forked from OSchip/llvm-project
[OpenMP] Limit reduction support for pragma 'distribute' when combined with pragma 'simd'
Differential Revision: https://reviews.llvm.org/D43513 This is a bug fix that removes the emission of reduction support for pragma 'distribute' when found alone or in combinations without simd. Pragma 'distribute' does not have a reduction clause, but when combined with pragma 'simd' we need to emit the support for simd's reduction clause as part of code generation for distribute. This guard is similar to the one used for reduction support earlier in the same code gen function. llvm-svn: 325822
This commit is contained in:
Carlo Bertolli
parent
401b2a463c
commit
beda214996
|
|
@ -3358,26 +3358,30 @@ void CodeGenFunction::EmitOMPDistributeLoop(const OMPLoopDirective &S,
|
|||
CGF.EmitLoadOfScalar(IL, S.getLocStart()));
|
||||
});
|
||||
}
|
||||
OpenMPDirectiveKind ReductionKind = OMPD_unknown;
|
||||
if (isOpenMPParallelDirective(S.getDirectiveKind()) &&
|
||||
isOpenMPSimdDirective(S.getDirectiveKind())) {
|
||||
ReductionKind = OMPD_parallel_for_simd;
|
||||
} else if (isOpenMPParallelDirective(S.getDirectiveKind())) {
|
||||
ReductionKind = OMPD_parallel_for;
|
||||
} else if (isOpenMPSimdDirective(S.getDirectiveKind())) {
|
||||
ReductionKind = OMPD_simd;
|
||||
} else if (!isOpenMPTeamsDirective(S.getDirectiveKind()) &&
|
||||
S.hasClausesOfKind<OMPReductionClause>()) {
|
||||
llvm_unreachable(
|
||||
"No reduction clauses is allowed in distribute directive.");
|
||||
if (isOpenMPSimdDirective(S.getDirectiveKind()) &&
|
||||
!isOpenMPParallelDirective(S.getDirectiveKind()) &&
|
||||
!isOpenMPTeamsDirective(S.getDirectiveKind())) {
|
||||
OpenMPDirectiveKind ReductionKind = OMPD_unknown;
|
||||
if (isOpenMPParallelDirective(S.getDirectiveKind()) &&
|
||||
isOpenMPSimdDirective(S.getDirectiveKind())) {
|
||||
ReductionKind = OMPD_parallel_for_simd;
|
||||
} else if (isOpenMPParallelDirective(S.getDirectiveKind())) {
|
||||
ReductionKind = OMPD_parallel_for;
|
||||
} else if (isOpenMPSimdDirective(S.getDirectiveKind())) {
|
||||
ReductionKind = OMPD_simd;
|
||||
} else if (!isOpenMPTeamsDirective(S.getDirectiveKind()) &&
|
||||
S.hasClausesOfKind<OMPReductionClause>()) {
|
||||
llvm_unreachable(
|
||||
"No reduction clauses is allowed in distribute directive.");
|
||||
}
|
||||
EmitOMPReductionClauseFinal(S, ReductionKind);
|
||||
// Emit post-update of the reduction variables if IsLastIter != 0.
|
||||
emitPostUpdateForReductionClause(
|
||||
*this, S, [&](CodeGenFunction &CGF) -> llvm::Value * {
|
||||
return CGF.Builder.CreateIsNotNull(
|
||||
CGF.EmitLoadOfScalar(IL, S.getLocStart()));
|
||||
});
|
||||
}
|
||||
EmitOMPReductionClauseFinal(S, ReductionKind);
|
||||
// Emit post-update of the reduction variables if IsLastIter != 0.
|
||||
emitPostUpdateForReductionClause(
|
||||
*this, S, [&](CodeGenFunction &CGF) -> llvm::Value * {
|
||||
return CGF.Builder.CreateIsNotNull(
|
||||
CGF.EmitLoadOfScalar(IL, S.getLocStart()));
|
||||
});
|
||||
// Emit final copy of the lastprivate variables if IsLastIter != 0.
|
||||
if (HasLastprivateClause) {
|
||||
EmitOMPLastprivateClauseFinal(
|
||||
|
|
|
|||
|
|
@ -0,0 +1,84 @@
|
|||
// Test host code gen
|
||||
|
||||
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
|
||||
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
|
||||
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
|
||||
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
|
||||
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
|
||||
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
|
||||
|
||||
// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY1 %s
|
||||
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
|
||||
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
|
||||
// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY1 %s
|
||||
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
|
||||
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
|
||||
// SIMD-ONLY1-NOT: {{__kmpc|__tgt}}
|
||||
// expected-no-diagnostics
|
||||
#ifndef HEADER
|
||||
#define HEADER
|
||||
|
||||
|
||||
template <typename T>
|
||||
T tmain(T &r) {
|
||||
int n = 1000;
|
||||
// schedule: dynamic chunk
|
||||
#pragma omp target map(tofrom:r)
|
||||
#pragma omp teams
|
||||
#pragma omp distribute parallel for reduction(+:r)
|
||||
for (int i = 0; i < n; ++i)
|
||||
r += (T)i;
|
||||
|
||||
return r;
|
||||
}
|
||||
|
||||
int main() {
|
||||
int n = 1000;
|
||||
int r = 0;
|
||||
#pragma omp target map(tofrom:r)
|
||||
#pragma omp teams
|
||||
#pragma omp distribute parallel for reduction(+:r)
|
||||
for (int i = 0; i < n; ++i)
|
||||
r += i;
|
||||
|
||||
return tmain<int>(r);
|
||||
}
|
||||
|
||||
// CHECK-LABEL: main
|
||||
// CHECK: call{{.+}} @__tgt_target_teams(
|
||||
// CHECK: call void [[OFFL:@.+]](
|
||||
// CHECK: call{{.+}} [[TMAIN:@.+]](i{{32|64}}
|
||||
// CHECK: ret
|
||||
|
||||
// CHECK: define{{.+}} [[OFFL]](
|
||||
// CHECK: call{{.+}} @__kmpc_fork_teams({{.+}}, {{.+}}, {{.+}} [[TEOUTL:@.+]] to{{.+}}
|
||||
// CHECK: ret void
|
||||
|
||||
// CHECK: define{{.+}} [[TEOUTL]](
|
||||
// CHECK: call{{.+}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} [[PAROUTL:@.+]] to{{.+}}
|
||||
// CHECK: ret void
|
||||
|
||||
// CHECK: define{{.+}} [[PAROUTL]](
|
||||
// CHECK: call{{.+}} @__kmpc_reduce_nowait(
|
||||
// CHECK: call{{.+}} @__kmpc_end_reduce_nowait(
|
||||
// CHECK: ret void
|
||||
|
||||
// CHECK: define{{.+}} [[TMAIN]](i{{32|64}}
|
||||
// CHECK: call{{.+}} @__tgt_target_teams(
|
||||
// CHECK: call void [[TOFFL:@.+]](
|
||||
// CHECK: ret
|
||||
|
||||
// CHECK: define{{.+}} [[TOFFL]](
|
||||
// CHECK: call{{.+}} @__kmpc_fork_teams({{.+}}, {{.+}}, {{.+}} [[TEMPLTEOUTL:@.+]] to{{.+}}
|
||||
// CHECK: ret void
|
||||
|
||||
// CHECK: define{{.+}} [[TEMPLTEOUTL]](
|
||||
// CHECK: call{{.+}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} [[TPAROUTL:@.+]] to{{.+}}
|
||||
// CHECK: ret void
|
||||
|
||||
// CHECK: define{{.+}} [[TPAROUTL]](
|
||||
// CHECK: call{{.+}} @__kmpc_reduce_nowait(
|
||||
// CHECK: call{{.+}} @__kmpc_end_reduce_nowait(
|
||||
// CHECK: ret void
|
||||
|
||||
#endif // HEADER
|
||||
Loading…
Reference in New Issue