carlo.bertolli created this revision.
This patch adds two fields for use in the implementation of 'distribute
parallel for':
1. The increment expression for the distribute loop. As the chunk assigned to a
team is executed by multiple threads within the 'parallel for' region, the
increment expression has to correspond to the value returned by the related
runtime call (for_static_init).
2. The upper bound of the innermost loop ('for' in 'distribute parallel for')
is not the globalUB expression normally used for pragma 'for' when found in
isolation. It is instead the upper bound of the chunk assigned to the team
('distribute' loop). In this way, we prevent teams from executing chunks
assigned to other teams.
The use of these two fields can be see in a related explanatory patch:
https://reviews.llvm.org/D29508
Repository:
rL LLVM
https://reviews.llvm.org/D29922
Files:
include/clang/AST/StmtOpenMP.h
lib/AST/StmtOpenMP.cpp
lib/Basic/OpenMPKinds.cpp
lib/Sema/SemaOpenMP.cpp
lib/Serialization/ASTReaderStmt.cpp
lib/Serialization/ASTWriterStmt.cpp
Index: lib/Serialization/ASTWriterStmt.cpp
===================================================================
--- lib/Serialization/ASTWriterStmt.cpp
+++ lib/Serialization/ASTWriterStmt.cpp
@@ -2241,6 +2241,8 @@
if (isOpenMPLoopBoundSharingDirective(D->getDirectiveKind())) {
Record.AddStmt(D->getPrevLowerBoundVariable());
Record.AddStmt(D->getPrevUpperBoundVariable());
+ Record.AddStmt(D->getDistInc());
+ Record.AddStmt(D->getPrevEnsureUpperBound());
}
for (auto I : D->counters()) {
Record.AddStmt(I);
Index: lib/Serialization/ASTReaderStmt.cpp
===================================================================
--- lib/Serialization/ASTReaderStmt.cpp
+++ lib/Serialization/ASTReaderStmt.cpp
@@ -2571,6 +2571,8 @@
if (isOpenMPLoopBoundSharingDirective(D->getDirectiveKind())) {
D->setPrevLowerBoundVariable(Record.readSubExpr());
D->setPrevUpperBoundVariable(Record.readSubExpr());
+ D->setDistInc(Record.readSubExpr());
+ D->setPrevEnsureUpperBound(Record.readSubExpr());
}
SmallVector<Expr *, 4> Sub;
unsigned CollapsedNum = D->getCollapsedNumber();
Index: lib/Sema/SemaOpenMP.cpp
===================================================================
--- lib/Sema/SemaOpenMP.cpp
+++ lib/Sema/SemaOpenMP.cpp
@@ -4181,6 +4181,36 @@
return 0;
}
+ // Create: increment expression for distribute loop when combined in a same
+ // directive with for as IV = IV + ST; ensure upper bound expression based
+ // on PrevUB instead of NumIterations - used to implement 'for' when found
+ // in combination with 'distribute', like in 'distribute parallel for'
+ SourceLocation DistIncLoc;
+ ExprResult DistCond, DistInc, PrevEUB;
+ if (isOpenMPLoopBoundSharingDirective(DKind)) {
+ DistCond = SemaRef.BuildBinOp(CurScope, CondLoc, BO_LE, IV.get(), UB.get());
+ assert(DistCond.isUsable() && "distribute cond expr was not built");
+
+ DistInc =
+ SemaRef.BuildBinOp(CurScope, DistIncLoc, BO_Add, IV.get(), ST.get());
+ assert(DistInc.isUsable() && "distribute inc expr was not built");
+ DistInc = SemaRef.BuildBinOp(CurScope, DistIncLoc, BO_Assign, IV.get(),
+ DistInc.get());
+ DistInc = SemaRef.ActOnFinishFullExpr(DistInc.get());
+ assert(DistInc.isUsable() && "distribute inc expr was not built");
+
+ // Build expression: UB = min(UB, prevUB) for #for in composite or combined
+ // construct
+ SourceLocation DistEUBLoc;
+ ExprResult IsUBGreater =
+ SemaRef.BuildBinOp(CurScope, DistEUBLoc, BO_GT, UB.get(), PrevUB.get());
+ ExprResult CondOp = SemaRef.ActOnConditionalOp(
+ DistEUBLoc, DistEUBLoc, IsUBGreater.get(), PrevUB.get(), UB.get());
+ PrevEUB = SemaRef.BuildBinOp(CurScope, DistIncLoc, BO_Assign, UB.get(),
+ CondOp.get());
+ PrevEUB = SemaRef.ActOnFinishFullExpr(PrevEUB.get());
+ }
+
// Build updates and final values of the loop counters.
bool HasErrors = false;
Built.Counters.resize(NestedLoopCount);
@@ -4295,6 +4325,8 @@
Built.NUB = NextUB.get();
Built.PrevLB = PrevLB.get();
Built.PrevUB = PrevUB.get();
+ Built.DistInc = DistInc.get();
+ Built.PrevEUB = PrevEUB.get();
Expr *CounterVal = SemaRef.DefaultLvalueConversion(IV.get()).get();
// Fill data for doacross depend clauses.
Index: lib/Basic/OpenMPKinds.cpp
===================================================================
--- lib/Basic/OpenMPKinds.cpp
+++ lib/Basic/OpenMPKinds.cpp
@@ -873,6 +873,7 @@
case OMPD_parallel_for:
case OMPD_parallel_for_simd:
case OMPD_parallel_sections:
+ case OMPD_distribute_parallel_for:
CaptureRegions.push_back(OMPD_parallel);
break;
case OMPD_target_teams:
@@ -902,7 +903,6 @@
case OMPD_taskloop_simd:
case OMPD_distribute_parallel_for_simd:
case OMPD_distribute_simd:
- case OMPD_distribute_parallel_for:
case OMPD_teams_distribute:
case OMPD_teams_distribute_simd:
case OMPD_teams_distribute_parallel_for_simd:
Index: lib/AST/StmtOpenMP.cpp
===================================================================
--- lib/AST/StmtOpenMP.cpp
+++ lib/AST/StmtOpenMP.cpp
@@ -149,6 +149,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -201,6 +203,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -366,6 +370,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -417,6 +423,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -753,6 +761,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -896,6 +906,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -947,6 +959,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -997,6 +1011,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1071,6 +1087,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1127,6 +1145,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1182,6 +1202,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1236,6 +1258,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1330,6 +1354,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1383,6 +1409,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1438,6 +1466,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1496,6 +1526,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1576,6 +1608,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1634,6 +1668,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1695,6 +1731,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
@@ -1753,6 +1791,8 @@
Dir->setNumIterations(Exprs.NumIterations);
Dir->setPrevLowerBoundVariable(Exprs.PrevLB);
Dir->setPrevUpperBoundVariable(Exprs.PrevUB);
+ Dir->setDistInc(Exprs.DistInc);
+ Dir->setPrevEnsureUpperBound(Exprs.PrevEUB);
Dir->setCounters(Exprs.Counters);
Dir->setPrivateCounters(Exprs.PrivateCounters);
Dir->setInits(Exprs.Inits);
Index: include/clang/AST/StmtOpenMP.h
===================================================================
--- include/clang/AST/StmtOpenMP.h
+++ include/clang/AST/StmtOpenMP.h
@@ -324,6 +324,11 @@
/// allocated: loop counters, their updates and final values.
/// PrevLowerBound and PrevUpperBound are used to communicate blocking
/// information in composite constructs which require loop blocking
+ /// DistInc is used to generate the increment expression for the distribute
+ /// loop when combined with a further nested loop
+ /// PrevEnsureUpperBound is used as the EnsureUpperBound expression for the
+ /// for loop when combined with a previous distribute loop in the same pragma
+ /// (e.g. 'distribute parallel for')
///
enum {
AssociatedStmtOffset = 0,
@@ -339,7 +344,7 @@
// specify the offset to the end (and start of the following counters/
// updates/finals arrays).
DefaultEnd = 9,
- // The following 7 exprs are used by worksharing loops only.
+ // The following 12 exprs are used by worksharing and distribute loops only.
IsLastIterVariableOffset = 9,
LowerBoundVariableOffset = 10,
UpperBoundVariableOffset = 11,
@@ -350,9 +355,11 @@
NumIterationsOffset = 16,
PrevLowerBoundVariableOffset = 17,
PrevUpperBoundVariableOffset = 18,
+ DistIncOffset = 19,
+ PrevEnsureUpperBoundOffset = 20,
// Offset to the end (and start of the following counters/updates/finals
// arrays) for worksharing loop directives.
- WorksharingEnd = 19,
+ WorksharingEnd = 21,
};
/// \brief Get the counters storage.
@@ -521,6 +528,20 @@
"expected worksharing loop directive");
*std::next(child_begin(), PrevUpperBoundVariableOffset) = PrevUB;
}
+ void setDistInc(Expr *DistInc) {
+ assert((isOpenMPWorksharingDirective(getDirectiveKind()) ||
+ isOpenMPTaskLoopDirective(getDirectiveKind()) ||
+ isOpenMPDistributeDirective(getDirectiveKind())) &&
+ "expected worksharing loop directive");
+ *std::next(child_begin(), DistIncOffset) = DistInc;
+ }
+ void setPrevEnsureUpperBound(Expr *PrevEUB) {
+ assert((isOpenMPWorksharingDirective(getDirectiveKind()) ||
+ isOpenMPTaskLoopDirective(getDirectiveKind()) ||
+ isOpenMPDistributeDirective(getDirectiveKind())) &&
+ "expected worksharing loop directive");
+ *std::next(child_begin(), PrevEnsureUpperBoundOffset) = PrevEUB;
+ }
void setCounters(ArrayRef<Expr *> A);
void setPrivateCounters(ArrayRef<Expr *> A);
void setInits(ArrayRef<Expr *> A);
@@ -555,7 +576,7 @@
Expr *UB;
/// \brief Stride - local variable passed to runtime.
Expr *ST;
- /// \brief EnsureUpperBound -- expression LB = min(LB, NumIterations).
+ /// \brief EnsureUpperBound -- expression UB = min(UB, NumIterations).
Expr *EUB;
/// \brief Update of LowerBound for statically sheduled 'omp for' loops.
Expr *NLB;
@@ -567,6 +588,16 @@
/// \brief PreviousUpperBound - local variable passed to runtime in the
/// enclosing schedule or null if that does not apply.
Expr *PrevUB;
+ /// \brief DistInc - increment expression for distribute loop when found
+ /// combined with a further loop level (e.g. in 'distribute parallel for')
+ /// expression IV = IV + ST
+ Expr *DistInc;
+ /// \brief PrevEUB - expression similar to EUB but to be used when loop
+ /// scheduling uses PrevLB and PrevUB (e.g. in 'distribute parallel for'
+ /// when ensuring that the UB is either the calculated UB by the runtime or
+ /// the end of the assigned distribute chunk)
+ /// expression UB = min (UB, PrevUB)
+ Expr *PrevEUB;
/// \brief Counters Loop counters.
SmallVector<Expr *, 4> Counters;
/// \brief PrivateCounters Loop counters.
@@ -608,6 +639,8 @@
NumIterations = nullptr;
PrevLB = nullptr;
PrevUB = nullptr;
+ DistInc = nullptr;
+ PrevEUB = nullptr;
Counters.resize(Size);
PrivateCounters.resize(Size);
Inits.resize(Size);
@@ -739,6 +772,22 @@
return const_cast<Expr *>(reinterpret_cast<const Expr *>(
*std::next(child_begin(), PrevUpperBoundVariableOffset)));
}
+ Expr *getDistInc() const {
+ assert((isOpenMPWorksharingDirective(getDirectiveKind()) ||
+ isOpenMPTaskLoopDirective(getDirectiveKind()) ||
+ isOpenMPDistributeDirective(getDirectiveKind())) &&
+ "expected worksharing loop directive");
+ return const_cast<Expr *>(reinterpret_cast<const Expr *>(
+ *std::next(child_begin(), DistIncOffset)));
+ }
+ Expr *getPrevEnsureUpperBound() const {
+ assert((isOpenMPWorksharingDirective(getDirectiveKind()) ||
+ isOpenMPTaskLoopDirective(getDirectiveKind()) ||
+ isOpenMPDistributeDirective(getDirectiveKind())) &&
+ "expected worksharing loop directive");
+ return const_cast<Expr *>(reinterpret_cast<const Expr *>(
+ *std::next(child_begin(), PrevEnsureUpperBoundOffset)));
+ }
const Stmt *getBody() const {
// This relies on the loop form is already checked by Sema.
Stmt *Body = getAssociatedStmt()->IgnoreContainers(true);
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
