ordered_doacross_codegen.c
3.35 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
// RUN: %clang_cc1 -verify -fopenmp -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -triple x86_64-unknown-unknown -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -triple x86_64-unknown-unknown -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// RUN: %clang_cc1 -verify -fopenmp-simd -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -triple x86_64-unknown-unknown -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -triple x86_64-unknown-unknown -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
// CHECK: [[KMP_DIM:%.+]] = type { i64, i64, i64 }
extern int n;
int a[10], b[10], c[10], d[10];
void foo();
// CHECK-LABEL: @main()
int main() {
int i;
// CHECK: [[DIMS:%.+]] = alloca [1 x [[KMP_DIM]]],
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT:%.+]])
// CHECK: icmp
// CHECK-NEXT: br i1 %
// CHECK: [[CAST:%.+]] = bitcast [1 x [[KMP_DIM]]]* [[DIMS]] to i8*
// CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 [[CAST]], i8 0, i64 24, i1 false)
// CHECK: [[DIM:%.+]] = getelementptr inbounds [1 x [[KMP_DIM]]], [1 x [[KMP_DIM]]]* [[DIMS]], i64 0, i64 0
// CHECK: getelementptr inbounds [[KMP_DIM]], [[KMP_DIM]]* [[DIM]], i32 0, i32 1
// CHECK: store i64 %{{.+}}, i64* %
// CHECK: getelementptr inbounds [[KMP_DIM]], [[KMP_DIM]]* [[DIM]], i32 0, i32 2
// CHECK: store i64 1, i64* %
// CHECK: [[DIM:%.+]] = getelementptr inbounds [1 x [[KMP_DIM]]], [1 x [[KMP_DIM]]]* [[DIMS]], i64 0, i64 0
// CHECK: [[CAST:%.+]] = bitcast [[KMP_DIM]]* [[DIM]] to i8*
// CHECK: call void @__kmpc_doacross_init([[IDENT]], i32 [[GTID]], i32 1, i8* [[CAST]])
// CHECK: call void @__kmpc_for_static_init_4(%struct.ident_t* @{{.+}}, i32 [[GTID]], i32 33, i32* %{{.+}}, i32* %{{.+}}, i32* %{{.+}}, i32* %{{.+}}, i32 1, i32 1)
#pragma omp for ordered(1)
for (i = 0; i < n; ++i) {
a[i] = b[i] + 1;
foo();
// CHECK: call void [[FOO:.+]](
// CHECK: load i32, i32* [[I:%.+]],
// CHECK-NEXT: sub nsw i32 %{{.+}}, 0
// CHECK-NEXT: sdiv i32 %{{.+}}, 1
// CHECK-NEXT: sext i32 %{{.+}} to i64
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [1 x i64], [1 x i64]* [[CNT:%.+]], i64 0, i64 0
// CHECK-NEXT: store i64 %{{.+}}, i64* [[TMP]],
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [1 x i64], [1 x i64]* [[CNT]], i64 0, i64 0
// CHECK-NEXT: call void @__kmpc_doacross_post([[IDENT]], i32 [[GTID]], i64* [[TMP]])
#pragma omp ordered depend(source)
c[i] = c[i] + 1;
foo();
// CHECK: call void [[FOO]]
// CHECK: load i32, i32* [[I]],
// CHECK-NEXT: sub nsw i32 %{{.+}}, 2
// CHECK-NEXT: sub nsw i32 %{{.+}}, 0
// CHECK-NEXT: sdiv i32 %{{.+}}, 1
// CHECK-NEXT: sext i32 %{{.+}} to i64
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [1 x i64], [1 x i64]* [[CNT:%.+]], i64 0, i64 0
// CHECK-NEXT: store i64 %{{.+}}, i64* [[TMP]],
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [1 x i64], [1 x i64]* [[CNT]], i64 0, i64 0
// CHECK-NEXT: call void @__kmpc_doacross_wait([[IDENT]], i32 [[GTID]], i64* [[TMP]])
#pragma omp ordered depend(sink : i - 2)
d[i] = a[i - 2];
}
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: call void @__kmpc_doacross_fini([[IDENT]], i32 [[GTID]])
// CHECK: ret i32 0
return 0;
}
#endif // HEADER