8. 万花筒：编译为目标代码¶
8.1. 第 8 章 简介¶
欢迎来到“使用 LLVM 实现语言”教程的第 8 章。本章介绍如何将我们的语言编译成目标文件。
8.2. 选择目标¶
LLVM 原生支持交叉编译。您可以编译到您当前机器的架构，或者轻松地编译到其他架构。在本教程中，我们将以当前机器为目标。
要指定要编译的目标架构，我们使用一个称为“目标三元组”的字符串。它的格式为 <arch><sub>-<vendor>-<sys>-<abi>（请参阅 交叉编译文档）。
例如，我们可以查看 clang 认为我们的当前目标三元组是什么
$ clang --version | grep Target
Target: x86_64-unknown-linux-gnu
运行此命令可能会在您的机器上显示不同的结果，因为您可能使用与我不同的架构或操作系统。
幸运的是，我们不需要硬编码目标三元组来定位当前机器。LLVM 提供了 sys::getDefaultTargetTriple，它返回当前机器的目标三元组。
auto TargetTriple = sys::getDefaultTargetTriple();
LLVM 不要求我们将所有目标功能都链接进来。例如，如果我们只使用 JIT，则不需要汇编打印程序。类似地，如果我们只针对某些架构，则可以只链接这些架构的功能。
对于此示例，我们将初始化所有用于输出目标代码的目标。
InitializeAllTargetInfos();
InitializeAllTargets();
InitializeAllTargetMCs();
InitializeAllAsmParsers();
InitializeAllAsmPrinters();
现在我们可以使用我们的目标三元组来获取一个 Target
std::string Error;
auto Target = TargetRegistry::lookupTarget(TargetTriple, Error);
// Print an error and exit if we couldn't find the requested target.
// This generally occurs if we've forgotten to initialise the
// TargetRegistry or we have a bogus target triple.
if (!Target) {
errs() << Error;
return 1;
}
8.3. 目标机器¶
我们还需要一个 TargetMachine。此类提供了我们所针对机器的完整机器描述。如果我们想针对特定功能（例如 SSE）或特定 CPU（例如 Intel 的 Sandylake），现在就可以这么做了。
要查看 LLVM 了解哪些功能和 CPU，我们可以使用 llc。例如，让我们看看 x86
$ llvm-as < /dev/null | llc -march=x86 -mattr=help
Available CPUs for this target:
amdfam10 - Select the amdfam10 processor.
athlon - Select the athlon processor.
athlon-4 - Select the athlon-4 processor.
...
Available features for this target:
16bit-mode - 16-bit mode (i8086).
32bit-mode - 32-bit mode (80386).
3dnow - Enable 3DNow! instructions.
3dnowa - Enable 3DNow! Athlon instructions.
...
对于我们的示例，我们将使用通用 CPU，没有任何其他功能或目标选项。
auto CPU = "generic";
auto Features = "";
TargetOptions opt;
auto TargetMachine = Target->createTargetMachine(TargetTriple, CPU, Features, opt, Reloc::PIC_);
8.4. 配置模块¶
现在我们准备配置我们的模块，以指定目标和数据布局。这并非严格必要，但 前端性能指南 建议这样做。优化可以从了解目标和数据布局中获益。
TheModule->setDataLayout(TargetMachine->createDataLayout());
TheModule->setTargetTriple(TargetTriple);
8.5. 输出目标代码¶
我们准备输出目标代码了！让我们定义我们想要将文件写入的位置
auto Filename = "output.o";
std::error_code EC;
raw_fd_ostream dest(Filename, EC, sys::fs::OF_None);
if (EC) {
errs() << "Could not open file: " << EC.message();
return 1;
}
最后，我们定义一个输出目标代码的 Pass，然后运行该 Pass
legacy::PassManager pass;
auto FileType = CodeGenFileType::ObjectFile;
if (TargetMachine->addPassesToEmitFile(pass, dest, nullptr, FileType)) {
errs() << "TargetMachine can't emit a file of this type";
return 1;
}
pass.run(*TheModule);
dest.flush();
8.6. 整合所有内容¶
它有效吗？让我们试一试。我们需要编译我们的代码，但请注意，与前面的章节相比，llvm-config 的参数有所不同。
$ clang++ -g -O3 toy.cpp `llvm-config --cxxflags --ldflags --system-libs --libs all` -o toy
让我们运行它，并定义一个简单的 average 函数。完成后，按 Ctrl-D。
$ ./toy
ready> def average(x y) (x + y) * 0.5;
^D
Wrote output.o
我们得到一个目标文件！为了测试它，让我们编写一个简单的程序并将其与我们的输出链接起来。以下是源代码
#include <iostream>
extern "C" {
double average(double, double);
}
int main() {
std::cout << "average of 3.0 and 4.0: " << average(3.0, 4.0) << std::endl;
}
我们将我们的程序链接到 output.o 并检查结果是否符合预期
$ clang++ main.cpp output.o -o main
$ ./main
average of 3.0 and 4.0: 3.5
8.7. 完整代码清单¶
#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/Instructions.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/Verifier.h"
#include "llvm/MC/TargetRegistry.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/TargetSelect.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/TargetParser/Host.h"
#include <algorithm>
#include <cassert>
#include <cctype>
#include <cstdio>
#include <cstdlib>
#include <map>
#include <memory>
#include <string>
#include <system_error>
#include <utility>
#include <vector>
using namespace llvm;
using namespace llvm::sys;
//===----------------------------------------------------------------------===//
// 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,
// control
tok_if = -6,
tok_then = -7,
tok_else = -8,
tok_for = -9,
tok_in = -10,
// operators
tok_binary = -11,
tok_unary = -12,
// var definition
tok_var = -13
};
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;
if (IdentifierStr == "if")
return tok_if;
if (IdentifierStr == "then")
return tok_then;
if (IdentifierStr == "else")
return tok_else;
if (IdentifierStr == "for")
return tok_for;
if (IdentifierStr == "in")
return tok_in;
if (IdentifierStr == "binary")
return tok_binary;
if (IdentifierStr == "unary")
return tok_unary;
if (IdentifierStr == "var")
return tok_var;
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;
const std::string &getName() const { return Name; }
};
/// UnaryExprAST - Expression class for a unary operator.
class UnaryExprAST : public ExprAST {
char Opcode;
std::unique_ptr<ExprAST> Operand;
public:
UnaryExprAST(char Opcode, std::unique_ptr<ExprAST> Operand)
: Opcode(Opcode), Operand(std::move(Operand)) {}
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;
};
/// IfExprAST - Expression class for if/then/else.
class IfExprAST : public ExprAST {
std::unique_ptr<ExprAST> Cond, Then, Else;
public:
IfExprAST(std::unique_ptr<ExprAST> Cond, std::unique_ptr<ExprAST> Then,
std::unique_ptr<ExprAST> Else)
: Cond(std::move(Cond)), Then(std::move(Then)), Else(std::move(Else)) {}
Value *codegen() override;
};
/// ForExprAST - Expression class for for/in.
class ForExprAST : public ExprAST {
std::string VarName;
std::unique_ptr<ExprAST> Start, End, Step, Body;
public:
ForExprAST(const std::string &VarName, std::unique_ptr<ExprAST> Start,
std::unique_ptr<ExprAST> End, std::unique_ptr<ExprAST> Step,
std::unique_ptr<ExprAST> Body)
: VarName(VarName), Start(std::move(Start)), End(std::move(End)),
Step(std::move(Step)), Body(std::move(Body)) {}
Value *codegen() override;
};
/// VarExprAST - Expression class for var/in
class VarExprAST : public ExprAST {
std::vector<std::pair<std::string, std::unique_ptr<ExprAST>>> VarNames;
std::unique_ptr<ExprAST> Body;
public:
VarExprAST(
std::vector<std::pair<std::string, std::unique_ptr<ExprAST>>> VarNames,
std::unique_ptr<ExprAST> Body)
: VarNames(std::move(VarNames)), Body(std::move(Body)) {}
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), as well as if it is an operator.
class PrototypeAST {
std::string Name;
std::vector<std::string> Args;
bool IsOperator;
unsigned Precedence; // Precedence if a binary op.
public:
PrototypeAST(const std::string &Name, std::vector<std::string> Args,
bool IsOperator = false, unsigned Prec = 0)
: Name(Name), Args(std::move(Args)), IsOperator(IsOperator),
Precedence(Prec) {}
Function *codegen();
const std::string &getName() const { return Name; }
bool isUnaryOp() const { return IsOperator && Args.size() == 1; }
bool isBinaryOp() const { return IsOperator && Args.size() == 2; }
char getOperatorName() const {
assert(isUnaryOp() || isBinaryOp());
return Name[Name.size() - 1];
}
unsigned getBinaryPrecedence() const { return Precedence; }
};
/// 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));
}
/// ifexpr ::= 'if' expression 'then' expression 'else' expression
static std::unique_ptr<ExprAST> ParseIfExpr() {
getNextToken(); // eat the if.
// condition.
auto Cond = ParseExpression();
if (!Cond)
return nullptr;
if (CurTok != tok_then)
return LogError("expected then");
getNextToken(); // eat the then
auto Then = ParseExpression();
if (!Then)
return nullptr;
if (CurTok != tok_else)
return LogError("expected else");
getNextToken();
auto Else = ParseExpression();
if (!Else)
return nullptr;
return std::make_unique<IfExprAST>(std::move(Cond), std::move(Then),
std::move(Else));
}
/// forexpr ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression
static std::unique_ptr<ExprAST> ParseForExpr() {
getNextToken(); // eat the for.
if (CurTok != tok_identifier)
return LogError("expected identifier after for");
std::string IdName = IdentifierStr;
getNextToken(); // eat identifier.
if (CurTok != '=')
return LogError("expected '=' after for");
getNextToken(); // eat '='.
auto Start = ParseExpression();
if (!Start)
return nullptr;
if (CurTok != ',')
return LogError("expected ',' after for start value");
getNextToken();
auto End = ParseExpression();
if (!End)
return nullptr;
// The step value is optional.
std::unique_ptr<ExprAST> Step;
if (CurTok == ',') {
getNextToken();
Step = ParseExpression();
if (!Step)
return nullptr;
}
if (CurTok != tok_in)
return LogError("expected 'in' after for");
getNextToken(); // eat 'in'.
auto Body = ParseExpression();
if (!Body)
return nullptr;
return std::make_unique<ForExprAST>(IdName, std::move(Start), std::move(End),
std::move(Step), std::move(Body));
}
/// varexpr ::= 'var' identifier ('=' expression)?
// (',' identifier ('=' expression)?)* 'in' expression
static std::unique_ptr<ExprAST> ParseVarExpr() {
getNextToken(); // eat the var.
std::vector<std::pair<std::string, std::unique_ptr<ExprAST>>> VarNames;
// At least one variable name is required.
if (CurTok != tok_identifier)
return LogError("expected identifier after var");
while (true) {
std::string Name = IdentifierStr;
getNextToken(); // eat identifier.
// Read the optional initializer.
std::unique_ptr<ExprAST> Init = nullptr;
if (CurTok == '=') {
getNextToken(); // eat the '='.
Init = ParseExpression();
if (!Init)
return nullptr;
}
VarNames.push_back(std::make_pair(Name, std::move(Init)));
// End of var list, exit loop.
if (CurTok != ',')
break;
getNextToken(); // eat the ','.
if (CurTok != tok_identifier)
return LogError("expected identifier list after var");
}
// At this point, we have to have 'in'.
if (CurTok != tok_in)
return LogError("expected 'in' keyword after 'var'");
getNextToken(); // eat 'in'.
auto Body = ParseExpression();
if (!Body)
return nullptr;
return std::make_unique<VarExprAST>(std::move(VarNames), std::move(Body));
}
/// primary
/// ::= identifierexpr
/// ::= numberexpr
/// ::= parenexpr
/// ::= ifexpr
/// ::= forexpr
/// ::= varexpr
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();
case tok_if:
return ParseIfExpr();
case tok_for:
return ParseForExpr();
case tok_var:
return ParseVarExpr();
}
}
/// unary
/// ::= primary
/// ::= '!' unary
static std::unique_ptr<ExprAST> ParseUnary() {
// If the current token is not an operator, it must be a primary expr.
if (!isascii(CurTok) || CurTok == '(' || CurTok == ',')
return ParsePrimary();
// If this is a unary operator, read it.
int Opc = CurTok;
getNextToken();
if (auto Operand = ParseUnary())
return std::make_unique<UnaryExprAST>(Opc, std::move(Operand));
return nullptr;
}
/// binoprhs
/// ::= ('+' unary)*
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 unary expression after the binary operator.
auto RHS = ParseUnary();
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
/// ::= unary binoprhs
///
static std::unique_ptr<ExprAST> ParseExpression() {
auto LHS = ParseUnary();
if (!LHS)
return nullptr;
return ParseBinOpRHS(0, std::move(LHS));
}
/// prototype
/// ::= id '(' id* ')'
/// ::= binary LETTER number? (id, id)
/// ::= unary LETTER (id)
static std::unique_ptr<PrototypeAST> ParsePrototype() {
std::string FnName;
unsigned Kind = 0; // 0 = identifier, 1 = unary, 2 = binary.
unsigned BinaryPrecedence = 30;
switch (CurTok) {
default:
return LogErrorP("Expected function name in prototype");
case tok_identifier:
FnName = IdentifierStr;
Kind = 0;
getNextToken();
break;
case tok_unary:
getNextToken();
if (!isascii(CurTok))
return LogErrorP("Expected unary operator");
FnName = "unary";
FnName += (char)CurTok;
Kind = 1;
getNextToken();
break;
case tok_binary:
getNextToken();
if (!isascii(CurTok))
return LogErrorP("Expected binary operator");
FnName = "binary";
FnName += (char)CurTok;
Kind = 2;
getNextToken();
// Read the precedence if present.
if (CurTok == tok_number) {
if (NumVal < 1 || NumVal > 100)
return LogErrorP("Invalid precedence: must be 1..100");
BinaryPrecedence = (unsigned)NumVal;
getNextToken();
}
break;
}
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 ')'.
// Verify right number of names for operator.
if (Kind && ArgNames.size() != Kind)
return LogErrorP("Invalid number of operands for operator");
return std::make_unique<PrototypeAST>(FnName, ArgNames, Kind != 0,
BinaryPrecedence);
}
/// 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, AllocaInst *> NamedValues;
static std::map<std::string, std::unique_ptr<PrototypeAST>> FunctionProtos;
static ExitOnError ExitOnErr;
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;
}
/// CreateEntryBlockAlloca - Create an alloca instruction in the entry block of
/// the function. This is used for mutable variables etc.
static AllocaInst *CreateEntryBlockAlloca(Function *TheFunction,
StringRef VarName) {
IRBuilder<> TmpB(&TheFunction->getEntryBlock(),
TheFunction->getEntryBlock().begin());
return TmpB.CreateAlloca(Type::getDoubleTy(*TheContext), nullptr, VarName);
}
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");
// Load the value.
return Builder->CreateLoad(Type::getDoubleTy(*TheContext), V, Name.c_str());
}
Value *UnaryExprAST::codegen() {
Value *OperandV = Operand->codegen();
if (!OperandV)
return nullptr;
Function *F = getFunction(std::string("unary") + Opcode);
if (!F)
return LogErrorV("Unknown unary operator");
return Builder->CreateCall(F, OperandV, "unop");
}
Value *BinaryExprAST::codegen() {
// Special case '=' because we don't want to emit the LHS as an expression.
if (Op == '=') {
// Assignment requires the LHS to be an identifier.
// This assume we're building without RTTI because LLVM builds that way by
// default. If you build LLVM with RTTI this can be changed to a
// dynamic_cast for automatic error checking.
VariableExprAST *LHSE = static_cast<VariableExprAST *>(LHS.get());
if (!LHSE)
return LogErrorV("destination of '=' must be a variable");
// Codegen the RHS.
Value *Val = RHS->codegen();
if (!Val)
return nullptr;
// Look up the name.
Value *Variable = NamedValues[LHSE->getName()];
if (!Variable)
return LogErrorV("Unknown variable name");
Builder->CreateStore(Val, Variable);
return Val;
}
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:
break;
}
// If it wasn't a builtin binary operator, it must be a user defined one. Emit
// a call to it.
Function *F = getFunction(std::string("binary") + Op);
assert(F && "binary operator not found!");
Value *Ops[] = {L, R};
return Builder->CreateCall(F, Ops, "binop");
}
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");
}
Value *IfExprAST::codegen() {
Value *CondV = Cond->codegen();
if (!CondV)
return nullptr;
// Convert condition to a bool by comparing non-equal to 0.0.
CondV = Builder->CreateFCmpONE(
CondV, ConstantFP::get(*TheContext, APFloat(0.0)), "ifcond");
Function *TheFunction = Builder->GetInsertBlock()->getParent();
// Create blocks for the then and else cases. Insert the 'then' block at the
// end of the function.
BasicBlock *ThenBB = BasicBlock::Create(*TheContext, "then", TheFunction);
BasicBlock *ElseBB = BasicBlock::Create(*TheContext, "else");
BasicBlock *MergeBB = BasicBlock::Create(*TheContext, "ifcont");
Builder->CreateCondBr(CondV, ThenBB, ElseBB);
// Emit then value.
Builder->SetInsertPoint(ThenBB);
Value *ThenV = Then->codegen();
if (!ThenV)
return nullptr;
Builder->CreateBr(MergeBB);
// Codegen of 'Then' can change the current block, update ThenBB for the PHI.
ThenBB = Builder->GetInsertBlock();
// Emit else block.
TheFunction->insert(TheFunction->end(), ElseBB);
Builder->SetInsertPoint(ElseBB);
Value *ElseV = Else->codegen();
if (!ElseV)
return nullptr;
Builder->CreateBr(MergeBB);
// Codegen of 'Else' can change the current block, update ElseBB for the PHI.
ElseBB = Builder->GetInsertBlock();
// Emit merge block.
TheFunction->insert(TheFunction->end(), MergeBB);
Builder->SetInsertPoint(MergeBB);
PHINode *PN = Builder->CreatePHI(Type::getDoubleTy(*TheContext), 2, "iftmp");
PN->addIncoming(ThenV, ThenBB);
PN->addIncoming(ElseV, ElseBB);
return PN;
}
// Output for-loop as:
// var = alloca double
// ...
// start = startexpr
// store start -> var
// goto loop
// loop:
// ...
// bodyexpr
// ...
// loopend:
// step = stepexpr
// endcond = endexpr
//
// curvar = load var
// nextvar = curvar + step
// store nextvar -> var
// br endcond, loop, endloop
// outloop:
Value *ForExprAST::codegen() {
Function *TheFunction = Builder->GetInsertBlock()->getParent();
// Create an alloca for the variable in the entry block.
AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, VarName);
// Emit the start code first, without 'variable' in scope.
Value *StartVal = Start->codegen();
if (!StartVal)
return nullptr;
// Store the value into the alloca.
Builder->CreateStore(StartVal, Alloca);
// Make the new basic block for the loop header, inserting after current
// block.
BasicBlock *LoopBB = BasicBlock::Create(*TheContext, "loop", TheFunction);
// Insert an explicit fall through from the current block to the LoopBB.
Builder->CreateBr(LoopBB);
// Start insertion in LoopBB.
Builder->SetInsertPoint(LoopBB);
// Within the loop, the variable is defined equal to the PHI node. If it
// shadows an existing variable, we have to restore it, so save it now.
AllocaInst *OldVal = NamedValues[VarName];
NamedValues[VarName] = Alloca;
// Emit the body of the loop. This, like any other expr, can change the
// current BB. Note that we ignore the value computed by the body, but don't
// allow an error.
if (!Body->codegen())
return nullptr;
// Emit the step value.
Value *StepVal = nullptr;
if (Step) {
StepVal = Step->codegen();
if (!StepVal)
return nullptr;
} else {
// If not specified, use 1.0.
StepVal = ConstantFP::get(*TheContext, APFloat(1.0));
}
// Compute the end condition.
Value *EndCond = End->codegen();
if (!EndCond)
return nullptr;
// Reload, increment, and restore the alloca. This handles the case where
// the body of the loop mutates the variable.
Value *CurVar = Builder->CreateLoad(Type::getDoubleTy(*TheContext), Alloca,
VarName.c_str());
Value *NextVar = Builder->CreateFAdd(CurVar, StepVal, "nextvar");
Builder->CreateStore(NextVar, Alloca);
// Convert condition to a bool by comparing non-equal to 0.0.
EndCond = Builder->CreateFCmpONE(
EndCond, ConstantFP::get(*TheContext, APFloat(0.0)), "loopcond");
// Create the "after loop" block and insert it.
BasicBlock *AfterBB =
BasicBlock::Create(*TheContext, "afterloop", TheFunction);
// Insert the conditional branch into the end of LoopEndBB.
Builder->CreateCondBr(EndCond, LoopBB, AfterBB);
// Any new code will be inserted in AfterBB.
Builder->SetInsertPoint(AfterBB);
// Restore the unshadowed variable.
if (OldVal)
NamedValues[VarName] = OldVal;
else
NamedValues.erase(VarName);
// for expr always returns 0.0.
return Constant::getNullValue(Type::getDoubleTy(*TheContext));
}
Value *VarExprAST::codegen() {
std::vector<AllocaInst *> OldBindings;
Function *TheFunction = Builder->GetInsertBlock()->getParent();
// Register all variables and emit their initializer.
for (unsigned i = 0, e = VarNames.size(); i != e; ++i) {
const std::string &VarName = VarNames[i].first;
ExprAST *Init = VarNames[i].second.get();
// Emit the initializer before adding the variable to scope, this prevents
// the initializer from referencing the variable itself, and permits stuff
// like this:
// var a = 1 in
// var a = a in ... # refers to outer 'a'.
Value *InitVal;
if (Init) {
InitVal = Init->codegen();
if (!InitVal)
return nullptr;
} else { // If not specified, use 0.0.
InitVal = ConstantFP::get(*TheContext, APFloat(0.0));
}
AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, VarName);
Builder->CreateStore(InitVal, Alloca);
// Remember the old variable binding so that we can restore the binding when
// we unrecurse.
OldBindings.push_back(NamedValues[VarName]);
// Remember this binding.
NamedValues[VarName] = Alloca;
}
// Codegen the body, now that all vars are in scope.
Value *BodyVal = Body->codegen();
if (!BodyVal)
return nullptr;
// Pop all our variables from scope.
for (unsigned i = 0, e = VarNames.size(); i != e; ++i)
NamedValues[VarNames[i].first] = OldBindings[i];
// Return the body computation.
return BodyVal;
}
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() {
// 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;
// If this is an operator, install it.
if (P.isBinaryOp())
BinopPrecedence[P.getOperatorName()] = P.getBinaryPrecedence();
// 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()) {
// Create an alloca for this variable.
AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, Arg.getName());
// Store the initial value into the alloca.
Builder->CreateStore(&Arg, Alloca);
// Add arguments to variable symbol table.
NamedValues[std::string(Arg.getName())] = Alloca;
}
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();
if (P.isBinaryOp())
BinopPrecedence.erase(P.getOperatorName());
return nullptr;
}
//===----------------------------------------------------------------------===//
// Top-Level parsing and JIT Driver
//===----------------------------------------------------------------------===//
static void InitializeModuleAndPassManager() {
// Open a new 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");
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()) {
FnAST->codegen();
} else {
// Skip token for error recovery.
getNextToken();
}
}
/// top ::= definition | external | expression | ';'
static void MainLoop() {
while (true) {
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.
//===----------------------------------------------------------------------===//
#ifdef _WIN32
#define DLLEXPORT __declspec(dllexport)
#else
#define DLLEXPORT
#endif
/// putchard - putchar that takes a double and returns 0.
extern "C" DLLEXPORT 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" DLLEXPORT double printd(double X) {
fprintf(stderr, "%f\n", X);
return 0;
}
//===----------------------------------------------------------------------===//
// 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();
InitializeModuleAndPassManager();
// Run the main "interpreter loop" now.
MainLoop();
// Initialize the target registry etc.
InitializeAllTargetInfos();
InitializeAllTargets();
InitializeAllTargetMCs();
InitializeAllAsmParsers();
InitializeAllAsmPrinters();
auto TargetTriple = sys::getDefaultTargetTriple();
TheModule->setTargetTriple(TargetTriple);
std::string Error;
auto Target = TargetRegistry::lookupTarget(TargetTriple, Error);
// Print an error and exit if we couldn't find the requested target.
// This generally occurs if we've forgotten to initialise the
// TargetRegistry or we have a bogus target triple.
if (!Target) {
errs() << Error;
return 1;
}
auto CPU = "generic";
auto Features = "";
TargetOptions opt;
auto TheTargetMachine = Target->createTargetMachine(
TargetTriple, CPU, Features, opt, Reloc::PIC_);
TheModule->setDataLayout(TheTargetMachine->createDataLayout());
auto Filename = "output.o";
std::error_code EC;
raw_fd_ostream dest(Filename, EC, sys::fs::OF_None);
if (EC) {
errs() << "Could not open file: " << EC.message();
return 1;
}
legacy::PassManager pass;
auto FileType = CodeGenFileType::ObjectFile;
if (TheTargetMachine->addPassesToEmitFile(pass, dest, nullptr, FileType)) {
errs() << "TheTargetMachine can't emit a file of this type";
return 1;
}
pass.run(*TheModule);
dest.flush();
outs() << "Wrote " << Filename << "\n";
return 0;
}