[CIR] Refactor StructType with TableGen (#1504)

el-ev · Lancern · AmrDeveloper · web-flow · commit 9ec10f93feed · 2025-03-25T11:07:51.000-07:00
Closes #1367 --------- Co-authored-by: Sirui Mu <msrlancern@gmail.com> Co-authored-by: Amr Hesham <amr96@programmer.net> Co-authored-by: Chibuoyim (Wilson) Ogbonna <ogbonnachibuoyim12@gmail.com> Co-authored-by: Yue Huang <30948580+AdUhTkJm@users.noreply.github.com> Co-authored-by: Morris Hafner <mmha@users.noreply.github.com> Co-authored-by: Morris Hafner <mhafner@nvidia.com> Co-authored-by: Sharp-Edged <48861530+Sharp-Edged@users.noreply.github.com> Co-authored-by: Bruno Cardoso Lopes <bruno.cardoso@gmail.com> Co-authored-by: Letu Ren <fantasquex@gmail.com>
diff --git a/clang/include/clang/CIR/Dialect/IR/CIROps.td b/clang/include/clang/CIR/Dialect/IR/CIROps.td
@@ -2918,7 +2918,7 @@ def ExtractMemberOp : CIR_Op<"extract_member", [Pure]> {
     ```
   }];
 
-  let arguments = (ins CIR_StructType:$record, IndexAttr:$index_attr);
+  let arguments = (ins CIRStructType:$record, IndexAttr:$index_attr);
   let results = (outs CIR_AnyType:$result);
 
   let assemblyFormat = [{
@@ -2982,9 +2982,9 @@ def InsertMemberOp : CIR_Op<"insert_member",
     ```
   }];
 
-  let arguments = (ins CIR_StructType:$record, IndexAttr:$index_attr,
+  let arguments = (ins CIRStructType:$record, IndexAttr:$index_attr,
                        CIR_AnyType:$value);
-  let results = (outs CIR_StructType:$result);
+  let results = (outs CIRStructType:$result);
 
   let builders = [
     OpBuilder<(ins "mlir::Value":$record, "uint64_t":$index,
diff --git a/clang/include/clang/CIR/Dialect/IR/CIRTypes.h b/clang/include/clang/CIR/Dialect/IR/CIRTypes.h
@@ -16,173 +16,15 @@
 #include "mlir/IR/BuiltinAttributes.h"
 #include "mlir/IR/Types.h"
 #include "mlir/Interfaces/DataLayoutInterfaces.h"
-#include "clang/CIR/Interfaces/CIRFPTypeInterface.h"
-
-#include "clang/CIR/Interfaces/ASTAttrInterfaces.h"
-
 #include "clang/CIR/Dialect/IR/CIROpsEnums.h"
-
-//===----------------------------------------------------------------------===//
-// CIR StructType
-//
-// The base type for all RecordDecls.
-//===----------------------------------------------------------------------===//
+#include "clang/CIR/Interfaces/ASTAttrInterfaces.h"
+#include "clang/CIR/Interfaces/CIRFPTypeInterface.h"
 
 namespace cir {
-
 namespace detail {
 struct StructTypeStorage;
 } // namespace detail
 
-/// Each unique clang::RecordDecl is mapped to a `cir.struct` and any object in
-/// C/C++ that has a struct type will have a `cir.struct` in CIR.
-///
-/// There are three possible formats for this type:
-///
-///  - Identified and complete structs: unique name and a known body.
-///  - Identified and incomplete structs: unique name and unknown body.
-///  - Anonymous structs: no name and a known body.
-///
-/// Identified structs are uniqued by their name, and anonymous structs are
-/// uniqued by their body. This means that two anonymous structs with the same
-/// body will be the same type, and two identified structs with the same name
-/// will be the same type. Attempting to build a struct with an existing name,
-/// but a different body will result in an error.
-///
-/// A few examples:
-///
-/// ```mlir
-///     !complete = !cir.struct<struct "complete" {!cir.int<u, 8>}>
-///     !incomplete = !cir.struct<struct "incomplete" incomplete>
-///     !anonymous = !cir.struct<struct {!cir.int<u, 8>}>
-/// ```
-///
-/// Incomplete structs are mutable, meaning they can be later completed with a
-/// body automatically updating in place every type in the code that uses the
-/// incomplete struct. Mutability allows for recursive types to be represented,
-/// meaning the struct can have members that refer to itself. This is useful for
-/// representing recursive records and is implemented through a special syntax.
-/// In the example below, the `Node` struct has a member that is a pointer to a
-/// `Node` struct:
-///
-/// ```mlir
-///     !struct = !cir.struct<struct "Node" {!cir.ptr<!cir.struct<struct
-///     "Node">>}>
-/// ```
-class StructType
-    : public mlir::Type::TypeBase<
-          StructType, mlir::Type, detail::StructTypeStorage,
-          mlir::DataLayoutTypeInterface::Trait, mlir::TypeTrait::IsMutable> {
-  // FIXME(cir): migrate this type to Tablegen once mutable types are supported.
-public:
-  using Base::Base;
-  using Base::getChecked;
-  using Base::verifyInvariants;
-
-  static constexpr llvm::StringLiteral name = "cir.struct";
-
-  enum RecordKind : uint32_t { Class, Union, Struct };
-
-  /// Create an identified and complete struct type.
-  static StructType get(mlir::MLIRContext *context,
-                        llvm::ArrayRef<mlir::Type> members,
-                        mlir::StringAttr name, bool packed, bool padded,
-                        RecordKind kind, ASTRecordDeclInterface ast = {});
-  static StructType
-  getChecked(llvm::function_ref<mlir::InFlightDiagnostic()> emitError,
-             mlir::MLIRContext *context, llvm::ArrayRef<mlir::Type> members,
-             mlir::StringAttr name, bool packed, bool padded, RecordKind kind,
-             ASTRecordDeclInterface ast = {});
-
-  /// Create an identified and incomplete struct type.
-  static StructType get(mlir::MLIRContext *context, mlir::StringAttr name,
-                        RecordKind kind);
-  static StructType
-  getChecked(llvm::function_ref<mlir::InFlightDiagnostic()> emitError,
-             mlir::MLIRContext *context, mlir::StringAttr name,
-             RecordKind kind);
-
-  /// Create an anonymous struct type (always complete).
-  static StructType get(mlir::MLIRContext *context,
-                        llvm::ArrayRef<mlir::Type> members, bool packed,
-                        bool padded, RecordKind kind,
-                        ASTRecordDeclInterface ast = {});
-  static StructType
-  getChecked(llvm::function_ref<mlir::InFlightDiagnostic()> emitError,
-             mlir::MLIRContext *context, llvm::ArrayRef<mlir::Type> members,
-             bool packed, bool padded, RecordKind kind,
-             ASTRecordDeclInterface ast = {});
-
-  /// Validate the struct about to be constructed.
-  static llvm::LogicalResult
-  verifyInvariants(llvm::function_ref<mlir::InFlightDiagnostic()> emitError,
-                   llvm::ArrayRef<mlir::Type> members, mlir::StringAttr name,
-                   bool incomplete, bool packed, bool padded,
-                   StructType::RecordKind kind, ASTRecordDeclInterface ast);
-
-  // Parse/print methods.
-  static constexpr llvm::StringLiteral getMnemonic() { return {"struct"}; }
-  static mlir::Type parse(mlir::AsmParser &odsParser);
-  void print(mlir::AsmPrinter &odsPrinter) const;
-
-  // Accessors
-  ASTRecordDeclInterface getAst() const;
-  llvm::ArrayRef<mlir::Type> getMembers() const;
-  mlir::StringAttr getName() const;
-  StructType::RecordKind getKind() const;
-  bool getIncomplete() const;
-  bool getPacked() const;
-  bool getPadded() const;
-  void dropAst();
-
-  // Predicates
-  bool isClass() const { return getKind() == RecordKind::Class; };
-  bool isStruct() const { return getKind() == RecordKind::Struct; };
-  bool isUnion() const { return getKind() == RecordKind::Union; };
-  bool isComplete() const { return !isIncomplete(); };
-  bool isIncomplete() const;
-
-  // Utilities
-  mlir::Type getLargestMember(const mlir::DataLayout &dataLayout) const;
-  size_t getNumElements() const { return getMembers().size(); };
-  std::string getKindAsStr() {
-    switch (getKind()) {
-    case RecordKind::Class:
-      return "class";
-    case RecordKind::Union:
-      return "union";
-    case RecordKind::Struct:
-      return "struct";
-    }
-    llvm_unreachable("Invalid value for StructType::getKind()");
-  }
-  std::string getPrefixedName() {
-    return getKindAsStr() + "." + getName().getValue().str();
-  }
-
-  /// Complete the struct type by mutating its members and attributes.
-  void complete(llvm::ArrayRef<mlir::Type> members, bool packed, bool isPadded,
-                ASTRecordDeclInterface ast = {});
-
-  /// DataLayoutTypeInterface methods.
-  llvm::TypeSize getTypeSizeInBits(const mlir::DataLayout &dataLayout,
-                                   mlir::DataLayoutEntryListRef params) const;
-  uint64_t getABIAlignment(const mlir::DataLayout &dataLayout,
-                           mlir::DataLayoutEntryListRef params) const;
-  uint64_t getElementOffset(const mlir::DataLayout &dataLayout,
-                            unsigned idx) const;
-
-  bool isLayoutIdentical(const StructType &other);
-
-  // Utilities for lazily computing and cacheing data layout info.
-private:
-  // FIXME: currently opaque because there's a cycle if CIRTypes.types include
-  // from CIRAttrs.h. The implementation operates in terms of StructLayoutAttr
-  // instead.
-  mutable mlir::Attribute layoutInfo;
-  void computeSizeAndAlignment(const mlir::DataLayout &dataLayout) const;
-};
-
 bool isAnyFloatingPointType(mlir::Type t);
 bool isScalarType(mlir::Type t);
 bool isFPOrFPVectorTy(mlir::Type);
diff --git a/clang/include/clang/CIR/Dialect/IR/CIRTypes.td b/clang/include/clang/CIR/Dialect/IR/CIRTypes.td
@@ -603,11 +603,164 @@ def FuncPtr : Type<
 }
 
 //===----------------------------------------------------------------------===//
-// StructType (defined in cpp files)
+// StructType
+//
+// The base type for all RecordDecls.
 //===----------------------------------------------------------------------===//
 
-def CIR_StructType : Type<CPred<"::mlir::isa<::cir::StructType>($_self)">,
-                          "CIR struct type">;
+def CIR_StructType : CIR_Type<"Struct", "struct",
+    [
+      DeclareTypeInterfaceMethods<DataLayoutTypeInterface>,
+      MutableType,
+    ]> {
+  let summary = "CIR struct type";
+  let description = [{
+    Each unique clang::RecordDecl is mapped to a `cir.struct` and any object in
+    C/C++ that has a struct type will have a `cir.struct` in CIR.
+
+    There are three possible formats for this type:
+
+     - Identified and complete structs: unique name and a known body.
+     - Identified and incomplete structs: unique name and unknown body.
+     - Anonymous structs: no name and a known body.
+
+    Identified structs are uniqued by their name, and anonymous structs are
+    uniqued by their body. This means that two anonymous structs with the same
+    body will be the same type, and two identified structs with the same name
+    will be the same type. Attempting to build a struct with an existing name,
+    but a different body will result in an error.
+
+    A few examples:
+
+    ```mlir
+        !complete = !cir.struct<struct "complete" {!cir.int<u, 8>}>
+        !incomplete = !cir.struct<struct "incomplete" incomplete>
+        !anonymous = !cir.struct<struct {!cir.int<u, 8>}>
+    ```
+
+    Incomplete structs are mutable, meaning they can be later completed with a
+    body automatically updating in place every type in the code that uses the
+    incomplete struct. Mutability allows for recursive types to be represented,
+    meaning the struct can have members that refer to itself. This is useful for
+    representing recursive records and is implemented through a special syntax.
+    In the example below, the `Node` struct has a member that is a pointer to a
+    `Node` struct:
+
+    ```mlir
+        !struct = !cir.struct<struct "Node" {!cir.ptr<!cir.struct<struct
+        "Node">>}>
+    ```
+  }];
+
+  let parameters = (ins
+    OptionalArrayRefParameter<"mlir::Type">:$members,
+    OptionalParameter<"mlir::StringAttr">:$name,
+    "bool":$incomplete,
+    "bool":$packed,
+    "bool":$padded,
+    "StructType::RecordKind":$kind,
+    OptionalParameter<"ASTRecordDeclInterface">:$ast
+  );
+
+  // StorageClass is defined in C++ for mutability.
+  let storageClass = "StructTypeStorage";
+  let genStorageClass = 0;
+
+  let skipDefaultBuilders = 1;
+  let genVerifyDecl = 1;
+
+  let builders = [
+    // Create an identified and complete struct type.
+    TypeBuilder<(ins
+      "llvm::ArrayRef<mlir::Type>":$members,
+      "mlir::StringAttr":$name,
+      "bool":$packed,
+      "bool":$padded,
+      "RecordKind":$kind,
+      CArg<"ASTRecordDeclInterface", "{}">:$ast
+    ), [{
+      return $_get($_ctxt, members, name, /*incomplete=*/false, packed, padded,
+                       kind, ast);    
+    }]>,
+
+    // Create an identified and incomplete struct type.
+    TypeBuilder<(ins
+      "mlir::StringAttr":$name,
+      "RecordKind":$kind
+    ), [{
+      return $_get($_ctxt, /*members=*/llvm::ArrayRef<Type>{}, name,
+                         /*incomplete=*/true, /*packed=*/false,
+                         /*padded=*/false, kind,
+                         /*ast=*/ASTRecordDeclInterface{});    
+    }]>,
+
+    // Create an anonymous struct type (always complete).
+    TypeBuilder<(ins
+      "llvm::ArrayRef<mlir::Type>":$members,
+      "bool":$packed,
+      "bool":$padded,
+      "RecordKind":$kind,
+      CArg<"ASTRecordDeclInterface", "{}">:$ast
+    ), [{
+      return $_get($_ctxt, members, mlir::StringAttr{}, /*incomplete=*/false,
+                      packed, padded, kind, ast);
+    }]>];
+
+  let extraClassDeclaration = [{
+    using Base::verifyInvariants;
+
+    enum RecordKind : uint32_t { Class, Union, Struct };
+
+    bool isClass() const { return getKind() == RecordKind::Class; };
+    bool isStruct() const { return getKind() == RecordKind::Struct; };
+    bool isUnion() const { return getKind() == RecordKind::Union; };
+    bool isComplete() const { return !isIncomplete(); };
+    bool isIncomplete() const;
+
+    void dropAst();
+
+    mlir::Type getLargestMember(const mlir::DataLayout &dataLayout) const;
+    size_t getNumElements() const { return getMembers().size(); };
+    std::string getKindAsStr() {
+      switch (getKind()) {
+      case RecordKind::Class:
+        return "class";
+      case RecordKind::Union:
+        return "union";
+      case RecordKind::Struct:
+        return "struct";
+      }
+      llvm_unreachable("Invalid value for StructType::getKind()");
+    }
+    std::string getPrefixedName() {
+      return getKindAsStr() + "." + getName().getValue().str();
+    }
+
+    void complete(llvm::ArrayRef<mlir::Type> members, bool packed,
+              bool isPadded, ASTRecordDeclInterface ast = {});
+
+    uint64_t getElementOffset(const mlir::DataLayout &dataLayout,
+              unsigned idx) const;
+
+    bool isLayoutIdentical(const StructType &other);
+
+  // Utilities for lazily computing and cacheing data layout info.
+  // FIXME: currently opaque because there's a cycle if CIRTypes.types include
+  // from CIRAttrs.h. The implementation operates in terms of StructLayoutAttr
+  // instead.
+  private:
+    mutable mlir::Attribute layoutInfo;
+    void computeSizeAndAlignment(const mlir::DataLayout &dataLayout) const;
+  public:
+  }];
+
+  let hasCustomAssemblyFormat = 1;
+}
+
+// Note CIRStructType is used instead of CIR_StructType
+// because of tablegen conflicts.
+def CIRStructType : Type<
+  CPred<"::mlir::isa<::cir::StructType>($_self)">, "CIR struct type">;
 
 //===----------------------------------------------------------------------===//
 // Global type constraints
diff --git a/clang/lib/CIR/Dialect/IR/CIRTypes.cpp b/clang/lib/CIR/Dialect/IR/CIRTypes.cpp
