MIR Serialization: Print and parse function's MBBs and simple MBB attributes.

[arphaman]

Summary

This patch implements the initial serialization of the machine basic blocks in a machine function. Only the simple, scalar MBB attributes are serialized. The link to LLVM IR's basic block is preserved when that basic block has a name.

[arphaman]

I've updated the patch to address Duncan's comments:

• Use the symbol table to look up BB by name.
• Print "<unnamed bb>" for names in MBBs with unnamed BB references.

llvm/trunk/include/llvm/CodeGen/MIRYamlMapping.h

 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LLVM_LIB_CODEGEN_MIRYAMLMAPPING_H
 #define LLVM_LIB_CODEGEN_MIRYAMLMAPPING_H
 
 #include "llvm/ADT/StringRef.h"
 #include "llvm/Support/YAMLTraits.h"
+#include <vector>
+
+namespace llvm {
+namespace yaml {
+
+struct MachineBasicBlock {
+  std::string Name;
+  unsigned Alignment = 0;
+  bool IsLandingPad = false;
+  bool AddressTaken = false;
+  // TODO: Serialize the successors and liveins.
+  // TODO: Serialize machine instructions.
+};
+
+template <> struct MappingTraits<MachineBasicBlock> {
+  static void mapping(IO &YamlIO, MachineBasicBlock &MBB) {
+    YamlIO.mapOptional("name", MBB.Name,
+                       std::string()); // Don't print out an empty name.
+    YamlIO.mapOptional("alignment", MBB.Alignment);
+    YamlIO.mapOptional("isLandingPad", MBB.IsLandingPad);
+    YamlIO.mapOptional("addressTaken", MBB.AddressTaken);
+  }
+};
+
+} // end namespace yaml
+} // end namespace llvm
+
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::yaml::MachineBasicBlock)
 
 namespace llvm {
 namespace yaml {
 
 struct MachineFunction {
   StringRef Name;
   unsigned Alignment = 0;
   bool ExposesReturnsTwice = false;
   bool HasInlineAsm = false;
+
+  std::vector<MachineBasicBlock> BasicBlocks;
 };
 
 template <> struct MappingTraits<MachineFunction> {
   static void mapping(IO &YamlIO, MachineFunction &MF) {
     YamlIO.mapRequired("name", MF.Name);
     YamlIO.mapOptional("alignment", MF.Alignment);
     YamlIO.mapOptional("exposesReturnsTwice", MF.ExposesReturnsTwice);
     YamlIO.mapOptional("hasInlineAsm", MF.HasInlineAsm);
+    YamlIO.mapOptional("body", MF.BasicBlocks);
   }
 };
 
 } // end namespace yaml
 } // end namespace llvm
 
 #endif

llvm/trunk/lib/CodeGen/MIRParser/MIRParser.cpp

 
 #include "llvm/CodeGen/MIRParser/MIRParser.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/AsmParser/Parser.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MIRYamlMapping.h"
+#include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
+#include "llvm/IR/ValueSymbolTable.h"
 #include "llvm/Support/LineIterator.h"
 #include "llvm/Support/SMLoc.h"
 #include "llvm/Support/SourceMgr.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/YAMLTraits.h"
 #include <memory>
 
 using namespace llvm;
public:
   bool parseMachineFunction(yaml::Input &In, Module &M, bool NoLLVMIR);
 
   /// Initialize the machine function to the state that's described in the MIR
   /// file.
   ///
   /// Return true if error occurred.
   bool initializeMachineFunction(MachineFunction &MF);
 
+  /// Initialize the machine basic block using it's YAML representation.
+  ///
+  /// Return true if an error occurred.
+  bool initializeMachineBasicBlock(MachineBasicBlock &MBB,
+                                   const yaml::MachineBasicBlock &YamlMBB);
+
 private:
   /// Return a MIR diagnostic converted from an LLVM assembly diagnostic.
   SMDiagnostic diagFromLLVMAssemblyDiag(const SMDiagnostic &Error,
                                         SMRange SourceRange);
 
   /// Create an empty function with the given name.
   void createDummyFunction(StringRef Name, Module &M);
 };
if (It == Functions.end())
     return error(Twine("no machine function information for function '") +
                  MF.getName() + "' in the MIR file");
   // TODO: Recreate the machine function.
   const yaml::MachineFunction &YamlMF = *It->getValue();
   if (YamlMF.Alignment)
     MF.setAlignment(YamlMF.Alignment);
   MF.setExposesReturnsTwice(YamlMF.ExposesReturnsTwice);
   MF.setHasInlineAsm(YamlMF.HasInlineAsm);
+  const auto &F = *MF.getFunction();
+  for (const auto &YamlMBB : YamlMF.BasicBlocks) {
+    const BasicBlock *BB = nullptr;
+    if (!YamlMBB.Name.empty()) {
+      BB = dyn_cast_or_null<BasicBlock>(
+          F.getValueSymbolTable().lookup(YamlMBB.Name));
+      // TODO: Report an error if a basic block isn't found.
+    }
+    auto *MBB = MF.CreateMachineBasicBlock(BB);
+    MF.insert(MF.end(), MBB);
+    if (initializeMachineBasicBlock(*MBB, YamlMBB))
+      return true;
+  }
+  return false;
+}
+
+bool MIRParserImpl::initializeMachineBasicBlock(
+    MachineBasicBlock &MBB, const yaml::MachineBasicBlock &YamlMBB) {
+  MBB.setAlignment(YamlMBB.Alignment);
+  if (YamlMBB.AddressTaken)
+    MBB.setHasAddressTaken();
+  MBB.setIsLandingPad(YamlMBB.IsLandingPad);
   return false;
 }
 
 SMDiagnostic MIRParserImpl::diagFromLLVMAssemblyDiag(const SMDiagnostic &Error,
                                                      SMRange SourceRange) {
   assert(SourceRange.isValid());
 
   // Translate the location of the error from the location in the llvm IR string

llvm/trunk/lib/CodeGen/MIRPrinter.cpp

 // functions using the MIR serialization format.
 //
 //===----------------------------------------------------------------------===//
 
 #include "MIRPrinter.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MIRYamlMapping.h"
+#include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Support/YAMLTraits.h"
 
 using namespace llvm;
 
 namespace {
 
 /// This class prints out the machine functions using the MIR serialization
 /// format.
 class MIRPrinter {
   raw_ostream &OS;
 
 public:
   MIRPrinter(raw_ostream &OS) : OS(OS) {}
 
   void print(const MachineFunction &MF);
+
+  void convert(yaml::MachineBasicBlock &YamlMBB, const MachineBasicBlock &MBB);
 };
 
 } // end anonymous namespace
 
 namespace llvm {
 namespace yaml {
 
 /// This struct serializes the LLVM IR module.

 } // end namespace llvm
 
 void MIRPrinter::print(const MachineFunction &MF) {
   yaml::MachineFunction YamlMF;
   YamlMF.Name = MF.getName();
   YamlMF.Alignment = MF.getAlignment();
   YamlMF.ExposesReturnsTwice = MF.exposesReturnsTwice();
   YamlMF.HasInlineAsm = MF.hasInlineAsm();
+  for (const auto &MBB : MF) {
+    yaml::MachineBasicBlock YamlMBB;
+    convert(YamlMBB, MBB);
+    YamlMF.BasicBlocks.push_back(YamlMBB);
+  }
   yaml::Output Out(OS);
   Out << YamlMF;
 }
 
+void MIRPrinter::convert(yaml::MachineBasicBlock &YamlMBB,
+                         const MachineBasicBlock &MBB) {
+  // TODO: Serialize unnamed BB references.
+  if (const auto *BB = MBB.getBasicBlock())
+    YamlMBB.Name = BB->hasName() ? BB->getName() : "<unnamed bb>";
+  else
+    YamlMBB.Name = "";
+  YamlMBB.Alignment = MBB.getAlignment();
+  YamlMBB.AddressTaken = MBB.hasAddressTaken();
+  YamlMBB.IsLandingPad = MBB.isLandingPad();
+}
+
 void llvm::printMIR(raw_ostream &OS, const Module &M) {
   yaml::Output Out(OS);
   Out << const_cast<Module &>(M);
 }
 
 void llvm::printMIR(raw_ostream &OS, const MachineFunction &MF) {
   MIRPrinter Printer(OS);
   Printer.print(MF);
 }

llvm/trunk/test/CodeGen/MIR/basic-blocks.mir

+# RUN: llc -start-after branch-folder -stop-after branch-folder -o /dev/null %s | FileCheck %s
+# This test ensures that the MIR parser parses machine functions correctly.
+
+--- |
+
+  define i32 @foo() {
+  entry:
+    ret i32 0
+  }
+
+  define i32 @bar() {
+  start:
+    ret i32 0
+  }
+
+...
+---
+# CHECK: name: foo
+# CHECK: body:
+# CHECK-NEXT: - name: entry
+# CHECK-NEXT:   alignment: 0
+# CHECK-NEXT:   isLandingPad: false
+# CHECK-NEXT:   addressTaken: false
+name:            foo
+body:
+ - name:         entry
+...
+---
+# CHECK: name: bar
+# CHECK: body:
+# CHECK-NEXT: - name: start
+# CHECK-NEXT:   alignment: 4
+# CHECK-NEXT:   isLandingPad: false
+# CHECK-NEXT:   addressTaken: false
+# CHECK-NEXT: - alignment: 0
+# CHECK-NEXT:   isLandingPad: false
+# CHECK-NEXT:   addressTaken: true
+name:            bar
+body:
+ - name:         start
+   alignment:    4
+ - addressTaken: true
+...