gtbercea updated this revision to Diff 195644.
gtbercea added a comment.
- Update tests.
- Move error check in sema.
Repository:
rC Clang
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D60568/new/
https://reviews.llvm.org/D60568
Files:
include/clang/Basic/DiagnosticSemaKinds.td
lib/CodeGen/CGOpenMPRuntime.cpp
lib/CodeGen/CGOpenMPRuntime.h
lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
lib/CodeGen/CGOpenMPRuntimeNVPTX.h
lib/CodeGen/CodeGenModule.cpp
lib/Sema/SemaOpenMP.cpp
test/OpenMP/openmp_offload_registration.cpp
test/OpenMP/target_codegen.cpp
test/OpenMP/target_codegen_registration.cpp
Index: test/OpenMP/target_codegen_registration.cpp
===================================================================
--- test/OpenMP/target_codegen_registration.cpp
+++ test/OpenMP/target_codegen_registration.cpp
@@ -180,10 +180,11 @@
// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]])
// We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function.
-// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [
+// CHECK: @llvm.global_ctors = appending global [5 x { i32, void ()*, i8* }] [
// CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null },
// CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null },
// CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null },
+// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null },
// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }]
// CHECK-NTARGET: @llvm.global_ctors = appending global [3 x { i32, void ()*, i8* }] [
@@ -387,6 +388,10 @@
// Check registration and unregistration
+//CHECK: define internal void @.omp_offloading.requires_reg()
+//CHECK: call void @__tgt_register_requires(i64 1)
+//CHECK: ret void
+
//CHECK: define internal void @[[UNREGFN:.+]](i8*)
//CHECK-SAME: comdat($[[REGFN]]) {
//CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]])
@@ -432,31 +437,31 @@
// Check metadata is properly generated:
// CHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 266, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 282, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 288, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 299, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 305, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 427, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 311, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 305, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 311, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 299, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 241, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 217, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 267, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 283, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 289, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 300, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 306, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 432, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 312, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 306, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 312, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 300, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}}
// TCHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 266, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 282, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 288, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 299, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 305, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 427, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 311, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 305, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 311, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 299, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 241, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 217, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 267, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 283, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 289, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 300, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 306, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 432, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 312, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 306, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 312, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 300, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}}
#endif
Index: test/OpenMP/target_codegen.cpp
===================================================================
--- test/OpenMP/target_codegen.cpp
+++ test/OpenMP/target_codegen.cpp
@@ -96,7 +96,7 @@
// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]])
// Check target registration is registered as a Ctor.
-// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }]
+// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }]
template<typename tx, typename ty>
Index: test/OpenMP/openmp_offload_registration.cpp
===================================================================
--- test/OpenMP/openmp_offload_registration.cpp
+++ test/OpenMP/openmp_offload_registration.cpp
@@ -26,7 +26,7 @@
// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 2, [[DEVTY]]* getelementptr inbounds ([2 x [[DEVTY]]], [2 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]])
// Check target registration is registered as a Ctor.
-// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }]
+// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }]
// Check presence of foo() and the outlined target region
// CHECK: define void [[FOO:@.+]]()
@@ -34,6 +34,11 @@
// Check registration and unregistration code.
+// CHECK: define internal void @.omp_offloading.requires_reg()
+// CHECK: call void @__tgt_register_requires(i64 1)
+// CHECK: ret void
+// CHECK: declare void @__tgt_register_requires(i64)
+
// CHECK: define internal void @[[UNREGFN:.+]](i8*)
// CHECK-SAME: comdat($[[REGFN]]) {
// CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]])
Index: lib/Sema/SemaOpenMP.cpp
===================================================================
--- lib/Sema/SemaOpenMP.cpp
+++ lib/Sema/SemaOpenMP.cpp
@@ -193,6 +193,8 @@
/// Expression for the predefined allocators.
Expr *OMPPredefinedAllocators[OMPAllocateDeclAttr::OMPUserDefinedMemAlloc] = {
nullptr};
+ /// Vector of previously encountered target directives
+ SmallVector<SourceLocation, 2> TargetLocations;
public:
explicit DSAStackTy(Sema &S) : SemaRef(S) {}
@@ -454,6 +456,34 @@
return IsDuplicate;
}
+ /// Add location of previously encountered target to internal vector
+ void addTargetDirLocation(SourceLocation LocStart) {
+ TargetLocations.push_back(LocStart);
+ }
+
+ /// For target specific clauses, the requires directive cannot be
+ /// specified after the handling of any of the target regions in the
+ /// current compilation unit.
+ void checkEncounteredTargets(SourceLocation Loc,
+ ArrayRef<OMPClause *> ClauseList) {
+ for (OMPClause *CNew : ClauseList) {
+ // Check if any of the requires clauses affect target regions.
+ if (!TargetLocations.empty() &&
+ (isa<OMPUnifiedSharedMemoryClause>(CNew) ||
+ isa<OMPUnifiedAddressClause>(CNew) ||
+ isa<OMPReverseOffloadClause>(CNew) ||
+ isa<OMPDynamicAllocatorsClause>(CNew))) {
+ SemaRef.Diag(Loc,
+ diag::err_omp_target_before_requires)
+ << getOpenMPClauseName(CNew->getClauseKind());
+ for (SourceLocation TargetLoc : TargetLocations) {
+ SemaRef.Diag(TargetLoc,
+ diag::note_omp_requires_encountered_target);
+ }
+ }
+ }
+ }
+
/// Set default data sharing attribute to none.
void setDefaultDSANone(SourceLocation Loc) {
assert(!isStackEmpty());
@@ -2418,6 +2448,7 @@
OMPRequiresDecl *Sema::CheckOMPRequiresDecl(SourceLocation Loc,
ArrayRef<OMPClause *> ClauseList) {
+ DSAStack->checkEncounteredTargets(Loc, ClauseList);
if (!DSAStack->hasDuplicateRequiresClause(ClauseList))
return OMPRequiresDecl::Create(Context, getCurLexicalContext(), Loc,
ClauseList);
@@ -4167,6 +4198,16 @@
->setIsOMPStructuredBlock(true);
}
+ if (isOpenMPTargetExecutionDirective(Kind) &&
+ !(DSAStack->hasRequiresDeclWithClause<OMPUnifiedSharedMemoryClause>() ||
+ DSAStack->hasRequiresDeclWithClause<OMPUnifiedAddressClause>() ||
+ DSAStack->hasRequiresDeclWithClause<OMPReverseOffloadClause>() ||
+ DSAStack->hasRequiresDeclWithClause<OMPDynamicAllocatorsClause>()) &&
+ !CurContext->isDependentContext()) {
+ // Register target to DSA Stack.
+ DSAStack->addTargetDirLocation(StartLoc);
+ }
+
return Res;
}
Index: lib/CodeGen/CodeGenModule.cpp
===================================================================
--- lib/CodeGen/CodeGenModule.cpp
+++ lib/CodeGen/CodeGenModule.cpp
@@ -410,6 +410,10 @@
AddGlobalCtor(CudaCtorFunction);
}
if (OpenMPRuntime) {
+ if (llvm::Function *OpenMPRequiresDirectiveRegFun =
+ OpenMPRuntime->emitRequiresDirectiveRegFun()) {
+ AddGlobalCtor(OpenMPRequiresDirectiveRegFun, 0);
+ }
if (llvm::Function *OpenMPRegistrationFunction =
OpenMPRuntime->emitRegistrationFunction()) {
auto ComdatKey = OpenMPRegistrationFunction->hasComdat() ?
Index: lib/CodeGen/CGOpenMPRuntimeNVPTX.h
===================================================================
--- lib/CodeGen/CGOpenMPRuntimeNVPTX.h
+++ lib/CodeGen/CGOpenMPRuntimeNVPTX.h
@@ -383,7 +383,7 @@
/// Perform check on requires decl to ensure that target architecture
/// supports unified addressing
- void checkArchForUnifiedAddressing(const OMPRequiresDecl *D) const override;
+ void checkArchForUnifiedAddressing(const OMPRequiresDecl *D) override;
/// Returns default address space for the constant firstprivates, __constant__
/// address space by default.
Index: lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
===================================================================
--- lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
+++ lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
@@ -4942,7 +4942,7 @@
/// Check to see if target architecture supports unified addressing which is
/// a restriction for OpenMP requires clause "unified_shared_memory".
void CGOpenMPRuntimeNVPTX::checkArchForUnifiedAddressing(
- const OMPRequiresDecl *D) const {
+ const OMPRequiresDecl *D) {
for (const OMPClause *Clause : D->clauselists()) {
if (Clause->getClauseKind() == OMPC_unified_shared_memory) {
switch (getCudaArch(CGM)) {
@@ -4987,6 +4987,7 @@
}
}
}
+ CGOpenMPRuntime::checkArchForUnifiedAddressing(D);
}
/// Get number of SMs and number of blocks per SM.
Index: lib/CodeGen/CGOpenMPRuntime.h
===================================================================
--- lib/CodeGen/CGOpenMPRuntime.h
+++ lib/CodeGen/CGOpenMPRuntime.h
@@ -636,6 +636,17 @@
/// must be emitted.
llvm::SmallDenseSet<const VarDecl *> DeferredGlobalVariables;
+ /// Flag for keeping track of weather a requires unified_shared_memory
+ /// directive is present.
+ bool HasRequiresUnifiedSharedMemory = false;
+
+ /// Flag for keeping track of weather a target region has been emitted.
+ bool HasEmittedTargetRegion = false;
+
+ /// Flag for keeping track of weather a device routine has been emitted.
+ /// Device routines are specific to the
+ bool HasEmittedDeclareTargetRegion = false;
+
/// Creates and registers offloading binary descriptor for the current
/// compilation unit. The function that does the registration is returned.
llvm::Function *createOffloadingBinaryDescriptorRegistration();
@@ -1429,6 +1440,10 @@
/// \param GD Global to scan.
virtual bool emitTargetGlobal(GlobalDecl GD);
+ /// Creates and returns a registration function for when at least one
+ /// requires directives was used in the current module.
+ llvm::Function *emitRequiresDirectiveRegFun();
+
/// Creates the offloading descriptor in the event any target region
/// was emitted in the current module and return the function that registers
/// it.
@@ -1576,7 +1591,7 @@
/// Emits OpenMP-specific function prolog.
/// Required for device constructs.
- virtual void emitFunctionProlog(CodeGenFunction &CGF, const Decl *D) {}
+ virtual void emitFunctionProlog(CodeGenFunction &CGF, const Decl *D);
/// Gets the OpenMP-specific address of the local variable.
virtual Address getAddressOfLocalVariable(CodeGenFunction &CGF,
@@ -1597,7 +1612,7 @@
/// Perform check on requires decl to ensure that target architecture
/// supports unified addressing
- virtual void checkArchForUnifiedAddressing(const OMPRequiresDecl *D) const {}
+ virtual void checkArchForUnifiedAddressing(const OMPRequiresDecl *D);
/// Checks if the variable has associated OMPAllocateDeclAttr attribute with
/// the predefined allocator and translates it into the corresponding address
Index: lib/CodeGen/CGOpenMPRuntime.cpp
===================================================================
--- lib/CodeGen/CGOpenMPRuntime.cpp
+++ lib/CodeGen/CGOpenMPRuntime.cpp
@@ -457,6 +457,26 @@
LLVM_MARK_AS_BITMASK_ENUM(/*LargestValue=*/OMP_IDENT_WORK_DISTRIBUTE)
};
+namespace {
+LLVM_ENABLE_BITMASK_ENUMS_IN_NAMESPACE();
+/// Values for bit flags for marking which requires clauses have been used.
+enum OpenMPOffloadingRequiresDirFlags : int64_t {
+ /// flag undefined.
+ OMP_REQ_UNDEFINED = 0x000,
+ /// no requires clause present.
+ OMP_REQ_NONE = 0x001,
+ /// reverse_offload clause.
+ OMP_REQ_REVERSE_OFFLOAD = 0x002,
+ /// unified_address clause.
+ OMP_REQ_UNIFIED_ADDRESS = 0x004,
+ /// unified_shared_memory clause.
+ OMP_REQ_UNIFIED_SHARED_MEMORY = 0x008,
+ /// dynamic_allocators clause.
+ OMP_REQ_DYNAMIC_ALLOCATORS = 0x010,
+ LLVM_MARK_AS_BITMASK_ENUM(/*LargestValue=*/OMP_REQ_DYNAMIC_ALLOCATORS)
+};
+} // anonymous namespace
+
/// Describes ident structure that describes a source location.
/// All descriptions are taken from
/// https://github.com/llvm/llvm-project/blob/master/openmp/runtime/src/kmp.h
@@ -694,6 +714,8 @@
// *host_ptr, int32_t arg_num, void** args_base, void **args, size_t
// *arg_sizes, int64_t *arg_types, int32_t num_teams, int32_t thread_limit);
OMPRTL__tgt_target_teams_nowait,
+ // Call to void __tgt_register_requires(int64_t flags);
+ OMPRTL__tgt_register_requires,
// Call to void __tgt_register_lib(__tgt_bin_desc *desc);
OMPRTL__tgt_register_lib,
// Call to void __tgt_unregister_lib(__tgt_bin_desc *desc);
@@ -2294,6 +2316,14 @@
RTLFn = CGM.CreateRuntimeFunction(FnTy, "__tgt_target_teams_nowait");
break;
}
+ case OMPRTL__tgt_register_requires: {
+ // Build void __tgt_register_requires(int64_t flags);
+ llvm::Type *TypeParams[] = {CGM.Int64Ty};
+ auto *FnTy =
+ llvm::FunctionType::get(CGM.VoidTy, TypeParams, /*isVarArg*/ false);
+ RTLFn = CGM.CreateRuntimeFunction(FnTy, "__tgt_register_requires");
+ break;
+ }
case OMPRTL__tgt_register_lib: {
// Build void __tgt_register_lib(__tgt_bin_desc *desc);
QualType ParamTy =
@@ -6404,6 +6434,7 @@
llvm::Function *&OutlinedFn, llvm::Constant *&OutlinedFnID,
bool IsOffloadEntry, const RegionCodeGenTy &CodeGen) {
assert(!ParentName.empty() && "Invalid target region parent name!");
+ HasEmittedTargetRegion = true;
emitTargetOutlinedFunctionHelper(D, ParentName, OutlinedFn, OutlinedFnID,
IsOffloadEntry, CodeGen);
}
@@ -7922,7 +7953,7 @@
MapValuesArrayTy &Sizes,
MapFlagsArrayTy &Types) const {
// Map other list items in the map clause which are not captured variables
- // but "declare target link" global variables.,
+ // but "declare target link" global variables.
for (const auto *C : this->CurDir.getClausesOfKind<OMPMapClause>()) {
for (const auto &L : C->component_lists()) {
if (!L.first)
@@ -8935,6 +8966,16 @@
" Expected target-based directive.");
}
+void CGOpenMPRuntime::checkArchForUnifiedAddressing(
+ const OMPRequiresDecl *D) {
+ for (const OMPClause *Clause : D->clauselists()) {
+ if (Clause->getClauseKind() == OMPC_unified_shared_memory) {
+ HasRequiresUnifiedSharedMemory = true;
+ break;
+ }
+ }
+}
+
bool CGOpenMPRuntime::hasAllocateAttributeForGlobalVar(const VarDecl *VD,
LangAS &AS) {
if (!VD || !VD->hasAttr<OMPAllocateDeclAttr>())
@@ -8993,6 +9034,41 @@
return !AlreadyEmittedTargetFunctions.insert(Name).second;
}
+llvm::Function *CGOpenMPRuntime::emitRequiresDirectiveRegFun() {
+ // If we don't have entries or if we are emitting code for the device, we
+ // don't need to do anything.
+ if (CGM.getLangOpts().OpenMPSimd || CGM.getLangOpts().OpenMPIsDevice ||
+ (OffloadEntriesInfoManager.empty() && !HasEmittedDeclareTargetRegion))
+ return nullptr;
+
+ // Create and register the function that handles the requires directives.
+ ASTContext &C = CGM.getContext();
+
+ llvm::Function *RequiresRegFn;
+ {
+ CodeGenFunction CGF(CGM);
+ const auto &FI = CGM.getTypes().arrangeNullaryFunction();
+ llvm::FunctionType *FTy = CGM.getTypes().GetFunctionType(FI);
+ std::string ReqName = getName({"omp_offloading", "requires_reg"});
+ RequiresRegFn = CGM.CreateGlobalInitOrDestructFunction(FTy, ReqName, FI);
+ CGF.StartFunction(GlobalDecl(), C.VoidTy, RequiresRegFn, FI, {});
+ OpenMPOffloadingRequiresDirFlags Flags = OMP_REQ_NONE;
+ // TODO: check for other requires clauses.
+ // The requires directive takes effect only when a target region is
+ // present in the compilation unit. Otherwise it is ignored and not
+ // passed to the runtime. This avoids the runtime from throwing an error
+ // for mismatching requires clauses across compilation units that don't
+ // contain at least 1 target region.
+ if ((HasEmittedTargetRegion || HasEmittedDeclareTargetRegion) &&
+ HasRequiresUnifiedSharedMemory)
+ Flags = OMP_REQ_UNIFIED_SHARED_MEMORY;
+ CGF.EmitRuntimeCall(createRuntimeFunction(OMPRTL__tgt_register_requires),
+ llvm::ConstantInt::get(CGM.Int64Ty, Flags));
+ CGF.FinishFunction();
+ }
+ return RequiresRegFn;
+}
+
llvm::Function *CGOpenMPRuntime::emitRegistrationFunction() {
// If we have offloading in the current module, we need to emit the entries
// now and register the offloading descriptor.
@@ -9718,6 +9794,14 @@
emitCall(CGF, Loc, OutlinedFn, Args);
}
+void CGOpenMPRuntime::emitFunctionProlog(CodeGenFunction &CGF, const Decl *D){
+ if (const auto *FD = dyn_cast<FunctionDecl>(D)) {
+ if (OMPDeclareTargetDeclAttr::isDeclareTargetDeclaration(FD)) {
+ HasEmittedDeclareTargetRegion = true;
+ }
+ }
+}
+
Address CGOpenMPRuntime::getParameterAddress(CodeGenFunction &CGF,
const VarDecl *NativeParam,
const VarDecl *TargetParam) const {
Index: include/clang/Basic/DiagnosticSemaKinds.td
===================================================================
--- include/clang/Basic/DiagnosticSemaKinds.td
+++ include/clang/Basic/DiagnosticSemaKinds.td
@@ -9132,6 +9132,10 @@
"Only one %0 clause can appear on a requires directive in a single translation unit">;
def note_omp_requires_previous_clause : Note <
"%0 clause previously used here">;
+def err_omp_target_before_requires : Error <
+ "Target region encountered before requires directive with %0 clause.">;
+def note_omp_requires_encountered_target : Note <
+ "Target previously encountered here">;
def err_omp_invalid_scope : Error <
"'#pragma omp %0' directive must appear only in file scope">;
def note_omp_invalid_length_on_this_ptr_mapping : Note <
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
