First Language Frontend with LLVM
Lexer
一个简单的 “递归下降” 的单步词法分析器，结合 “符号栈” 和 “向前看” 一个字符完成单步词法单元的提取
//===----------------------------------------------------------------------===//
// 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;
}
Parser And AST
AST 实现对抽象语法树上不同类型的结点的描述；函数是比较难处理的部分，我们要同时捕捉函数调用，函数原型，函数定义
//===----------------------------------------------------------------------===//
// Abstract Syntax Tree (aka Parse Tree)
//===----------------------------------------------------------------------===//
namespace {
/// ExprAST - Base class for all expression nodes.
class ExprAST {
public:
virtual ~ExprAST() = default;
};
/// NumberExprAST - Expression class for numeric literals like "1.0".
class NumberExprAST : public ExprAST {
double Val;
public:
NumberExprAST(double Val) : Val(Val) {}
};
/// VariableExprAST - Expression class for referencing a variable, like "a".
class VariableExprAST : public ExprAST {
std::string Name;
public:
VariableExprAST(const std::string &Name) : Name(Name) {}
};
/// 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)) {}
};
/// 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)) {}
};
/// 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)) {}
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)) {}
};
} // end anonymous namespace
然后是一个简单的递归下降的 Parser，执行一步向前看动作
值得关注的是优先级处理方法，通过建立一个 map 规定优先级次序，然后递归的执行 ParserBinaryOp，传入当前 token 左部的字符及左部优先级，如果低于右侧优先级就递归执行右边，否则 merge 左右子树
//===----------------------------------------------------------------------===//
// 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();
}
//===----------------------------------------------------------------------===//
// Top-Level parsing
//===----------------------------------------------------------------------===//
static void HandleDefinition() {
if (ParseDefinition()) {
fprintf(stderr, "Parsed a function definition.\n");
} else {
// Skip token for error recovery.
getNextToken();
}
}
static void HandleExtern() {
if (ParseExtern()) {
fprintf(stderr, "Parsed an extern\n");
} else {
// Skip token for error recovery.
getNextToken();
}
}
static void HandleTopLevelExpression() {
// Evaluate a top-level expression into an anonymous function.
if (ParseTopLevelExpr()) {
fprintf(stderr, "Parsed a top-level expr\n");
} 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();
// Run the main "interpreter loop" now.
MainLoop();
return 0;
}
IR Generation
从现在开始接触到 llvm core
首先给抽象语法树基类添加一个虚函数 codegen 用来生成 IR
class ExprAST {
public:
virtual ~ExprAST() {}
virtual Value *Codegen() = 0;
};
比如，在 number 结点上：
/// NumberExprAST - Expression class for numeric literals like "1.0".
class NumberExprAST : public ExprAST {
double Val;
public:
NumberExprAST(double val) : Val(val) {}
virtual Value *Codegen();
};
为了辅助代码生成，还有三个全局变量
static Module *TheModule;
static IRBuilder<> Builder(getGlobalContext());
static std::map<std::string, Value*> NamedValues;
Module 看作中间代码的顶层容器，其实也可以看作增量式翻译的容器
Builder 提供了 llvm 的一些关于 IR 生成的接口
NamedValues 命名空间保存了当前域内的可引用变量
- 数值结点 IR 生成
Value *NumberExprAST::Codegen() {
return ConstantFP::get(getGlobalContext(), APFloat(Val));
}
无论从编译还是祭祖（）的角度来看，程序中直接出线的立即数被认为是一种常量；llvm 中的数值常量用类 ConstantFP 存储并共享
- 变量引用 IR 生成
Value *VariableExprAST::Codegen() {
// Look this variable up in the function.
Value *V = NamedValues[Name];
return V ? V : ErrorV("Unknown variable name");
}
假设变量存在并直接在表中查询
- 二元运算表达式 IR 生成
Value *BinaryExprAST::Codegen() {
Value *L = LHS->Codegen();
Value *R = RHS->Codegen();
if (L == 0 || R == 0) return 0;
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 ErrorV("invalid binary operator");
}
}
这里调用了 Builder 辅助生成中间代码，在处理 '<' 时没那么粗暴，使用了一些特别的技巧（
Builder.CreateFCmpULT 是 LLVM 中的一个函数调用，用于执行浮点数比较操作，检查第一个浮点数是否无序或小于第二个浮点数，返回一个布尔值（i1 单布尔整数）；然而实际上这破坏了这个简单语言的类型安全（也许），我们需要用 Builder.CreateUIToFP 将其转换为 1.0 0.0
- 函数调用 IR 生成
Value *CallExprAST::Codegen() {
// Look up the name in the global module table.
Function *CalleeF = TheModule->getFunction(Callee);
if (CalleeF == 0)
return ErrorV("Unknown function referenced");
// If argument mismatch error.
if (CalleeF->arg_size() != Args.size())
return ErrorV("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() == 0) return 0;
}
return Builder.CreateCall(CalleeF, ArgsV, "calltmp");
}
很简单
- 函数原型的 IR 生成
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);
// If F conflicted, there was already something named 'Name'. If it has a
// body, don't allow redefinition or reextern.
if (F->getName() != Name) {
// Delete the one we just made and get the existing one.
F->eraseFromParent();
F = TheModule->getFunction(Name);
// If F already has a body, reject this.
if (!F->empty()) {
ErrorF("redefinition of function");
return 0;
}
// If F took a different number of args, reject.
if (F->arg_size() != Args.size()) {
ErrorF("redefinition of function with different # args");
return 0;
}
// Set names for all arguments.
unsigned Idx = 0;
for (Function::arg_iterator AI = F->arg_begin(); Idx != Args.size();
++AI, ++Idx) {
AI->setName(Args[Idx]);
// Add arguments to variable symbol table.
NamedValues[Args[Idx]] = AI;
}
}
函数原型描述了函数功能，实际上并不是一个直接的 value（实际上是个无代入值的 lambda），因此不再返回 Value 而返回 Funcrtion
Doubles 定义了一个类似于 list 的数据类型，FunctionType::get 则根据 Doubles 构建一个参数类型不可变的函数类型，FunctionType *FT = FunctionType::get(ReturnType, {Arg1Type, Arg2Type}, IsVarArg);
最后 Function::Create 创建一个新的函数并捆绑到 TheModule 上，ExternalLinkage 指外部链接
接下来检查重复定义；在处理名称冲突时，Module的符号表与Function的符号表类似：在模块中添加新函数时，如果发现函数名与符号表中现有的名称重复，新函数会被默默地重命名，因此可以用 F->getName() != Name 检查表内是否已经定义过一个同名函数；如果定义过一个同名函数，删除刚刚定义的函数，检查原先定义的函数是否为空、参数是否相同
接下来对于参数，依次把参数名注册到符号表中
- 函数定义的 IR 生成
Function *FunctionAST::Codegen() {
NamedValues.clear();
Function *TheFunction = Proto->Codegen();
if (TheFunction == 0)
return 0;
// Create a new basic block to start insertion into.
BasicBlock *BB = BasicBlock::Create(getGlobalContext(), "entry", TheFunction);
Builder.SetInsertPoint(BB);
if (Value *RetVal = Body->Codegen()) {
// Finish off the function.
Builder.CreateRet(RetVal);
// Validate the generated code, checking for consistency.
verifyFunction(*TheFunction);
return TheFunction;
}
首先调用函数原型的 codegen，这一部分暂时只写了新建基本块（在 LLVM 中，基本块是指程序中的基本的控制流单元，通常表示为一系列指令的序列），我粘一下原文：
第一行新建了一个名为“entry”的基本块对象，稍后该对象将被插入TheFunction。第二行告诉Builder，后续的新指令应该插至刚刚新建的基本块的末尾处。LLVM基本块是用于定义控制流图（Control Flow Graph）的重要部件。当前我们还不涉及到控制流，所以所有的函数都只有一个基本块。这个问题我们留到第五章再改
#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;
}