maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/OpenMP/distribute_parallel_for_if_...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

198 lines
7.8 KiB
C++
Raw Normal View History

Recommit of [OpenMP] Initial implementation of code generation for pragma 'distribute parallel for' on host https://reviews.llvm.org/D29508 This patch makes the following additions: It abstracts away loop bound generation code from procedures associated with pragma 'for' and loops in general, in such a way that the same procedures can be used for 'distribute parallel for' without the need for a full re-implementation. It implements code generation for 'distribute parallel for' and adds regression tests. It includes tests for clauses. It is important to notice that most of the clauses are implemented as part of existing procedures. For instance, firstprivate is already implemented for 'distribute' and 'for' as separate pragmas. As the implementation of 'distribute parallel for' is based on the same procedures, then we automatically obtain implementation for such clauses without the need to add new code. However, this requires regression tests that verify correctness of produced code. llvm-svn: 301340
2017-04-26 01:52:12 +08:00
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple %itanium_abi_triple -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple %itanium_abi_triple -emit-pch -o %t %s
[clang] Remove redundant check-prefix=CHECK from tests. NFC. Reviewers: t.p.northover, mstorsjo, rsmith, mcrosier Reviewed By: mstorsjo, mcrosier Subscribers: mcrosier, javed.absar, cfe-commits Differential Revision: https://reviews.llvm.org/D35465 llvm-svn: 308192
2017-07-18 01:31:44 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple %itanium_abi_triple -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple %itanium_abi_triple -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple %itanium_abi_triple -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple %itanium_abi_triple -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
Recommit of [OpenMP] Initial implementation of code generation for pragma 'distribute parallel for' on host https://reviews.llvm.org/D29508 This patch makes the following additions: It abstracts away loop bound generation code from procedures associated with pragma 'for' and loops in general, in such a way that the same procedures can be used for 'distribute parallel for' without the need for a full re-implementation. It implements code generation for 'distribute parallel for' and adds regression tests. It includes tests for clauses. It is important to notice that most of the clauses are implemented as part of existing procedures. For instance, firstprivate is already implemented for 'distribute' and 'for' as separate pragmas. As the implementation of 'distribute parallel for' is based on the same procedures, then we automatically obtain implementation for such clauses without the need to add new code. However, this requires regression tests that verify correctness of produced code. llvm-svn: 301340
2017-04-26 01:52:12 +08:00
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
void fn1();
void fn2();
void fn3();
void fn4();
void fn5();
void fn6();
int Arg;
// CHECK-LABEL: define {{.*}}void @{{.+}}gtid_test
void gtid_test() {
#pragma omp target
#pragma omp teams
// CHECK: call i{{[0-9]+}} @__tgt_target_teams(
// CHECK: call void [[OFFLOADING_FUN_0:@.+]](
// CHECK: call i{{[0-9]+}} @__tgt_target_teams(
// CHECK: call void [[OFFLOADING_FUN_1:@.+]](
#pragma omp distribute parallel for
for(int i = 0 ; i < 100; i++) {}
// CHECK: define internal void [[OFFLOADING_FUN_0]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[OMP_TEAMS_OUTLINED_0:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_0]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 2, {{.+}}* [[OMP_OUTLINED_0:@.+]] to void
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define{{.+}} void [[OMP_OUTLINED_0]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for if (parallel: false)
for(int i = 0 ; i < 100; i++) {
// CHECK: define internal void [[OFFLOADING_FUN_1]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[OMP_TEAMS_OUTLINED_1:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_1]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void @__kmpc_serialized_parallel(
// CHECK: call void [[OMP_OUTLINED_1:@.+]](
// CHECK: call void @__kmpc_end_serialized_parallel(
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define{{.+}} void [[OMP_OUTLINED_1]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void @{{.+}}gtid_test
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret
gtid_test();
}
}
template <typename T>
int tmain(T Arg) {
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for if (true)
for(int i = 0 ; i < 100; i++) {
fn1();
}
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for if (false)
for(int i = 0 ; i < 100; i++) {
fn2();
}
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for if (parallel: Arg)
for(int i = 0 ; i < 100; i++) {
fn3();
}
return 0;
}
// CHECK-LABEL: define {{.*}}i{{[0-9]+}} @main()
int main() {
// CHECK: call i{{[0-9]+}} @__tgt_target_teams(
// CHECK: call void [[OFFLOADING_FUN_0:@.+]](
// CHECK: call i{{[0-9]+}} @__tgt_target_teams(
// CHECK: call void [[OFFLOADING_FUN_1:@.+]](
// CHECK: call i{{[0-9]+}} @__tgt_target_teams(
// CHECK: call void [[OFFLOADING_FUN_2:@.+]](
// CHECK: = call {{.*}}i{{.+}} @{{.+}}tmain
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for if (true)
for(int i = 0 ; i < 100; i++) {
// CHECK: define internal void [[OFFLOADING_FUN_0]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[OMP_TEAMS_OUTLINED_0:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_0]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 2, {{.+}}* [[OMP_OUTLINED_2:@.+]] to void
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define{{.+}} void [[OMP_OUTLINED_2]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn4
// CHECK: call void @__kmpc_for_static_fini(
fn4();
}
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for if (false)
for(int i = 0 ; i < 100; i++) {
// CHECK: define internal void [[OFFLOADING_FUN_1]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[OMP_TEAMS_OUTLINED_1:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_1]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void @__kmpc_serialized_parallel(
// CHECK: call void [[OMP_OUTLINED_3:@.+]](
// CHECK: call void @__kmpc_end_serialized_parallel(
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define{{.+}} void [[OMP_OUTLINED_3]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn5
// CHECK: call void @__kmpc_for_static_fini(
fn5();
}
#pragma omp target
#pragma omp teams
#pragma omp distribute parallel for if (Arg)
for(int i = 0 ; i < 100; i++) {
// CHECK: define internal void [[OFFLOADING_FUN_2]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}}* [[OMP_TEAMS_OUTLINED_2:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_2]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 2, {{.+}}* [[OMP_OUTLINED_4:@.+]] to void
// CHECK: call void @__kmpc_serialized_parallel(
// CHECK: call void [[OMP_OUTLINED_4:@.+]](
// CHECK: call void @__kmpc_end_serialized_parallel(
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define{{.+}} void [[OMP_OUTLINED_4]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn6
// CHECK: call void @__kmpc_for_static_fini(
fn6();
}
return tmain(Arg);
}
// CHECK-LABEL: define {{.+}} @{{.+}}tmain
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 2, void {{.+}}* [[T_OUTLINE_FUN_1:@.+]] to void
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define internal {{.*}}void [[T_OUTLINE_FUN_1]]
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn1
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @__kmpc_serialized_parallel(
// CHECK: call void [[T_OUTLINE_FUN_2:@.+]](
// CHECK: call {{.*}}void @__kmpc_end_serialized_parallel(
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define internal {{.*}}void [[T_OUTLINE_FUN_2]]
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn2
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 2, void {{.+}}* [[T_OUTLINE_FUN_3:@.+]] to void
// CHECK: call {{.*}}void @__kmpc_serialized_parallel(
// call void [[T_OUTLINE_FUN_3:@.+]](
// CHECK: call {{.*}}void @__kmpc_end_serialized_parallel(
// CHECK: define internal {{.*}}void [[T_OUTLINE_FUN_3]]
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn3
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
#endif