmp sle i32 [[IV]], [[UB]]
// CHECK-NEXT: br i1 [[CMP]], label %[[LOOP1_BODY:[^,]+]], label %[[LOOP1_END:[^,]+]]
for (int i = 32000000; i > 33; i += -7) {
// CHECK: [[LOOP1_BODY]]
// Start of body: calculate i from IV:
// CHECK: [[IV1_1:%.+]] = load i32, i32* [[OMP_IV]]
// CHECK-NEXT: [[CALC_I_1:%.+]] = mul nsw i32 [[IV1_1]], 7
// CHECK-NEXT: [[CALC_I_2:%.+]] = sub nsw i32 32000000, [[CALC_I_1]]
// CHECK-NEXT: store i32 [[CALC_I_2]], i32* [[LC_I:.+]]
// ... start of ordered region ...
// CHECK-NEXT: call void @__kmpc_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK-NEXT: call void @__kmpc_end_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... end of ordered region ...
#pragma omp ordered
a[i] = b[i] * c[i] * d[i];
// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}
// CHECK-NEXT: [[ADD1_2:%.+]] = add nsw i32 [[IV1_2]], 1
// CHECK-NEXT: store i32 [[ADD1_2]], i32* [[OMP_IV]]
// CHECK-NEXT: call void @__kmpc_dispatch_fini_4([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// CHECK-NEXT: br label %{{.+}}
}
// CHECK: [[LOOP1_END]]
// CHECK: [[O_LOOP1_END]]
// CHECK: call {{.+}} @__kmpc_barrier([[IDENT_T_TY]]* [[IMPLICIT_BARRIER_LOC]], i32 [[GTID]])
// CHECK: ret void
}
// CHECK-LABEL: define {{.*void}} @{{.*}}dynamic1{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}})
void dynamic1(float *a, float *b, float *c, float *d) {
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]])
#pragma omp for schedule(dynamic) ordered
// CHECK: call void @__kmpc_dispatch_init_8u([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 67, i64 0, i64 16908287, i64 1, i64 1)
//
// CHECK: [[HASWORK:%.+]] = call i32 @__kmpc_dispatch_next_8u([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32* [[OMP_ISLAST:%[^,]+]], i64* [[OMP_LB:%[^,]+]], i64* [[OMP_UB:%[^,]+]], i64* [[OMP_ST:%[^,]+]])
// CHECK-NEXT: [[O_CMP:%.+]] = icmp ne i32 [[HASWORK]], 0
// CHECK-NEXT: br i1 [[O_CMP]], label %[[O_LOOP1_BODY:[^,]+]], label %[[O_LOOP1_END:[^,]+]]
// Loop header
// CHECK: [[O_LOOP1_BODY]]
// CHECK: [[LB:%.+]] = load i64, i64* [[OMP_LB]]
// CHECK-NEXT: store i64 [[LB]], i64* [[OMP_IV:[^,]+]]
// CHECK: [[IV:%.+]] = load i64, i64* [[OMP_IV]]
// CHECK-NEXT: [[UB:%.+]] = load i64, i64* [[OMP_UB]]
// CHECK-NEXT: [[CMP:%.+]] = icmp ule i64 [[IV]], [[UB]]
// CHECK-NEXT: br i1 [[CMP]], label %[[LOOP1_BODY:[^,]+]], label %[[LOOP1_END:[^,]+]]
for (unsigned long long i = 131071; i < 2147483647; i += 127) {
// CHECK: [[LOOP1_BODY]]
// Start of body: calculate i from IV:
// CHECK: [[IV1_1:%.+]] = load i64, i64* [[OMP_IV]]
// CHECK-NEXT: [[CALC_I_1:%.+]] = mul i64 [[IV1_1]], 127
// CHECK-NEXT: [[CALC_I_2:%.+]] = add i64 131071, [[CALC_I_1]]
// CHECK-NEXT: store i64 [[CALC_I_2]], i64* [[LC_I:.+]]
// ... start of ordered region ...
// CHECK-NEXT: call void @__kmpc_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK-NEXT: call void @__kmpc_end_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... end of ordered region ...
#pragma omp ordered
a[i] = b[i] * c[i] * d[i];
// CHECK: [[IV1_2:%.+]] = load i64, i64* [[OMP_IV]]{{.*}}
// CHECK-NEXT: [[ADD1_2:%.+]] = add i64 [[IV1_2]], 1
// CHECK-NEXT: store i64 [[ADD1_2]], i64* [[OMP_IV]]
// ... end iteration for ordered loop ...
// CHECK-NEXT: call void @__kmpc_dispatch_fini_8u([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// CHECK-NEXT: br label %{{.+}}
}
// CHECK: [[LOOP1_END]]
// CHECK: [[O_LOOP1_END]]
// CHECK: call {{.+}} @__kmpc_barrier([[IDENT_T_TY]]* [[IMPLICIT_BARRIER_LOC]], i32 [[GTID]])
// CHECK: ret void
}
// CHECK-LABEL: define {{.*void}} @{{.*}}test_auto{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}})
void test_auto(float *a, float *b, float *c, float *d) {
unsigned int x = 0;
unsigned int y = 0;
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]])
#pragma omp for schedule(auto) collapse(2) ordered
// CHECK: call void @__kmpc_dispatch_init_8([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 70, i64 0, i64 [[LAST_ITER:%[^,]+]], i64 1, i64 1)
//
// CHECK: [[HASWORK:%.+]] = call i32 @__kmpc_dispatch_next_8([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32* [[OMP_ISLAST:%[^,]+]], i64* [[OMP_LB:%[^,]+]], i64* [[OMP_UB:%[^,]+]], i64* [[OMP_ST:%[^,]+]])
// CHECK-NEXT: [[O_CMP:%.+]] = icmp ne i32 [[HASWORK]], 0
// CHECK-NEXT: br i1 [[O_CMP]], label %[[O_LOOP1_BODY:[^,]+]], label %[[O_LOOP1_END:[^,]+]]
// Loop header
// CHECK: [[O_LOOP1_BODY]]
// CHECK: [[LB:%.+]] = load i64, i64* [[OMP_LB]]
// CHECK-NEXT: store i64 [[LB]], i64* [[OMP_IV:[^,]+]]
// CHECK: [[IV:%.+]] = load i64, i64* [[OMP_IV]]
// CHECK-NEXT: [[UB:%.+]] = load i64, i64* [[OMP_UB]]
// CHECK-NEXT: [[CMP:%.+]] = icmp sle i64 [[IV]], [[UB]]
// CHECK-NEXT: br i1 [[CMP]], label %[[LOOP1_BODY:[^,]+]], label %[[LOOP1_END:[^,]+]]
// FIXME: When the iteration count of some nested loop is not a known constant,
// we should pre-calculate it, like we do for the total number of iterations!
for (char i = static_cast<char>(y); i <= '9'; ++i)
for (x = 11; x > 0; --x) {
// CHECK: [[LOOP1_BODY]]
// Start of body: indices are calculated from IV:
// CHECK: store i8 {{%[^,]+}}, i8* {{%[^,]+}}
// CHECK: store i32 {{%[^,]+}}, i32* {{%[^,]+}}
// ... start of ordered region ...
// CHECK: call void @__kmpc_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK-NEXT: call void @__kmpc_end_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... end of ordered region ...
#pragma omp ordered
a[i] = b[i] * c[i] * d[i];
// CHECK: [[IV1_2:%.+]] = load i64, i64* [[OMP_IV]]{{.*}}
// CHECK-NEXT: [[ADD1_2:%.+]] = add nsw i64 [[IV1_2]], 1
// CHECK-NEXT: store i64 [[ADD1_2]], i64* [[OMP_IV]]
// ... end iteration for ordered loop ...
// CHECK-NEXT: call void @__kmpc_dispatch_fini_8([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// CHECK-NEXT: br label %{{.+}}
}
// CHECK: [[LOOP1_END]]
// CHECK: [[O_LOOP1_END]]
// CHECK: call {{.+}} @__kmpc_barrier([[IDENT_T_TY]]* [[IMPLICIT_BARRIER_LOC]], i32 [[GTID]])
// CHECK: ret void
}
// CHECK-LABEL: define {{.*void}} @{{.*}}runtime{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}})
void runtime(float *a, float *b, float *c, float *d) {
int x = 0;
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]])
#pragma omp for collapse(2) schedule(runtime) ordered
// CHECK: call void @__kmpc_dispatch_init_4([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 69, i32 0, i32 199, i32 1, i32 1)
//
// CHECK: [[HASWORK:%.+]] = call i32 @__kmpc_dispatch_next_4([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32* [[OMP_ISLAST:%[^,]+]], i32* [[OMP_LB:%[^,]+]], i32* [[OMP_UB:%[^,]+]], i32* [[OMP_ST:%[^,]+]])
// CHECK-NEXT: [[O_CMP:%.+]] = icmp ne i32 [[HASWORK]], 0
// CHECK-NEXT: br i1 [[O_CMP]], label %[[O_LOOP1_BODY:[^,]+]], label %[[O_LOOP1_END:[^,]+]]
// Loop header
// CHECK: [[O_LOOP1_BODY]]
// CHECK: [[LB:%.+]] = load i32, i32* [[OMP_LB]]
// CHECK-NEXT: store i32 [[LB]], i32* [[OMP_IV:[^,]+]]
// CHECK: [[IV:%.+]] = load i32, i32* [[OMP_IV]]
// CHECK-NEXT: [[UB:%.+]] = load i32, i32* [[OMP_UB]]
// CHECK-NEXT: [[CMP:%.+]] = icmp sle i32 [[IV]], [[UB]]
// CHECK-NEXT: br i1 [[CMP]], label %[[LOOP1_BODY:[^,]+]], label %[[LOOP1_END:[^,]+]]
for (unsigned char i = '0' ; i <= '9'; ++i)
for (x = -10; x < 10; ++x) {
// CHECK: [[LOOP1_BODY]]
// Start of body: indices are calculated from IV:
// CHECK: store i8 {{%[^,]+}}, i8* {{%[^,]+}}
// CHECK: store i32 {{%[^,]+}}, i32* {{%[^,]+}}
// ... start of ordered region ...
// CHECK: call void @__kmpc_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK-NEXT: call void @__kmpc_end_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... end of ordered region ...
#pragma omp ordered
a[i] = b[i] * c[i] * d[i];
// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}
// CHECK-NEXT: [[ADD1_2:%.+]] = add nsw i32 [[IV1_2]], 1
// CHECK-NEXT: store i32 [[ADD1_2]], i32* [[OMP_IV]]
// ... end iteration for ordered loop ...
// CHECK-NEXT: call void @__kmpc_dispatch_fini_4([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// CHECK-NEXT: br label %{{.+}}
}
// CHECK: [[LOOP1_END]]
// CHECK: [[O_LOOP1_END]]
// CHECK: call {{.+}} @__kmpc_barrier([[IDENT_T_TY]]* [[IMPLICIT_BARRIER_LOC]], i32 [[GTID]])
// CHECK: ret void
}
#endif // HEADER
|
