Revert r301223
llvm-svn: 301233
diff --git a/clang/lib/CodeGen/CGOpenMPRuntime.cpp b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
index d1a706b..874b6a6 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntime.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
@@ -2466,14 +2466,16 @@
return Schedule | Modifier;
}
-void CGOpenMPRuntime::emitForDispatchInit(
- CodeGenFunction &CGF, SourceLocation Loc,
- const OpenMPScheduleTy &ScheduleKind, unsigned IVSize, bool IVSigned,
- bool Ordered, const DispatchRTInput &DispatchValues) {
+void CGOpenMPRuntime::emitForDispatchInit(CodeGenFunction &CGF,
+ SourceLocation Loc,
+ const OpenMPScheduleTy &ScheduleKind,
+ unsigned IVSize, bool IVSigned,
+ bool Ordered, llvm::Value *UB,
+ llvm::Value *Chunk) {
if (!CGF.HaveInsertPoint())
return;
- OpenMPSchedType Schedule = getRuntimeSchedule(
- ScheduleKind.Schedule, DispatchValues.Chunk != nullptr, Ordered);
+ OpenMPSchedType Schedule =
+ getRuntimeSchedule(ScheduleKind.Schedule, Chunk != nullptr, Ordered);
assert(Ordered ||
(Schedule != OMP_sch_static && Schedule != OMP_sch_static_chunked &&
Schedule != OMP_ord_static && Schedule != OMP_ord_static_chunked &&
@@ -2484,14 +2486,14 @@
// kmp_int[32|64] stride, kmp_int[32|64] chunk);
// If the Chunk was not specified in the clause - use default value 1.
- llvm::Value *Chunk = DispatchValues.Chunk ? DispatchValues.Chunk
- : CGF.Builder.getIntN(IVSize, 1);
+ if (Chunk == nullptr)
+ Chunk = CGF.Builder.getIntN(IVSize, 1);
llvm::Value *Args[] = {
emitUpdateLocation(CGF, Loc), getThreadID(CGF, Loc),
CGF.Builder.getInt32(addMonoNonMonoModifier(
Schedule, ScheduleKind.M1, ScheduleKind.M2)), // Schedule type
- DispatchValues.LB, // Lower
- DispatchValues.UB, // Upper
+ CGF.Builder.getIntN(IVSize, 0), // Lower
+ UB, // Upper
CGF.Builder.getIntN(IVSize, 1), // Stride
Chunk // Chunk
};
diff --git a/clang/lib/CodeGen/CGOpenMPRuntime.h b/clang/lib/CodeGen/CGOpenMPRuntime.h
index 6f460f1..7901a6b 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntime.h
+++ b/clang/lib/CodeGen/CGOpenMPRuntime.h
@@ -672,50 +672,16 @@
///
virtual bool isDynamic(OpenMPScheduleClauseKind ScheduleKind) const;
- /// struct with the values to be passed to the dispatch runtime function
- struct DispatchRTInput {
- /// Loop lower bound
- llvm::Value *LB = nullptr;
- /// Loop upper bound
- llvm::Value *UB = nullptr;
- /// Chunk size specified using 'schedule' clause (nullptr if chunk
- /// was not specified)
- llvm::Value *Chunk = nullptr;
- DispatchRTInput() = default;
- DispatchRTInput(llvm::Value *LB, llvm::Value *UB, llvm::Value *Chunk)
- : LB(LB), UB(UB), Chunk(Chunk) {}
- };
-
- /// Call the appropriate runtime routine to initialize it before start
- /// of loop.
-
- /// This is used for non static scheduled types and when the ordered
- /// clause is present on the loop construct.
- /// Depending on the loop schedule, it is necessary to call some runtime
- /// routine before start of the OpenMP loop to get the loop upper / lower
- /// bounds \a LB and \a UB and stride \a ST.
- ///
- /// \param CGF Reference to current CodeGenFunction.
- /// \param Loc Clang source location.
- /// \param ScheduleKind Schedule kind, specified by the 'schedule' clause.
- /// \param IVSize Size of the iteration variable in bits.
- /// \param IVSigned Sign of the interation variable.
- /// \param Ordered true if loop is ordered, false otherwise.
- /// \param DispatchValues struct containing llvm values for lower bound, upper
- /// bound, and chunk expression.
- /// For the default (nullptr) value, the chunk 1 will be used.
- ///
virtual void emitForDispatchInit(CodeGenFunction &CGF, SourceLocation Loc,
const OpenMPScheduleTy &ScheduleKind,
unsigned IVSize, bool IVSigned, bool Ordered,
- const DispatchRTInput &DispatchValues);
+ llvm::Value *UB,
+ llvm::Value *Chunk = nullptr);
/// \brief Call the appropriate runtime routine to initialize it before start
/// of loop.
///
- /// This is used only in case of static schedule, when the user did not
- /// specify a ordered clause on the loop construct.
- /// Depending on the loop schedule, it is necessary to call some runtime
+ /// Depending on the loop schedule, it is nesessary to call some runtime
/// routine before start of the OpenMP loop to get the loop upper / lower
/// bounds \a LB and \a UB and stride \a ST.
///
diff --git a/clang/lib/CodeGen/CGStmtOpenMP.cpp b/clang/lib/CodeGen/CGStmtOpenMP.cpp
index f738dd0..22269e4 100644
--- a/clang/lib/CodeGen/CGStmtOpenMP.cpp
+++ b/clang/lib/CodeGen/CGStmtOpenMP.cpp
@@ -87,8 +87,7 @@
class OMPParallelScope final : public OMPLexicalScope {
bool EmitPreInitStmt(const OMPExecutableDirective &S) {
OpenMPDirectiveKind Kind = S.getDirectiveKind();
- return !(isOpenMPTargetExecutionDirective(Kind) ||
- isOpenMPLoopBoundSharingDirective(Kind)) &&
+ return !isOpenMPTargetExecutionDirective(Kind) &&
isOpenMPParallelDirective(Kind);
}
@@ -1250,20 +1249,10 @@
CGF.EmitBlock(DoneBB, /*IsFinished=*/true);
}
-namespace {
-/// Codegen lambda for appending distribute lower and upper bounds to outlined
-/// parallel function. This is necessary for combined constructs such as
-/// 'distribute parallel for'
-typedef llvm::function_ref<void(CodeGenFunction &,
- const OMPExecutableDirective &,
- llvm::SmallVectorImpl<llvm::Value *> &)>
- CodeGenBoundParametersTy;
-} // anonymous namespace
-
-static void emitCommonOMPParallelDirective(
- CodeGenFunction &CGF, const OMPExecutableDirective &S,
- OpenMPDirectiveKind InnermostKind, const RegionCodeGenTy &CodeGen,
- const CodeGenBoundParametersTy &CodeGenBoundParameters) {
+static void emitCommonOMPParallelDirective(CodeGenFunction &CGF,
+ const OMPExecutableDirective &S,
+ OpenMPDirectiveKind InnermostKind,
+ const RegionCodeGenTy &CodeGen) {
const CapturedStmt *CS = S.getCapturedStmt(OMPD_parallel);
auto OutlinedFn = CGF.CGM.getOpenMPRuntime().emitParallelOutlinedFunction(
S, *CS->getCapturedDecl()->param_begin(), InnermostKind, CodeGen);
@@ -1290,20 +1279,11 @@
OMPParallelScope Scope(CGF, S);
llvm::SmallVector<llvm::Value *, 16> CapturedVars;
- // Combining 'distribute' with 'for' requires sharing each 'distribute' chunk
- // lower and upper bounds with the pragma 'for' chunking mechanism.
- // The following lambda takes care of appending the lower and upper bound
- // parameters when necessary
- CodeGenBoundParameters(CGF, S, CapturedVars);
CGF.GenerateOpenMPCapturedVars(*CS, CapturedVars);
CGF.CGM.getOpenMPRuntime().emitParallelCall(CGF, S.getLocStart(), OutlinedFn,
CapturedVars, IfCond);
}
-static void emitEmptyBoundParameters(CodeGenFunction &,
- const OMPExecutableDirective &,
- llvm::SmallVectorImpl<llvm::Value *> &) {}
-
void CodeGenFunction::EmitOMPParallelDirective(const OMPParallelDirective &S) {
// Emit parallel region as a standalone region.
auto &&CodeGen = [&S](CodeGenFunction &CGF, PrePostActionTy &) {
@@ -1324,8 +1304,7 @@
CGF.EmitStmt(cast<CapturedStmt>(S.getAssociatedStmt())->getCapturedStmt());
CGF.EmitOMPReductionClauseFinal(S, /*ReductionKind=*/OMPD_parallel);
};
- emitCommonOMPParallelDirective(*this, S, OMPD_parallel, CodeGen,
- emitEmptyBoundParameters);
+ emitCommonOMPParallelDirective(*this, S, OMPD_parallel, CodeGen);
emitPostUpdateForReductionClause(
*this, S, [](CodeGenFunction &) -> llvm::Value * { return nullptr; });
}
@@ -1670,13 +1649,6 @@
EmitBlock(DoneBB, /*IsFinished=*/true);
}
-static void emitOMPLoopBodyWithStopPoint(CodeGenFunction &CGF,
- const OMPLoopDirective &S,
- CodeGenFunction::JumpDest LoopExit) {
- CGF.EmitOMPLoopBody(S, LoopExit);
- CGF.EmitStopPoint(&S);
-};
-
void CodeGenFunction::EmitOMPSimdDirective(const OMPSimdDirective &S) {
auto &&CodeGen = [&S](CodeGenFunction &CGF, PrePostActionTy &) {
OMPLoopScope PreInitScope(CGF, S);
@@ -1759,12 +1731,9 @@
CGM.getOpenMPRuntime().emitInlinedDirective(*this, OMPD_simd, CodeGen);
}
-void CodeGenFunction::EmitOMPOuterLoop(
- bool DynamicOrOrdered, bool IsMonotonic, const OMPLoopDirective &S,
- CodeGenFunction::OMPPrivateScope &LoopScope,
- const CodeGenFunction::OMPLoopArguments &LoopArgs,
- const CodeGenFunction::CodeGenLoopTy &CodeGenLoop,
- const CodeGenFunction::CodeGenOrderedTy &CodeGenOrdered) {
+void CodeGenFunction::EmitOMPOuterLoop(bool DynamicOrOrdered, bool IsMonotonic,
+ const OMPLoopDirective &S, OMPPrivateScope &LoopScope, bool Ordered,
+ Address LB, Address UB, Address ST, Address IL, llvm::Value *Chunk) {
auto &RT = CGM.getOpenMPRuntime();
const Expr *IVExpr = S.getIterationVariable();
@@ -1782,18 +1751,15 @@
llvm::Value *BoolCondVal = nullptr;
if (!DynamicOrOrdered) {
- // UB = min(UB, GlobalUB) or
- // UB = min(UB, PrevUB) for combined loop sharing constructs (e.g.
- // 'distribute parallel for')
- EmitIgnoredExpr(LoopArgs.EUB);
+ // UB = min(UB, GlobalUB)
+ EmitIgnoredExpr(S.getEnsureUpperBound());
// IV = LB
- EmitIgnoredExpr(LoopArgs.Init);
+ EmitIgnoredExpr(S.getInit());
// IV < UB
- BoolCondVal = EvaluateExprAsBool(LoopArgs.Cond);
+ BoolCondVal = EvaluateExprAsBool(S.getCond());
} else {
- BoolCondVal =
- RT.emitForNext(*this, S.getLocStart(), IVSize, IVSigned, LoopArgs.IL,
- LoopArgs.LB, LoopArgs.UB, LoopArgs.ST);
+ BoolCondVal = RT.emitForNext(*this, S.getLocStart(), IVSize, IVSigned, IL,
+ LB, UB, ST);
}
// If there are any cleanups between here and the loop-exit scope,
@@ -1813,7 +1779,7 @@
// Emit "IV = LB" (in case of static schedule, we have already calculated new
// LB for loop condition and emitted it above).
if (DynamicOrOrdered)
- EmitIgnoredExpr(LoopArgs.Init);
+ EmitIgnoredExpr(S.getInit());
// Create a block for the increment.
auto Continue = getJumpDestInCurrentScope("omp.dispatch.inc");
@@ -1827,27 +1793,24 @@
EmitOMPSimdInit(S, IsMonotonic);
SourceLocation Loc = S.getLocStart();
-
- // when 'distribute' is not combined with a 'for':
- // while (idx <= UB) { BODY; ++idx; }
- // when 'distribute' is combined with a 'for'
- // (e.g. 'distribute parallel for')
- // while (idx <= UB) { <CodeGen rest of pragma>; idx += ST; }
- EmitOMPInnerLoop(
- S, LoopScope.requiresCleanups(), LoopArgs.Cond, LoopArgs.IncExpr,
- [&S, LoopExit, &CodeGenLoop](CodeGenFunction &CGF) {
- CodeGenLoop(CGF, S, LoopExit);
- },
- [IVSize, IVSigned, Loc, &CodeGenOrdered](CodeGenFunction &CGF) {
- CodeGenOrdered(CGF, Loc, IVSize, IVSigned);
- });
+ EmitOMPInnerLoop(S, LoopScope.requiresCleanups(), S.getCond(), S.getInc(),
+ [&S, LoopExit](CodeGenFunction &CGF) {
+ CGF.EmitOMPLoopBody(S, LoopExit);
+ CGF.EmitStopPoint(&S);
+ },
+ [Ordered, IVSize, IVSigned, Loc](CodeGenFunction &CGF) {
+ if (Ordered) {
+ CGF.CGM.getOpenMPRuntime().emitForOrderedIterationEnd(
+ CGF, Loc, IVSize, IVSigned);
+ }
+ });
EmitBlock(Continue.getBlock());
BreakContinueStack.pop_back();
if (!DynamicOrOrdered) {
// Emit "LB = LB + Stride", "UB = UB + Stride".
- EmitIgnoredExpr(LoopArgs.NextLB);
- EmitIgnoredExpr(LoopArgs.NextUB);
+ EmitIgnoredExpr(S.getNextLowerBound());
+ EmitIgnoredExpr(S.getNextUpperBound());
}
EmitBranch(CondBlock);
@@ -1866,8 +1829,7 @@
void CodeGenFunction::EmitOMPForOuterLoop(
const OpenMPScheduleTy &ScheduleKind, bool IsMonotonic,
const OMPLoopDirective &S, OMPPrivateScope &LoopScope, bool Ordered,
- const OMPLoopArguments &LoopArgs,
- const CodeGenDispatchBoundsTy &CGDispatchBounds) {
+ Address LB, Address UB, Address ST, Address IL, llvm::Value *Chunk) {
auto &RT = CGM.getOpenMPRuntime();
// Dynamic scheduling of the outer loop (dynamic, guided, auto, runtime).
@@ -1876,7 +1838,7 @@
assert((Ordered ||
!RT.isStaticNonchunked(ScheduleKind.Schedule,
- LoopArgs.Chunk != nullptr)) &&
+ /*Chunked=*/Chunk != nullptr)) &&
"static non-chunked schedule does not need outer loop");
// Emit outer loop.
@@ -1934,46 +1896,22 @@
const bool IVSigned = IVExpr->getType()->hasSignedIntegerRepresentation();
if (DynamicOrOrdered) {
- auto DispatchBounds = CGDispatchBounds(*this, S, LoopArgs.LB, LoopArgs.UB);
- llvm::Value *LBVal = DispatchBounds.first;
- llvm::Value *UBVal = DispatchBounds.second;
- CGOpenMPRuntime::DispatchRTInput DipatchRTInputValues = {LBVal, UBVal,
- LoopArgs.Chunk};
+ llvm::Value *UBVal = EmitScalarExpr(S.getLastIteration());
RT.emitForDispatchInit(*this, S.getLocStart(), ScheduleKind, IVSize,
- IVSigned, Ordered, DipatchRTInputValues);
+ IVSigned, Ordered, UBVal, Chunk);
} else {
RT.emitForStaticInit(*this, S.getLocStart(), ScheduleKind, IVSize, IVSigned,
- Ordered, LoopArgs.IL, LoopArgs.LB, LoopArgs.UB,
- LoopArgs.ST, LoopArgs.Chunk);
+ Ordered, IL, LB, UB, ST, Chunk);
}
- auto &&CodeGenOrdered = [Ordered](CodeGenFunction &CGF, SourceLocation Loc,
- const unsigned IVSize,
- const bool IVSigned) {
- if (Ordered) {
- CGF.CGM.getOpenMPRuntime().emitForOrderedIterationEnd(CGF, Loc, IVSize,
- IVSigned);
- }
- };
-
- OMPLoopArguments OuterLoopArgs(LoopArgs.LB, LoopArgs.UB, LoopArgs.ST,
- LoopArgs.IL, LoopArgs.Chunk, LoopArgs.EUB);
- OuterLoopArgs.IncExpr = S.getInc();
- OuterLoopArgs.Init = S.getInit();
- OuterLoopArgs.Cond = S.getCond();
- OuterLoopArgs.NextLB = S.getNextLowerBound();
- OuterLoopArgs.NextUB = S.getNextUpperBound();
- EmitOMPOuterLoop(DynamicOrOrdered, IsMonotonic, S, LoopScope, OuterLoopArgs,
- emitOMPLoopBodyWithStopPoint, CodeGenOrdered);
+ EmitOMPOuterLoop(DynamicOrOrdered, IsMonotonic, S, LoopScope, Ordered, LB, UB,
+ ST, IL, Chunk);
}
-static void emitEmptyOrdered(CodeGenFunction &, SourceLocation Loc,
- const unsigned IVSize, const bool IVSigned) {}
-
void CodeGenFunction::EmitOMPDistributeOuterLoop(
- OpenMPDistScheduleClauseKind ScheduleKind, const OMPLoopDirective &S,
- OMPPrivateScope &LoopScope, const OMPLoopArguments &LoopArgs,
- const CodeGenLoopTy &CodeGenLoopContent) {
+ OpenMPDistScheduleClauseKind ScheduleKind,
+ const OMPDistributeDirective &S, OMPPrivateScope &LoopScope,
+ Address LB, Address UB, Address ST, Address IL, llvm::Value *Chunk) {
auto &RT = CGM.getOpenMPRuntime();
@@ -1986,159 +1924,26 @@
const unsigned IVSize = getContext().getTypeSize(IVExpr->getType());
const bool IVSigned = IVExpr->getType()->hasSignedIntegerRepresentation();
- RT.emitDistributeStaticInit(*this, S.getLocStart(), ScheduleKind, IVSize,
- IVSigned, /* Ordered = */ false, LoopArgs.IL,
- LoopArgs.LB, LoopArgs.UB, LoopArgs.ST,
- LoopArgs.Chunk);
+ RT.emitDistributeStaticInit(*this, S.getLocStart(), ScheduleKind,
+ IVSize, IVSigned, /* Ordered = */ false,
+ IL, LB, UB, ST, Chunk);
- // for combined 'distribute' and 'for' the increment expression of distribute
- // is store in DistInc. For 'distribute' alone, it is in Inc.
- Expr *IncExpr;
- if (isOpenMPLoopBoundSharingDirective(S.getDirectiveKind()))
- IncExpr = S.getDistInc();
- else
- IncExpr = S.getInc();
-
- // this routine is shared by 'omp distribute parallel for' and
- // 'omp distribute': select the right EUB expression depending on the
- // directive
- OMPLoopArguments OuterLoopArgs;
- OuterLoopArgs.LB = LoopArgs.LB;
- OuterLoopArgs.UB = LoopArgs.UB;
- OuterLoopArgs.ST = LoopArgs.ST;
- OuterLoopArgs.IL = LoopArgs.IL;
- OuterLoopArgs.Chunk = LoopArgs.Chunk;
- OuterLoopArgs.EUB = isOpenMPLoopBoundSharingDirective(S.getDirectiveKind())
- ? S.getCombinedEnsureUpperBound()
- : S.getEnsureUpperBound();
- OuterLoopArgs.IncExpr = IncExpr;
- OuterLoopArgs.Init = isOpenMPLoopBoundSharingDirective(S.getDirectiveKind())
- ? S.getCombinedInit()
- : S.getInit();
- OuterLoopArgs.Cond = isOpenMPLoopBoundSharingDirective(S.getDirectiveKind())
- ? S.getCombinedCond()
- : S.getCond();
- OuterLoopArgs.NextLB = isOpenMPLoopBoundSharingDirective(S.getDirectiveKind())
- ? S.getCombinedNextLowerBound()
- : S.getNextLowerBound();
- OuterLoopArgs.NextUB = isOpenMPLoopBoundSharingDirective(S.getDirectiveKind())
- ? S.getCombinedNextUpperBound()
- : S.getNextUpperBound();
-
- EmitOMPOuterLoop(/* DynamicOrOrdered = */ false, /* IsMonotonic = */ false, S,
- LoopScope, OuterLoopArgs, CodeGenLoopContent,
- emitEmptyOrdered);
-}
-
-/// Emit a helper variable and return corresponding lvalue.
-static LValue EmitOMPHelperVar(CodeGenFunction &CGF,
- const DeclRefExpr *Helper) {
- auto VDecl = cast<VarDecl>(Helper->getDecl());
- CGF.EmitVarDecl(*VDecl);
- return CGF.EmitLValue(Helper);
-}
-
-static std::pair<LValue, LValue>
-emitDistributeParallelForInnerBounds(CodeGenFunction &CGF,
- const OMPExecutableDirective &S) {
- const OMPLoopDirective &LS = cast<OMPLoopDirective>(S);
- LValue LB =
- EmitOMPHelperVar(CGF, cast<DeclRefExpr>(LS.getLowerBoundVariable()));
- LValue UB =
- EmitOMPHelperVar(CGF, cast<DeclRefExpr>(LS.getUpperBoundVariable()));
-
- // When composing 'distribute' with 'for' (e.g. as in 'distribute
- // parallel for') we need to use the 'distribute'
- // chunk lower and upper bounds rather than the whole loop iteration
- // space. These are parameters to the outlined function for 'parallel'
- // and we copy the bounds of the previous schedule into the
- // the current ones.
- LValue PrevLB = CGF.EmitLValue(LS.getPrevLowerBoundVariable());
- LValue PrevUB = CGF.EmitLValue(LS.getPrevUpperBoundVariable());
- llvm::Value *PrevLBVal = CGF.EmitLoadOfScalar(PrevLB, SourceLocation());
- PrevLBVal = CGF.EmitScalarConversion(
- PrevLBVal, LS.getPrevLowerBoundVariable()->getType(),
- LS.getIterationVariable()->getType(), SourceLocation());
- llvm::Value *PrevUBVal = CGF.EmitLoadOfScalar(PrevUB, SourceLocation());
- PrevUBVal = CGF.EmitScalarConversion(
- PrevUBVal, LS.getPrevUpperBoundVariable()->getType(),
- LS.getIterationVariable()->getType(), SourceLocation());
-
- CGF.EmitStoreOfScalar(PrevLBVal, LB);
- CGF.EmitStoreOfScalar(PrevUBVal, UB);
-
- return {LB, UB};
-}
-
-/// if the 'for' loop has a dispatch schedule (e.g. dynamic, guided) then
-/// we need to use the LB and UB expressions generated by the worksharing
-/// code generation support, whereas in non combined situations we would
-/// just emit 0 and the LastIteration expression
-/// This function is necessary due to the difference of the LB and UB
-/// types for the RT emission routines for 'for_static_init' and
-/// 'for_dispatch_init'
-static std::pair<llvm::Value *, llvm::Value *>
-emitDistributeParallelForDispatchBounds(CodeGenFunction &CGF,
- const OMPExecutableDirective &S,
- Address LB, Address UB) {
- const OMPLoopDirective &LS = cast<OMPLoopDirective>(S);
- const Expr *IVExpr = LS.getIterationVariable();
- // when implementing a dynamic schedule for a 'for' combined with a
- // 'distribute' (e.g. 'distribute parallel for'), the 'for' loop
- // is not normalized as each team only executes its own assigned
- // distribute chunk
- QualType IteratorTy = IVExpr->getType();
- llvm::Value *LBVal = CGF.EmitLoadOfScalar(LB, /*Volatile=*/false, IteratorTy,
- SourceLocation());
- llvm::Value *UBVal = CGF.EmitLoadOfScalar(UB, /*Volatile=*/false, IteratorTy,
- SourceLocation());
- return {LBVal, UBVal};
-};
-
-static void emitDistributeParallelForDistributeInnerBoundParams(
- CodeGenFunction &CGF, const OMPExecutableDirective &S,
- llvm::SmallVectorImpl<llvm::Value *> &CapturedVars) {
- const auto &Dir = cast<OMPLoopDirective>(S);
- LValue LB =
- CGF.EmitLValue(cast<DeclRefExpr>(Dir.getCombinedLowerBoundVariable()));
- auto LBCast = CGF.Builder.CreateIntCast(
- CGF.Builder.CreateLoad(LB.getAddress()), CGF.SizeTy, /*isSigned=*/false);
- CapturedVars.push_back(LBCast);
- LValue UB =
- CGF.EmitLValue(cast<DeclRefExpr>(Dir.getCombinedUpperBoundVariable()));
-
- auto UBCast = CGF.Builder.CreateIntCast(
- CGF.Builder.CreateLoad(UB.getAddress()), CGF.SizeTy, /*isSigned=*/false);
- CapturedVars.push_back(UBCast);
-};
-
-static void
-emitInnerParallelForWhenCombined(CodeGenFunction &CGF,
- const OMPLoopDirective &S,
- CodeGenFunction::JumpDest LoopExit) {
- auto &&CGInlinedWorksharingLoop = [&S](CodeGenFunction &CGF,
- PrePostActionTy &) {
- CGF.EmitOMPWorksharingLoop(S, S.getPrevEnsureUpperBound(),
- emitDistributeParallelForInnerBounds,
- emitDistributeParallelForDispatchBounds);
- };
-
- emitCommonOMPParallelDirective(
- CGF, S, OMPD_for, CGInlinedWorksharingLoop,
- emitDistributeParallelForDistributeInnerBoundParams);
+ EmitOMPOuterLoop(/* DynamicOrOrdered = */ false, /* IsMonotonic = */ false,
+ S, LoopScope, /* Ordered = */ false, LB, UB, ST, IL, Chunk);
}
void CodeGenFunction::EmitOMPDistributeParallelForDirective(
const OMPDistributeParallelForDirective &S) {
- auto &&CodeGen = [&S](CodeGenFunction &CGF, PrePostActionTy &) {
- CGF.EmitOMPDistributeLoop(S, emitInnerParallelForWhenCombined,
- S.getDistInc());
- };
OMPLexicalScope Scope(*this, S, /*AsInlined=*/true);
- OMPCancelStackRAII CancelRegion(*this, OMPD_distribute_parallel_for,
- /*HasCancel=*/false);
- CGM.getOpenMPRuntime().emitInlinedDirective(*this, OMPD_distribute, CodeGen,
- /*HasCancel=*/false);
+ CGM.getOpenMPRuntime().emitInlinedDirective(
+ *this, OMPD_distribute_parallel_for,
+ [&S](CodeGenFunction &CGF, PrePostActionTy &) {
+ OMPLoopScope PreInitScope(CGF, S);
+ OMPCancelStackRAII CancelRegion(CGF, OMPD_distribute_parallel_for,
+ /*HasCancel=*/false);
+ CGF.EmitStmt(
+ cast<CapturedStmt>(S.getAssociatedStmt())->getCapturedStmt());
+ });
}
void CodeGenFunction::EmitOMPDistributeParallelForSimdDirective(
@@ -2276,6 +2081,14 @@
});
}
+/// \brief Emit a helper variable and return corresponding lvalue.
+static LValue EmitOMPHelperVar(CodeGenFunction &CGF,
+ const DeclRefExpr *Helper) {
+ auto VDecl = cast<VarDecl>(Helper->getDecl());
+ CGF.EmitVarDecl(*VDecl);
+ return CGF.EmitLValue(Helper);
+}
+
namespace {
struct ScheduleKindModifiersTy {
OpenMPScheduleClauseKind Kind;
@@ -2288,10 +2101,7 @@
};
} // namespace
-bool CodeGenFunction::EmitOMPWorksharingLoop(
- const OMPLoopDirective &S, Expr *EUB,
- const CodeGenLoopBoundsTy &CodeGenLoopBounds,
- const CodeGenDispatchBoundsTy &CGDispatchBounds) {
+bool CodeGenFunction::EmitOMPWorksharingLoop(const OMPLoopDirective &S) {
// Emit the loop iteration variable.
auto IVExpr = cast<DeclRefExpr>(S.getIterationVariable());
auto IVDecl = cast<VarDecl>(IVExpr->getDecl());
@@ -2341,10 +2151,10 @@
emitAlignedClause(*this, S);
EmitOMPLinearClauseInit(S);
// Emit helper vars inits.
-
- std::pair<LValue, LValue> Bounds = CodeGenLoopBounds(*this, S);
- LValue LB = Bounds.first;
- LValue UB = Bounds.second;
+ LValue LB =
+ EmitOMPHelperVar(*this, cast<DeclRefExpr>(S.getLowerBoundVariable()));
+ LValue UB =
+ EmitOMPHelperVar(*this, cast<DeclRefExpr>(S.getUpperBoundVariable()));
LValue ST =
EmitOMPHelperVar(*this, cast<DeclRefExpr>(S.getStrideVariable()));
LValue IL =
@@ -2430,11 +2240,9 @@
ScheduleKind.M2 == OMPC_SCHEDULE_MODIFIER_monotonic;
// Emit the outer loop, which requests its work chunk [LB..UB] from
// runtime and runs the inner loop to process it.
- const OMPLoopArguments LoopArguments(LB.getAddress(), UB.getAddress(),
- ST.getAddress(), IL.getAddress(),
- Chunk, EUB);
EmitOMPForOuterLoop(ScheduleKind, IsMonotonic, S, LoopScope, Ordered,
- LoopArguments, CGDispatchBounds);
+ LB.getAddress(), UB.getAddress(), ST.getAddress(),
+ IL.getAddress(), Chunk);
}
if (isOpenMPSimdDirective(S.getDirectiveKind())) {
EmitOMPSimdFinal(S,
@@ -2472,42 +2280,12 @@
return HasLastprivateClause;
}
-/// The following two functions generate expressions for the loop lower
-/// and upper bounds in case of static and dynamic (dispatch) schedule
-/// of the associated 'for' or 'distribute' loop.
-static std::pair<LValue, LValue>
-emitForLoopBounds(CodeGenFunction &CGF, const OMPExecutableDirective &S) {
- const OMPLoopDirective &LS = cast<OMPLoopDirective>(S);
- LValue LB =
- EmitOMPHelperVar(CGF, cast<DeclRefExpr>(LS.getLowerBoundVariable()));
- LValue UB =
- EmitOMPHelperVar(CGF, cast<DeclRefExpr>(LS.getUpperBoundVariable()));
- return {LB, UB};
-}
-
-/// When dealing with dispatch schedules (e.g. dynamic, guided) we do not
-/// consider the lower and upper bound expressions generated by the
-/// worksharing loop support, but we use 0 and the iteration space size as
-/// constants
-static std::pair<llvm::Value *, llvm::Value *>
-emitDispatchForLoopBounds(CodeGenFunction &CGF, const OMPExecutableDirective &S,
- Address LB, Address UB) {
- const OMPLoopDirective &LS = cast<OMPLoopDirective>(S);
- const Expr *IVExpr = LS.getIterationVariable();
- const unsigned IVSize = CGF.getContext().getTypeSize(IVExpr->getType());
- llvm::Value *LBVal = CGF.Builder.getIntN(IVSize, 0);
- llvm::Value *UBVal = CGF.EmitScalarExpr(LS.getLastIteration());
- return {LBVal, UBVal};
-}
-
void CodeGenFunction::EmitOMPForDirective(const OMPForDirective &S) {
bool HasLastprivates = false;
auto &&CodeGen = [&S, &HasLastprivates](CodeGenFunction &CGF,
PrePostActionTy &) {
OMPCancelStackRAII CancelRegion(CGF, OMPD_for, S.hasCancel());
- HasLastprivates = CGF.EmitOMPWorksharingLoop(S, S.getEnsureUpperBound(),
- emitForLoopBounds,
- emitDispatchForLoopBounds);
+ HasLastprivates = CGF.EmitOMPWorksharingLoop(S);
};
{
OMPLexicalScope Scope(*this, S, /*AsInlined=*/true);
@@ -2525,9 +2303,7 @@
bool HasLastprivates = false;
auto &&CodeGen = [&S, &HasLastprivates](CodeGenFunction &CGF,
PrePostActionTy &) {
- HasLastprivates = CGF.EmitOMPWorksharingLoop(S, S.getEnsureUpperBound(),
- emitForLoopBounds,
- emitDispatchForLoopBounds);
+ HasLastprivates = CGF.EmitOMPWorksharingLoop(S);
};
{
OMPLexicalScope Scope(*this, S, /*AsInlined=*/true);
@@ -2778,11 +2554,9 @@
// directives: 'parallel' with 'for' directive.
auto &&CodeGen = [&S](CodeGenFunction &CGF, PrePostActionTy &) {
OMPCancelStackRAII CancelRegion(CGF, OMPD_parallel_for, S.hasCancel());
- CGF.EmitOMPWorksharingLoop(S, S.getEnsureUpperBound(), emitForLoopBounds,
- emitDispatchForLoopBounds);
+ CGF.EmitOMPWorksharingLoop(S);
};
- emitCommonOMPParallelDirective(*this, S, OMPD_for, CodeGen,
- emitEmptyBoundParameters);
+ emitCommonOMPParallelDirective(*this, S, OMPD_for, CodeGen);
}
void CodeGenFunction::EmitOMPParallelForSimdDirective(
@@ -2790,11 +2564,9 @@
// Emit directive as a combined directive that consists of two implicit
// directives: 'parallel' with 'for' directive.
auto &&CodeGen = [&S](CodeGenFunction &CGF, PrePostActionTy &) {
- CGF.EmitOMPWorksharingLoop(S, S.getEnsureUpperBound(), emitForLoopBounds,
- emitDispatchForLoopBounds);
+ CGF.EmitOMPWorksharingLoop(S);
};
- emitCommonOMPParallelDirective(*this, S, OMPD_simd, CodeGen,
- emitEmptyBoundParameters);
+ emitCommonOMPParallelDirective(*this, S, OMPD_simd, CodeGen);
}
void CodeGenFunction::EmitOMPParallelSectionsDirective(
@@ -2804,8 +2576,7 @@
auto &&CodeGen = [&S](CodeGenFunction &CGF, PrePostActionTy &) {
CGF.EmitSections(S);
};
- emitCommonOMPParallelDirective(*this, S, OMPD_sections, CodeGen,
- emitEmptyBoundParameters);
+ emitCommonOMPParallelDirective(*this, S, OMPD_sections, CodeGen);
}
void CodeGenFunction::EmitOMPTaskBasedDirective(const OMPExecutableDirective &S,
@@ -3023,9 +2794,7 @@
}(), S.getLocStart());
}
-void CodeGenFunction::EmitOMPDistributeLoop(const OMPLoopDirective &S,
- const CodeGenLoopTy &CodeGenLoop,
- Expr *IncExpr) {
+void CodeGenFunction::EmitOMPDistributeLoop(const OMPDistributeDirective &S) {
// Emit the loop iteration variable.
auto IVExpr = cast<DeclRefExpr>(S.getIterationVariable());
auto IVDecl = cast<VarDecl>(IVExpr->getDecl());
@@ -3066,17 +2835,10 @@
// Emit 'then' code.
{
// Emit helper vars inits.
-
- LValue LB = EmitOMPHelperVar(
- *this, cast<DeclRefExpr>(
- (isOpenMPLoopBoundSharingDirective(S.getDirectiveKind())
- ? S.getCombinedLowerBoundVariable()
- : S.getLowerBoundVariable())));
- LValue UB = EmitOMPHelperVar(
- *this, cast<DeclRefExpr>(
- (isOpenMPLoopBoundSharingDirective(S.getDirectiveKind())
- ? S.getCombinedUpperBoundVariable()
- : S.getUpperBoundVariable())));
+ LValue LB =
+ EmitOMPHelperVar(*this, cast<DeclRefExpr>(S.getLowerBoundVariable()));
+ LValue UB =
+ EmitOMPHelperVar(*this, cast<DeclRefExpr>(S.getUpperBoundVariable()));
LValue ST =
EmitOMPHelperVar(*this, cast<DeclRefExpr>(S.getStrideVariable()));
LValue IL =
@@ -3128,25 +2890,15 @@
auto LoopExit =
getJumpDestInCurrentScope(createBasicBlock("omp.loop.exit"));
// UB = min(UB, GlobalUB);
- EmitIgnoredExpr(isOpenMPLoopBoundSharingDirective(S.getDirectiveKind())
- ? S.getCombinedEnsureUpperBound()
- : S.getEnsureUpperBound());
+ EmitIgnoredExpr(S.getEnsureUpperBound());
// IV = LB;
- EmitIgnoredExpr(isOpenMPLoopBoundSharingDirective(S.getDirectiveKind())
- ? S.getCombinedInit()
- : S.getInit());
-
- Expr *Cond = isOpenMPLoopBoundSharingDirective(S.getDirectiveKind())
- ? S.getCombinedCond()
- : S.getCond();
-
- // for distribute alone, codegen
+ EmitIgnoredExpr(S.getInit());
// while (idx <= UB) { BODY; ++idx; }
- // when combined with 'for' (e.g. as in 'distribute parallel for')
- // while (idx <= UB) { <CodeGen rest of pragma>; idx += ST; }
- EmitOMPInnerLoop(S, LoopScope.requiresCleanups(), Cond, IncExpr,
- [&S, LoopExit, &CodeGenLoop](CodeGenFunction &CGF) {
- CodeGenLoop(CGF, S, LoopExit);
+ EmitOMPInnerLoop(S, LoopScope.requiresCleanups(), S.getCond(),
+ S.getInc(),
+ [&S, LoopExit](CodeGenFunction &CGF) {
+ CGF.EmitOMPLoopBody(S, LoopExit);
+ CGF.EmitStopPoint(&S);
},
[](CodeGenFunction &) {});
EmitBlock(LoopExit.getBlock());
@@ -3155,11 +2907,9 @@
} else {
// Emit the outer loop, which requests its work chunk [LB..UB] from
// runtime and runs the inner loop to process it.
- const OMPLoopArguments LoopArguments = {
- LB.getAddress(), UB.getAddress(), ST.getAddress(), IL.getAddress(),
- Chunk};
- EmitOMPDistributeOuterLoop(ScheduleKind, S, LoopScope, LoopArguments,
- CodeGenLoop);
+ EmitOMPDistributeOuterLoop(ScheduleKind, S, LoopScope,
+ LB.getAddress(), UB.getAddress(), ST.getAddress(),
+ IL.getAddress(), Chunk);
}
// Emit final copy of the lastprivate variables if IsLastIter != 0.
@@ -3181,8 +2931,7 @@
void CodeGenFunction::EmitOMPDistributeDirective(
const OMPDistributeDirective &S) {
auto &&CodeGen = [&S](CodeGenFunction &CGF, PrePostActionTy &) {
-
- CGF.EmitOMPDistributeLoop(S, emitOMPLoopBodyWithStopPoint, S.getInc());
+ CGF.EmitOMPDistributeLoop(S);
};
OMPLexicalScope Scope(*this, S, /*AsInlined=*/true);
CGM.getOpenMPRuntime().emitInlinedDirective(*this, OMPD_distribute, CodeGen,
@@ -4091,8 +3840,7 @@
CGF.EmitStmt(CS->getCapturedStmt());
CGF.EmitOMPReductionClauseFinal(S, /*ReductionKind=*/OMPD_parallel);
};
- emitCommonOMPParallelDirective(CGF, S, OMPD_parallel, CodeGen,
- emitEmptyBoundParameters);
+ emitCommonOMPParallelDirective(CGF, S, OMPD_parallel, CodeGen);
emitPostUpdateForReductionClause(
CGF, S, [](CodeGenFunction &) -> llvm::Value * { return nullptr; });
}
diff --git a/clang/lib/CodeGen/CodeGenFunction.h b/clang/lib/CodeGen/CodeGenFunction.h
index 1ded824..fa72019 100644
--- a/clang/lib/CodeGen/CodeGenFunction.h
+++ b/clang/lib/CodeGen/CodeGenFunction.h
@@ -175,25 +175,6 @@
// because of jumps.
VarBypassDetector Bypasses;
- // CodeGen lambda for loops and support for ordered clause
- typedef llvm::function_ref<void(CodeGenFunction &, const OMPLoopDirective &,
- JumpDest)>
- CodeGenLoopTy;
- typedef llvm::function_ref<void(CodeGenFunction &, SourceLocation,
- const unsigned, const bool)>
- CodeGenOrderedTy;
-
- // Codegen lambda for loop bounds in worksharing loop constructs
- typedef llvm::function_ref<std::pair<LValue, LValue>(
- CodeGenFunction &, const OMPExecutableDirective &S)>
- CodeGenLoopBoundsTy;
-
- // Codegen lambda for loop bounds in dispatch-based loop implementation
- typedef llvm::function_ref<std::pair<llvm::Value *, llvm::Value *>(
- CodeGenFunction &, const OMPExecutableDirective &S, Address LB,
- Address UB)>
- CodeGenDispatchBoundsTy;
-
/// \brief CGBuilder insert helper. This function is called after an
/// instruction is created using Builder.
void InsertHelper(llvm::Instruction *I, const llvm::Twine &Name,
@@ -2775,6 +2756,7 @@
void EmitOMPTaskLoopDirective(const OMPTaskLoopDirective &S);
void EmitOMPTaskLoopSimdDirective(const OMPTaskLoopSimdDirective &S);
void EmitOMPDistributeDirective(const OMPDistributeDirective &S);
+ void EmitOMPDistributeLoop(const OMPDistributeDirective &S);
void EmitOMPDistributeParallelForDirective(
const OMPDistributeParallelForDirective &S);
void EmitOMPDistributeParallelForSimdDirective(
@@ -2831,78 +2813,32 @@
void EmitOMPPrivateLoopCounters(const OMPLoopDirective &S,
OMPPrivateScope &LoopScope);
- /// Helper for the OpenMP loop directives.
- void EmitOMPLoopBody(const OMPLoopDirective &D, JumpDest LoopExit);
-
- /// \brief Emit code for the worksharing loop-based directive.
- /// \return true, if this construct has any lastprivate clause, false -
- /// otherwise.
- bool EmitOMPWorksharingLoop(const OMPLoopDirective &S, Expr *EUB,
- const CodeGenLoopBoundsTy &CodeGenLoopBounds,
- const CodeGenDispatchBoundsTy &CGDispatchBounds);
-
private:
/// Helpers for blocks
llvm::Value *EmitBlockLiteral(const CGBlockInfo &Info);
/// Helpers for the OpenMP loop directives.
+ void EmitOMPLoopBody(const OMPLoopDirective &D, JumpDest LoopExit);
void EmitOMPSimdInit(const OMPLoopDirective &D, bool IsMonotonic = false);
void EmitOMPSimdFinal(
const OMPLoopDirective &D,
const llvm::function_ref<llvm::Value *(CodeGenFunction &)> &CondGen);
-
- void EmitOMPDistributeLoop(const OMPLoopDirective &S,
- const CodeGenLoopTy &CodeGenLoop, Expr *IncExpr);
-
- /// struct with the values to be passed to the OpenMP loop-related functions
- struct OMPLoopArguments {
- /// loop lower bound
- Address LB = Address::invalid();
- /// loop upper bound
- Address UB = Address::invalid();
- /// loop stride
- Address ST = Address::invalid();
- /// isLastIteration argument for runtime functions
- Address IL = Address::invalid();
- /// Chunk value generated by sema
- llvm::Value *Chunk = nullptr;
- /// EnsureUpperBound
- Expr *EUB = nullptr;
- /// IncrementExpression
- Expr *IncExpr = nullptr;
- /// Loop initialization
- Expr *Init = nullptr;
- /// Loop exit condition
- Expr *Cond = nullptr;
- /// Update of LB after a whole chunk has been executed
- Expr *NextLB = nullptr;
- /// Update of UB after a whole chunk has been executed
- Expr *NextUB = nullptr;
- OMPLoopArguments() = default;
- OMPLoopArguments(Address LB, Address UB, Address ST, Address IL,
- llvm::Value *Chunk = nullptr, Expr *EUB = nullptr,
- Expr *IncExpr = nullptr, Expr *Init = nullptr,
- Expr *Cond = nullptr, Expr *NextLB = nullptr,
- Expr *NextUB = nullptr)
- : LB(LB), UB(UB), ST(ST), IL(IL), Chunk(Chunk), EUB(EUB),
- IncExpr(IncExpr), Init(Init), Cond(Cond), NextLB(NextLB),
- NextUB(NextUB) {}
- };
- void EmitOMPOuterLoop(bool DynamicOrOrdered, bool IsMonotonic,
- const OMPLoopDirective &S, OMPPrivateScope &LoopScope,
- const OMPLoopArguments &LoopArgs,
- const CodeGenLoopTy &CodeGenLoop,
- const CodeGenOrderedTy &CodeGenOrdered);
+ /// \brief Emit code for the worksharing loop-based directive.
+ /// \return true, if this construct has any lastprivate clause, false -
+ /// otherwise.
+ bool EmitOMPWorksharingLoop(const OMPLoopDirective &S);
+ void EmitOMPOuterLoop(bool IsMonotonic, bool DynamicOrOrdered,
+ const OMPLoopDirective &S, OMPPrivateScope &LoopScope, bool Ordered,
+ Address LB, Address UB, Address ST, Address IL, llvm::Value *Chunk);
void EmitOMPForOuterLoop(const OpenMPScheduleTy &ScheduleKind,
bool IsMonotonic, const OMPLoopDirective &S,
- OMPPrivateScope &LoopScope, bool Ordered,
- const OMPLoopArguments &LoopArgs,
- const CodeGenDispatchBoundsTy &CGDispatchBounds);
- void EmitOMPDistributeOuterLoop(OpenMPDistScheduleClauseKind ScheduleKind,
- const OMPLoopDirective &S,
- OMPPrivateScope &LoopScope,
- const OMPLoopArguments &LoopArgs,
- const CodeGenLoopTy &CodeGenLoopContent);
+ OMPPrivateScope &LoopScope, bool Ordered, Address LB,
+ Address UB, Address ST, Address IL,
+ llvm::Value *Chunk);
+ void EmitOMPDistributeOuterLoop(
+ OpenMPDistScheduleClauseKind ScheduleKind,
+ const OMPDistributeDirective &S, OMPPrivateScope &LoopScope,
+ Address LB, Address UB, Address ST, Address IL, llvm::Value *Chunk);
/// \brief Emit code for sections directive.
void EmitSections(const OMPExecutableDirective &S);