19b911cb75
This patch adds support for codegen of 'target parallel' on the host. It is also the first combined directive that requires two or more captured statements. Support for this functionality is included in the patch. A combined directive such as 'target parallel' has two captured statements, one for the 'target' and the other for the 'parallel' region. Two captured statements are required because each has different implicit parameters (see SemaOpenMP.cpp). For example, the 'parallel' has 'global_tid' and 'bound_tid' while the 'target' does not. The patch adds support for handling multiple captured statements based on the combined directive. When codegen'ing the 'target parallel' directive, the 'target' outlined function is created using the outer captured statement and the 'parallel' outlined function is created using the inner captured statement. Reviewers: ABataev Differential Revision: https://reviews.llvm.org/D28753 llvm-svn: 292419
67 lines
4.3 KiB
C++
67 lines
4.3 KiB
C++
// Test host codegen.
|
|
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
|
|
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
|
|
|
|
// Test target parallel codegen - host bc file has to be created first.
|
|
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
|
|
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s -check-prefix=TCHECK
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s -check-prefix=TCHECK
|
|
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
|
|
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s -check-prefix=TCHECK
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s -check-prefix=TCHECK
|
|
|
|
// expected-no-diagnostics
|
|
#ifndef HEADER
|
|
#define HEADER
|
|
|
|
// CHECK: [[CA:%.+]] = type { i32* }
|
|
|
|
// CHECK: define {{.*}}i32 @[[NNAME:.+]](i32 {{.*}}%{{.+}})
|
|
int nested(int a){
|
|
// CHECK: call void @__omp_offloading_[[FILEID:[0-9a-f]+_[0-9a-f]+]]_[[NNAME]]_l[[T1L:[0-9]+]](
|
|
#pragma omp target parallel
|
|
++a;
|
|
|
|
// CHECK: call void @"[[LNAME:.+]]"([[CA]]*
|
|
auto F = [&](){
|
|
#pragma omp parallel
|
|
{
|
|
#pragma omp target parallel
|
|
++a;
|
|
}
|
|
};
|
|
|
|
F();
|
|
|
|
return a;
|
|
}
|
|
|
|
// CHECK: define {{.*}}void @__omp_offloading_[[FILEID]]_[[NNAME]]_l[[T1L]](
|
|
// TCHECK: define {{.*}}void @__omp_offloading_[[FILEID:[0-9a-f]+_[0-9a-f]+]]_[[NNAME:.+]]_l[[T1L:[0-9]+]](
|
|
|
|
// CHECK: define {{.*}}void @"[[LNAME]]"(
|
|
// CHECK: call void {{.*}}@__kmpc_fork_call{{.+}}[[PNAME:@.+]] to
|
|
|
|
// CHECK: define {{.*}}void [[PNAME]](
|
|
// CHECK: call void @__omp_offloading_[[FILEID]]_[[NNAME]]_l[[T2L:[0-9]+]](
|
|
|
|
// CHECK: define {{.*}}void @__omp_offloading_[[FILEID]]_[[NNAME]]_l[[T2L]](
|
|
// TCHECK: define {{.*}}void @__omp_offloading_[[FILEID]]_[[NNAME:.+]]_l[[T2L:[0-9]+]](
|
|
|
|
|
|
// Check metadata is properly generated:
|
|
// CHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}}
|
|
// CHECK-DAG: = !{i32 0, i32 {{-?[0-9]+}}, i32 {{-?[0-9]+}}, !"[[NNAME]]", i32 [[T1L]], i32 {{[0-9]+}}}
|
|
// CHECK-DAG: = !{i32 0, i32 {{-?[0-9]+}}, i32 {{-?[0-9]+}}, !"[[NNAME]]", i32 [[T2L]], i32 {{[0-9]+}}}
|
|
|
|
// TCHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}}
|
|
// TCHECK-DAG: = !{i32 0, i32 {{-?[0-9]+}}, i32 {{-?[0-9]+}}, !"[[NNAME]]", i32 [[T1L]], i32 {{[0-9]+}}}
|
|
// TCHECK-DAG: = !{i32 0, i32 {{-?[0-9]+}}, i32 {{-?[0-9]+}}, !"[[NNAME]]", i32 [[T2L]], i32 {{[0-9]+}}}
|
|
#endif
|