maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[OPENMP] Fix emission of the loop doacross constructs. 

The number of loops associated with the OpenMP loop constructs should
not be considered as the number loops to collapse.

llvm-svn: 339603
This commit is contained in:
Alexey Bataev 2018-08-13 19:04:24 +00:00
parent 2da1ef5b9e
commit f138fda5ed
11 changed files with 568 additions and 215 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

96
clang/include/clang/AST/OpenMPClause.h
View File

@ -930,8 +930,11 @@ public:
/// \endcode
/// In this example directive '#pragma omp for' has 'ordered' clause with
/// parameter 2.
class OMPOrderedClause : public OMPClause {
class OMPOrderedClause final
: public OMPClause,
private llvm::TrailingObjects<OMPOrderedClause, Expr *> {
friend class OMPClauseReader;
friend TrailingObjects;
/// Location of '('.
SourceLocation LParenLoc;
@ -939,6 +942,26 @@ class OMPOrderedClause : public OMPClause {
/// Number of for-loops.
Stmt *NumForLoops = nullptr;
/// Real number of loops.
unsigned NumberOfLoops = 0;
/// Build 'ordered' clause.
///
/// \param Num Expression, possibly associated with this clause.
/// \param NumLoops Number of loops, associated with this clause.
/// \param StartLoc Starting location of the clause.
/// \param LParenLoc Location of '('.
/// \param EndLoc Ending location of the clause.
OMPOrderedClause(Expr *Num, unsigned NumLoops, SourceLocation StartLoc,
SourceLocation LParenLoc, SourceLocation EndLoc)
: OMPClause(OMPC_ordered, StartLoc, EndLoc), LParenLoc(LParenLoc),
NumForLoops(Num), NumberOfLoops(NumLoops) {}
/// Build an empty clause.
explicit OMPOrderedClause(unsigned NumLoops)
: OMPClause(OMPC_ordered, SourceLocation(), SourceLocation()),
NumberOfLoops(NumLoops) {}
/// Set the number of associated for-loops.
void setNumForLoops(Expr *Num) { NumForLoops = Num; }
@ -946,17 +969,17 @@ public:
/// Build 'ordered' clause.
///
/// \param Num Expression, possibly associated with this clause.
/// \param NumLoops Number of loops, associated with this clause.
/// \param StartLoc Starting location of the clause.
/// \param LParenLoc Location of '('.
/// \param EndLoc Ending location of the clause.
OMPOrderedClause(Expr *Num, SourceLocation StartLoc,
SourceLocation LParenLoc, SourceLocation EndLoc)
: OMPClause(OMPC_ordered, StartLoc, EndLoc), LParenLoc(LParenLoc),
NumForLoops(Num) {}
static OMPOrderedClause *Create(const ASTContext &C, Expr *Num,
unsigned NumLoops, SourceLocation StartLoc,
SourceLocation LParenLoc,
SourceLocation EndLoc);
/// Build an empty clause.
explicit OMPOrderedClause()
: OMPClause(OMPC_ordered, SourceLocation(), SourceLocation()) {}
static OMPOrderedClause* CreateEmpty(const ASTContext &C, unsigned NumLoops);
/// Sets the location of '('.
void setLParenLoc(SourceLocation Loc) { LParenLoc = Loc; }
@ -967,6 +990,17 @@ public:
/// Return the number of associated for-loops.
Expr *getNumForLoops() const { return cast_or_null<Expr>(NumForLoops); }
/// Set number of iterations for the specified loop.
void setLoopNumIterations(unsigned NumLoop, Expr *NumIterations);
/// Get number of iterations for all the loops.
ArrayRef<Expr *> getLoopNumIterations() const;
/// Set loop counter for the specified loop.
void setLoopCounter(unsigned NumLoop, Expr *Counter);
/// Get loops counter for the specified loop.
Expr *getLoopCunter(unsigned NumLoop);
const Expr *getLoopCunter(unsigned NumLoop) const;
child_range children() { return child_range(&NumForLoops, &NumForLoops + 1); }
static bool classof(const OMPClause *T) {
@ -3095,24 +3129,32 @@ class OMPDependClause final
/// Colon location.
SourceLocation ColonLoc;
/// Number of loops, associated with the depend clause.
unsigned NumLoops = 0;
/// Build clause with number of variables \a N.
///
/// \param StartLoc Starting location of the clause.
/// \param LParenLoc Location of '('.
/// \param EndLoc Ending location of the clause.
/// \param N Number of the variables in the clause.
/// \param NumLoops Number of loops that is associated with this depend
/// clause.
OMPDependClause(SourceLocation StartLoc, SourceLocation LParenLoc,
SourceLocation EndLoc, unsigned N)
SourceLocation EndLoc, unsigned N, unsigned NumLoops)
: OMPVarListClause<OMPDependClause>(OMPC_depend, StartLoc, LParenLoc,
EndLoc, N) {}
EndLoc, N), NumLoops(NumLoops) {}
/// Build an empty clause.
///
/// \param N Number of variables.
explicit OMPDependClause(unsigned N)
/// \param NumLoops Number of loops that is associated with this depend
/// clause.
explicit OMPDependClause(unsigned N, unsigned NumLoops)
: OMPVarListClause<OMPDependClause>(OMPC_depend, SourceLocation(),
SourceLocation(), SourceLocation(),
N) {}
N),
NumLoops(NumLoops) {}
/// Set dependency kind.
void setDependencyKind(OpenMPDependClauseKind K) { DepKind = K; }
@ -3134,16 +3176,23 @@ public:
/// \param DepLoc Location of the dependency type.
/// \param ColonLoc Colon location.
/// \param VL List of references to the variables.
static OMPDependClause *
Create(const ASTContext &C, SourceLocation StartLoc, SourceLocation LParenLoc,
SourceLocation EndLoc, OpenMPDependClauseKind DepKind,
SourceLocation DepLoc, SourceLocation ColonLoc, ArrayRef<Expr *> VL);
/// \param NumLoops Number of loops that is associated with this depend
/// clause.
static OMPDependClause *Create(const ASTContext &C, SourceLocation StartLoc,
SourceLocation LParenLoc,
SourceLocation EndLoc,
OpenMPDependClauseKind DepKind,
SourceLocation DepLoc, SourceLocation ColonLoc,
ArrayRef<Expr *> VL, unsigned NumLoops);
/// Creates an empty clause with \a N variables.
///
/// \param C AST context.
/// \param N The number of variables.
static OMPDependClause *CreateEmpty(const ASTContext &C, unsigned N);
/// \param NumLoops Number of loops that is associated with this depend
/// clause.
static OMPDependClause *CreateEmpty(const ASTContext &C, unsigned N,
unsigned NumLoops);
/// Get dependency type.
OpenMPDependClauseKind getDependencyKind() const { return DepKind; }
@ -3154,15 +3203,16 @@ public:
/// Get colon location.
SourceLocation getColonLoc() const { return ColonLoc; }
/// Set the loop counter value for the depend clauses with 'sink|source' kind
/// of dependency. Required for codegen.
void setCounterValue(Expr *V);
/// Get number of loops associated with the clause.
unsigned getNumLoops() const { return NumLoops; }
/// Get the loop counter value.
Expr *getCounterValue();
/// Set the loop data for the depend clauses with 'sink|source' kind of
/// dependency.
void setLoopData(unsigned NumLoop, Expr *Cnt);
/// Get the loop counter value.
const Expr *getCounterValue() const;
/// Get the loop data.
Expr *getLoopData(unsigned NumLoop);
const Expr *getLoopData(unsigned NumLoop) const;
child_range children() {
return child_range(reinterpret_cast<Stmt **>(varlist_begin()),

115
clang/lib/AST/OpenMPClause.cpp
View File

@ -181,6 +181,57 @@ const OMPClauseWithPostUpdate *OMPClauseWithPostUpdate::get(const OMPClause *C)
return nullptr;
}
OMPOrderedClause *OMPOrderedClause::Create(const ASTContext &C, Expr *Num,
unsigned NumLoops,
SourceLocation StartLoc,
SourceLocation LParenLoc,
SourceLocation EndLoc) {
void *Mem = C.Allocate(totalSizeToAlloc<Expr *>(2 * NumLoops));
auto *Clause =
new (Mem) OMPOrderedClause(Num, NumLoops, StartLoc, LParenLoc, EndLoc);
for (unsigned I = 0; I < NumLoops; ++I) {
Clause->setLoopNumIterations(I, nullptr);
Clause->setLoopCounter(I, nullptr);
}
return Clause;
}
OMPOrderedClause *OMPOrderedClause::CreateEmpty(const ASTContext &C,
unsigned NumLoops) {
void *Mem = C.Allocate(totalSizeToAlloc<Expr *>(2 * NumLoops));
auto *Clause = new (Mem) OMPOrderedClause(NumLoops);
for (unsigned I = 0; I < NumLoops; ++I) {
Clause->setLoopNumIterations(I, nullptr);
Clause->setLoopCounter(I, nullptr);
}
return Clause;
}
void OMPOrderedClause::setLoopNumIterations(unsigned NumLoop,
Expr *NumIterations) {
assert(NumLoop < NumberOfLoops && "out of loops number.");
getTrailingObjects<Expr *>()[NumLoop] = NumIterations;
}
ArrayRef<Expr *> OMPOrderedClause::getLoopNumIterations() const {
return llvm::makeArrayRef(getTrailingObjects<Expr *>(), NumberOfLoops);
}
void OMPOrderedClause::setLoopCounter(unsigned NumLoop, Expr *Counter) {
assert(NumLoop < NumberOfLoops && "out of loops number.");
getTrailingObjects<Expr *>()[NumberOfLoops + NumLoop] = Counter;
}
Expr *OMPOrderedClause::getLoopCunter(unsigned NumLoop) {
assert(NumLoop < NumberOfLoops && "out of loops number.");
return getTrailingObjects<Expr *>()[NumberOfLoops + NumLoop];
}
const Expr *OMPOrderedClause::getLoopCunter(unsigned NumLoop) const {
assert(NumLoop < NumberOfLoops && "out of loops number.");
return getTrailingObjects<Expr *>()[NumberOfLoops + NumLoop];
}
void OMPPrivateClause::setPrivateCopies(ArrayRef<Expr *> VL) {
assert(VL.size() == varlist_size() &&
"Number of private copies is not the same as the preallocated buffer");
@ -653,44 +704,58 @@ OMPFlushClause *OMPFlushClause::CreateEmpty(const ASTContext &C, unsigned N) {
return new (Mem) OMPFlushClause(N);
}
OMPDependClause *OMPDependClause::Create(
const ASTContext &C, SourceLocation StartLoc, SourceLocation LParenLoc,
SourceLocation EndLoc, OpenMPDependClauseKind DepKind,
SourceLocation DepLoc, SourceLocation ColonLoc, ArrayRef<Expr *> VL) {
void *Mem = C.Allocate(totalSizeToAlloc<Expr *>(VL.size() + 1));
OMPDependClause *Clause =
new (Mem) OMPDependClause(StartLoc, LParenLoc, EndLoc, VL.size());
OMPDependClause *
OMPDependClause::Create(const ASTContext &C, SourceLocation StartLoc,
SourceLocation LParenLoc, SourceLocation EndLoc,
OpenMPDependClauseKind DepKind, SourceLocation DepLoc,
SourceLocation ColonLoc, ArrayRef<Expr *> VL,
unsigned NumLoops) {
void *Mem = C.Allocate(totalSizeToAlloc<Expr *>(VL.size() + NumLoops));
OMPDependClause *Clause = new (Mem)
OMPDependClause(StartLoc, LParenLoc, EndLoc, VL.size(), NumLoops);
Clause->setVarRefs(VL);
Clause->setDependencyKind(DepKind);
Clause->setDependencyLoc(DepLoc);
Clause->setColonLoc(ColonLoc);
Clause->setCounterValue(nullptr);
for (unsigned I = 0 ; I < NumLoops; ++I)
Clause->setLoopData(I, nullptr);
return Clause;
}
OMPDependClause *OMPDependClause::CreateEmpty(const ASTContext &C, unsigned N) {
void *Mem = C.Allocate(totalSizeToAlloc<Expr *>(N + 1));
return new (Mem) OMPDependClause(N);
OMPDependClause *OMPDependClause::CreateEmpty(const ASTContext &C, unsigned N,
unsigned NumLoops) {
void *Mem = C.Allocate(totalSizeToAlloc<Expr *>(N + NumLoops));
return new (Mem) OMPDependClause(N, NumLoops);
}
void OMPDependClause::setCounterValue(Expr *V) {
assert(getDependencyKind() == OMPC_DEPEND_sink ||
getDependencyKind() == OMPC_DEPEND_source || V == nullptr);
*getVarRefs().end() = V;
void OMPDependClause::setLoopData(unsigned NumLoop, Expr *Cnt) {
assert((getDependencyKind() == OMPC_DEPEND_sink ||
getDependencyKind() == OMPC_DEPEND_source) &&
NumLoop < NumLoops &&
"Expected sink or source depend + loop index must be less number of "
"loops.");
auto It = std::next(getVarRefs().end(), NumLoop);
*It = Cnt;
}
const Expr *OMPDependClause::getCounterValue() const {
auto *V = *getVarRefs().end();
assert(getDependencyKind() == OMPC_DEPEND_sink ||
getDependencyKind() == OMPC_DEPEND_source || V == nullptr);
return V;
Expr *OMPDependClause::getLoopData(unsigned NumLoop) {
assert((getDependencyKind() == OMPC_DEPEND_sink ||
getDependencyKind() == OMPC_DEPEND_source) &&
NumLoop < NumLoops &&
"Expected sink or source depend + loop index must be less number of "
"loops.");
auto It = std::next(getVarRefs().end(), NumLoop);
return *It;
}
Expr *OMPDependClause::getCounterValue() {
auto *V = *getVarRefs().end();
assert(getDependencyKind() == OMPC_DEPEND_sink ||
getDependencyKind() == OMPC_DEPEND_source || V == nullptr);
return V;
const Expr *OMPDependClause::getLoopData(unsigned NumLoop) const {
assert((getDependencyKind() == OMPC_DEPEND_sink ||
getDependencyKind() == OMPC_DEPEND_source) &&
NumLoop < NumLoops &&
"Expected sink or source depend + loop index must be less number of "
"loops.");
auto It = std::next(getVarRefs().end(), NumLoop);
return *It;
}
unsigned OMPClauseMappableExprCommon::getComponentsTotalNumber(

92
clang/lib/CodeGen/CGOpenMPRuntime.cpp
View File

@ -8811,7 +8811,8 @@ public:
} // namespace
void CGOpenMPRuntime::emitDoacrossInit(CodeGenFunction &CGF,
const OMPLoopDirective &D) {
const OMPLoopDirective &D,
ArrayRef<Expr *> NumIterations) {
if (!CGF.HaveInsertPoint())
return;
@ -8834,32 +8835,45 @@ void CGOpenMPRuntime::emitDoacrossInit(CodeGenFunction &CGF,
} else {
RD = cast<RecordDecl>(KmpDimTy->getAsTagDecl());
}
llvm::APInt Size(/*numBits=*/32, NumIterations.size());
QualType ArrayTy =
C.getConstantArrayType(KmpDimTy, Size, ArrayType::Normal, 0);
Address DimsAddr = CGF.CreateMemTemp(KmpDimTy, "dims");
CGF.EmitNullInitialization(DimsAddr, KmpDimTy);
Address DimsAddr = CGF.CreateMemTemp(ArrayTy, "dims");
CGF.EmitNullInitialization(DimsAddr, ArrayTy);
enum { LowerFD = 0, UpperFD, StrideFD };
// Fill dims with data.
LValue DimsLVal = CGF.MakeAddrLValue(DimsAddr, KmpDimTy);
// dims.upper = num_iterations;
LValue UpperLVal =
CGF.EmitLValueForField(DimsLVal, *std::next(RD->field_begin(), UpperFD));
llvm::Value *NumIterVal = CGF.EmitScalarConversion(
CGF.EmitScalarExpr(D.getNumIterations()), D.getNumIterations()->getType(),
Int64Ty, D.getNumIterations()->getExprLoc());
CGF.EmitStoreOfScalar(NumIterVal, UpperLVal);
// dims.stride = 1;
LValue StrideLVal =
CGF.EmitLValueForField(DimsLVal, *std::next(RD->field_begin(), StrideFD));
CGF.EmitStoreOfScalar(llvm::ConstantInt::getSigned(CGM.Int64Ty, /*V=*/1),
StrideLVal);
for (unsigned I = 0, E = NumIterations.size(); I < E; ++I) {
LValue DimsLVal =
CGF.MakeAddrLValue(CGF.Builder.CreateConstArrayGEP(
DimsAddr, I, C.getTypeSizeInChars(KmpDimTy)),
KmpDimTy);
// dims.upper = num_iterations;
LValue UpperLVal = CGF.EmitLValueForField(
DimsLVal, *std::next(RD->field_begin(), UpperFD));
llvm::Value *NumIterVal =
CGF.EmitScalarConversion(CGF.EmitScalarExpr(NumIterations[I]),
D.getNumIterations()->getType(), Int64Ty,
D.getNumIterations()->getExprLoc());
CGF.EmitStoreOfScalar(NumIterVal, UpperLVal);
// dims.stride = 1;
LValue StrideLVal = CGF.EmitLValueForField(
DimsLVal, *std::next(RD->field_begin(), StrideFD));
CGF.EmitStoreOfScalar(llvm::ConstantInt::getSigned(CGM.Int64Ty, /*V=*/1),
StrideLVal);
}
// Build call void __kmpc_doacross_init(ident_t *loc, kmp_int32 gtid,
// kmp_int32 num_dims, struct kmp_dim * dims);
llvm::Value *Args[] = {emitUpdateLocation(CGF, D.getBeginLoc()),
getThreadID(CGF, D.getBeginLoc()),
llvm::ConstantInt::getSigned(CGM.Int32Ty, 1),
CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(
DimsAddr.getPointer(), CGM.VoidPtrTy)};
llvm::Value *Args[] = {
emitUpdateLocation(CGF, D.getBeginLoc()),
getThreadID(CGF, D.getBeginLoc()),
llvm::ConstantInt::getSigned(CGM.Int32Ty, NumIterations.size()),
CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(
CGF.Builder
.CreateConstArrayGEP(DimsAddr, 0, C.getTypeSizeInChars(KmpDimTy))
.getPointer(),
CGM.VoidPtrTy)};
llvm::Value *RTLFn = createRuntimeFunction(OMPRTL__kmpc_doacross_init);
CGF.EmitRuntimeCall(RTLFn, Args);
@ -8874,16 +8888,29 @@ void CGOpenMPRuntime::emitDoacrossOrdered(CodeGenFunction &CGF,
const OMPDependClause *C) {
QualType Int64Ty =
CGM.getContext().getIntTypeForBitwidth(/*DestWidth=*/64, /*Signed=*/1);
const Expr *CounterVal = C->getCounterValue();
assert(CounterVal);
llvm::Value *CntVal = CGF.EmitScalarConversion(CGF.EmitScalarExpr(CounterVal),
CounterVal->getType(), Int64Ty,
CounterVal->getExprLoc());
Address CntAddr = CGF.CreateMemTemp(Int64Ty, ".cnt.addr");
CGF.EmitStoreOfScalar(CntVal, CntAddr, /*Volatile=*/false, Int64Ty);
llvm::Value *Args[] = {emitUpdateLocation(CGF, C->getBeginLoc()),
getThreadID(CGF, C->getBeginLoc()),
CntAddr.getPointer()};
llvm::APInt Size(/*numBits=*/32, C->getNumLoops());
QualType ArrayTy = CGM.getContext().getConstantArrayType(
Int64Ty, Size, ArrayType::Normal, 0);
Address CntAddr = CGF.CreateMemTemp(ArrayTy, ".cnt.addr");
for (unsigned I = 0, E = C->getNumLoops(); I < E; ++I) {
const Expr *CounterVal = C->getLoopData(I);
assert(CounterVal);
llvm::Value *CntVal = CGF.EmitScalarConversion(
CGF.EmitScalarExpr(CounterVal), CounterVal->getType(), Int64Ty,
CounterVal->getExprLoc());
CGF.EmitStoreOfScalar(
CntVal,
CGF.Builder.CreateConstArrayGEP(
CntAddr, I, CGM.getContext().getTypeSizeInChars(Int64Ty)),
/*Volatile=*/false, Int64Ty);
}
llvm::Value *Args[] = {
emitUpdateLocation(CGF, C->getBeginLoc()),
getThreadID(CGF, C->getBeginLoc()),
CGF.Builder
.CreateConstArrayGEP(CntAddr, 0,
CGM.getContext().getTypeSizeInChars(Int64Ty))
.getPointer()};
llvm::Value *RTLFn;
if (C->getDependencyKind() == OMPC_DEPEND_source) {
RTLFn = createRuntimeFunction(OMPRTL__kmpc_doacross_post);
@ -9198,7 +9225,8 @@ void CGOpenMPSIMDRuntime::emitTargetDataStandAloneCall(
}
void CGOpenMPSIMDRuntime::emitDoacrossInit(CodeGenFunction &CGF,
const OMPLoopDirective &D) {
const OMPLoopDirective &D,
ArrayRef<Expr *> NumIterations) {
llvm_unreachable("Not supported in SIMD-only mode");
}

8
clang/lib/CodeGen/CGOpenMPRuntime.h
View File

@ -1469,8 +1469,8 @@ public:
/// Emit initialization for doacross loop nesting support.
/// \param D Loop-based construct used in doacross nesting construct.
virtual void emitDoacrossInit(CodeGenFunction &CGF,
const OMPLoopDirective &D);
virtual void emitDoacrossInit(CodeGenFunction &CGF, const OMPLoopDirective &D,
ArrayRef<Expr *> NumIterations);
/// Emit code for doacross ordered directive with 'depend' clause.
/// \param C 'depend' clause with 'sink|source' dependency kind.
@ -2057,8 +2057,8 @@ public:
/// Emit initialization for doacross loop nesting support.
/// \param D Loop-based construct used in doacross nesting construct.
void emitDoacrossInit(CodeGenFunction &CGF,
const OMPLoopDirective &D) override;
void emitDoacrossInit(CodeGenFunction &CGF, const OMPLoopDirective &D,
ArrayRef<Expr *> NumIterations) override;
/// Emit code for doacross ordered directive with 'depend' clause.
/// \param C 'depend' clause with 'sink|source' dependency kind.

33
clang/lib/CodeGen/CGStmtOpenMP.cpp
View File

@ -1509,6 +1509,23 @@ void CodeGenFunction::EmitOMPPrivateLoopCounters(
}
++I;
}
// Privatize extra loop counters used in loops for ordered(n) clauses.
for (const auto *C : S.getClausesOfKind<OMPOrderedClause>()) {
if (!C->getNumForLoops())
continue;
for (unsigned I = S.getCollapsedNumber(),
E = C->getLoopNumIterations().size();
I < E; ++I) {
const auto *DRE = cast<DeclRefExpr>(C->getLoopCunter(I));
const auto *VD = cast<VarDecl>(DRE->getDecl());
// Override only those variables that are really emitted already.
if (LocalDeclMap.count(VD)) {
(void)LoopScope.addPrivate(VD, [this, DRE, VD]() {
return CreateMemTemp(DRE->getType(), VD->getName());
});
}
}
}
}
static void emitPreCond(CodeGenFunction &CGF, const OMPLoopDirective &S,
@ -2244,7 +2261,7 @@ bool CodeGenFunction::EmitOMPWorksharingLoop(
bool Ordered = false;
if (const auto *OrderedClause = S.getSingleClause<OMPOrderedClause>()) {
if (OrderedClause->getNumForLoops())
RT.emitDoacrossInit(*this, S);
RT.emitDoacrossInit(*this, S, OrderedClause->getLoopNumIterations());
else
Ordered = true;
}
@ -4942,6 +4959,20 @@ void CodeGenFunction::EmitSimpleOMPExecutableDirective(
CGF.EmitVarDecl(*VD);
}
}
for (const auto *C : D.getClausesOfKind<OMPOrderedClause>()) {
if (!C->getNumForLoops())
continue;
for (unsigned I = LD->getCollapsedNumber(),
E = C->getLoopNumIterations().size();
I < E; ++I) {
if (const auto *VD = dyn_cast<OMPCapturedExprDecl>(
cast<DeclRefExpr>(C->getLoopCunter(I))->getDecl())) {
// Emit only those that were not explicitly referenced in clauses.
if (!CGF.LocalDeclMap.count(VD))
CGF.EmitVarDecl(*VD);
}
}
}
}
CGF.EmitStmt(D.getInnermostCapturedStmt()->getCapturedStmt());
}

269
clang/lib/Sema/SemaOpenMP.cpp
View File

@ -73,6 +73,8 @@ public:
};
using OperatorOffsetTy =
llvm::SmallVector<std::pair<Expr *, OverloadedOperatorKind>, 4>;
using DoacrossDependMapTy =
llvm::DenseMap<OMPDependClause *, OperatorOffsetTy>;
private:
struct DSAInfo {
@ -97,8 +99,6 @@ private:
llvm::DenseMap<const ValueDecl *, MappedExprComponentTy>;
using CriticalsWithHintsTy =
llvm::StringMap<std::pair<const OMPCriticalDirective *, llvm::APSInt>>;
using DoacrossDependMapTy =
llvm::DenseMap<OMPDependClause *, OperatorOffsetTy>;
struct ReductionData {
using BOKPtrType = llvm::PointerEmbeddedInt<BinaryOperatorKind, 16>;
SourceRange ReductionRange;
@ -137,7 +137,7 @@ private:
/// first argument (Expr *) contains optional argument of the
/// 'ordered' clause, the second one is true if the regions has 'ordered'
/// clause, false otherwise.
llvm::PointerIntPair<const Expr *, 1, bool> OrderedRegion;
llvm::Optional<std::pair<const Expr *, OMPOrderedClause *>> OrderedRegion;
bool NowaitRegion = false;
bool CancelRegion = false;
unsigned AssociatedLoops = 1;
@ -398,23 +398,42 @@ public:
}
/// Marks current region as ordered (it has an 'ordered' clause).
void setOrderedRegion(bool IsOrdered, const Expr *Param) {
void setOrderedRegion(bool IsOrdered, const Expr *Param,
OMPOrderedClause *Clause) {
assert(!isStackEmpty());
Stack.back().first.back().OrderedRegion.setInt(IsOrdered);
Stack.back().first.back().OrderedRegion.setPointer(Param);
if (IsOrdered)
Stack.back().first.back().OrderedRegion.emplace(Param, Clause);
else
Stack.back().first.back().OrderedRegion.reset();
}
/// Returns true, if region is ordered (has associated 'ordered' clause),
/// false - otherwise.
bool isOrderedRegion() const {
if (isStackEmpty())
return false;
return Stack.back().first.rbegin()->OrderedRegion.hasValue();
}
/// Returns optional parameter for the ordered region.
std::pair<const Expr *, OMPOrderedClause *> getOrderedRegionParam() const {
if (isStackEmpty() ||
!Stack.back().first.rbegin()->OrderedRegion.hasValue())
return std::make_pair(nullptr, nullptr);
return Stack.back().first.rbegin()->OrderedRegion.getValue();
}
/// Returns true, if parent region is ordered (has associated
/// 'ordered' clause), false - otherwise.
bool isParentOrderedRegion() const {
if (isStackEmpty() || Stack.back().first.size() == 1)
return false;
return std::next(Stack.back().first.rbegin())->OrderedRegion.getInt();
return std::next(Stack.back().first.rbegin())->OrderedRegion.hasValue();
}
/// Returns optional parameter for the ordered region.
const Expr *getParentOrderedRegionParam() const {
if (isStackEmpty() || Stack.back().first.size() == 1)
return nullptr;
return std::next(Stack.back().first.rbegin())->OrderedRegion.getPointer();
std::pair<const Expr *, OMPOrderedClause *>
getParentOrderedRegionParam() const {
if (isStackEmpty() || Stack.back().first.size() == 1 ||
!std::next(Stack.back().first.rbegin())->OrderedRegion.hasValue())
return std::make_pair(nullptr, nullptr);
return std::next(Stack.back().first.rbegin())->OrderedRegion.getValue();
}
/// Marks current region as nowait (it has a 'nowait' clause).
void setNowaitRegion(bool IsNowait = true) {
@ -3745,6 +3764,13 @@ public:
Expr *buildCounterInit() const;
/// Build step of the counter be used for codegen.
Expr *buildCounterStep() const;
/// Build loop data with counter value for depend clauses in ordered
/// directives.
Expr *
buildOrderedLoopData(Scope *S, Expr *Counter,
llvm::MapVector<const Expr *, DeclRefExpr *> &Captures,
SourceLocation Loc, Expr *Inc = nullptr,
OverloadedOperatorKind OOK = OO_Amp);
/// Return true if any expression is dependent.
bool dependent() const;
@ -3909,7 +3935,12 @@ bool OpenMPIterationSpaceChecker::checkAndSetInit(Stmt *S, bool EmitDiags) {
SemaRef.Diag(S->getBeginLoc(),
diag::ext_omp_loop_not_canonical_init)
<< S->getSourceRange();
return setLCDeclAndLB(Var, nullptr, Var->getInit());
return setLCDeclAndLB(
Var,
buildDeclRefExpr(SemaRef, Var,
Var->getType().getNonReferenceType(),
DS->getBeginLoc()),
Var->getInit());
}
}
}
@ -4271,7 +4302,8 @@ Expr *OpenMPIterationSpaceChecker::buildPreCond(
/// Build reference expression to the counter be used for codegen.
DeclRefExpr *OpenMPIterationSpaceChecker::buildCounterVar(
llvm::MapVector<const Expr *, DeclRefExpr *> &Captures, DSAStackTy &DSA) const {
llvm::MapVector<const Expr *, DeclRefExpr *> &Captures,
DSAStackTy &DSA) const {
auto *VD = dyn_cast<VarDecl>(LCDecl);
if (!VD) {
VD = SemaRef.isOpenMPCapturedDecl(LCDecl);
@ -4311,6 +4343,63 @@ Expr *OpenMPIterationSpaceChecker::buildCounterInit() const { return LB; }
/// Build step of the counter be used for codegen.
Expr *OpenMPIterationSpaceChecker::buildCounterStep() const { return Step; }
Expr *OpenMPIterationSpaceChecker::buildOrderedLoopData(
Scope *S, Expr *Counter,
llvm::MapVector<const Expr *, DeclRefExpr *> &Captures, SourceLocation Loc,
Expr *Inc, OverloadedOperatorKind OOK) {
Expr *Cnt = SemaRef.DefaultLvalueConversion(Counter).get();
if (!Cnt)
return nullptr;
if (Inc) {
assert((OOK == OO_Plus || OOK == OO_Minus) &&
"Expected only + or - operations for depend clauses.");
BinaryOperatorKind BOK = (OOK == OO_Plus) ? BO_Add : BO_Sub;
Cnt = SemaRef.BuildBinOp(S, Loc, BOK, Cnt, Inc).get();
if (!Cnt)
return nullptr;
}
ExprResult Diff;
QualType VarType = LCDecl->getType().getNonReferenceType();
if (VarType->isIntegerType() || VarType->isPointerType() ||
SemaRef.getLangOpts().CPlusPlus) {
// Upper - Lower
Expr *Upper =
TestIsLessOp ? Cnt : tryBuildCapture(SemaRef, UB, Captures).get();
Expr *Lower =
TestIsLessOp ? tryBuildCapture(SemaRef, LB, Captures).get() : Cnt;
if (!Upper || !Lower)
return nullptr;
Diff = SemaRef.BuildBinOp(S, DefaultLoc, BO_Sub, Upper, Lower);
if (!Diff.isUsable() && VarType->getAsCXXRecordDecl()) {
// BuildBinOp already emitted error, this one is to point user to upper
// and lower bound, and to tell what is passed to 'operator-'.
SemaRef.Diag(Upper->getBeginLoc(), diag::err_omp_loop_diff_cxx)
<< Upper->getSourceRange() << Lower->getSourceRange();
return nullptr;
}
}
if (!Diff.isUsable())
return nullptr;
// Parentheses (for dumping/debugging purposes only).
Diff = SemaRef.ActOnParenExpr(DefaultLoc, DefaultLoc, Diff.get());
if (!Diff.isUsable())
return nullptr;
ExprResult NewStep = tryBuildCapture(SemaRef, Step, Captures);
if (!NewStep.isUsable())
return nullptr;
// (Upper - Lower) / Step
Diff = SemaRef.BuildBinOp(S, DefaultLoc, BO_Div, Diff.get(), NewStep.get());
if (!Diff.isUsable())
return nullptr;
return Diff.get();
}
/// Iteration space of a single for loop.
struct LoopIterationSpace final {
/// Condition of the loop.
@ -4370,7 +4459,8 @@ void Sema::ActOnOpenMPLoopInitialization(SourceLocation ForLoc, Stmt *Init) {
static bool checkOpenMPIterationSpace(
OpenMPDirectiveKind DKind, Stmt *S, Sema &SemaRef, DSAStackTy &DSA,
unsigned CurrentNestedLoopCount, unsigned NestedLoopCount,
Expr *CollapseLoopCountExpr, Expr *OrderedLoopCountExpr,
unsigned TotalNestedLoopCount, Expr *CollapseLoopCountExpr,
Expr *OrderedLoopCountExpr,
Sema::VarsWithInheritedDSAType &VarsWithImplicitDSA,
LoopIterationSpace &ResultIterSpace,
llvm::MapVector<const Expr *, DeclRefExpr *> &Captures) {
@ -4380,9 +4470,9 @@ static bool checkOpenMPIterationSpace(
if (!For) {
SemaRef.Diag(S->getBeginLoc(), diag::err_omp_not_for)
<< (CollapseLoopCountExpr != nullptr || OrderedLoopCountExpr != nullptr)
<< getOpenMPDirectiveName(DKind) << NestedLoopCount
<< getOpenMPDirectiveName(DKind) << TotalNestedLoopCount
<< (CurrentNestedLoopCount > 0) << CurrentNestedLoopCount;
if (NestedLoopCount > 1) {
if (TotalNestedLoopCount > 1) {
if (CollapseLoopCountExpr && OrderedLoopCountExpr)
SemaRef.Diag(DSA.getConstructLoc(),
diag::note_omp_collapse_ordered_expr)
@ -4515,6 +4605,41 @@ static bool checkOpenMPIterationSpace(
ResultIterSpace.PrivateCounterVar == nullptr ||
ResultIterSpace.CounterInit == nullptr ||
ResultIterSpace.CounterStep == nullptr);
if (!HasErrors && DSA.isOrderedRegion()) {
if (DSA.getOrderedRegionParam().second->getNumForLoops()) {
if (CurrentNestedLoopCount <
DSA.getOrderedRegionParam().second->getLoopNumIterations().size()) {
DSA.getOrderedRegionParam().second->setLoopNumIterations(
CurrentNestedLoopCount, ResultIterSpace.NumIterations);
DSA.getOrderedRegionParam().second->setLoopCounter(
CurrentNestedLoopCount, ResultIterSpace.CounterVar);
}
}
for (auto &Pair : DSA.getDoacrossDependClauses()) {
if (CurrentNestedLoopCount >= Pair.first->getNumLoops()) {
// Erroneous case - clause has some problems.
continue;
}
if (Pair.first->getDependencyKind() == OMPC_DEPEND_sink &&
Pair.second.size() <= CurrentNestedLoopCount) {
// Erroneous case - clause has some problems.
Pair.first->setLoopData(CurrentNestedLoopCount, nullptr);
continue;
}
Expr *CntValue;
if (Pair.first->getDependencyKind() == OMPC_DEPEND_source)
CntValue = ISC.buildOrderedLoopData(
DSA.getCurScope(), ResultIterSpace.CounterVar, Captures,
Pair.first->getDependencyLoc());
else
CntValue = ISC.buildOrderedLoopData(
DSA.getCurScope(), ResultIterSpace.CounterVar, Captures,
Pair.first->getDependencyLoc(),
Pair.second[CurrentNestedLoopCount].first,
Pair.second[CurrentNestedLoopCount].second);
Pair.first->setLoopData(CurrentNestedLoopCount, CntValue);
}
}
return HasErrors;
}
@ -4700,6 +4825,7 @@ checkOpenMPLoop(OpenMPDirectiveKind DKind, Expr *CollapseLoopCountExpr,
if (CollapseLoopCountExpr->EvaluateAsInt(Result, SemaRef.getASTContext()))
NestedLoopCount = Result.getLimitedValue();
}
unsigned OrderedLoopCount = 1;
if (OrderedLoopCountExpr) {
// Found 'ordered' clause - calculate collapse number.
llvm::APSInt Result;
@ -4712,20 +4838,21 @@ checkOpenMPLoop(OpenMPDirectiveKind DKind, Expr *CollapseLoopCountExpr,
diag::note_collapse_loop_count)
<< CollapseLoopCountExpr->getSourceRange();
}
NestedLoopCount = Result.getLimitedValue();
OrderedLoopCount = Result.getLimitedValue();
}
}
// This is helper routine for loop directives (e.g., 'for', 'simd',
// 'for simd', etc.).
llvm::MapVector<const Expr *, DeclRefExpr *> Captures;
SmallVector<LoopIterationSpace, 4> IterSpaces;
IterSpaces.resize(NestedLoopCount);
IterSpaces.resize(std::max(OrderedLoopCount, NestedLoopCount));
Stmt *CurStmt = AStmt->IgnoreContainers(/* IgnoreCaptured */ true);
for (unsigned Cnt = 0; Cnt < NestedLoopCount; ++Cnt) {
if (checkOpenMPIterationSpace(DKind, CurStmt, SemaRef, DSA, Cnt,
NestedLoopCount, CollapseLoopCountExpr,
OrderedLoopCountExpr, VarsWithImplicitDSA,
IterSpaces[Cnt], Captures))
if (checkOpenMPIterationSpace(
DKind, CurStmt, SemaRef, DSA, Cnt, NestedLoopCount,
std::max(OrderedLoopCount, NestedLoopCount), CollapseLoopCountExpr,
OrderedLoopCountExpr, VarsWithImplicitDSA, IterSpaces[Cnt],
Captures))
return 0;
// Move on to the next nested for loop, or to the loop body.
// OpenMP [2.8.1, simd construct, Restrictions]
@ -4734,6 +4861,27 @@ checkOpenMPLoop(OpenMPDirectiveKind DKind, Expr *CollapseLoopCountExpr,
// any two loops.
CurStmt = cast<ForStmt>(CurStmt)->getBody()->IgnoreContainers();
}
for (unsigned Cnt = NestedLoopCount; Cnt < OrderedLoopCount; ++Cnt) {
if (checkOpenMPIterationSpace(
DKind, CurStmt, SemaRef, DSA, Cnt, NestedLoopCount,
std::max(OrderedLoopCount, NestedLoopCount), CollapseLoopCountExpr,
OrderedLoopCountExpr, VarsWithImplicitDSA, IterSpaces[Cnt],
Captures))
return 0;
if (Cnt > 0 && IterSpaces[Cnt].CounterVar) {
// Handle initialization of captured loop iterator variables.
auto *DRE = cast<DeclRefExpr>(IterSpaces[Cnt].CounterVar);
if (isa<OMPCapturedExprDecl>(DRE->getDecl())) {
Captures[DRE] = DRE;
}
}
// Move on to the next nested for loop, or to the loop body.
// OpenMP [2.8.1, simd construct, Restrictions]
// All loops associated with the construct must be perfectly nested; that
// is, there must be no intervening code nor any OpenMP directive between
// any two loops.
CurStmt = cast<ForStmt>(CurStmt)->getBody()->IgnoreContainers();
}
Built.clear(/* size */ NestedLoopCount);
@ -5113,7 +5261,6 @@ checkOpenMPLoop(OpenMPDirectiveKind DKind, Expr *CollapseLoopCountExpr,
Built.Inits.resize(NestedLoopCount);
Built.Updates.resize(NestedLoopCount);
Built.Finals.resize(NestedLoopCount);
SmallVector<Expr *, 4> LoopMultipliers;
{
ExprResult Div;
// Go from inner nested loop to outer.
@ -5183,7 +5330,6 @@ checkOpenMPLoop(OpenMPDirectiveKind DKind, Expr *CollapseLoopCountExpr,
HasErrors = true;
break;
}
LoopMultipliers.push_back(Div.get());
}
if (!Update.isUsable() || !Final.isUsable()) {
HasErrors = true;
@ -5231,55 +5377,6 @@ checkOpenMPLoop(OpenMPDirectiveKind DKind, Expr *CollapseLoopCountExpr,
Built.DistCombinedFields.NLB = CombNextLB.get();
Built.DistCombinedFields.NUB = CombNextUB.get();
Expr *CounterVal = SemaRef.DefaultLvalueConversion(IV.get()).get();
// Fill data for doacross depend clauses.
for (const auto &Pair : DSA.getDoacrossDependClauses()) {
if (Pair.first->getDependencyKind() == OMPC_DEPEND_source) {
Pair.first->setCounterValue(CounterVal);
} else {
if (NestedLoopCount != Pair.second.size() ||
NestedLoopCount != LoopMultipliers.size() + 1) {
// Erroneous case - clause has some problems.
Pair.first->setCounterValue(CounterVal);
continue;
}
assert(Pair.first->getDependencyKind() == OMPC_DEPEND_sink);
auto I = Pair.second.rbegin();
auto IS = IterSpaces.rbegin();
auto ILM = LoopMultipliers.rbegin();
Expr *UpCounterVal = CounterVal;
Expr *Multiplier = nullptr;
for (int Cnt = NestedLoopCount - 1; Cnt >= 0; --Cnt) {
if (I->first) {
assert(IS->CounterStep);
Expr *NormalizedOffset =
SemaRef
.BuildBinOp(CurScope, I->first->getExprLoc(), BO_Div,
I->first, IS->CounterStep)
.get();
if (Multiplier) {
NormalizedOffset =
SemaRef
.BuildBinOp(CurScope, I->first->getExprLoc(), BO_Mul,
NormalizedOffset, Multiplier)
.get();
}
assert(I->second == OO_Plus || I->second == OO_Minus);
BinaryOperatorKind BOK = (I->second == OO_Plus) ? BO_Add : BO_Sub;
UpCounterVal = SemaRef
.BuildBinOp(CurScope, I->first->getExprLoc(), BOK,
UpCounterVal, NormalizedOffset)
.get();
}
Multiplier = *ILM;
++I;
++IS;
++ILM;
}
Pair.first->setCounterValue(UpCounterVal);
}
}
return NestedLoopCount;
}
@ -5847,12 +5944,12 @@ StmtResult Sema::ActOnOpenMPOrderedDirective(ArrayRef<OMPClause *> Clauses,
Diag(DependFound->getBeginLoc(), diag::err_omp_depend_clause_thread_simd)
<< getOpenMPClauseName(TC ? TC->getClauseKind() : SC->getClauseKind());
ErrorFound = true;
} else if (DependFound && !DSAStack->getParentOrderedRegionParam()) {
} else if (DependFound && !DSAStack->getParentOrderedRegionParam().first) {
Diag(DependFound->getBeginLoc(),
diag::err_omp_ordered_directive_without_param);
ErrorFound = true;
} else if (TC || Clauses.empty()) {
if (const Expr *Param = DSAStack->getParentOrderedRegionParam()) {
if (const Expr *Param = DSAStack->getParentOrderedRegionParam().first) {
SourceLocation ErrLoc = TC ? TC->getBeginLoc() : StartLoc;
Diag(ErrLoc, diag::err_omp_ordered_directive_with_param)
<< (TC != nullptr);
@ -8628,9 +8725,11 @@ OMPClause *Sema::ActOnOpenMPOrderedClause(SourceLocation StartLoc,
} else {
NumForLoops = nullptr;
}
DSAStack->setOrderedRegion(/*IsOrdered=*/true, NumForLoops);
return new (Context)
OMPOrderedClause(NumForLoops, StartLoc, LParenLoc, EndLoc);
auto *Clause = OMPOrderedClause::Create(
Context, NumForLoops, NumForLoops ? DSAStack->getAssociatedLoops() : 0,
StartLoc, LParenLoc, EndLoc);
DSAStack->setOrderedRegion(/*IsOrdered=*/true, NumForLoops, Clause);
return Clause;
}
OMPClause *Sema::ActOnOpenMPSimpleClause(
@ -11486,8 +11585,9 @@ Sema::ActOnOpenMPDependClause(OpenMPDependClauseKind DepKind,
DSAStackTy::OperatorOffsetTy OpsOffs;
llvm::APSInt DepCounter(/*BitWidth=*/32);
llvm::APSInt TotalDepCount(/*BitWidth=*/32);
if (DepKind == OMPC_DEPEND_sink) {
if (const Expr *OrderedCountExpr = DSAStack->getParentOrderedRegionParam()) {
if (DepKind == OMPC_DEPEND_sink || DepKind == OMPC_DEPEND_source) {
if (const Expr *OrderedCountExpr =
DSAStack->getParentOrderedRegionParam().first) {
TotalDepCount = OrderedCountExpr->EvaluateKnownConstInt(Context);
TotalDepCount.setIsUnsigned(/*Val=*/true);
}
@ -11503,7 +11603,7 @@ Sema::ActOnOpenMPDependClause(OpenMPDependClauseKind DepKind,
SourceLocation ELoc = RefExpr->getExprLoc();
Expr *SimpleExpr = RefExpr->IgnoreParenCasts();
if (DepKind == OMPC_DEPEND_sink) {
if (DSAStack->getParentOrderedRegionParam() &&
if (DSAStack->getParentOrderedRegionParam().first &&
DepCounter >= TotalDepCount) {
Diag(ELoc, diag::err_omp_depend_sink_unexpected_expr);
continue;
@ -11569,7 +11669,7 @@ Sema::ActOnOpenMPDependClause(OpenMPDependClauseKind DepKind,
continue;
}
if (!CurContext->isDependentContext() &&
DSAStack->getParentOrderedRegionParam() &&
DSAStack->getParentOrderedRegionParam().first &&
DepCounter != DSAStack->isParentLoopControlVariable(D).first) {
const ValueDecl *VD =
DSAStack->getParentLoopControlVariable(DepCounter.getZExtValue());
@ -11607,7 +11707,7 @@ Sema::ActOnOpenMPDependClause(OpenMPDependClauseKind DepKind,
if (!CurContext->isDependentContext() && DepKind == OMPC_DEPEND_sink &&
TotalDepCount > VarList.size() &&
DSAStack->getParentOrderedRegionParam() &&
DSAStack->getParentOrderedRegionParam().first &&
DSAStack->getParentLoopControlVariable(VarList.size() + 1)) {
Diag(EndLoc, diag::err_omp_depend_sink_expected_loop_iteration)
<< 1 << DSAStack->getParentLoopControlVariable(VarList.size() + 1);
@ -11617,7 +11717,8 @@ Sema::ActOnOpenMPDependClause(OpenMPDependClauseKind DepKind,
return nullptr;
auto *C = OMPDependClause::Create(Context, StartLoc, LParenLoc, EndLoc,
DepKind, DepLoc, ColonLoc, Vars);
DepKind, DepLoc, ColonLoc, Vars,
TotalDepCount.getZExtValue());
if ((DepKind == OMPC_DEPEND_sink || DepKind == OMPC_DEPEND_source) &&
DSAStack->isParentOrderedRegion())
DSAStack->addDoacrossDependClause(C, OpsOffs);

18
clang/lib/Serialization/ASTReaderStmt.cpp
View File

@ -1856,7 +1856,7 @@ OMPClause *OMPClauseReader::readClause() {
C = new (Context) OMPScheduleClause();
break;
case OMPC_ordered:
C = new (Context) OMPOrderedClause();
C = OMPOrderedClause::CreateEmpty(Context, Reader->Record.readInt());
break;
case OMPC_nowait:
C = new (Context) OMPNowaitClause();
@ -1927,9 +1927,12 @@ OMPClause *OMPClauseReader::readClause() {
case OMPC_flush:
C = OMPFlushClause::CreateEmpty(Context, Reader->Record.readInt());
break;
case OMPC_depend:
C = OMPDependClause::CreateEmpty(Context, Reader->Record.readInt());
case OMPC_depend: {
unsigned NumVars = Reader->Record.readInt();
unsigned NumLoops = Reader->Record.readInt();
C = OMPDependClause::CreateEmpty(Context, NumVars, NumLoops);
break;
}
case OMPC_device:
C = new (Context) OMPDeviceClause();
break;
@ -2087,6 +2090,10 @@ void OMPClauseReader::VisitOMPScheduleClause(OMPScheduleClause *C) {
void OMPClauseReader::VisitOMPOrderedClause(OMPOrderedClause *C) {
C->setNumForLoops(Reader->Record.readSubExpr());
for (unsigned I = 0, E = C->NumberOfLoops; I < E; ++I)
C->setLoopNumIterations(I, Reader->Record.readSubExpr());
for (unsigned I = 0, E = C->NumberOfLoops; I < E; ++I)
C->setLoopCounter(I, Reader->Record.readSubExpr());
C->setLParenLoc(Reader->ReadSourceLocation());
}
@ -2395,10 +2402,11 @@ void OMPClauseReader::VisitOMPDependClause(OMPDependClause *C) {
unsigned NumVars = C->varlist_size();
SmallVector<Expr *, 16> Vars;
Vars.reserve(NumVars);
for (unsigned i = 0; i != NumVars; ++i)
for (unsigned I = 0; I != NumVars; ++I)
Vars.push_back(Reader->Record.readSubExpr());
C->setVarRefs(Vars);
C->setCounterValue(Reader->Record.readSubExpr());
for (unsigned I = 0, E = C->getNumLoops(); I < E; ++I)
C->setLoopData(I, Reader->Record.readSubExpr());
}
void OMPClauseReader::VisitOMPDeviceClause(OMPDeviceClause *C) {

9
clang/lib/Serialization/ASTWriterStmt.cpp
View File

@ -1898,7 +1898,12 @@ void OMPClauseWriter::VisitOMPScheduleClause(OMPScheduleClause *C) {
}
void OMPClauseWriter::VisitOMPOrderedClause(OMPOrderedClause *C) {
Record.push_back(C->getLoopNumIterations().size());
Record.AddStmt(C->getNumForLoops());
for (Expr *NumIter : C->getLoopNumIterations())
Record.AddStmt(NumIter);
for (unsigned I = 0, E = C->getLoopNumIterations().size(); I <E; ++I)
Record.AddStmt(C->getLoopCunter(I));
Record.AddSourceLocation(C->getLParenLoc());
}
@ -2102,13 +2107,15 @@ void OMPClauseWriter::VisitOMPFlushClause(OMPFlushClause *C) {
void OMPClauseWriter::VisitOMPDependClause(OMPDependClause *C) {
Record.push_back(C->varlist_size());
Record.push_back(C->getNumLoops());
Record.AddSourceLocation(C->getLParenLoc());
Record.push_back(C->getDependencyKind());
Record.AddSourceLocation(C->getDependencyLoc());
Record.AddSourceLocation(C->getColonLoc());
for (auto *VE : C->varlists())
Record.AddStmt(VE);
Record.AddStmt(C->getCounterValue());
for (unsigned I = 0, E = C->getNumLoops(); I < E; ++I)
Record.AddStmt(C->getLoopData(I));
}
void OMPClauseWriter::VisitOMPDeviceClause(OMPDeviceClause *C) {

28
clang/test/OpenMP/ordered_doacross_codegen.c
View File

@ -19,17 +19,19 @@ void foo();
// CHECK-LABEL: @main()
int main() {
int i;
// CHECK: [[DIMS:%.+]] = alloca [[KMP_DIM]],
// 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 [[KMP_DIM]]* [[DIMS]] to i8*
// 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: getelementptr inbounds [[KMP_DIM]], [[KMP_DIM]]* [[DIMS]], i32 0, i32 1
// 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]]* [[DIMS]], i32 0, i32 2
// CHECK: getelementptr inbounds [[KMP_DIM]], [[KMP_DIM]]* [[DIM]], i32 0, i32 2
// CHECK: store i64 1, i64* %
// CHECK: [[CAST:%.+]] = bitcast [[KMP_DIM]]* [[DIMS]] to i8*
// 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(
#pragma omp for ordered(1)
@ -37,18 +39,26 @@ int main() {
a[i] = b[i] + 1;
foo();
// CHECK: call void [[FOO:.+]](
// CHECK: load i32, i32* [[CNT:%.+]],
// CHECK: load i32, i32* [[I:%.+]],
// CHECK-NEXT: sub nsw i32 %{{.+}}, 0
// CHECK-NEXT: sdiv i32 %{{.+}}, 1
// CHECK-NEXT: sext i32 %{{.+}} to i64
// CHECK-NEXT: store i64 %{{.+}}, i64* [[TMP:%.+]],
// 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* [[CNT]],
// 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: store i64 %{{.+}}, i64* [[TMP:%.+]],
// 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];

113
clang/test/OpenMP/ordered_doacross_codegen.cpp
View File

@ -19,17 +19,19 @@ void foo();
// CHECK-LABEL: @main()
int main() {
int i;
// CHECK: [[DIMS:%.+]] = alloca [[KMP_DIM]],
// 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 [[KMP_DIM]]* [[DIMS]] to i8*
// 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: getelementptr inbounds [[KMP_DIM]], [[KMP_DIM]]* [[DIMS]], i32 0, i32 1
// 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]]* [[DIMS]], i32 0, i32 2
// CHECK: getelementptr inbounds [[KMP_DIM]], [[KMP_DIM]]* [[DIM]], i32 0, i32 2
// CHECK: store i64 1, i64* %
// CHECK: [[CAST:%.+]] = bitcast [[KMP_DIM]]* [[DIMS]] to i8*
// 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(
#pragma omp for ordered(1)
@ -37,18 +39,26 @@ int main() {
a[i] = b[i] + 1;
foo();
// CHECK: invoke void [[FOO:.+]](
// CHECK: load i32, i32* [[CNT:%.+]],
// CHECK: load i32, i32* [[I:%.+]],
// CHECK-NEXT: sub nsw i32 %{{.+}}, 0
// CHECK-NEXT: sdiv i32 %{{.+}}, 1
// CHECK-NEXT: sext i32 %{{.+}} to i64
// CHECK-NEXT: store i64 %{{.+}}, i64* [[TMP:%.+]],
// 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: invoke void [[FOO]]
// CHECK: load i32, i32* [[CNT]],
// 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: store i64 %{{.+}}, i64* [[TMP:%.+]],
// 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];
@ -75,41 +85,84 @@ struct TestStruct {
T bar(T, T, T);
void baz(T, T);
TestStruct() {
// CHECK: [[CNT:%.+]] = alloca i64,
// CHECK: [[DIMS:%.+]] = alloca [[KMP_DIM]],
// CHECK: [[DIMS:%.+]] = alloca [2 x [[KMP_DIM]]],
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT:%.+]])
// CHECK: icmp
// CHECK-NEXT: br i1 %
// CHECK: [[CAST:%.+]] = bitcast [[KMP_DIM]]* [[DIMS]] to i8*
// CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 [[CAST]], i8 0, i64 24, i1 false)
// CHECK: getelementptr inbounds [[KMP_DIM]], [[KMP_DIM]]* [[DIMS]], i32 0, i32 1
// CHECK: store i64 %{{.+}}, i64* %
// CHECK: getelementptr inbounds [[KMP_DIM]], [[KMP_DIM]]* [[DIMS]], i32 0, i32 2
// CHECK: [[CAST:%.+]] = bitcast [2 x [[KMP_DIM]]]* [[DIMS]] to i8*
// CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 [[CAST]], i8 0, i64 48, i1 false)
// CHECK: [[DIM:%.+]] = getelementptr inbounds [2 x [[KMP_DIM]]], [2 x [[KMP_DIM]]]* [[DIMS]], i64 0, i64 0
// CHECK: getelementptr inbounds [[KMP_DIM]], [[KMP_DIM]]* [[DIM]], i32 0, i32 1
// CHECK: store i64 10, i64* %
// CHECK: getelementptr inbounds [[KMP_DIM]], [[KMP_DIM]]* [[DIM]], i32 0, i32 2
// CHECK: store i64 1, i64* %
// CHECK: [[CAST:%.+]] = bitcast [[KMP_DIM]]* [[DIMS]] to i8*
// CHECK: call void @__kmpc_doacross_init([[IDENT]], i32 [[GTID]], i32 1, i8* [[CAST]])
// CHECK: call void @__kmpc_for_static_init_8(
// CHECK: [[DIM:%.+]] = getelementptr inbounds [2 x [[KMP_DIM]]], [2 x [[KMP_DIM]]]* [[DIMS]], i64 0, i64 1
// 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 [2 x [[KMP_DIM]]], [2 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 2, i8* [[CAST]])
// CHECK: call void @__kmpc_for_static_init_4(
#pragma omp for ordered(2)
for (T j = 0; j < M; j++)
for (i = 0; i < n; i += 2) {
a[i][j] = foo(i, j);
// CHECK: invoke {{.+TestStruct.+foo}}
// CHECK: load i64, i64* [[CNT]],
// CHECK-NEXT: sub nsw i64 %{{.+}}, 1
// CHECK-NEXT: store i64 %{{.+}}, i64* [[TMP:%.+]],
// CHECK-NEXT: call void @__kmpc_doacross_wait([[IDENT]], i32 [[GTID]], i64* [[TMP]])
// CHECK-NEXT: load i64, i64* [[CNT]],
// CHECK-NEXT: load i32, i32* %
// CHECK-NEXT: mul nsw i32 1, %
// CHECK: load i32*, i32** %
// CHECK: load i32, i32* %
// CHECK: load i32, i32* %
// CHECK: load i32, i32* [[J:%.+]],
// CHECK-NEXT: sub nsw i32 %{{.+}}, 0
// CHECK-NEXT: sdiv i32 %{{.+}}, 1
// CHECK-NEXT: sext i32 %{{.+}} to i64
// CHECK-NEXT: sub nsw i64 %
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [2 x i64], [2 x i64]* [[CNT:%.+]], i64 0, i64 0
// CHECK-NEXT: store i64 %{{.+}}, i64* [[TMP:%.+]],
// CHECK-NEXT: [[I:%.+]] = load i32*, i32** [[I_REF:%.+]],
// CHECK-NEXT: load i32, i32* [[I]],
// CHECK-NEXT: sub nsw i32 %{{.+}}, 2
// CHECK-NEXT: sub nsw i32 %{{.+}}, 0
// CHECK-NEXT: sdiv i32 %{{.+}}, 2
// CHECK-NEXT: sext i32 %{{.+}} to i64
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [2 x i64], [2 x i64]* [[CNT]], i64 0, i64 1
// CHECK-NEXT: store i64 %{{.+}}, i64* [[TMP]],
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [2 x i64], [2 x i64]* [[CNT]], i64 0, i64 0
// CHECK-NEXT: call void @__kmpc_doacross_wait([[IDENT]], i32 [[GTID]], i64* [[TMP]])
// CHECK-NEXT: load i32, i32* [[J:%.+]],
// CHECK-NEXT: sub nsw i32 %{{.+}}, 1
// CHECK-NEXT: sub nsw i32 %{{.+}}, 0
// CHECK-NEXT: sdiv i32 %{{.+}}, 1
// CHECK-NEXT: sext i32 %{{.+}} to i64
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [2 x i64], [2 x i64]* [[CNT:%.+]], i64 0, i64 0
// CHECK-NEXT: store i64 %{{.+}}, i64* [[TMP:%.+]],
// CHECK-NEXT: [[I:%.+]] = load i32*, i32** [[I_REF]],
// CHECK-NEXT: load i32, i32* [[I]],
// CHECK-NEXT: sub nsw i32 %{{.+}}, 0
// CHECK-NEXT: sdiv i32 %{{.+}}, 2
// CHECK-NEXT: sext i32 %{{.+}} to i64
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [2 x i64], [2 x i64]* [[CNT]], i64 0, i64 1
// CHECK-NEXT: store i64 %{{.+}}, i64* [[TMP]],
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [2 x i64], [2 x i64]* [[CNT]], i64 0, i64 0
// CHECK-NEXT: call void @__kmpc_doacross_wait([[IDENT]], i32 [[GTID]], i64* [[TMP]])
#pragma omp ordered depend(sink : j, i - 2) depend(sink : j - 1, i)
b[i][j] = bar(a[i][j], b[i - 1][j], b[i][j - 1]);
// CHECK: invoke {{.+TestStruct.+bar}}
// CHECK: load i64, i64* [[CNT]],
// CHECK: load i32*, i32** %
// CHECK: load i32, i32* %
// CHECK: load i32, i32* %
// CHECK: load i32, i32* [[J]],
// CHECK-NEXT: sub nsw i32 %{{.+}}, 0
// CHECK-NEXT: sdiv i32 %{{.+}}, 1
// CHECK-NEXT: sext i32 %{{.+}} to i64
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [2 x i64], [2 x i64]* [[CNT:%.+]], i64 0, i64 0
// CHECK-NEXT: store i64 %{{.+}}, i64* [[TMP:%.+]],
// CHECK-NEXT: [[I:%.+]] = load i32*, i32** [[I_REF]],
// CHECK-NEXT: load i32, i32* [[I]],
// CHECK-NEXT: sub nsw i32 %{{.+}}, 0
// CHECK-NEXT: sdiv i32 %{{.+}}, 2
// CHECK-NEXT: sext i32 %{{.+}} to i64
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [2 x i64], [2 x i64]* [[CNT]], i64 0, i64 1
// CHECK-NEXT: store i64 %{{.+}}, i64* [[TMP]],
// CHECK-NEXT: [[TMP:%.+]] = getelementptr inbounds [2 x i64], [2 x i64]* [[CNT]], i64 0, i64 0
// CHECK-NEXT: call void @__kmpc_doacross_post([[IDENT]], i32 [[GTID]], i64* [[TMP]])
#pragma omp ordered depend(source)
baz(a[i][j], b[i][j]);

2
clang/test/OpenMP/parallel_for_simd_ast_print.cpp
View File

@ -48,7 +48,7 @@ class S8 : public S7<S1> {
public:
S8(int v) : S7<S1>(v){
#pragma omp parallel for simd private(a) private(this->a) private(S7<S1>::a)
#pragma omp parallel for simd private(a) private(this->a) private(S7 <S1>::a)
for (int k = 0; k < a.a; ++k)
++this->a.a;
}