llvm/examples/Kaleidoscope/Chapter4/toy.cpp

#include "llvm/ADT/STLExtras.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Verifier.h"
#include "llvm/Support/TargetSelect.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Scalar/GVN.h"
#include <cctype>
#include <cstdio>
#include <map>
#include <string>
#include <vector>
#include "../include/KaleidoscopeJIT.h"

using namespace llvm;
using namespace llvm::orc;

//===----------------------------------------------------------------------===//
// 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() {}
  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 = llvm::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 llvm::make_unique<VariableExprAST>(IdName);

  // Call.
  getNextToken(); // eat (
  std::vector<std::unique_ptr<ExprAST>> Args;
  if (CurTok != ')') {
    while (1) {
      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 llvm::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 (1) {
    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 =
        llvm::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 llvm::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 llvm::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 = llvm::make_unique<PrototypeAST>("__anon_expr",
                                                 std::vector<std::string>());
    return llvm::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<Module> TheModule;
static IRBuilder<> Builder(getGlobalContext());
static std::map<std::string, Value *> NamedValues;
static std::unique_ptr<legacy::FunctionPassManager> TheFPM;
static std::unique_ptr<KaleidoscopeJIT> TheJIT;
static std::map<std::string, std::unique_ptr<PrototypeAST>> FunctionProtos;

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

Function *getFunction(std::string Name) {
  // First, see if the function has already been added to the current module.
  if (auto *F = TheModule->getFunction(Name))
    return F;

  // If not, check whether we can codegen the declaration from some existing
  // prototype.
  auto FI = FunctionProtos.find(Name);
  if (FI != FunctionProtos.end())
    return FI->second->codegen();

  // If no existing prototype exists, return null.
  return nullptr;
}

Value *NumberExprAST::codegen() {
  return ConstantFP::get(getGlobalContext(), 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(getGlobalContext()),
                                "booltmp");
  default:
    return LogErrorV("invalid binary operator");
  }
}

Value *CallExprAST::codegen() {
  // Look up the name in the global module table.
  Function *CalleeF = 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(getGlobalContext()));
  FunctionType *FT =
      FunctionType::get(Type::getDoubleTy(getGlobalContext()), 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() {
  // Transfer ownership of the prototype to the FunctionProtos map, but keep a
  // reference to it for use below.
  auto &P = *Proto;
  FunctionProtos[Proto->getName()] = std::move(Proto);
  Function *TheFunction = getFunction(P.getName());
  if (!TheFunction)
    return nullptr;

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

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

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

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

    // Run the optimizer on the function.
    TheFPM->run(*TheFunction);

    return TheFunction;
  }

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

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

static void InitializeModuleAndPassManager() {
  // Open a new module.
  TheModule = llvm::make_unique<Module>("my cool jit", getGlobalContext());
  TheModule->setDataLayout(TheJIT->getTargetMachine().createDataLayout());

  // Create a new pass manager attached to it.
  TheFPM = llvm::make_unique<legacy::FunctionPassManager>(TheModule.get());

  // Do simple "peephole" optimizations and bit-twiddling optzns.
  TheFPM->add(createInstructionCombiningPass());
  // Reassociate expressions.
  TheFPM->add(createReassociatePass());
  // Eliminate Common SubExpressions.
  TheFPM->add(createGVNPass());
  // Simplify the control flow graph (deleting unreachable blocks, etc).
  TheFPM->add(createCFGSimplificationPass());

  TheFPM->doInitialization();
}

static void HandleDefinition() {
  if (auto FnAST = ParseDefinition()) {
    if (auto *FnIR = FnAST->codegen()) {
      fprintf(stderr, "Read function definition:");
      FnIR->dump();
      TheJIT->addModule(std::move(TheModule));
      InitializeModuleAndPassManager();
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

static void HandleExtern() {
  if (auto ProtoAST = ParseExtern()) {
    if (auto *FnIR = ProtoAST->codegen()) {
      fprintf(stderr, "Read extern: ");
      FnIR->dump();
      FunctionProtos[ProtoAST->getName()] = std::move(ProtoAST);
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

static void HandleTopLevelExpression() {
  // Evaluate a top-level expression into an anonymous function.
  if (auto FnAST = ParseTopLevelExpr()) {
    if (FnAST->codegen()) {

      // JIT the module containing the anonymous expression, keeping a handle so
      // we can free it later.
      auto H = TheJIT->addModule(std::move(TheModule));
      InitializeModuleAndPassManager();

      // Search the JIT for the __anon_expr symbol.
      auto ExprSymbol = TheJIT->findSymbol("__anon_expr");
      assert(ExprSymbol && "Function not found");

      // Get the symbol's address and cast it to the right type (takes no
      // arguments, returns a double) so we can call it as a native function.
      double (*FP)() = (double (*)())(intptr_t)ExprSymbol.getAddress();
      fprintf(stderr, "Evaluated to %f\n", FP());

      // Delete the anonymous expression module from the JIT.
      TheJIT->removeModule(H);
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

/// top ::= definition | external | expression | ';'
static void MainLoop() {
  while (1) {
    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;
    }
  }
}

//===----------------------------------------------------------------------===//
// "Library" functions that can be "extern'd" from user code.
//===----------------------------------------------------------------------===//

/// putchard - putchar that takes a double and returns 0.
extern "C" double putchard(double X) {
  fputc((char)X, stderr);
  return 0;
}

/// printd - printf that takes a double prints it as "%f\n", returning 0.
extern "C" double printd(double X) {
  fprintf(stderr, "%f\n", X);
  return 0;
}

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

int main() {
  InitializeNativeTarget();
  InitializeNativeTargetAsmPrinter();
  InitializeNativeTargetAsmParser();

  // 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();

  TheJIT = llvm::make_unique<KaleidoscopeJIT>();

  InitializeModuleAndPassManager();

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

  return 0;
}