英文看多了还是头痛，还是直接上代码
代码相比于上一篇为每个语法树新增了生成指令的函数codegen，并且新增了一些全局变量。
static LLVMContext TheContext;
static IRBuilder<> Builder(TheContext);
static std::unique_ptr<Module> TheModule;
static std::map<std::string, Value *> NamedValues;
TheContext 这是个神奇的变量，很多函数参数都要用它，官方解释说这个对象有llvm绝大多数的数据结构，类型和常量表。
Builder 一个生成IR指令的辅助类。
TheModule 所有生成的指令都会放在这里。
NameValues 就当作一个符号表，发生函数调用时其中的参数就会从这找。
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)
LogErrorV("Unknown variable name");
return V;
}
实际上，NumberExprAST和VariableExprAST的codegen方法都不产生IR指令，仅为上层的指令提供对象，想想也觉得合理，毕竟纯数字和标识符没有任何意义。
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");
}
}
代码简单取出两个操作数，根据具体的操作符利用Builder来生成指令。Builder.CreateF(,,)的第三个参数是生成指令中变量的名称。
特殊点的就是 ‘<‘ , 比较后的bool 值或者bool vector 转化为 double。
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");
}
这是产生调用函数的IR，判断是否已经定义了函数，已定义则判断参数个数是否相同，相同则生成调用指令。
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());
PrototypeAST 为def 和external 服务，是FunctionAST的成员之一，这段代码是为FunctionAST->codegen做铺垫。这个函数与其他codegen函数不同的是返回function* 不是values*，原因如上，为def 和 external服务。第一行创建为Arg.size() 个double的vector。第二行创建了使用Arg.size()个double作为参数，返回值为double的函数类型，最后一行创建了函数指定了函数类型、linkage，名称和插入代码的模块。这里函数是没有函数体的，就是llvm 来表示函数定义的方法。如果是一个external函数到这里就结束了。但对于函数定义我们需要函数体。
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;
}
判断模块中是否定义了函数，未定义则重新定义，body->codegen()生成函数体的运算执行，在生成ret指令，检查指令是否正常，返回函数。
#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 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;
}
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 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");
}
} 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.
TheModule = std::make_unique<Module>("my cool jit", TheContext);
// Run the main "interpreter loop" now.
MainLoop();
// Print out all of the generated code.
TheModule->print(errs(), nullptr);
return 0;
}
编译命令
$LLVM_HOME/bin/clang++ -g -O3 toy.cpp `$LLVM_HOME/bin/llvm-config --cxxflags --ldflags --system-libs --libs core` -o toy -I/usr/local/include
先从简单的开始分析:
ready> 1;
ready>Read top-level expression:define double @__anon_expr() {
entry:
ret double 1.000000e+00
}
因为既不是def 也不是 extern 直接进去到HandleTopLevelExpression， ParseTopLevelExpr创建了FunctionAST语法树， 如图：
PrototypeAST 的名称为”__anon_expr” , 参数为空，NumberExprAST 存了个”1″，语法树生成结束后。
调用FnAST->codegen() 来生成对应语法树的IR指令。先生成函数定义再生成函数体。过程描述过了，不多赘述。
https://llvm.org/docs/tutorial/MyFirstLanguageFrontend/LangImpl03.html
0 条评论