llvm_codegen

之前一篇博客我们介绍了抽象语法树的生成，这篇文章介绍如何将抽象语法树生成LLVM IR（Intermediate Representation,中间表示)代码。LLVM IR可以做很多后续的优化以及代码的生成工作。

代码生成准备工作

为了生成代码，我们需要在AST表达式类中加入一个代码生成的纯虚函数（codegen），每一个子类需要实现该函数。

/// ExprAST - Base class for all expression nodes.
class ExprAST {
public:
  virtual ~ExprAST() {}
  virtual Value *codegen() = 0;
};

/// NumberExprAST - Expression class for numeric literals like "1.0".
class NumberExprAST : public ExprAST {
  double Val;

public:
  NumberExprAST(double Val) : Val(Val) {}
  virtual Value *codegen();
};
...

codegen()用于将AST节点生成IR，它的返回值是LLVM Value对象。为了更好的实现，我们引入一些基本的LLVM数据结构以及LogError报错机制。

static LLVMContext TheContext;
static IRBuilder<> Builder(TheContext);
static std::unique_ptr<Module> TheModule;
static std::map<std::string, Value *> NamedValues;

Value *LogErrorV(const char *Str) {
  LogError(Str);
  return nullptr;
}

其中，LogError方法用于解析器来报告生成代码过程中的错误。
IRBuilder对象适用于生成LLVM指令，可以用于插入指令或者生成新指令。
TheModule是包含函数以及全局变量的LLVM数据结构。通常，它是整个LLVM代码的顶层结构。它拥有codegen生成代码的内存，因此我们用Value*指针作为codegen()的返回而不是unique_ptr。
NameValues是一张当前域的符号表（比如函数的参数所对应的变量或者值）。

表达式代码生成

首先，我们生成为数字字符值生成代码：

Value *NumberExprAST::codegen() {
  return ConstantFP::get(TheContext, APFloat(Val));
}

在LLVM IR中，数字常量用ConstantFP这个类来表示，APFloat表示任意精度的浮点数。词函数将会返回一个ConstantFP对象。注意，在LLVM中常量是唯一存在并且是共享的。

Value *BinaryExprAST::codegen() {
  Value *L = LHS->codegen();
  Value *R = RHS->codegen();
  if (!L || !R)
    return nullptr;

  switch (Op) {
  case '+':
    return Builder.CreateFAdd(L, R, "addtmp");
  case '-':
    return Builder.CreateFSub(L, R, "subtmp");
  case '*':
    return Builder.CreateFMul(L, R, "multmp");
  case '<':
    L = Builder.CreateFCmpULT(L, R, "cmptmp");
    // Convert bool 0/1 to double 0.0 or 1.0
    return Builder.CreateUIToFP(L, Type::getDoubleTy(TheContext),
                                "booltmp");
  default:
    return LogErrorV("invalid binary operator");
  }
}

对于二元表达式来说，可能会面临许多递归的调用，得益于AST本身包含了这种递归结构，通过递归的调用codegen()来生成二元表达式的代码。

Value *CallExprAST::codegen() {
  // Look up the name in the global module table.
  Function *CalleeF = TheModule->getFunction(Callee);
  if (!CalleeF)
    return LogErrorV("Unknown function referenced");

  // If argument mismatch error.
  if (CalleeF->arg_size() != Args.size())
    return LogErrorV("Incorrect # arguments passed");

  std::vector<Value *> ArgsV;
  for (unsigned i = 0, e = Args.size(); i != e; ++i) {
    ArgsV.push_back(Args[i]->codegen());
    if (!ArgsV.back())
      return nullptr;
  }

  return Builder.CreateCall(CalleeF, ArgsV, "calltmp");
}

对于函数调用，LLVM首先通过Module的符号表寻找函数名字，然后对其参数列表进行校验，如果校验成功，为其调用的参数生成代码，最后生成一个LLVM的调用指令。

函数代码生成

函数和函数原型的代码生成相对与表达式的代码生成含有更多的细节。首先我们来看函数原型的生成：

Function *PrototypeAST::codegen() {
  // Make the function type:  double(double,double) etc.
  std::vector<Type*> Doubles(Args.size(),
                             Type::getDoubleTy(TheContext));
  FunctionType *FT =
    FunctionType::get(Type::getDoubleTy(TheContext), Doubles, false);

  Function *F =
    Function::Create(FT, Function::ExternalLinkage, Name, TheModule.get());

代码第一行返回一个Function类型的指针而不是一个Value指针，因为“原型”表示的是一个函数的外部接口（而表达式更多的是产生一个值）。
FunctionType::get生成一个FunctionType对象，包括原型的参数列表，返回类型，最后一个false表示不是可变参数。
最后一个生成一个对应该原型的IR Function，包括之前的类型（FunctionType），链接方式，函数名称以及当前的Module。

// Set names for all arguments.
unsigned Idx = 0;
for (auto &Arg : F->args())
  Arg.setName(Args[Idx++]);

return F;

最后，我们在原型中为函数的每一个参数设置它们的名称。这个过程可以是IR更加具有可读性，而不是直接看原型的语法树。
至此，我们已经有了函数原型（函数声明）的代码，我们还需要有extern相关的函数声明以及对函数本身的代码生成。

Function *FunctionAST::codegen() {
    // First, check for an existing function from a previous 'extern' declaration.
  Function *TheFunction = TheModule->getFunction(Proto->getName());

  if (!TheFunction)
    TheFunction = Proto->codegen();

  if (!TheFunction)
    return nullptr;

  if (!TheFunction->empty())
    return (Function*)LogErrorV("Function cannot be redefined;

对于函数定义，我们首先通过TheModule的符号表来搜寻该函数是否已经存在，万一它已经用extern标识符声明。如果不是，则生成函数原型；如果是，则需要再次验证是否已经定义了函数本身。
最后我们为函数定义生成代码。

// Create a new basic block to start insertion into.
BasicBlock *BB = BasicBlock::Create(TheContext, "entry", TheFunction);
Builder.SetInsertPoint(BB);

// Record the function arguments in the NamedValues map.
NamedValues.clear();
for (auto &Arg : TheFunction->args())
  NamedValues[Arg.getName()] = &Arg;

首先我们定位当前Builder的位置，第一行代码生成了一个新的basic block（称为entry），用于插入TheFunction。第二行代码告诉builder需要插入的代码。接着将函数的参数加入NamedValues的映射，因此它们可以被VariableExprAST节点访问。

if (Value *RetVal = Body->codegen()) {
  // Finish off the function.
  Builder.CreateRet(RetVal);

  // Validate the generated code, checking for consistency.
  verifyFunction(*TheFunction);

  return TheFunction;
}

一旦确定插入点以及完成NamedValues的映射，我们调用函数本身（Body）的AST节点的代码生成，并生成一个LLVM返回指令。一旦函数构建完成，我们调用verifyFunction来对函数做一个一致性检查保证我们的编译器的正确性。

 TheFunction->eraseFromParent();
  return nullptr;

结果展示

我们利用llvm-config工具来编译

# Compile
clang++ -g -O3 toy.cpp `llvm-config --cxxflags --ldflags --system-libs --libs core` -o toy
# Run
./toy

运行之后有如下结果：

ready> def bar(a) foo(a, 4.0) + bar(31337);
Read function definition:
define double @bar(double %a) {
entry:
  %calltmp = call double @foo(double %a, double 4.000000e+00)
  %calltmp1 = call double @bar(double 3.133700e+04)
  %addtmp = fadd double %calltmp, %calltmp1
  ret double %addtmp
}

整个代码文件如下：

#include "llvm/ADT/APFloat.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/Verifier.h"
#include <algorithm>
#include <cctype>
#include <cstdio>
#include <cstdlib>
#include <map>
#include <memory>
#include <string>
#include <vector>

using namespace llvm;

//===----------------------------------------------------------------------===//
// Lexer
//===----------------------------------------------------------------------===//

// The lexer returns tokens [0-255] if it is an unknown character, otherwise one
// of these for known things.
enum Token {
  tok_eof = -1,

  // commands
  tok_def = -2,
  tok_extern = -3,

  // primary
  tok_identifier = -4,
  tok_number = -5
};

static std::string IdentifierStr; // Filled in if tok_identifier
static double NumVal;             // Filled in if tok_number

/// gettok - Return the next token from standard input.
static int gettok() {
  static int LastChar = ' ';

  // Skip any whitespace.
  while (isspace(LastChar))
    LastChar = getchar();

  if (isalpha(LastChar)) { // identifier: [a-zA-Z][a-zA-Z0-9]*
    IdentifierStr = LastChar;
    while (isalnum((LastChar = getchar())))
      IdentifierStr += LastChar;

    if (IdentifierStr == "def")
      return tok_def;
    if (IdentifierStr == "extern")
      return tok_extern;
    return tok_identifier;
  }

  if (isdigit(LastChar) || LastChar == '.') { // Number: [0-9.]+
    std::string NumStr;
    do {
      NumStr += LastChar;
      LastChar = getchar();
    } while (isdigit(LastChar) || LastChar == '.');

    NumVal = strtod(NumStr.c_str(), nullptr);
    return tok_number;
  }

  if (LastChar == '#') {
    // Comment until end of line.
    do
      LastChar = getchar();
    while (LastChar != EOF && LastChar != '\n' && LastChar != '\r');

    if (LastChar != EOF)
      return gettok();
  }

  // Check for end of file.  Don't eat the EOF.
  if (LastChar == EOF)
    return tok_eof;

  // Otherwise, just return the character as its ascii value.
  int ThisChar = LastChar;
  LastChar = getchar();
  return ThisChar;
}

//===----------------------------------------------------------------------===//
// Abstract Syntax Tree (aka Parse Tree)
//===----------------------------------------------------------------------===//

namespace {

/// ExprAST - Base class for all expression nodes.
class ExprAST {
public:
  virtual ~ExprAST() = default;

  virtual Value *codegen() = 0;
};

/// NumberExprAST - Expression class for numeric literals like "1.0".
class NumberExprAST : public ExprAST {
  double Val;

public:
  NumberExprAST(double Val) : Val(Val) {}

  Value *codegen() override;
};

/// VariableExprAST - Expression class for referencing a variable, like "a".
class VariableExprAST : public ExprAST {
  std::string Name;

public:
  VariableExprAST(const std::string &Name) : Name(Name) {}

  Value *codegen() override;
};

/// BinaryExprAST - Expression class for a binary operator.
class BinaryExprAST : public ExprAST {
  char Op;
  std::unique_ptr<ExprAST> LHS, RHS;

public:
  BinaryExprAST(char Op, std::unique_ptr<ExprAST> LHS,
                std::unique_ptr<ExprAST> RHS)
      : Op(Op), LHS(std::move(LHS)), RHS(std::move(RHS)) {}

  Value *codegen() override;
};

/// CallExprAST - Expression class for function calls.
class CallExprAST : public ExprAST {
  std::string Callee;
  std::vector<std::unique_ptr<ExprAST>> Args;

public:
  CallExprAST(const std::string &Callee,
              std::vector<std::unique_ptr<ExprAST>> Args)
      : Callee(Callee), Args(std::move(Args)) {}

  Value *codegen() override;
};

/// PrototypeAST - This class represents the "prototype" for a function,
/// which captures its name, and its argument names (thus implicitly the number
/// of arguments the function takes).
class PrototypeAST {
  std::string Name;
  std::vector<std::string> Args;

public:
  PrototypeAST(const std::string &Name, std::vector<std::string> Args)
      : Name(Name), Args(std::move(Args)) {}

  Function *codegen();
  const std::string &getName() const { return Name; }
};

/// FunctionAST - This class represents a function definition itself.
class FunctionAST {
  std::unique_ptr<PrototypeAST> Proto;
  std::unique_ptr<ExprAST> Body;

public:
  FunctionAST(std::unique_ptr<PrototypeAST> Proto,
              std::unique_ptr<ExprAST> Body)
      : Proto(std::move(Proto)), Body(std::move(Body)) {}

  Function *codegen();
};

} // end anonymous namespace

//===----------------------------------------------------------------------===//
// Parser
//===----------------------------------------------------------------------===//

/// CurTok/getNextToken - Provide a simple token buffer.  CurTok is the current
/// token the parser is looking at.  getNextToken reads another token from the
/// lexer and updates CurTok with its results.
static int CurTok;
static int getNextToken() { return CurTok = gettok(); }

/// BinopPrecedence - This holds the precedence for each binary operator that is
/// defined.
static std::map<char, int> BinopPrecedence;

/// GetTokPrecedence - Get the precedence of the pending binary operator token.
static int GetTokPrecedence() {
  if (!isascii(CurTok))
    return -1;

  // Make sure it's a declared binop.
  int TokPrec = BinopPrecedence[CurTok];
  if (TokPrec <= 0)
    return -1;
  return TokPrec;
}

/// LogError* - These are little helper functions for error handling.
std::unique_ptr<ExprAST> LogError(const char *Str) {
  fprintf(stderr, "Error: %s\n", Str);
  return nullptr;
}

std::unique_ptr<PrototypeAST> LogErrorP(const char *Str) {
  LogError(Str);
  return nullptr;
}

static std::unique_ptr<ExprAST> ParseExpression();

/// numberexpr ::= number
static std::unique_ptr<ExprAST> ParseNumberExpr() {
  auto Result = std::make_unique<NumberExprAST>(NumVal);
  getNextToken(); // consume the number
  return std::move(Result);
}

/// parenexpr ::= '(' expression ')'
static std::unique_ptr<ExprAST> ParseParenExpr() {
  getNextToken(); // eat (.
  auto V = ParseExpression();
  if (!V)
    return nullptr;

  if (CurTok != ')')
    return LogError("expected ')'");
  getNextToken(); // eat ).
  return V;
}

/// identifierexpr
///   ::= identifier
///   ::= identifier '(' expression* ')'
static std::unique_ptr<ExprAST> ParseIdentifierExpr() {
  std::string IdName = IdentifierStr;

  getNextToken(); // eat identifier.

  if (CurTok != '(') // Simple variable ref.
    return std::make_unique<VariableExprAST>(IdName);

  // Call.
  getNextToken(); // eat (
  std::vector<std::unique_ptr<ExprAST>> Args;
  if (CurTok != ')') {
    while (true) {
      if (auto Arg = ParseExpression())
        Args.push_back(std::move(Arg));
      else
        return nullptr;

      if (CurTok == ')')
        break;

      if (CurTok != ',')
        return LogError("Expected ')' or ',' in argument list");
      getNextToken();
    }
  }

  // Eat the ')'.
  getNextToken();

  return std::make_unique<CallExprAST>(IdName, std::move(Args));
}

/// primary
///   ::= identifierexpr
///   ::= numberexpr
///   ::= parenexpr
static std::unique_ptr<ExprAST> ParsePrimary() {
  switch (CurTok) {
  default:
    return LogError("unknown token when expecting an expression");
  case tok_identifier:
    return ParseIdentifierExpr();
  case tok_number:
    return ParseNumberExpr();
  case '(':
    return ParseParenExpr();
  }
}

/// binoprhs
///   ::= ('+' primary)*
static std::unique_ptr<ExprAST> ParseBinOpRHS(int ExprPrec,
                                              std::unique_ptr<ExprAST> LHS) {
  // If this is a binop, find its precedence.
  while (true) {
    int TokPrec = GetTokPrecedence();

    // If this is a binop that binds at least as tightly as the current binop,
    // consume it, otherwise we are done.
    if (TokPrec < ExprPrec)
      return LHS;

    // Okay, we know this is a binop.
    int BinOp = CurTok;
    getNextToken(); // eat binop

    // Parse the primary expression after the binary operator.
    auto RHS = ParsePrimary();
    if (!RHS)
      return nullptr;

    // If BinOp binds less tightly with RHS than the operator after RHS, let
    // the pending operator take RHS as its LHS.
    int NextPrec = GetTokPrecedence();
    if (TokPrec < NextPrec) {
      RHS = ParseBinOpRHS(TokPrec + 1, std::move(RHS));
      if (!RHS)
        return nullptr;
    }

    // Merge LHS/RHS.
    LHS =
        std::make_unique<BinaryExprAST>(BinOp, std::move(LHS), std::move(RHS));
  }
}

/// expression
///   ::= primary binoprhs
///
static std::unique_ptr<ExprAST> ParseExpression() {
  auto LHS = ParsePrimary();
  if (!LHS)
    return nullptr;

  return ParseBinOpRHS(0, std::move(LHS));
}

/// prototype
///   ::= id '(' id* ')'
static std::unique_ptr<PrototypeAST> ParsePrototype() {
  if (CurTok != tok_identifier)
    return LogErrorP("Expected function name in prototype");

  std::string FnName = IdentifierStr;
  getNextToken();

  if (CurTok != '(')
    return LogErrorP("Expected '(' in prototype");

  std::vector<std::string> ArgNames;
  while (getNextToken() == tok_identifier)
    ArgNames.push_back(IdentifierStr);
  if (CurTok != ')')
    return LogErrorP("Expected ')' in prototype");

  // success.
  getNextToken(); // eat ')'.

  return std::make_unique<PrototypeAST>(FnName, std::move(ArgNames));
}

/// definition ::= 'def' prototype expression
static std::unique_ptr<FunctionAST> ParseDefinition() {
  getNextToken(); // eat def.
  auto Proto = ParsePrototype();
  if (!Proto)
    return nullptr;

  if (auto E = ParseExpression())
    return std::make_unique<FunctionAST>(std::move(Proto), std::move(E));
  return nullptr;
}

/// toplevelexpr ::= expression
static std::unique_ptr<FunctionAST> ParseTopLevelExpr() {
  if (auto E = ParseExpression()) {
    // Make an anonymous proto.
    auto Proto = std::make_unique<PrototypeAST>("__anon_expr",
                                                 std::vector<std::string>());
    return std::make_unique<FunctionAST>(std::move(Proto), std::move(E));
  }
  return nullptr;
}

/// external ::= 'extern' prototype
static std::unique_ptr<PrototypeAST> ParseExtern() {
  getNextToken(); // eat extern.
  return ParsePrototype();
}

//===----------------------------------------------------------------------===//
// Code Generation
//===----------------------------------------------------------------------===//

static std::unique_ptr<LLVMContext> TheContext;
static std::unique_ptr<Module> TheModule;
static std::unique_ptr<IRBuilder<>> Builder;
static std::map<std::string, Value *> NamedValues;

Value *LogErrorV(const char *Str) {
  LogError(Str);
  return nullptr;
}

Value *NumberExprAST::codegen() {
  return ConstantFP::get(*TheContext, APFloat(Val));
}

Value *VariableExprAST::codegen() {
  // Look this variable up in the function.
  Value *V = NamedValues[Name];
  if (!V)
    return LogErrorV("Unknown variable name");
  return V;
}

Value *BinaryExprAST::codegen() {
  Value *L = LHS->codegen();
  Value *R = RHS->codegen();
  if (!L || !R)
    return nullptr;

  switch (Op) {
  case '+':
    return Builder->CreateFAdd(L, R, "addtmp");
  case '-':
    return Builder->CreateFSub(L, R, "subtmp");
  case '*':
    return Builder->CreateFMul(L, R, "multmp");
  case '<':
    L = Builder->CreateFCmpULT(L, R, "cmptmp");
    // Convert bool 0/1 to double 0.0 or 1.0
    return Builder->CreateUIToFP(L, Type::getDoubleTy(*TheContext), "booltmp");
  default:
    return LogErrorV("invalid binary operator");
  }
}

Value *CallExprAST::codegen() {
  // Look up the name in the global module table.
  Function *CalleeF = TheModule->getFunction(Callee);
  if (!CalleeF)
    return LogErrorV("Unknown function referenced");

  // If argument mismatch error.
  if (CalleeF->arg_size() != Args.size())
    return LogErrorV("Incorrect # arguments passed");

  std::vector<Value *> ArgsV;
  for (unsigned i = 0, e = Args.size(); i != e; ++i) {
    ArgsV.push_back(Args[i]->codegen());
    if (!ArgsV.back())
      return nullptr;
  }

  return Builder->CreateCall(CalleeF, ArgsV, "calltmp");
}

Function *PrototypeAST::codegen() {
  // Make the function type:  double(double,double) etc.
  std::vector<Type *> Doubles(Args.size(), Type::getDoubleTy(*TheContext));
  FunctionType *FT =
      FunctionType::get(Type::getDoubleTy(*TheContext), Doubles, false);

  Function *F =
      Function::Create(FT, Function::ExternalLinkage, Name, TheModule.get());

  // Set names for all arguments.
  unsigned Idx = 0;
  for (auto &Arg : F->args())
    Arg.setName(Args[Idx++]);

  return F;
}

Function *FunctionAST::codegen() {
  // First, check for an existing function from a previous 'extern' declaration.
  Function *TheFunction = TheModule->getFunction(Proto->getName());

  if (!TheFunction)
    TheFunction = Proto->codegen();

  if (!TheFunction)
    return nullptr;

  // Create a new basic block to start insertion into.
  BasicBlock *BB = BasicBlock::Create(*TheContext, "entry", TheFunction);
  Builder->SetInsertPoint(BB);

  // Record the function arguments in the NamedValues map.
  NamedValues.clear();
  for (auto &Arg : TheFunction->args())
    NamedValues[std::string(Arg.getName())] = &Arg;

  if (Value *RetVal = Body->codegen()) {
    // Finish off the function.
    Builder->CreateRet(RetVal);

    // Validate the generated code, checking for consistency.
    verifyFunction(*TheFunction);

    return TheFunction;
  }

  // Error reading body, remove function.
  TheFunction->eraseFromParent();
  return nullptr;
}

//===----------------------------------------------------------------------===//
// Top-Level parsing and JIT Driver
//===----------------------------------------------------------------------===//

static void InitializeModule() {
  // Open a new context and module.
  TheContext = std::make_unique<LLVMContext>();
  TheModule = std::make_unique<Module>("my cool jit", *TheContext);

  // Create a new builder for the module.
  Builder = std::make_unique<IRBuilder<>>(*TheContext);
}

static void HandleDefinition() {
  if (auto FnAST = ParseDefinition()) {
    if (auto *FnIR = FnAST->codegen()) {
      fprintf(stderr, "Read function definition:");
      FnIR->print(errs());
      fprintf(stderr, "\n");
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

static void HandleExtern() {
  if (auto ProtoAST = ParseExtern()) {
    if (auto *FnIR = ProtoAST->codegen()) {
      fprintf(stderr, "Read extern: ");
      FnIR->print(errs());
      fprintf(stderr, "\n");
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

static void HandleTopLevelExpression() {
  // Evaluate a top-level expression into an anonymous function.
  if (auto FnAST = ParseTopLevelExpr()) {
    if (auto *FnIR = FnAST->codegen()) {
      fprintf(stderr, "Read top-level expression:");
      FnIR->print(errs());
      fprintf(stderr, "\n");

      // Remove the anonymous expression.
      FnIR->eraseFromParent();
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

/// top ::= definition | external | expression | ';'
static void MainLoop() {
  while (true) {
    fprintf(stderr, "ready> ");
    switch (CurTok) {
    case tok_eof:
      return;
    case ';': // ignore top-level semicolons.
      getNextToken();
      break;
    case tok_def:
      HandleDefinition();
      break;
    case tok_extern:
      HandleExtern();
      break;
    default:
      HandleTopLevelExpression();
      break;
    }
  }
}

//===----------------------------------------------------------------------===//
// Main driver code.
//===----------------------------------------------------------------------===//

int main() {
  // Install standard binary operators.
  // 1 is lowest precedence.
  BinopPrecedence['<'] = 10;
  BinopPrecedence['+'] = 20;
  BinopPrecedence['-'] = 20;
  BinopPrecedence['*'] = 40; // highest.

  // Prime the first token.
  fprintf(stderr, "ready> ");
  getNextToken();

  // Make the module, which holds all the code.
  InitializeModule();

  // Run the main "interpreter loop" now.
  MainLoop();

  // Print out all of the generated code.
  TheModule->print(errs(), nullptr);

  return 0;
}