merge main into amd-staging

clang/include/clang/AST/Attr.h

@@ -233,44 +233,19 @@ class HLSLAnnotationAttr : public InheritableAttr {
   }
 };
 
-class HLSLSemanticAttr : public HLSLAnnotationAttr {
-  unsigned SemanticIndex = 0;
-  LLVM_PREFERRED_TYPE(bool)
-  unsigned SemanticIndexable : 1;
-  LLVM_PREFERRED_TYPE(bool)
-  unsigned SemanticExplicitIndex : 1;
-
-  Decl *TargetDecl = nullptr;
-
+class HLSLSemanticBaseAttr : public HLSLAnnotationAttr {
 protected:
-  HLSLSemanticAttr(ASTContext &Context, const AttributeCommonInfo &CommonInfo,
-                   attr::Kind AK, bool IsLateParsed,
-                   bool InheritEvenIfAlreadyPresent, bool SemanticIndexable)
+  HLSLSemanticBaseAttr(ASTContext &Context,
+                       const AttributeCommonInfo &CommonInfo, attr::Kind AK,
+                       bool IsLateParsed, bool InheritEvenIfAlreadyPresent)
       : HLSLAnnotationAttr(Context, CommonInfo, AK, IsLateParsed,
-                           InheritEvenIfAlreadyPresent) {
-    this->SemanticIndexable = SemanticIndexable;
-    this->SemanticExplicitIndex = false;
-  }
+                           InheritEvenIfAlreadyPresent) {}
 
 public:
-  bool isSemanticIndexable() const { return SemanticIndexable; }
-
-  void setSemanticIndex(unsigned SemanticIndex) {
-    this->SemanticIndex = SemanticIndex;
-    this->SemanticExplicitIndex = true;
-  }
-
-  unsigned getSemanticIndex() const { return SemanticIndex; }
-
-  bool isSemanticIndexExplicit() const { return SemanticExplicitIndex; }
-
-  void setTargetDecl(Decl *D) { TargetDecl = D; }
-  Decl *getTargetDecl() const { return TargetDecl; }
-
   // Implement isa/cast/dyncast/etc.
   static bool classof(const Attr *A) {
-    return A->getKind() >= attr::FirstHLSLSemanticAttr &&
-           A->getKind() <= attr::LastHLSLSemanticAttr;
+    return A->getKind() >= attr::FirstHLSLSemanticBaseAttr &&
+           A->getKind() <= attr::LastHLSLSemanticBaseAttr;
   }
 };
 

clang/include/clang/Analysis/FlowSensitive/StorageLocation.h

@@ -131,7 +131,7 @@ class RecordStorageLocation final : public StorageLocation {
                      << " on StorageLocation " << this << " of type "
                      << getType() << "\n";
         llvm::dbgs() << "Existing children:\n";
-        for ([[maybe_unused]] auto [Field, Loc] : Children) {
+        for (const auto &Field : Children.keys()) {
           llvm::dbgs() << Field->getNameAsString() << "\n";
         }
       }

clang/include/clang/Basic/Attr.td

@@ -783,18 +783,6 @@ class DeclOrStmtAttr : InheritableAttr;
 /// An attribute class for HLSL Annotations.
 class HLSLAnnotationAttr : InheritableAttr;
 
-class HLSLSemanticAttr<bit Indexable> : HLSLAnnotationAttr {
-  bit SemanticIndexable = Indexable;
-  int SemanticIndex = 0;
-  bit SemanticExplicitIndex = 0;
-
-  let Spellings = [];
-  let Subjects = SubjectList<[ParmVar, Field, Function]>;
-  let LangOpts = [HLSL];
-  let Args = [DeclArgument<Named, "Target">, IntArgument<"SemanticIndex">,
-              BoolArgument<"SemanticExplicitIndex">];
-}
-
 /// A target-specific attribute.  This class is meant to be used as a mixin
 /// with InheritableAttr or Attr depending on the attribute's needs.
 class TargetSpecificAttr<TargetSpec target> {
@@ -5021,28 +5009,28 @@ def HLSLUnparsedSemantic : HLSLAnnotationAttr {
   let Documentation = [InternalOnly];
 }
 
-def HLSLUserSemantic : HLSLSemanticAttr</* Indexable= */ 1> {
-  let Documentation = [InternalOnly];
-}
-
-def HLSLSV_Position : HLSLSemanticAttr</* Indexable= */ 1> {
-  let Documentation = [HLSLSV_PositionDocs];
-}
+class HLSLSemanticBaseAttr : HLSLAnnotationAttr {
+  int SemanticIndex = 0;
 
-def HLSLSV_GroupThreadID : HLSLSemanticAttr</* Indexable= */ 0> {
-  let Documentation = [HLSLSV_GroupThreadIDDocs];
-}
+  let Spellings = [];
+  let Subjects = SubjectList<[ParmVar, Field, Function]>;
+  let LangOpts = [HLSL];
 
-def HLSLSV_GroupID : HLSLSemanticAttr</* Indexable= */ 0> {
-  let Documentation = [HLSLSV_GroupIDDocs];
+  let Args = [StringArgument<"SemanticName">, IntArgument<"SemanticIndex">];
 }
 
-def HLSLSV_GroupIndex : HLSLSemanticAttr</* Indexable= */ 0> {
-  let Documentation = [HLSLSV_GroupIndexDocs];
+def HLSLParsedSemantic : HLSLSemanticBaseAttr {
+  let Spellings = [];
+  let Subjects = SubjectList<[ParmVar, Field, Function]>;
+  let LangOpts = [HLSL];
+  let Documentation = [InternalOnly];
 }
 
-def HLSLSV_DispatchThreadID : HLSLSemanticAttr</* Indexable= */ 0> {
-  let Documentation = [HLSLSV_DispatchThreadIDDocs];
+def HLSLAppliedSemantic : HLSLSemanticBaseAttr {
+  let Spellings = [];
+  let Subjects = SubjectList<[ParmVar, Field, Function]>;
+  let LangOpts = [HLSL];
+  let Documentation = [InternalOnly];
 }
 
 def HLSLPackOffset: HLSLAnnotationAttr {

clang/include/clang/Basic/AttrDocs.td

@@ -8672,38 +8672,6 @@ randomized.
   }];
 }
 
-def HLSLSV_GroupThreadIDDocs : Documentation {
-  let Category = DocHLSLSemantics;
-  let Content = [{
-The ``SV_GroupThreadID`` semantic, when applied to an input parameter, specifies which
-individual thread within a thread group is executing in. This attribute is
-only supported in compute shaders.
-
-The full documentation is available here: https://docs.microsoft.com/en-us/windows/win32/direct3dhlsl/sv-groupthreadid
-  }];
-}
-
-def HLSLSV_GroupIDDocs : Documentation {
-  let Category = DocHLSLSemantics;
-  let Content = [{
-The ``SV_GroupID`` semantic, when applied to an input parameter, specifies which
-thread group a shader is executing in. This attribute is only supported in compute shaders.
-
-The full documentation is available here: https://docs.microsoft.com/en-us/windows/win32/direct3dhlsl/sv-groupid
-  }];
-}
-
-def HLSLSV_GroupIndexDocs : Documentation {
-  let Category = DocHLSLSemantics;
-  let Content = [{
-The ``SV_GroupIndex`` semantic, when applied to an input parameter, specifies a
-data binding to map the group index to the specified parameter. This attribute
-is only supported in compute shaders.
-
-The full documentation is available here: https://docs.microsoft.com/en-us/windows/win32/direct3dhlsl/sv-groupindex
-  }];
-}
-
 def HLSLResourceBindingDocs : Documentation {
   let Category = DocCatFunction;
   let Content = [{
@@ -8750,35 +8718,6 @@ The full documentation is available here: https://learn.microsoft.com/en-us/wind
   }];
 }
 
-def HLSLSV_DispatchThreadIDDocs : Documentation {
-  let Category = DocHLSLSemantics;
-  let Content = [{
-The ``SV_DispatchThreadID`` semantic, when applied to an input parameter,
-specifies a data binding to map the global thread offset within the Dispatch
-call (per dimension of the group) to the specified parameter.
-When applied to a field of a struct, the data binding is specified to the field
-when the struct is used as a parameter type.
-The semantic on the field is ignored when not used as a parameter.
-This attribute is only supported in compute shaders.
-
-The full documentation is available here: https://docs.microsoft.com/en-us/windows/win32/direct3dhlsl/sv-dispatchthreadid
-  }];
-}
-
-def HLSLSV_PositionDocs : Documentation {
-  let Category = DocHLSLSemantics;
-  let Content = [{
-The ``SV_Position`` semantic, when applied to an input parameter in a pixel
-shader, contains the location of the pixel center (x, y) in screen space.
-This semantic can be applied to the parameter, or a field in a struct used
-as an input parameter.
-This attribute is supported as an input in pixel, hull, domain and mesh shaders.
-This attribute is supported as an output in vertex, geometry and domain shaders.
-
-The full documentation is available here: https://docs.microsoft.com/en-us/windows/win32/direct3dhlsl/dx-graphics-hlsl-semantics
-  }];
-}
-
 def HLSLGroupSharedAddressSpaceDocs : Documentation {
   let Category = DocCatVariable;
   let Content = [{

clang/include/clang/Basic/BuiltinsX86.td

@@ -617,9 +617,7 @@ let Features = "avx2", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] i
   def psrlw256 : X86Builtin<"_Vector<16, short>(_Vector<16, short>, _Vector<8, short>)">;
   def psrld256 : X86Builtin<"_Vector<8, int>(_Vector<8, int>, _Vector<4, int>)">;
   def psrlq256 : X86Builtin<"_Vector<4, long long int>(_Vector<4, long long int>, _Vector<2, long long int>)">;
-  def permvarsi256 : X86Builtin<"_Vector<8, int>(_Vector<8, int>, _Vector<8, int>)">;
   def permdf256 : X86Builtin<"_Vector<4, double>(_Vector<4, double>, _Constant int)">;
-  def permvarsf256 : X86Builtin<"_Vector<8, float>(_Vector<8, float>, _Vector<8, int>)">;
   def permti256 : X86Builtin<"_Vector<4, long long int>(_Vector<4, long long int>, _Vector<4, long long int>, _Constant int)">;
   def permdi256 : X86Builtin<"_Vector<4, long long int>(_Vector<4, long long int>, _Constant int)">;
 }
@@ -692,6 +690,9 @@ let Features = "avx2", Attributes = [NoThrow, Const, Constexpr, RequiredVectorWi
   def pshuflw256 : X86Builtin<"_Vector<16, short>(_Vector<16, short>, _Constant int)">;
   def pshufhw256 : X86Builtin<"_Vector<16, short>(_Vector<16, short>, _Constant int)">;
   def pshufd256  : X86Builtin<"_Vector<8, int>(_Vector<8, int>, _Constant int)">;
+
+  def permvarsi256 : X86Builtin<"_Vector<8, int>(_Vector<8, int>, _Vector<8, int>)">;
+  def permvarsf256 : X86Builtin<"_Vector<8, float>(_Vector<8, float>, _Vector<8, int>)">;
 }
 
 let Features = "avx2", Attributes = [NoThrow, Const, Constexpr, RequiredVectorWidth<128>] in {
@@ -3042,38 +3043,38 @@ let Features = "avx512f", Attributes = [NoThrow, Const, RequiredVectorWidth<512>
   def permdi512 : X86Builtin<"_Vector<8, long long int>(_Vector<8, long long int>, _Constant int)">;
 }
 
-let Features = "avx512bw", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
+let Features = "avx512bw", Attributes = [NoThrow, Const, Constexpr, RequiredVectorWidth<512>] in {
   def permvarhi512 : X86Builtin<"_Vector<32, short>(_Vector<32, short>, _Vector<32, short>)">;
 }
 
-let Features = "avx512f", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
+let Features = "avx512f", Attributes = [NoThrow, Const, Constexpr, RequiredVectorWidth<512>] in {
   def permvardf512 : X86Builtin<"_Vector<8, double>(_Vector<8, double>, _Vector<8, long long int>)">;
   def permvardi512 : X86Builtin<"_Vector<8, long long int>(_Vector<8, long long int>, _Vector<8, long long int>)">;
   def permvarsf512 : X86Builtin<"_Vector<16, float>(_Vector<16, float>, _Vector<16, int>)">;
   def permvarsi512 : X86Builtin<"_Vector<16, int>(_Vector<16, int>, _Vector<16, int>)">;
 }
 
-let Features = "avx512vbmi", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
+let Features = "avx512vbmi", Attributes = [NoThrow, Const, Constexpr, RequiredVectorWidth<512>] in {
   def permvarqi512 : X86Builtin<"_Vector<64, char>(_Vector<64, char>, _Vector<64, char>)">;
 }
 
-let Features = "avx512vbmi,avx512vl", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
+let Features = "avx512vbmi,avx512vl", Attributes = [NoThrow, Const, Constexpr, RequiredVectorWidth<128>] in {
   def permvarqi128 : X86Builtin<"_Vector<16, char>(_Vector<16, char>, _Vector<16, char>)">;
 }
 
-let Features = "avx512vbmi,avx512vl", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
+let Features = "avx512vbmi,avx512vl", Attributes = [NoThrow, Const, Constexpr, RequiredVectorWidth<256>] in {
   def permvarqi256 : X86Builtin<"_Vector<32, char>(_Vector<32, char>, _Vector<32, char>)">;
 }
 
-let Features = "avx512bw,avx512vl", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
+let Features = "avx512bw,avx512vl", Attributes = [NoThrow, Const, Constexpr, RequiredVectorWidth<128>] in {
   def permvarhi128 : X86Builtin<"_Vector<8, short>(_Vector<8, short>, _Vector<8, short>)">;
 }
 
-let Features = "avx512bw,avx512vl", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
+let Features = "avx512bw,avx512vl", Attributes = [NoThrow, Const, Constexpr, RequiredVectorWidth<256>] in {
   def permvarhi256 : X86Builtin<"_Vector<16, short>(_Vector<16, short>, _Vector<16, short>)">;
 }
 
-let Features = "avx512vl", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
+let Features = "avx512vl", Attributes = [NoThrow, Const, Constexpr, RequiredVectorWidth<256>] in {
   def permvardf256 : X86Builtin<"_Vector<4, double>(_Vector<4, double>, _Vector<4, long long int>)">;
   def permvardi256 : X86Builtin<"_Vector<4, long long int>(_Vector<4, long long int>, _Vector<4, long long int>)">;
 }

clang/include/clang/Sema/SemaHLSL.h

@@ -178,18 +178,11 @@ class SemaHLSL : public SemaBase {
   bool handleResourceTypeAttr(QualType T, const ParsedAttr &AL);
 
   template <typename T>
-  T *createSemanticAttr(const AttributeCommonInfo &ACI, NamedDecl *TargetDecl,
+  T *createSemanticAttr(const AttributeCommonInfo &ACI,
                         std::optional<unsigned> Location) {
-    T *Attr =
-        ::new (getASTContext()) T(getASTContext(), ACI, TargetDecl,
-                                  Location.value_or(0), Location.has_value());
-
-    if (!Attr->isSemanticIndexable() && Location.has_value()) {
-      Diag(Attr->getLocation(), diag::err_hlsl_semantic_indexing_not_supported)
-          << Attr->getAttrName()->getName();
-      return nullptr;
-    }
-    return Attr;
+    return ::new (getASTContext())
+        T(getASTContext(), ACI, ACI.getAttrName()->getName(),
+          Location.value_or(0));
   }
 
   void diagnoseSystemSemanticAttr(Decl *D, const ParsedAttr &AL,
@@ -247,7 +240,7 @@ class SemaHLSL : public SemaBase {
   IdentifierInfo *RootSigOverrideIdent = nullptr;
 
   struct SemanticInfo {
-    HLSLSemanticAttr *Semantic;
+    HLSLParsedSemanticAttr *Semantic;
     std::optional<uint32_t> Index;
   };
 
@@ -257,14 +250,14 @@ class SemaHLSL : public SemaBase {
                                                const RecordType *RT);
 
   void checkSemanticAnnotation(FunctionDecl *EntryPoint, const Decl *Param,
-                               const HLSLSemanticAttr *SemanticAttr);
-  HLSLSemanticAttr *createSemantic(const SemanticInfo &Semantic,
-                                   DeclaratorDecl *TargetDecl);
-  bool determineActiveSemanticOnScalar(FunctionDecl *FD, DeclaratorDecl *D,
+                               const HLSLAppliedSemanticAttr *SemanticAttr);
+  bool determineActiveSemanticOnScalar(FunctionDecl *FD,
+                                       DeclaratorDecl *OutputDecl,
+                                       DeclaratorDecl *D,
                                        SemanticInfo &ActiveSemantic,
                                        llvm::StringSet<> &ActiveInputSemantics);
-  bool determineActiveSemantic(FunctionDecl *FD, DeclaratorDecl *D,
-                               SemanticInfo &ActiveSemantic,
+  bool determineActiveSemantic(FunctionDecl *FD, DeclaratorDecl *OutputDecl,
+                               DeclaratorDecl *D, SemanticInfo &ActiveSemantic,
                                llvm::StringSet<> &ActiveInputSemantics);
 
   void processExplicitBindingsOnDecl(VarDecl *D);

clang/lib/AST/ByteCode/InterpBuiltin.cpp

@@ -4414,6 +4414,45 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call,
             return std::pair<unsigned, int>{0, static_cast<int>(DstIdx)};
           }
         });
+  case X86::BI__builtin_ia32_permvarsi256:
+  case X86::BI__builtin_ia32_permvarsf256:
+  case X86::BI__builtin_ia32_permvardf512:
+  case X86::BI__builtin_ia32_permvardi512:
+  case X86::BI__builtin_ia32_permvarhi128:
+    return interp__builtin_ia32_shuffle_generic(
+        S, OpPC, Call, [](unsigned DstIdx, unsigned ShuffleMask) {
+          int Offset = ShuffleMask & 0x7;
+          return std::pair<unsigned, int>{0, Offset};
+        });
+  case X86::BI__builtin_ia32_permvarqi128:
+  case X86::BI__builtin_ia32_permvarhi256:
+  case X86::BI__builtin_ia32_permvarsi512:
+  case X86::BI__builtin_ia32_permvarsf512:
+    return interp__builtin_ia32_shuffle_generic(
+        S, OpPC, Call, [](unsigned DstIdx, unsigned ShuffleMask) {
+          int Offset = ShuffleMask & 0xF;
+          return std::pair<unsigned, int>{0, Offset};
+        });
+  case X86::BI__builtin_ia32_permvardi256:
+  case X86::BI__builtin_ia32_permvardf256:
+    return interp__builtin_ia32_shuffle_generic(
+        S, OpPC, Call, [](unsigned DstIdx, unsigned ShuffleMask) {
+          int Offset = ShuffleMask & 0x3;
+          return std::pair<unsigned, int>{0, Offset};
+        });
+  case X86::BI__builtin_ia32_permvarqi256:
+  case X86::BI__builtin_ia32_permvarhi512:
+    return interp__builtin_ia32_shuffle_generic(
+        S, OpPC, Call, [](unsigned DstIdx, unsigned ShuffleMask) {
+          int Offset = ShuffleMask & 0x1F;
+          return std::pair<unsigned, int>{0, Offset};
+        });
+  case X86::BI__builtin_ia32_permvarqi512:
+    return interp__builtin_ia32_shuffle_generic(
+        S, OpPC, Call, [](unsigned DstIdx, unsigned ShuffleMask) {
+          int Offset = ShuffleMask & 0x3F;
+          return std::pair<unsigned, int>{0, Offset};
+        });
   case X86::BI__builtin_ia32_vpermi2varq128:
   case X86::BI__builtin_ia32_vpermi2varpd128:
     return interp__builtin_ia32_shuffle_generic(