mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-07-21 02:29:22 +00:00
788 lines
22 KiB
HTML
788 lines
22 KiB
HTML
|
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
|
||
|
|
"http://www.w3.org/TR/html4/strict.dtd">
|
||
|
|
|
||
|
|
<html>
|
||
|
|
<head>
|
||
|
|
<title>Kaleidoscope: Implementing code generation to LLVM IR</title>
|
||
|
|
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
|
||
|
|
<meta name="author" content="Chris Lattner">
|
||
|
|
<link rel="stylesheet" href="../llvm.css" type="text/css">
|
||
|
|
</head>
|
||
|
|
|
||
|
|
<body>
|
||
|
|
|
||
|
|
<div class="doc_title">Kaleidoscope: Code generation to LLVM IR</div>
|
||
|
|
|
||
|
|
<div class="doc_author">
|
||
|
|
<p>Written by <a href="mailto:sabre@nondot.org">Chris Lattner</a></p>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<!-- *********************************************************************** -->
|
||
|
|
<div class="doc_section"><a name="intro">Part 3 Introduction</a></div>
|
||
|
|
<!-- *********************************************************************** -->
|
||
|
|
|
||
|
|
<div class="doc_text">
|
||
|
|
|
||
|
|
<p>Welcome to part 3 of the "<a href="index.html">Implementing a language with
|
||
|
|
LLVM</a>" tutorial. This chapter shows you how to transform the <a
|
||
|
|
href="LangImpl2.html">Abstract Syntax Tree built in Chapter 2</a> into LLVM IR.
|
||
|
|
This will teach you a little bit about how LLVM does things, as well as
|
||
|
|
demonstrate how easy it is to use. It's much more work to build a lexer and
|
||
|
|
parser than it is to generate LLVM IR code.
|
||
|
|
</p>
|
||
|
|
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<!-- *********************************************************************** -->
|
||
|
|
<div class="doc_section"><a name="basics">Code Generation setup</a></div>
|
||
|
|
<!-- *********************************************************************** -->
|
||
|
|
|
||
|
|
<div class="doc_text">
|
||
|
|
|
||
|
|
<p>
|
||
|
|
In order to generate LLVM IR, we want some simple setup to get started. First,
|
||
|
|
we define virtual codegen methods in each AST class:</p>
|
||
|
|
|
||
|
|
<div class="doc_code">
|
||
|
|
<pre>
|
||
|
|
/// ExprAST - Base class for all expression nodes.
|
||
|
|
class ExprAST {
|
||
|
|
public:
|
||
|
|
virtual ~ExprAST() {}
|
||
|
|
virtual Value *Codegen() = 0;
|
||
|
|
};
|
||
|
|
|
||
|
|
/// NumberExprAST - Expression class for numeric literals like "1.0".
|
||
|
|
class NumberExprAST : public ExprAST {
|
||
|
|
double Val;
|
||
|
|
public:
|
||
|
|
NumberExprAST(double val) : Val(val) {}
|
||
|
|
virtual Value *Codegen();
|
||
|
|
};
|
||
|
|
...
|
||
|
|
</pre>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<p>"Value" is the class used to represent a "register" in LLVM. The Codegen()
|
||
|
|
method says to emit IR for that AST node and all things it depends on. The
|
||
|
|
second thing we want is an "Error" method like we used for parser, which will
|
||
|
|
be used to report errors found during code generation (for example, use of an
|
||
|
|
undeclared parameter):</p>
|
||
|
|
|
||
|
|
<div class="doc_code">
|
||
|
|
<pre>
|
||
|
|
Value *ErrorV(const char *Str) { Error(Str); return 0; }
|
||
|
|
|
||
|
|
static Module *TheModule;
|
||
|
|
static LLVMBuilder Builder;
|
||
|
|
static std::map<std::string, Value*> NamedValues;
|
||
|
|
</pre>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<p>The static variables will be used during code generation. <tt>TheModule</tt>
|
||
|
|
is the LLVM construct that contains all of the functions and global variables in
|
||
|
|
a chunk of code. In many ways, it is the top-level structure that the LLVM IR
|
||
|
|
uses to contain code.</p>
|
||
|
|
|
||
|
|
<p>The <tt>Builder</tt> object is a helper object that makes it easy to generate
|
||
|
|
LLVM instructions. The <tt>Builder</tt> keeps track of the current place to
|
||
|
|
insert instructions and has methods to create new instructions.</p>
|
||
|
|
|
||
|
|
<p>The <tt>NamedValues</tt> map keeps track of which values are defined in the
|
||
|
|
current scope and what their LLVM representation is. In this form of
|
||
|
|
Kaleidoscope, the only things that can be referenced are function parameters.
|
||
|
|
As such, function parameters will be in this map when generating code for their
|
||
|
|
function body.</p>
|
||
|
|
|
||
|
|
<p>
|
||
|
|
With these basics in place, we can start talking about how to generate code for
|
||
|
|
each expression. Note that this assumes that the <tt>Builder</tt> has been set
|
||
|
|
up to generate code <em>into</em> something. For now, we'll assume that this
|
||
|
|
has already been done, and we'll just use it to emit code.
|
||
|
|
</p>
|
||
|
|
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<!-- *********************************************************************** -->
|
||
|
|
<div class="doc_section"><a name="exprs">Expression Code Generation</a></div>
|
||
|
|
<!-- *********************************************************************** -->
|
||
|
|
|
||
|
|
<div class="doc_text">
|
||
|
|
|
||
|
|
<p>Generating LLVM code for expression nodes is very straight-forward: less
|
||
|
|
than 45 lines of commented code for all four of our expression nodes. First,
|
||
|
|
we'll do numeric literals:</p>
|
||
|
|
|
||
|
|
<div class="doc_code">
|
||
|
|
<pre>
|
||
|
|
Value *NumberExprAST::Codegen() {
|
||
|
|
return ConstantFP::get(Type::DoubleTy, APFloat(Val));
|
||
|
|
}
|
||
|
|
</pre>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<p>In the LLVM IR, numeric constants are represented with the ConstantFP class,
|
||
|
|
which holds the numeric value in an APFloat internally (APFloat has the
|
||
|
|
capability of holding floating point constants of arbitrary precision). This
|
||
|
|
code basically just creates and returns a ConstantFP. Note that in the LLVM IR
|
||
|
|
that constants are all uniqued together and shared. For this reason, the API
|
||
|
|
uses "the foo::get(...)" idiom instead of a "create" method or "new foo".</p>
|
||
|
|
|
||
|
|
<div class="doc_code">
|
||
|
|
<pre>
|
||
|
|
Value *VariableExprAST::Codegen() {
|
||
|
|
// Look this variable up in the function.
|
||
|
|
Value *V = NamedValues[Name];
|
||
|
|
return V ? V : ErrorV("Unknown variable name");
|
||
|
|
}
|
||
|
|
</pre>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<p>References to variables is also quite simple here. In our system, we assume
|
||
|
|
that the variable has already been emited somewhere and its value is available.
|
||
|
|
In practice, the only values in the NamedValues map will be arguments. This
|
||
|
|
code simply checks to see that the specified name is in the map (if not, an
|
||
|
|
unknown variable is being referenced) and returns the value for it.</p>
|
||
|
|
|
||
|
|
<div class="doc_code">
|
||
|
|
<pre>
|
||
|
|
Value *BinaryExprAST::Codegen() {
|
||
|
|
Value *L = LHS->Codegen();
|
||
|
|
Value *R = RHS->Codegen();
|
||
|
|
if (L == 0 || R == 0) return 0;
|
||
|
|
|
||
|
|
switch (Op) {
|
||
|
|
case '+': return Builder.CreateAdd(L, R, "addtmp");
|
||
|
|
case '-': return Builder.CreateSub(L, R, "subtmp");
|
||
|
|
case '*': return Builder.CreateMul(L, R, "multmp");
|
||
|
|
case '<':
|
||
|
|
L = Builder.CreateFCmpULT(L, R, "multmp");
|
||
|
|
// Convert bool 0/1 to double 0.0 or 1.0
|
||
|
|
return Builder.CreateUIToFP(L, Type::DoubleTy, "booltmp");
|
||
|
|
default: return ErrorV("invalid binary operator");
|
||
|
|
}
|
||
|
|
}
|
||
|
|
</pre>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
<div class="doc_code">
|
||
|
|
<pre>
|
||
|
|
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.begin(), ArgsV.end(), "calltmp");
|
||
|
|
}
|
||
|
|
</pre>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<h1> more todo</h1>
|
||
|
|
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<!-- *********************************************************************** -->
|
||
|
|
<div class="doc_section"><a name="code">Conclusions and the Full Code</a></div>
|
||
|
|
<!-- *********************************************************************** -->
|
||
|
|
|
||
|
|
<div class="doc_text">
|
||
|
|
|
||
|
|
<div class="doc_code">
|
||
|
|
<pre>
|
||
|
|
// To build this:
|
||
|
|
// g++ -g toy.cpp `llvm-config --cppflags` `llvm-config --ldflags` \
|
||
|
|
// `llvm-config --libs core` -I ~/llvm/include/
|
||
|
|
// ./a.out
|
||
|
|
// See example below.
|
||
|
|
|
||
|
|
#include "llvm/DerivedTypes.h"
|
||
|
|
#include "llvm/Module.h"
|
||
|
|
#include "llvm/Support/LLVMBuilder.h"
|
||
|
|
#include <cstdio>
|
||
|
|
#include <string>
|
||
|
|
#include <map>
|
||
|
|
#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(), 0);
|
||
|
|
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)
|
||
|
|
//===----------------------------------------------------------------------===//
|
||
|
|
|
||
|
|
/// ExprAST - Base class for all expression nodes.
|
||
|
|
class ExprAST {
|
||
|
|
public:
|
||
|
|
virtual ~ExprAST() {}
|
||
|
|
virtual Value *Codegen() = 0;
|
||
|
|
};
|
||
|
|
|
||
|
|
/// NumberExprAST - Expression class for numeric literals like "1.0".
|
||
|
|
class NumberExprAST : public ExprAST {
|
||
|
|
double Val;
|
||
|
|
public:
|
||
|
|
NumberExprAST(double val) : Val(val) {}
|
||
|
|
virtual Value *Codegen();
|
||
|
|
};
|
||
|
|
|
||
|
|
/// VariableExprAST - Expression class for referencing a variable, like "a".
|
||
|
|
class VariableExprAST : public ExprAST {
|
||
|
|
std::string Name;
|
||
|
|
public:
|
||
|
|
VariableExprAST(const std::string &name) : Name(name) {}
|
||
|
|
virtual Value *Codegen();
|
||
|
|
};
|
||
|
|
|
||
|
|
/// BinaryExprAST - Expression class for a binary operator.
|
||
|
|
class BinaryExprAST : public ExprAST {
|
||
|
|
char Op;
|
||
|
|
ExprAST *LHS, *RHS;
|
||
|
|
public:
|
||
|
|
BinaryExprAST(char op, ExprAST *lhs, ExprAST *rhs)
|
||
|
|
: Op(op), LHS(lhs), RHS(rhs) {}
|
||
|
|
virtual Value *Codegen();
|
||
|
|
};
|
||
|
|
|
||
|
|
/// CallExprAST - Expression class for function calls.
|
||
|
|
class CallExprAST : public ExprAST {
|
||
|
|
std::string Callee;
|
||
|
|
std::vector<ExprAST*> Args;
|
||
|
|
public:
|
||
|
|
CallExprAST(const std::string &callee, std::vector<ExprAST*> &args)
|
||
|
|
: Callee(callee), Args(args) {}
|
||
|
|
virtual Value *Codegen();
|
||
|
|
};
|
||
|
|
|
||
|
|
/// PrototypeAST - This class represents the "prototype" for a function,
|
||
|
|
/// which captures its argument names as well as if it is an operator.
|
||
|
|
class PrototypeAST {
|
||
|
|
std::string Name;
|
||
|
|
std::vector<std::string> Args;
|
||
|
|
public:
|
||
|
|
PrototypeAST(const std::string &name, const std::vector<std::string> &args)
|
||
|
|
: Name(name), Args(args) {}
|
||
|
|
|
||
|
|
Function *Codegen();
|
||
|
|
};
|
||
|
|
|
||
|
|
/// FunctionAST - This class represents a function definition itself.
|
||
|
|
class FunctionAST {
|
||
|
|
PrototypeAST *Proto;
|
||
|
|
ExprAST *Body;
|
||
|
|
public:
|
||
|
|
FunctionAST(PrototypeAST *proto, ExprAST *body)
|
||
|
|
: Proto(proto), Body(body) {}
|
||
|
|
|
||
|
|
Function *Codegen();
|
||
|
|
};
|
||
|
|
|
||
|
|
//===----------------------------------------------------------------------===//
|
||
|
|
// Parser
|
||
|
|
//===----------------------------------------------------------------------===//
|
||
|
|
|
||
|
|
/// CurTok/getNextToken - Provide a simple token buffer. CurTok is the current
|
||
|
|
/// token the parser it 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;
|
||
|
|
}
|
||
|
|
|
||
|
|
/// Error* - These are little helper functions for error handling.
|
||
|
|
ExprAST *Error(const char *Str) { fprintf(stderr, "Error: %s\n", Str);return 0;}
|
||
|
|
PrototypeAST *ErrorP(const char *Str) { Error(Str); return 0; }
|
||
|
|
FunctionAST *ErrorF(const char *Str) { Error(Str); return 0; }
|
||
|
|
|
||
|
|
static ExprAST *ParseExpression();
|
||
|
|
|
||
|
|
/// identifierexpr
|
||
|
|
/// ::= identifer
|
||
|
|
/// ::= identifer '(' expression* ')'
|
||
|
|
static ExprAST *ParseIdentifierExpr() {
|
||
|
|
std::string IdName = IdentifierStr;
|
||
|
|
|
||
|
|
getNextToken(); // eat identifer.
|
||
|
|
|
||
|
|
if (CurTok != '(') // Simple variable ref.
|
||
|
|
return new VariableExprAST(IdName);
|
||
|
|
|
||
|
|
// Call.
|
||
|
|
getNextToken(); // eat (
|
||
|
|
std::vector<ExprAST*> Args;
|
||
|
|
while (1) {
|
||
|
|
ExprAST *Arg = ParseExpression();
|
||
|
|
if (!Arg) return 0;
|
||
|
|
Args.push_back(Arg);
|
||
|
|
|
||
|
|
if (CurTok == ')') break;
|
||
|
|
|
||
|
|
if (CurTok != ',')
|
||
|
|
return Error("Expected ')'");
|
||
|
|
getNextToken();
|
||
|
|
}
|
||
|
|
|
||
|
|
// Eat the ')'.
|
||
|
|
getNextToken();
|
||
|
|
|
||
|
|
return new CallExprAST(IdName, Args);
|
||
|
|
}
|
||
|
|
|
||
|
|
/// numberexpr ::= number
|
||
|
|
static ExprAST *ParseNumberExpr() {
|
||
|
|
ExprAST *Result = new NumberExprAST(NumVal);
|
||
|
|
getNextToken(); // consume the number
|
||
|
|
return Result;
|
||
|
|
}
|
||
|
|
|
||
|
|
/// parenexpr ::= '(' expression ')'
|
||
|
|
static ExprAST *ParseParenExpr() {
|
||
|
|
getNextToken(); // eat (.
|
||
|
|
ExprAST *V = ParseExpression();
|
||
|
|
if (!V) return 0;
|
||
|
|
|
||
|
|
if (CurTok != ')')
|
||
|
|
return Error("expected ')'");
|
||
|
|
getNextToken(); // eat ).
|
||
|
|
return V;
|
||
|
|
}
|
||
|
|
|
||
|
|
/// primary
|
||
|
|
/// ::= identifierexpr
|
||
|
|
/// ::= numberexpr
|
||
|
|
/// ::= parenexpr
|
||
|
|
static ExprAST *ParsePrimary() {
|
||
|
|
switch (CurTok) {
|
||
|
|
default: return Error("unknown token when expecting an expression");
|
||
|
|
case tok_identifier: return ParseIdentifierExpr();
|
||
|
|
case tok_number: return ParseNumberExpr();
|
||
|
|
case '(': return ParseParenExpr();
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
/// binoprhs
|
||
|
|
/// ::= ('+' primary)*
|
||
|
|
static ExprAST *ParseBinOpRHS(int ExprPrec, 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.
|
||
|
|
ExprAST *RHS = ParsePrimary();
|
||
|
|
if (!RHS) return 0;
|
||
|
|
|
||
|
|
// 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, RHS);
|
||
|
|
if (RHS == 0) return 0;
|
||
|
|
}
|
||
|
|
|
||
|
|
// Merge LHS/RHS.
|
||
|
|
LHS = new BinaryExprAST(BinOp, LHS, RHS);
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
/// expression
|
||
|
|
/// ::= primary binoprhs
|
||
|
|
///
|
||
|
|
static ExprAST *ParseExpression() {
|
||
|
|
ExprAST *LHS = ParsePrimary();
|
||
|
|
if (!LHS) return 0;
|
||
|
|
|
||
|
|
return ParseBinOpRHS(0, LHS);
|
||
|
|
}
|
||
|
|
|
||
|
|
/// prototype
|
||
|
|
/// ::= id '(' id* ')'
|
||
|
|
static PrototypeAST *ParsePrototype() {
|
||
|
|
if (CurTok != tok_identifier)
|
||
|
|
return ErrorP("Expected function name in prototype");
|
||
|
|
|
||
|
|
std::string FnName = IdentifierStr;
|
||
|
|
getNextToken();
|
||
|
|
|
||
|
|
if (CurTok != '(')
|
||
|
|
return ErrorP("Expected '(' in prototype");
|
||
|
|
|
||
|
|
std::vector<std::string> ArgNames;
|
||
|
|
while (getNextToken() == tok_identifier)
|
||
|
|
ArgNames.push_back(IdentifierStr);
|
||
|
|
if (CurTok != ')')
|
||
|
|
return ErrorP("Expected ')' in prototype");
|
||
|
|
|
||
|
|
// success.
|
||
|
|
getNextToken(); // eat ')'.
|
||
|
|
|
||
|
|
return new PrototypeAST(FnName, ArgNames);
|
||
|
|
}
|
||
|
|
|
||
|
|
/// definition ::= 'def' prototype expression
|
||
|
|
static FunctionAST *ParseDefinition() {
|
||
|
|
getNextToken(); // eat def.
|
||
|
|
PrototypeAST *Proto = ParsePrototype();
|
||
|
|
if (Proto == 0) return 0;
|
||
|
|
|
||
|
|
if (ExprAST *E = ParseExpression())
|
||
|
|
return new FunctionAST(Proto, E);
|
||
|
|
return 0;
|
||
|
|
}
|
||
|
|
|
||
|
|
/// toplevelexpr ::= expression
|
||
|
|
static FunctionAST *ParseTopLevelExpr() {
|
||
|
|
if (ExprAST *E = ParseExpression()) {
|
||
|
|
// Make an anonymous proto.
|
||
|
|
PrototypeAST *Proto = new PrototypeAST("", std::vector<std::string>());
|
||
|
|
return new FunctionAST(Proto, E);
|
||
|
|
}
|
||
|
|
return 0;
|
||
|
|
}
|
||
|
|
|
||
|
|
/// external ::= 'extern' prototype
|
||
|
|
static PrototypeAST *ParseExtern() {
|
||
|
|
getNextToken(); // eat extern.
|
||
|
|
return ParsePrototype();
|
||
|
|
}
|
||
|
|
|
||
|
|
//===----------------------------------------------------------------------===//
|
||
|
|
// Code Generation
|
||
|
|
//===----------------------------------------------------------------------===//
|
||
|
|
|
||
|
|
static Module *TheModule;
|
||
|
|
static LLVMBuilder Builder;
|
||
|
|
static std::map<std::string, Value*> NamedValues;
|
||
|
|
|
||
|
|
Value *ErrorV(const char *Str) { Error(Str); return 0; }
|
||
|
|
|
||
|
|
Value *NumberExprAST::Codegen() {
|
||
|
|
return ConstantFP::get(Type::DoubleTy, APFloat(Val));
|
||
|
|
}
|
||
|
|
|
||
|
|
Value *VariableExprAST::Codegen() {
|
||
|
|
// Look this variable up in the function.
|
||
|
|
Value *V = NamedValues[Name];
|
||
|
|
return V ? V : ErrorV("Unknown variable name");
|
||
|
|
}
|
||
|
|
|
||
|
|
Value *BinaryExprAST::Codegen() {
|
||
|
|
Value *L = LHS->Codegen();
|
||
|
|
Value *R = RHS->Codegen();
|
||
|
|
if (L == 0 || R == 0) return 0;
|
||
|
|
|
||
|
|
switch (Op) {
|
||
|
|
case '+': return Builder.CreateAdd(L, R, "addtmp");
|
||
|
|
case '-': return Builder.CreateSub(L, R, "subtmp");
|
||
|
|
case '*': return Builder.CreateMul(L, R, "multmp");
|
||
|
|
case '<':
|
||
|
|
L = Builder.CreateFCmpULT(L, R, "multmp");
|
||
|
|
// Convert bool 0/1 to double 0.0 or 1.0
|
||
|
|
return Builder.CreateUIToFP(L, Type::DoubleTy, "booltmp");
|
||
|
|
default: return ErrorV("invalid binary operator");
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
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.begin(), ArgsV.end(), "calltmp");
|
||
|
|
}
|
||
|
|
|
||
|
|
Function *PrototypeAST::Codegen() {
|
||
|
|
// Make the function type: double(double,double) etc.
|
||
|
|
FunctionType *FT =
|
||
|
|
FunctionType::get(Type::DoubleTy, std::vector<const Type*>(Args.size(),
|
||
|
|
Type::DoubleTy),
|
||
|
|
false);
|
||
|
|
|
||
|
|
Function *F = new Function(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;
|
||
|
|
}
|
||
|
|
|
||
|
|
return F;
|
||
|
|
}
|
||
|
|
|
||
|
|
Function *FunctionAST::Codegen() {
|
||
|
|
NamedValues.clear();
|
||
|
|
|
||
|
|
Function *TheFunction = Proto->Codegen();
|
||
|
|
if (TheFunction == 0)
|
||
|
|
return 0;
|
||
|
|
|
||
|
|
// Create a new basic block to start insertion into.
|
||
|
|
Builder.SetInsertPoint(new BasicBlock("entry", TheFunction));
|
||
|
|
|
||
|
|
if (Value *RetVal = Body->Codegen()) {
|
||
|
|
// Finish off the function.
|
||
|
|
Builder.CreateRet(RetVal);
|
||
|
|
return TheFunction;
|
||
|
|
}
|
||
|
|
|
||
|
|
// Error reading body, remove function.
|
||
|
|
TheFunction->eraseFromParent();
|
||
|
|
return 0;
|
||
|
|
}
|
||
|
|
|
||
|
|
//===----------------------------------------------------------------------===//
|
||
|
|
// Top-Level parsing and JIT Driver
|
||
|
|
//===----------------------------------------------------------------------===//
|
||
|
|
|
||
|
|
static void HandleDefinition() {
|
||
|
|
if (FunctionAST *F = ParseDefinition()) {
|
||
|
|
if (Function *LF = F->Codegen()) {
|
||
|
|
fprintf(stderr, "Read function definition:");
|
||
|
|
LF->dump();
|
||
|
|
}
|
||
|
|
} else {
|
||
|
|
// Skip token for error recovery.
|
||
|
|
getNextToken();
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
static void HandleExtern() {
|
||
|
|
if (PrototypeAST *P = ParseExtern()) {
|
||
|
|
if (Function *F = P->Codegen()) {
|
||
|
|
fprintf(stderr, "Read extern: ");
|
||
|
|
F->dump();
|
||
|
|
}
|
||
|
|
} else {
|
||
|
|
// Skip token for error recovery.
|
||
|
|
getNextToken();
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
static void HandleTopLevelExpression() {
|
||
|
|
// Evaluate a top level expression into an anonymous function.
|
||
|
|
if (FunctionAST *F = ParseTopLevelExpr()) {
|
||
|
|
if (Function *LF = F->Codegen()) {
|
||
|
|
fprintf(stderr, "Read top-level expression:");
|
||
|
|
LF->dump();
|
||
|
|
}
|
||
|
|
} 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 ';': getNextToken(); break; // ignore top level semicolons.
|
||
|
|
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) {
|
||
|
|
putchar((char)X);
|
||
|
|
return 0;
|
||
|
|
}
|
||
|
|
|
||
|
|
//===----------------------------------------------------------------------===//
|
||
|
|
// Main driver code.
|
||
|
|
//===----------------------------------------------------------------------===//
|
||
|
|
|
||
|
|
int main() {
|
||
|
|
TheModule = new Module("my cool jit");
|
||
|
|
|
||
|
|
// 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();
|
||
|
|
|
||
|
|
MainLoop();
|
||
|
|
TheModule->dump();
|
||
|
|
return 0;
|
||
|
|
}
|
||
|
|
|
||
|
|
/* Examples:
|
||
|
|
|
||
|
|
def fib(x)
|
||
|
|
if (x < 3) then
|
||
|
|
1
|
||
|
|
else
|
||
|
|
fib(x-1)+fib(x-2);
|
||
|
|
|
||
|
|
fib(10);
|
||
|
|
|
||
|
|
*/
|
||
|
|
</pre>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<!-- *********************************************************************** -->
|
||
|
|
<hr>
|
||
|
|
<address>
|
||
|
|
<a href="http://jigsaw.w3.org/css-validator/check/referer"><img
|
||
|
|
src="http://jigsaw.w3.org/css-validator/images/vcss" alt="Valid CSS!"></a>
|
||
|
|
<a href="http://validator.w3.org/check/referer"><img
|
||
|
|
src="http://www.w3.org/Icons/valid-html401" alt="Valid HTML 4.01!" /></a>
|
||
|
|
|
||
|
|
<a href="mailto:sabre@nondot.org">Chris Lattner</a><br>
|
||
|
|
<a href="http://llvm.org">The LLVM Compiler Infrastructure</a><br>
|
||
|
|
Last modified: $Date: 2007-10-17 11:05:13 -0700 (Wed, 17 Oct 2007) $
|
||
|
|
</address>
|
||
|
|
</body>
|
||
|
|
</html>
|