[CIR] Build out AST consumer patterns to reach the entry point into C…

…IRGen

Build out the necessary infrastructure for the main entry point into
ClangIR generation -- CIRGenModule. A set of boilerplate classes exist
to facilitate this -- CIRGenerator, CIRGenAction, EmitCIRAction and
CIRGenConsumer. These all mirror the corresponding types from LLVM
generation by Clang's CodeGen.

The main entry point to CIR generation is
`CIRGenModule::buildTopLevelDecl`. It is currently just an empty
function. We've added a test to ensure that the pipeline reaches this
point and doesn't fail, but does nothing else. This will be removed in
one of the subsequent patches that'll add basic `cir.func` emission.

This patch also re-adds `-emit-cir` to the driver. lib/Driver/Driver.cpp
requires that a driver flag exists to facilirate the selection of the
right actions for the driver to create. Without a driver flag you get
the standard behaviors of `-S`, `-c`, etc. If we want to emit CIR IR
and, eventually, bytecode we'll need a driver flag to force this. This
is why `-emit-llvm` is a driver flag. Notably, `-emit-llvm-bc` as a cc1
flag doesn't ever do the right thing. Without a driver flag it is
incorrectly ignored and an executable is emitted. With `-S` a file named
`something.s` is emitted which actually contains bitcode.

Reviewers: AaronBallman, MaskRay, bcardosolopes

Reviewed By: bcardosolopes, AaronBallman

Pull Request: #91007

clang/include/clang/CIR/CIRGenerator.h

@@ -0,0 +1,60 @@
+//===- CIRGenerator.h - CIR Generation from Clang AST ---------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file declares a simple interface to perform CIR generation from Clang
+// AST
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_CIR_CIRGENERATOR_H
+#define LLVM_CLANG_CIR_CIRGENERATOR_H
+
+#include "clang/AST/ASTConsumer.h"
+#include "clang/Basic/CodeGenOptions.h"
+
+#include "llvm/ADT/IntrusiveRefCntPtr.h"
+#include "llvm/Support/VirtualFileSystem.h"
+
+#include <memory>
+
+namespace clang {
+class DeclGroupRef;
+class DiagnosticsEngine;
+} // namespace clang
+
+namespace mlir {
+class MLIRContext;
+} // namespace mlir
+namespace cir {
+class CIRGenModule;
+
+class CIRGenerator : public clang::ASTConsumer {
+  virtual void anchor();
+  clang::DiagnosticsEngine &diags;
+  clang::ASTContext *astCtx;
+  // Only used for debug info.
+  llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> fs;
+
+  const clang::CodeGenOptions &codeGenOpts;
+
+protected:
+  std::unique_ptr<mlir::MLIRContext> mlirCtx;
+  std::unique_ptr<CIRGenModule> cgm;
+
+public:
+  CIRGenerator(clang::DiagnosticsEngine &diags,
+               llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> fs,
+               const clang::CodeGenOptions &cgo);
+  ~CIRGenerator() override;
+  void Initialize(clang::ASTContext &astCtx) override;
+  bool HandleTopLevelDecl(clang::DeclGroupRef group) override;
+};
+
+} // namespace cir
+
+#endif // LLVM_CLANG_CIR_CIRGENERATOR_H

clang/include/clang/CIR/FrontendAction/CIRGenAction.h

@@ -0,0 +1,60 @@
+//===---- CIRGenAction.h - CIR Code Generation Frontend Action -*- C++ -*--===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_CIR_CIRGENACTION_H
+#define LLVM_CLANG_CIR_CIRGENACTION_H
+
+#include "clang/Frontend/FrontendAction.h"
+
+#include "mlir/IR/BuiltinOps.h"
+#include "mlir/IR/OwningOpRef.h"
+
+namespace mlir {
+class MLIRContext;
+class ModuleOp;
+} // namespace mlir
+
+namespace cir {
+class CIRGenConsumer;
+
+class CIRGenAction : public clang::ASTFrontendAction {
+public:
+  enum class OutputType {
+    EmitCIR,
+  };
+
+private:
+  friend class CIRGenConsumer;
+
+  mlir::OwningOpRef<mlir::ModuleOp> MLIRMod;
+
+  mlir::MLIRContext *MLIRCtx;
+
+protected:
+  CIRGenAction(OutputType Action, mlir::MLIRContext *MLIRCtx = nullptr);
+
+  std::unique_ptr<clang::ASTConsumer>
+  CreateASTConsumer(clang::CompilerInstance &CI,
+                    llvm::StringRef InFile) override;
+
+public:
+  ~CIRGenAction() override;
+
+  OutputType Action;
+};
+
+class EmitCIRAction : public CIRGenAction {
+  virtual void anchor();
+
+public:
+  EmitCIRAction(mlir::MLIRContext *MLIRCtx = nullptr);
+};
+
+} // namespace cir
+
+#endif

clang/include/clang/Driver/Options.td

@@ -2996,7 +2996,7 @@ defm clangir : BoolFOption<"clangir",
   PosFlag<SetTrue, [], [ClangOption, CC1Option], "Use the ClangIR pipeline to compile">,
   NegFlag<SetFalse, [], [ClangOption, CC1Option], "Use the AST -> LLVM pipeline to compile">,
   BothFlags<[], [ClangOption, CC1Option], "">>;
-def emit_cir : Flag<["-"], "emit-cir">, Visibility<[CC1Option]>,
+def emit_cir : Flag<["-"], "emit-cir">, Visibility<[ClangOption, CC1Option]>,
   Group<Action_Group>, HelpText<"Build ASTs and then lower to ClangIR">;
 /// ClangIR-specific options - END
 

clang/lib/CIR/CMakeLists.txt

@@ -2,3 +2,5 @@ include_directories(${LLVM_MAIN_SRC_DIR}/../mlir/include)
 include_directories(${CMAKE_BINARY_DIR}/tools/mlir/include)
 
 add_subdirectory(Dialect)
+add_subdirectory(CodeGen)
+add_subdirectory(FrontendAction)

clang/lib/CIR/CodeGen/CIRGenModule.cpp

@@ -0,0 +1,32 @@
+//===- CIRGenModule.cpp - Per-Module state for CIR generation -------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This is the internal per-translation-unit state used for CIR translation.
+//
+//===----------------------------------------------------------------------===//
+
+#include "CIRGenModule.h"
+
+#include "clang/AST/ASTContext.h"
+#include "clang/AST/DeclBase.h"
+
+#include "mlir/IR/BuiltinOps.h"
+#include "mlir/IR/Location.h"
+#include "mlir/IR/MLIRContext.h"
+
+using namespace cir;
+CIRGenModule::CIRGenModule(mlir::MLIRContext &context,
+                           clang::ASTContext &astctx,
+                           const clang::CodeGenOptions &cgo,
+                           DiagnosticsEngine &diags)
+    : astCtx(astctx), langOpts(astctx.getLangOpts()),
+      theModule{mlir::ModuleOp::create(mlir::UnknownLoc())},
+      target(astCtx.getTargetInfo()) {}
+
+// Emit code for a single top level declaration.
+void CIRGenModule::buildTopLevelDecl(Decl *decl) {}

clang/lib/CIR/CodeGen/CIRGenModule.h

@@ -0,0 +1,62 @@
+//===--- CIRGenModule.h - Per-Module state for CIR gen ----------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This is the internal per-translation-unit state used for CIR translation.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_LIB_CIR_CODEGEN_CIRGENMODULE_H
+#define LLVM_CLANG_LIB_CIR_CODEGEN_CIRGENMODULE_H
+
+#include "CIRGenTypeCache.h"
+
+#include "mlir/IR/BuiltinOps.h"
+#include "mlir/IR/MLIRContext.h"
+
+namespace clang {
+class ASTContext;
+class CodeGenOptions;
+class Decl;
+class DiagnosticsEngine;
+class LangOptions;
+class TargetInfo;
+} // namespace clang
+
+using namespace clang;
+namespace cir {
+
+/// This class organizes the cross-function state that is used while generating
+/// CIR code.
+class CIRGenModule : public CIRGenTypeCache {
+  CIRGenModule(CIRGenModule &) = delete;
+  CIRGenModule &operator=(CIRGenModule &) = delete;
+
+public:
+  CIRGenModule(mlir::MLIRContext &context, clang::ASTContext &astctx,
+               const clang::CodeGenOptions &cgo,
+               clang::DiagnosticsEngine &diags);
+
+  ~CIRGenModule() = default;
+
+private:
+  /// Hold Clang AST information.
+  clang::ASTContext &astCtx;
+
+  const clang::LangOptions &langOpts;
+
+  /// A "module" matches a c/cpp source file: containing a list of functions.
+  mlir::ModuleOp theModule;
+
+  const clang::TargetInfo ⌖
+
+public:
+  void buildTopLevelDecl(clang::Decl *decl);
+};
+} // namespace cir
+
+#endif // LLVM_CLANG_LIB_CIR_CODEGEN_CIRGENMODULE_H

clang/lib/CIR/CodeGen/CIRGenTypeCache.h

@@ -0,0 +1,27 @@
+//===--- CIRGenTypeCache.h - Commonly used LLVM types and info -*- C++ --*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This structure provides a set of common types useful during CIR emission.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_LIB_CIR_CIRGENTYPECACHE_H
+#define LLVM_CLANG_LIB_CIR_CIRGENTYPECACHE_H
+
+namespace cir {
+
+/// This structure provides a set of types that are commonly used
+/// during IR emission. It's initialized once in CodeGenModule's
+/// constructor and then copied around into new CIRGenFunction's.
+struct CIRGenTypeCache {
+  CIRGenTypeCache() = default;
+};
+
+} // namespace cir
+
+#endif // LLVM_CLANG_LIB_CIR_CODEGEN_CIRGENTYPECACHE_H

clang/lib/CIR/CodeGen/CIRGenerator.cpp

@@ -0,0 +1,43 @@
+//===--- CIRGenerator.cpp - Emit CIR from ASTs ----------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This builds an AST and converts it to CIR.
+//
+//===----------------------------------------------------------------------===//
+
+#include "CIRGenModule.h"
+
+#include "clang/AST/DeclGroup.h"
+#include "clang/CIR/CIRGenerator.h"
+
+using namespace cir;
+using namespace clang;
+
+void CIRGenerator::anchor() {}
+
+CIRGenerator::CIRGenerator(clang::DiagnosticsEngine &diags,
+                           llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> vfs,
+                           const CodeGenOptions &cgo)
+    : diags(diags), fs(std::move(vfs)), codeGenOpts{cgo} {}
+CIRGenerator::~CIRGenerator() = default;
+
+void CIRGenerator::Initialize(ASTContext &astCtx) {
+  using namespace llvm;
+
+  this->astCtx = &astCtx;
+
+  cgm = std::make_unique<CIRGenModule>(*mlirCtx, astCtx, codeGenOpts, diags);
+}
+
+bool CIRGenerator::HandleTopLevelDecl(DeclGroupRef group) {
+
+  for (Decl *decl : group)
+    cgm->buildTopLevelDecl(decl);
+
+  return true;
+}

clang/lib/CIR/CodeGen/CMakeLists.txt

@@ -0,0 +1,23 @@
+set(
+  LLVM_LINK_COMPONENTS
+  Core
+  Support
+)
+
+get_property(dialect_libs GLOBAL PROPERTY MLIR_DIALECT_LIBS)
+
+add_clang_library(clangCIR
+  CIRGenerator.cpp
+  CIRGenModule.cpp
+
+  DEPENDS
+  MLIRCIR
+  ${dialect_libs}
+
+  LINK_LIBS
+  clangAST
+  clangBasic
+  clangLex
+  ${dialect_libs}
+  MLIRCIR
+)