[OpenACC] Switch Clang to use the Flang 'appertainment' rules for cla…

clang/include/clang/Basic/DiagnosticSemaKinds.td

@@ -12961,6 +12961,19 @@ def err_acc_clause_after_device_type
 def err_acc_clause_cannot_combine
     : Error<"OpenACC clause '%0' may not appear on the same construct as a "
             "'%1' clause on a '%2' construct">;
+def err_acc_clause_routine_cannot_combine_before_device_type
+    : Error<"OpenACC clause '%0' after 'device_type' clause on a 'routine' "
+              "conflicts with the '%1' clause before the first 'device_type'">;
+def err_acc_clause_routine_cannot_combine_same_device_type
+    : Error<"OpenACC clause '%0' on a 'routine' directive conflicts with the "
+            "'%1' clause applying to the same 'device_type'">;
+def err_acc_clause_routine_one_of_in_region
+    : Error<"OpenACC 'routine' construct must have at least one 'gang', 'seq', "
+            "'vector', or 'worker' clause that applies to each 'device_type'">;
+def err_acc_clause_since_last_device_type
+    : Error<"OpenACC '%0' clause cannot appear more than once%select{| in a "
+            "'device_type' region}2 on a '%1' directive">;
+
 def err_acc_reduction_num_gangs_conflict
     : Error<"OpenACC '%1' clause %select{|with more than 1 argument }0may not "
             "appear on a '%2' construct "
@@ -12978,9 +12991,6 @@ def note_acc_reduction_composite_member_loc : Note<"invalid field is here">;
 def err_acc_loop_not_for_loop
     : Error<"OpenACC '%0' construct can only be applied to a 'for' loop">;
 def note_acc_construct_here : Note<"'%0' construct is here">;
-def err_acc_loop_spec_conflict
-    : Error<"OpenACC clause '%0' on '%1' construct conflicts with previous "
-            "data dependence clause">;
 def err_acc_collapse_loop_count
     : Error<"OpenACC 'collapse' clause loop count must be a %select{constant "
             "expression|positive integer value, evaluated to %1}0">;
@@ -13032,9 +13042,10 @@ def err_acc_gang_reduction_numgangs_conflict
             "'%1' clause %select{inside a compute construct with a|and a}3 "
             "'num_gangs' clause with more than one argument">;
 
-    def err_reduction_op_mismatch
+def err_reduction_op_mismatch
     : Error<"OpenACC 'reduction' variable must have the same operator in all "
             "nested constructs (%0 vs %1)">;
+
 def err_acc_loop_variable_type
     : Error<"loop variable of loop associated with an OpenACC '%0' construct "
             "must be of integer, pointer, or random-access-iterator type (is "

clang/include/clang/Basic/OpenACCKinds.h

@@ -202,133 +202,140 @@ inline llvm::raw_ostream &operator<<(llvm::raw_ostream &Out,
   return printOpenACCAtomicKind(Out, AK);
 }
 
-/// Represents the kind of an OpenACC clause.
+/// Represents the kind of an OpenACC clause. Sorted alphabetically, since this
+/// order ends up influencing the sorting of the list diagnostic.
 enum class OpenACCClauseKind : uint8_t {
-  /// 'finalize' clause, allowed on 'exit data' directive.
-  Finalize,
-  /// 'if_present' clause, allowed on 'host_data' and 'update' directives.
-  IfPresent,
-  /// 'seq' clause, allowed on 'loop' and 'routine' directives.
-  Seq,
-  /// 'independent' clause, allowed on 'loop' directives.
-  Independent,
+  /// 'async' clause, allowed on Compute, Data, 'update', 'wait', and Combined
+  /// constructs.
+  Async,
+  /// 'attach' clause, allowed on Compute and Combined constructs, plus 'data'
+  /// and 'enter data'.
+  Attach,
   /// 'auto' clause, allowed on 'loop' directives.
   Auto,
-  /// 'worker' clause, allowed on 'loop', Combined, and 'routine' directives.
-  Worker,
-  /// 'vector' clause, allowed on 'loop', Combined, and 'routine' directives.
-  Vector,
-  /// 'nohost' clause, allowed on 'routine' directives.
-  NoHost,
-  /// 'default' clause, allowed on parallel, serial, kernel (and compound)
-  /// constructs.
-  Default,
-  /// 'if' clause, allowed on all the Compute Constructs, Data Constructs,
-  /// Executable Constructs, and Combined Constructs.
-  If,
-  /// 'self' clause, allowed on Compute and Combined Constructs, plus 'update'.
-  Self,
+  /// 'bind' clause, allowed on routine constructs.
+  Bind,
+  /// 'collapse' clause, allowed on 'loop' and Combined constructs.
+  Collapse,
   /// 'copy' clause, allowed on Compute and Combined Constructs, plus 'data' and
   /// 'declare'.
   Copy,
   /// 'copy' clause alias 'pcopy'.  Preserved for diagnostic purposes.
   PCopy,
   /// 'copy' clause alias 'present_or_copy'.  Preserved for diagnostic purposes.
   PresentOrCopy,
-  /// 'use_device' clause, allowed on 'host_data' construct.
-  UseDevice,
-  /// 'attach' clause, allowed on Compute and Combined constructs, plus 'data'
-  /// and 'enter data'.
-  Attach,
+  /// 'copyin' clause, allowed on Compute and Combined constructs, plus 'data',
+  /// 'enter data', and 'declare'.
+  CopyIn,
+  /// 'copyin' clause alias 'pcopyin'.  Preserved for diagnostic purposes.
+  PCopyIn,
+  /// 'copyin' clause alias 'present_or_copyin'.  Preserved for diagnostic
+  /// purposes.
+  PresentOrCopyIn,
+  /// 'copyout' clause, allowed on Compute and Combined constructs, plus 'data',
+  /// 'exit data', and 'declare'.
+  CopyOut,
+  /// 'copyout' clause alias 'pcopyout'.  Preserved for diagnostic purposes.
+  PCopyOut,
+  /// 'copyout' clause alias 'present_or_copyout'.  Preserved for diagnostic
+  /// purposes.
+  PresentOrCopyOut,
+  /// 'create' clause, allowed on Compute and Combined constructs, plus 'data',
+  /// 'enter data', and 'declare'.
+  Create,
+  /// 'create' clause alias 'pcreate'.  Preserved for diagnostic purposes.
+  PCreate,
+  /// 'create' clause alias 'present_or_create'.  Preserved for diagnostic
+  /// purposes.
+  PresentOrCreate,
+  /// 'default' clause, allowed on parallel, serial, kernel (and compound)
+  /// constructs.
+  Default,
+  /// 'default_async' clause, allowed on 'set' construct.
+  DefaultAsync,
   /// 'delete' clause, allowed on the 'exit data' construct.
   Delete,
   /// 'detach' clause, allowed on the 'exit data' construct.
   Detach,
   /// 'device' clause, allowed on the 'update' construct.
   Device,
+  /// 'device_num' clause, allowed on 'init', 'shutdown', and 'set' constructs.
+  DeviceNum,
   /// 'deviceptr' clause, allowed on Compute and Combined Constructs, plus
   /// 'data' and 'declare'.
   DevicePtr,
   /// 'device_resident' clause, allowed on the 'declare' construct.
   DeviceResident,
+  /// 'device_type' clause, allowed on Compute, 'data', 'init', 'shutdown',
+  /// 'set', update', 'loop', 'routine', and Combined constructs.
+  DeviceType,
+  /// 'dtype' clause, an alias for 'device_type', stored separately for
+  /// diagnostic purposes.
+  DType,
+  /// 'finalize' clause, allowed on 'exit data' directive.
+  Finalize,
   /// 'firstprivate' clause, allowed on 'parallel', 'serial', 'parallel loop',
   /// and 'serial loop' constructs.
   FirstPrivate,
+  /// 'gang' clause, allowed on 'loop' and Combined constructs.
+  Gang,
   /// 'host' clause, allowed on 'update' construct.
   Host,
+  /// 'if' clause, allowed on all the Compute Constructs, Data Constructs,
+  /// Executable Constructs, and Combined Constructs.
+  If,
+  /// 'if_present' clause, allowed on 'host_data' and 'update' directives.
+  IfPresent,
+  /// 'independent' clause, allowed on 'loop' directives.
+  Independent,
   /// 'link' clause, allowed on 'declare' construct.
   Link,
   /// 'no_create' clause, allowed on allowed on Compute and Combined constructs,
   /// plus 'data'.
   NoCreate,
+  /// 'nohost' clause, allowed on 'routine' directives.
+  NoHost,
+  /// 'num_gangs' clause, allowed on 'parallel', 'kernels', parallel loop', and
+  /// 'kernels loop' constructs.
+  NumGangs,
+  /// 'num_workers' clause, allowed on 'parallel', 'kernels', parallel loop',
+  /// and 'kernels loop' constructs.
+  NumWorkers,
   /// 'present' clause, allowed on Compute and Combined constructs, plus 'data'
   /// and 'declare'.
   Present,
   /// 'private' clause, allowed on 'parallel', 'serial', 'loop', 'parallel
   /// loop', and 'serial loop' constructs.
   Private,
-  /// 'copyout' clause, allowed on Compute and Combined constructs, plus 'data',
-  /// 'exit data', and 'declare'.
-  CopyOut,
-  /// 'copyout' clause alias 'pcopyout'.  Preserved for diagnostic purposes.
-  PCopyOut,
-  /// 'copyout' clause alias 'present_or_copyout'.  Preserved for diagnostic
-  /// purposes.
-  PresentOrCopyOut,
-  /// 'copyin' clause, allowed on Compute and Combined constructs, plus 'data',
-  /// 'enter data', and 'declare'.
-  CopyIn,
-  /// 'copyin' clause alias 'pcopyin'.  Preserved for diagnostic purposes.
-  PCopyIn,
-  /// 'copyin' clause alias 'present_or_copyin'.  Preserved for diagnostic
-  /// purposes.
-  PresentOrCopyIn,
-  /// 'create' clause, allowed on Compute and Combined constructs, plus 'data',
-  /// 'enter data', and 'declare'.
-  Create,
-  /// 'create' clause alias 'pcreate'.  Preserved for diagnostic purposes.
-  PCreate,
-  /// 'create' clause alias 'present_or_create'.  Preserved for diagnostic
-  /// purposes.
-  PresentOrCreate,
   /// 'reduction' clause, allowed on Parallel, Serial, Loop, and the combined
   /// constructs.
   Reduction,
-  /// 'collapse' clause, allowed on 'loop' and Combined constructs.
-  Collapse,
-  /// 'bind' clause, allowed on routine constructs.
-  Bind,
+  /// 'self' clause, allowed on Compute and Combined Constructs, plus 'update'.
+  Self,
+  /// 'seq' clause, allowed on 'loop' and 'routine' directives.
+  Seq,
+  /// 'tile' clause, allowed on 'loop' and Combined constructs.
+  Tile,
+  /// 'use_device' clause, allowed on 'host_data' construct.
+  UseDevice,
+  /// 'vector' clause, allowed on 'loop', Combined, and 'routine' directives.
+  Vector,
   /// 'vector_length' clause, allowed on 'parallel', 'kernels', 'parallel loop',
   /// and 'kernels loop' constructs.
   VectorLength,
-  /// 'num_gangs' clause, allowed on 'parallel', 'kernels', parallel loop', and
-  /// 'kernels loop' constructs.
-  NumGangs,
-  /// 'num_workers' clause, allowed on 'parallel', 'kernels', parallel loop',
-  /// and 'kernels loop' constructs.
-  NumWorkers,
-  /// 'device_num' clause, allowed on 'init', 'shutdown', and 'set' constructs.
-  DeviceNum,
-  /// 'default_async' clause, allowed on 'set' construct.
-  DefaultAsync,
-  /// 'device_type' clause, allowed on Compute, 'data', 'init', 'shutdown',
-  /// 'set', update', 'loop', 'routine', and Combined constructs.
-  DeviceType,
-  /// 'dtype' clause, an alias for 'device_type', stored separately for
-  /// diagnostic purposes.
-  DType,
-  /// 'async' clause, allowed on Compute, Data, 'update', 'wait', and Combined
-  /// constructs.
-  Async,
-  /// 'tile' clause, allowed on 'loop' and Combined constructs.
-  Tile,
-  /// 'gang' clause, allowed on 'loop' and Combined constructs.
-  Gang,
   /// 'wait' clause, allowed on Compute, Data, 'update', and Combined
   /// constructs.
   Wait,
+  /// 'worker' clause, allowed on 'loop', Combined, and 'routine' directives.
+  Worker,
 
-  /// Represents an invalid clause, for the purposes of parsing.
+  /// 'shortloop' is represented in the ACC.td file, but isn't present in the
+  /// standard. This appears to be an old extension for the nvidia fortran
+  // compiler, but seemingly not elsewhere. Put it here as a placeholder, but it
+  // is never expected to be generated.
+  Shortloop,
+  /// Represents an invalid clause, for the purposes of parsing. Should be
+  /// 'last'.
   Invalid,
 };
 
@@ -485,6 +492,9 @@ inline StreamTy &printOpenACCClauseKind(StreamTy &Out, OpenACCClauseKind K) {
   case OpenACCClauseKind::Wait:
     return Out << "wait";
 
+  case OpenACCClauseKind::Shortloop:
+    llvm_unreachable("Shortloop shouldn't be generated in clang");
+    LLVM_FALLTHROUGH;
   case OpenACCClauseKind::Invalid:
     return Out << "<invalid>";
   }

clang/include/clang/Sema/SemaOpenACC.h

@@ -78,7 +78,7 @@ class SemaOpenACC : public SemaBase {
   /// Collapse has an 'N' count that makes it apply to a number of loops 'below'
   /// it.
   struct CollapseCheckingInfo {
-    OpenACCCollapseClause *ActiveCollapse = nullptr;
+    const OpenACCCollapseClause *ActiveCollapse = nullptr;
 
     /// This is a value that maintains the current value of the 'N' on the
     /// current collapse, minus the depth that has already been traversed. When
@@ -107,7 +107,7 @@ class SemaOpenACC : public SemaBase {
     /// own counting of elements.
     UnsignedOrNone CurTileCount = std::nullopt;
 
-    /// Records whether we've hit a 'CurTileCount' of '0' on the wya down,
+    /// Records whether we've hit a 'CurTileCount' of '0' on the way down,
     /// which allows us to diagnose if the number of arguments is too large for
     /// the current number of 'for' loops.
     bool TileDepthSatisfied = true;
@@ -177,6 +177,21 @@ class SemaOpenACC : public SemaBase {
 
   void CheckLastRoutineDeclNameConflict(const NamedDecl *ND);
 
+  bool DiagnoseRequiredClauses(OpenACCDirectiveKind DK, SourceLocation DirLoc,
+                               ArrayRef<const OpenACCClause *> Clauses);
+
+  bool DiagnoseAllowedClauses(OpenACCDirectiveKind DK, OpenACCClauseKind CK,
+                              SourceLocation ClauseLoc);
+
+public:
+  // Needed from the visitor, so should be public.
+  bool DiagnoseAllowedOnceClauses(OpenACCDirectiveKind DK, OpenACCClauseKind CK,
+                                  SourceLocation ClauseLoc,
+                                  ArrayRef<const OpenACCClause *> Clauses);
+  bool DiagnoseExclusiveClauses(OpenACCDirectiveKind DK, OpenACCClauseKind CK,
+                                SourceLocation ClauseLoc,
+                                ArrayRef<const OpenACCClause *> Clauses);
+
 public:
   ComputeConstructInfo &getActiveComputeConstructInfo() {
     return ActiveComputeConstructInfo;

clang/lib/AST/OpenACCClause.cpp

@@ -190,18 +190,15 @@ OpenACCCollapseClause::OpenACCCollapseClause(SourceLocation BeginLoc,
                                              SourceLocation EndLoc)
     : OpenACCClauseWithSingleIntExpr(OpenACCClauseKind::Collapse, BeginLoc,
                                      LParenLoc, LoopCount, EndLoc),
-      HasForce(HasForce) {
-  assert(LoopCount && "LoopCount required");
-}
+      HasForce(HasForce) {}
 
 OpenACCCollapseClause *
 OpenACCCollapseClause::Create(const ASTContext &C, SourceLocation BeginLoc,
                               SourceLocation LParenLoc, bool HasForce,
                               Expr *LoopCount, SourceLocation EndLoc) {
-  assert(
-      LoopCount &&
-      (LoopCount->isInstantiationDependent() || isa<ConstantExpr>(LoopCount)) &&
-      "Loop count not constant expression");
+  assert((!LoopCount || (LoopCount->isInstantiationDependent() ||
+                         isa<ConstantExpr>(LoopCount))) &&
+         "Loop count not constant expression");
   void *Mem =
       C.Allocate(sizeof(OpenACCCollapseClause), alignof(OpenACCCollapseClause));
   return new (Mem)

clang/lib/AST/TextNodeDumper.cpp

@@ -433,6 +433,7 @@ void TextNodeDumper::Visit(const OpenACCClause *C) {
     case OpenACCClauseKind::Vector:
     case OpenACCClauseKind::VectorLength:
     case OpenACCClauseKind::Invalid:
+    case OpenACCClauseKind::Shortloop:
       // The condition expression will be printed as a part of the 'children',
       // but print 'clause' here so it is clear what is happening from the dump.
       OS << " clause";

clang/lib/Parse/ParseOpenACC.cpp

@@ -537,6 +537,8 @@ ClauseParensKind getClauseParensKind(OpenACCDirectiveKind DirKind,
   case OpenACCClauseKind::Tile:
     return ClauseParensKind::Required;
 
+  case OpenACCClauseKind::Shortloop:
+    llvm_unreachable("Shortloop shouldn't be generated in clang");
   case OpenACCClauseKind::Auto:
   case OpenACCClauseKind::Finalize:
   case OpenACCClauseKind::IfPresent:

clang/lib/Sema/CMakeLists.txt

@@ -75,6 +75,7 @@ add_clang_library(clangSema
   SemaOpenACC.cpp
   SemaOpenACCAtomic.cpp
   SemaOpenACCClause.cpp
+  SemaOpenACCClauseAppertainment.cpp
   SemaOpenCL.cpp
   SemaOpenMP.cpp
   SemaOverload.cpp