Browse Source

chapter 6

Andrea Gussoni 8 years ago
parent
commit
afb6a21169
9 changed files with 1213 additions and 33 deletions
  1. 39 14
      source/Ast.cpp
  2. 33 7
      source/Ast.h
  3. 1 1
      source/CMakeLists.txt
  4. 1 1
      source/Chapters/CMakeLists.txt
  5. 1063 0
      source/Chapters/Chapter6.cpp
  6. 4 0
      source/Lexer.cpp
  7. 4 1
      source/Lexer.h
  8. 67 9
      source/Parser.cpp
  9. 1 0
      source/Parser.h

+ 39 - 14
source/Ast.cpp

@@ -32,27 +32,47 @@ Value *VariableExprAST::codegen() {
   return V;
 }
 
+Value *UnaryExprAST::codegen() {
+  Value *OperandV = Operand->codegen();
+  if (!OperandV)
+    return nullptr;
+
+  Function *F = getFunction(std::string("unary") + Opcode);
+  if (!F)
+    return ErrorV("Unknown unary operator");
+
+  return AstObjects::Builder.CreateCall(F, OperandV, "unop");
+}
+
 Value *BinaryExprAST::codegen() {
   Value *L = LHS->codegen();
   Value *R = RHS->codegen();
   if (!L || !R)
-  return nullptr;
+    return nullptr;
 
   switch (Op) {
-    case '+':
+  case '+':
     return AstObjects::Builder.CreateFAdd(L, R, "addtmp");
-    case '-':
+  case '-':
     return AstObjects::Builder.CreateFSub(L, R, "subtmp");
-    case '*':
+  case '*':
     return AstObjects::Builder.CreateFMul(L, R, "multmp");
-    case '<':
+  case '<':
     L = AstObjects::Builder.CreateFCmpULT(L, R, "cmptmp");
     // Convert bool 0/1 to double 0.0 or 1.0
-    return AstObjects::Builder.CreateUIToFP(L,
-        Type::getDoubleTy(getGlobalContext()), "booltmp");
-    default:
-    return ErrorV("invalid binary operator");
+    return AstObjects::Builder.CreateUIToFP(L, Type::getDoubleTy(getGlobalContext()),
+                                "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 = AstObjects::TheModule->getFunction(std::string("binary") + Op);
+  assert(F && "binary operator not found!");
+
+  Value *Ops[2] = { L, R };
+  return AstObjects::Builder.CreateCall(F, Ops, "binop");
 }
 
 Value *CallExprAST::codegen() {
@@ -232,16 +252,18 @@ Function *FunctionAST::codegen() {
   if (!TheFunction)
     return nullptr;
 
+  // If this is an operator, install it.
+  if (P.isBinaryOp())
+    parser::BinopPrecedence[P.getOperatorName()] = P.getBinaryPrecedence();
+
   // Create a new basic block to start insertion into.
-  BasicBlock *BB = BasicBlock::Create(getGlobalContext(),
-      "entry", TheFunction);
+  BasicBlock *BB = BasicBlock::Create(getGlobalContext(), "entry", TheFunction);
   AstObjects::Builder.SetInsertPoint(BB);
 
   // Record the function arguments in the NamedValues map.
   AstObjects::NamedValues.clear();
-  for (auto &Arg : TheFunction->args()) {
+  for (auto &Arg : TheFunction->args())
     AstObjects::NamedValues[Arg.getName()] = &Arg;
-  }
 
   if (Value *RetVal = Body->codegen()) {
     // Finish off the function.
@@ -250,7 +272,7 @@ Function *FunctionAST::codegen() {
     // Validate the generated code, checking for consistency.
     verifyFunction(*TheFunction);
 
-    // Optimize the function.
+    // Run the optimizer on the function.
     JITObjects::TheFPM->run(*TheFunction);
 
     return TheFunction;
@@ -258,6 +280,9 @@ Function *FunctionAST::codegen() {
 
   // Error reading body, remove function.
   TheFunction->eraseFromParent();
+
+  if (P.isBinaryOp())
+    parser::BinopPrecedence.erase(Proto->getOperatorName());
   return nullptr;
 }
 

+ 33 - 7
source/Ast.h

@@ -47,6 +47,17 @@ public:
   Value *codegen() override;
 };
 
+/// 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;
@@ -54,7 +65,8 @@ class BinaryExprAST : public ExprAST {
 
 public:
   BinaryExprAST(char Op, std::unique_ptr<ExprAST> LHS,
-      std::unique_ptr<ExprAST> RHS) : Op(Op), LHS(std::move(LHS)), RHS(std::move(RHS)) {}
+                std::unique_ptr<ExprAST> RHS)
+      : Op(Op), LHS(std::move(LHS)), RHS(std::move(RHS)) {}
   Value *codegen() override;
 };
 
@@ -95,18 +107,32 @@ public:
   virtual Value *codegen();
 };
 
-  /// 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).
+/// 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) : Name(Name), Args(std::move(Args)) {}
+  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.
@@ -116,7 +142,7 @@ class FunctionAST {
 
 public:
   FunctionAST(std::unique_ptr<PrototypeAST> Proto,
-      std::unique_ptr<ExprAST> Body)
+              std::unique_ptr<ExprAST> Body)
       : Proto(std::move(Proto)), Body(std::move(Body)) {}
   Function *codegen();
 };

+ 1 - 1
source/CMakeLists.txt

@@ -21,7 +21,7 @@ add_executable(kaleidoscope Main.cpp Lexer.cpp Parser.cpp Ast.cpp JIT.cpp)
 
 # Find the libraries that correspond to the LLVM components
 # that we wish to use
-llvm_map_components_to_libnames(llvm_libs core support native mcjit object scalaropts instcombine RuntimeDyld ExecutionEngine all)
+llvm_map_components_to_libnames(llvm_libs core support native mcjit object scalaropts instcombine RuntimeDyld ExecutionEngine)
 
 # Link against LLVM libraries
 target_link_libraries(kaleidoscope ${llvm_libs})

+ 1 - 1
source/Chapters/CMakeLists.txt

@@ -17,7 +17,7 @@ set(CMAKE_CXX_FLAGS ${CMAKE_CXX_FLAGS} ${LLVM_CXX_FLAGS})
 include_directories(${LLVM_INCLUDE_DIRS})
 add_definitions(${LLVM_DEFINITIONS})
 
-add_executable(kaleidoscope Chapter5.cpp)
+add_executable(kaleidoscope Chapter6.cpp)
 
 # Find the libraries that correspond to the LLVM components
 # that we wish to use

+ 1063 - 0
source/Chapters/Chapter6.cpp

@@ -0,0 +1,1063 @@
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/Analysis/Passes.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/LegacyPassManager.h"
+#include "llvm/IR/Module.h"
+#include "llvm/IR/Verifier.h"
+#include "llvm/Support/TargetSelect.h"
+#include "llvm/Transforms/Scalar.h"
+#include <cctype>
+#include <cstdio>
+#include <map>
+#include <string>
+#include <vector>
+#include "../KaleidoscopeJIT.h"
+
+using namespace llvm;
+using namespace llvm::orc;
+
+//===----------------------------------------------------------------------===//
+// Lexer
+//===----------------------------------------------------------------------===//
+
+// The lexer returns tokens [0-255] if it is an unknown character, otherwise one
+// of these for known things.
+enum Token {
+  tok_eof = -1,
+
+  // commands
+  tok_def = -2,
+  tok_extern = -3,
+
+  // primary
+  tok_identifier = -4,
+  tok_number = -5,
+
+  // control
+  tok_if = -6,
+  tok_then = -7,
+  tok_else = -8,
+  tok_for = -9,
+  tok_in = -10,
+
+  // operators
+  tok_binary = -11,
+  tok_unary = -12
+};
+
+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;
+    return tok_identifier;
+  }
+
+  if (isdigit(LastChar) || LastChar == '.') { // Number: [0-9.]+
+    std::string NumStr;
+    do {
+      NumStr += LastChar;
+      LastChar = getchar();
+    } while (isdigit(LastChar) || LastChar == '.');
+
+    NumVal = strtod(NumStr.c_str(), nullptr);
+    return tok_number;
+  }
+
+  if (LastChar == '#') {
+    // Comment until end of line.
+    do
+      LastChar = getchar();
+    while (LastChar != EOF && LastChar != '\n' && LastChar != '\r');
+
+    if (LastChar != EOF)
+      return gettok();
+  }
+
+  // Check for end of file.  Don't eat the EOF.
+  if (LastChar == EOF)
+    return tok_eof;
+
+  // Otherwise, just return the character as its ascii value.
+  int ThisChar = LastChar;
+  LastChar = getchar();
+  return ThisChar;
+}
+
+//===----------------------------------------------------------------------===//
+// Abstract Syntax Tree (aka Parse Tree)
+//===----------------------------------------------------------------------===//
+namespace {
+/// ExprAST - Base class for all expression nodes.
+class ExprAST {
+public:
+  virtual ~ExprAST() {}
+  virtual Value *codegen() = 0;
+};
+
+/// NumberExprAST - Expression class for numeric literals like "1.0".
+class NumberExprAST : public ExprAST {
+  double Val;
+
+public:
+  NumberExprAST(double Val) : Val(Val) {}
+  Value *codegen() override;
+};
+
+/// VariableExprAST - Expression class for referencing a variable, like "a".
+class VariableExprAST : public ExprAST {
+  std::string Name;
+
+public:
+  VariableExprAST(const std::string &Name) : Name(Name) {}
+  Value *codegen() override;
+};
+
+/// 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;
+};
+
+/// 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;
+}
+
+/// Error* - These are little helper functions for error handling.
+std::unique_ptr<ExprAST> Error(const char *Str) {
+  fprintf(stderr, "Error: %s\n", Str);
+  return nullptr;
+}
+
+std::unique_ptr<PrototypeAST> ErrorP(const char *Str) {
+  Error(Str);
+  return nullptr;
+}
+
+static std::unique_ptr<ExprAST> ParseExpression();
+
+/// numberexpr ::= number
+static std::unique_ptr<ExprAST> ParseNumberExpr() {
+  auto Result = llvm::make_unique<NumberExprAST>(NumVal);
+  getNextToken(); // consume the number
+  return std::move(Result);
+}
+
+/// parenexpr ::= '(' expression ')'
+static std::unique_ptr<ExprAST> ParseParenExpr() {
+  getNextToken(); // eat (.
+  auto V = ParseExpression();
+  if (!V)
+    return nullptr;
+
+  if (CurTok != ')')
+    return Error("expected ')'");
+  getNextToken(); // eat ).
+  return V;
+}
+
+/// identifierexpr
+///   ::= identifier
+///   ::= identifier '(' expression* ')'
+static std::unique_ptr<ExprAST> ParseIdentifierExpr() {
+  std::string IdName = IdentifierStr;
+
+  getNextToken(); // eat identifier.
+
+  if (CurTok != '(') // Simple variable ref.
+    return llvm::make_unique<VariableExprAST>(IdName);
+
+  // Call.
+  getNextToken(); // eat (
+  std::vector<std::unique_ptr<ExprAST>> Args;
+  if (CurTok != ')') {
+    while (1) {
+      if (auto Arg = ParseExpression())
+        Args.push_back(std::move(Arg));
+      else
+        return nullptr;
+
+      if (CurTok == ')')
+        break;
+
+      if (CurTok != ',')
+        return Error("Expected ')' or ',' in argument list");
+      getNextToken();
+    }
+  }
+
+  // Eat the ')'.
+  getNextToken();
+
+  return llvm::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 Error("expected then");
+  getNextToken(); // eat the then
+
+  auto Then = ParseExpression();
+  if (!Then)
+    return nullptr;
+
+  if (CurTok != tok_else)
+    return Error("expected else");
+
+  getNextToken();
+
+  auto Else = ParseExpression();
+  if (!Else)
+    return nullptr;
+
+  return llvm::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 Error("expected identifier after for");
+
+  std::string IdName = IdentifierStr;
+  getNextToken(); // eat identifier.
+
+  if (CurTok != '=')
+    return Error("expected '=' after for");
+  getNextToken(); // eat '='.
+
+  auto Start = ParseExpression();
+  if (!Start)
+    return nullptr;
+  if (CurTok != ',')
+    return Error("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 Error("expected 'in' after for");
+  getNextToken(); // eat 'in'.
+
+  auto Body = ParseExpression();
+  if (!Body)
+    return nullptr;
+
+  return llvm::make_unique<ForExprAST>(IdName, std::move(Start), std::move(End),
+                                       std::move(Step), std::move(Body));
+}
+
+/// primary
+///   ::= identifierexpr
+///   ::= numberexpr
+///   ::= parenexpr
+///   ::= ifexpr
+///   ::= forexpr
+static std::unique_ptr<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();
+  case tok_if:
+    return ParseIfExpr();
+  case tok_for:
+    return ParseForExpr();
+  }
+}
+
+/// 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 llvm::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 (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 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 =
+        llvm::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 ErrorP("Expected function name in prototype");
+  case tok_identifier:
+    FnName = IdentifierStr;
+    Kind = 0;
+    getNextToken();
+    break;
+  case tok_unary:
+    getNextToken();
+    if (!isascii(CurTok))
+      return ErrorP("Expected unary operator");
+    FnName = "unary";
+    FnName += (char)CurTok;
+    Kind = 1;
+    getNextToken();
+    break;
+  case tok_binary:
+    getNextToken();
+    if (!isascii(CurTok))
+      return ErrorP("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 ErrorP("Invalid precedecnce: must be 1..100");
+      BinaryPrecedence = (unsigned)NumVal;
+      getNextToken();
+    }
+    break;
+  }
+
+  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 ')'.
+
+  // Verify right number of names for operator.
+  if (Kind && ArgNames.size() != Kind)
+    return ErrorP("Invalid number of operands for operator");
+
+  return llvm::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 llvm::make_unique<FunctionAST>(std::move(Proto), std::move(E));
+  return nullptr;
+}
+
+/// toplevelexpr ::= expression
+static std::unique_ptr<FunctionAST> ParseTopLevelExpr() {
+  if (auto E = ParseExpression()) {
+    // Make an anonymous proto.
+    auto Proto = llvm::make_unique<PrototypeAST>("__anon_expr",
+                                                 std::vector<std::string>());
+    return llvm::make_unique<FunctionAST>(std::move(Proto), std::move(E));
+  }
+  return nullptr;
+}
+
+/// external ::= 'extern' prototype
+static std::unique_ptr<PrototypeAST> ParseExtern() {
+  getNextToken(); // eat extern.
+  return ParsePrototype();
+}
+
+//===----------------------------------------------------------------------===//
+// Code Generation
+//===----------------------------------------------------------------------===//
+
+static std::unique_ptr<Module> TheModule;
+static IRBuilder<> Builder(getGlobalContext());
+static std::map<std::string, Value *> NamedValues;
+static std::unique_ptr<legacy::FunctionPassManager> TheFPM;
+static std::unique_ptr<KaleidoscopeJIT> TheJIT;
+static std::map<std::string, std::unique_ptr<PrototypeAST>> FunctionProtos;
+
+Value *ErrorV(const char *Str) {
+  Error(Str);
+  return nullptr;
+}
+
+Function *getFunction(std::string Name) {
+  // First, see if the function has already been added to the current module.
+  if (auto *F = TheModule->getFunction(Name))
+    return F;
+
+  // If not, check whether we can codegen the declaration from some existing
+  // prototype.
+  auto FI = FunctionProtos.find(Name);
+  if (FI != FunctionProtos.end())
+    return FI->second->codegen();
+
+  // If no existing prototype exists, return null.
+  return nullptr;
+}
+
+Value *NumberExprAST::codegen() {
+  return ConstantFP::get(getGlobalContext(), APFloat(Val));
+}
+
+Value *VariableExprAST::codegen() {
+  // Look this variable up in the function.
+  Value *V = NamedValues[Name];
+  if (!V)
+    return ErrorV("Unknown variable name");
+  return V;
+}
+
+Value *UnaryExprAST::codegen() {
+  Value *OperandV = Operand->codegen();
+  if (!OperandV)
+    return nullptr;
+
+  Function *F = getFunction(std::string("unary") + Opcode);
+  if (!F)
+    return ErrorV("Unknown unary operator");
+
+  return Builder.CreateCall(F, OperandV, "unop");
+}
+
+Value *BinaryExprAST::codegen() {
+  Value *L = LHS->codegen();
+  Value *R = RHS->codegen();
+  if (!L || !R)
+    return nullptr;
+
+  switch (Op) {
+  case '+':
+    return Builder.CreateFAdd(L, R, "addtmp");
+  case '-':
+    return Builder.CreateFSub(L, R, "subtmp");
+  case '*':
+    return Builder.CreateFMul(L, R, "multmp");
+  case '<':
+    L = Builder.CreateFCmpULT(L, R, "cmptmp");
+    // Convert bool 0/1 to double 0.0 or 1.0
+    return Builder.CreateUIToFP(L, Type::getDoubleTy(getGlobalContext()),
+                                "booltmp");
+  default:
+    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 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())
+      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 equal to 0.0.
+  CondV = Builder.CreateFCmpONE(
+      CondV, ConstantFP::get(getGlobalContext(), 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(getGlobalContext(), "then", TheFunction);
+  BasicBlock *ElseBB = BasicBlock::Create(getGlobalContext(), "else");
+  BasicBlock *MergeBB = BasicBlock::Create(getGlobalContext(), "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->getBasicBlockList().push_back(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->getBasicBlockList().push_back(MergeBB);
+  Builder.SetInsertPoint(MergeBB);
+  PHINode *PN =
+      Builder.CreatePHI(Type::getDoubleTy(getGlobalContext()), 2, "iftmp");
+
+  PN->addIncoming(ThenV, ThenBB);
+  PN->addIncoming(ElseV, ElseBB);
+  return PN;
+}
+
+// Output for-loop as:
+//   ...
+//   start = startexpr
+//   goto loop
+// loop:
+//   variable = phi [start, loopheader], [nextvariable, loopend]
+//   ...
+//   bodyexpr
+//   ...
+// loopend:
+//   step = stepexpr
+//   nextvariable = variable + step
+//   endcond = endexpr
+//   br endcond, loop, endloop
+// outloop:
+Value *ForExprAST::codegen() {
+  // Emit the start code first, without 'variable' in scope.
+  Value *StartVal = Start->codegen();
+  if (!StartVal)
+    return nullptr;
+
+  // Make the new basic block for the loop header, inserting after current
+  // block.
+  Function *TheFunction = Builder.GetInsertBlock()->getParent();
+  BasicBlock *PreheaderBB = Builder.GetInsertBlock();
+  BasicBlock *LoopBB =
+      BasicBlock::Create(getGlobalContext(), "loop", TheFunction);
+
+  // Insert an explicit fall through from the current block to the LoopBB.
+  Builder.CreateBr(LoopBB);
+
+  // Start insertion in LoopBB.
+  Builder.SetInsertPoint(LoopBB);
+
+  // Start the PHI node with an entry for Start.
+  PHINode *Variable = Builder.CreatePHI(Type::getDoubleTy(getGlobalContext()),
+                                        2, VarName.c_str());
+  Variable->addIncoming(StartVal, PreheaderBB);
+
+  // 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.
+  Value *OldVal = NamedValues[VarName];
+  NamedValues[VarName] = Variable;
+
+  // 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(getGlobalContext(), APFloat(1.0));
+  }
+
+  Value *NextVar = Builder.CreateFAdd(Variable, StepVal, "nextvar");
+
+  // Compute the end condition.
+  Value *EndCond = End->codegen();
+  if (!EndCond)
+    return nullptr;
+
+  // Convert condition to a bool by comparing equal to 0.0.
+  EndCond = Builder.CreateFCmpONE(
+      EndCond, ConstantFP::get(getGlobalContext(), APFloat(0.0)), "loopcond");
+
+  // Create the "after loop" block and insert it.
+  BasicBlock *LoopEndBB = Builder.GetInsertBlock();
+  BasicBlock *AfterBB =
+      BasicBlock::Create(getGlobalContext(), "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);
+
+  // Add a new entry to the PHI node for the backedge.
+  Variable->addIncoming(NextVar, LoopEndBB);
+
+  // Restore the unshadowed variable.
+  if (OldVal)
+    NamedValues[VarName] = OldVal;
+  else
+    NamedValues.erase(VarName);
+
+  // for expr always returns 0.0.
+  return Constant::getNullValue(Type::getDoubleTy(getGlobalContext()));
+}
+
+Function *PrototypeAST::codegen() {
+  // Make the function type:  double(double,double) etc.
+  std::vector<Type *> Doubles(Args.size(),
+                              Type::getDoubleTy(getGlobalContext()));
+  FunctionType *FT =
+      FunctionType::get(Type::getDoubleTy(getGlobalContext()), Doubles, false);
+
+  Function *F =
+      Function::Create(FT, Function::ExternalLinkage, Name, TheModule.get());
+
+  // Set names for all arguments.
+  unsigned Idx = 0;
+  for (auto &Arg : F->args())
+    Arg.setName(Args[Idx++]);
+
+  return F;
+}
+
+Function *FunctionAST::codegen() {
+  // Transfer ownership of the prototype to the FunctionProtos map, but keep a
+  // reference to it for use below.
+  auto &P = *Proto;
+  FunctionProtos[Proto->getName()] = std::move(Proto);
+  Function *TheFunction = getFunction(P.getName());
+  if (!TheFunction)
+    return nullptr;
+
+  // 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(getGlobalContext(), "entry", TheFunction);
+  Builder.SetInsertPoint(BB);
+
+  // Record the function arguments in the NamedValues map.
+  NamedValues.clear();
+  for (auto &Arg : TheFunction->args())
+    NamedValues[Arg.getName()] = &Arg;
+
+  if (Value *RetVal = Body->codegen()) {
+    // Finish off the function.
+    Builder.CreateRet(RetVal);
+
+    // Validate the generated code, checking for consistency.
+    verifyFunction(*TheFunction);
+
+    // Run the optimizer on the function.
+    TheFPM->run(*TheFunction);
+
+    return TheFunction;
+  }
+
+  // Error reading body, remove function.
+  TheFunction->eraseFromParent();
+
+  if (P.isBinaryOp())
+    BinopPrecedence.erase(Proto->getOperatorName());
+  return nullptr;
+}
+
+//===----------------------------------------------------------------------===//
+// Top-Level parsing and JIT Driver
+//===----------------------------------------------------------------------===//
+
+static void InitializeModuleAndPassManager() {
+  // Open a new module.
+  TheModule = llvm::make_unique<Module>("my cool jit", getGlobalContext());
+  TheModule->setDataLayout(TheJIT->getTargetMachine().createDataLayout());
+
+  // Create a new pass manager attached to it.
+  TheFPM = llvm::make_unique<legacy::FunctionPassManager>(TheModule.get());
+
+  // Do simple "peephole" optimizations and bit-twiddling optzns.
+  TheFPM->add(createInstructionCombiningPass());
+  // Reassociate expressions.
+  TheFPM->add(createReassociatePass());
+  // Eliminate Common SubExpressions.
+  TheFPM->add(createGVNPass());
+  // Simplify the control flow graph (deleting unreachable blocks, etc).
+  TheFPM->add(createCFGSimplificationPass());
+
+  TheFPM->doInitialization();
+}
+
+static void HandleDefinition() {
+  if (auto FnAST = ParseDefinition()) {
+    if (auto *FnIR = FnAST->codegen()) {
+      fprintf(stderr, "Read function definition:");
+      FnIR->dump();
+      TheJIT->addModule(std::move(TheModule));
+      InitializeModuleAndPassManager();
+    }
+  } else {
+    // Skip token for error recovery.
+    getNextToken();
+  }
+}
+
+static void HandleExtern() {
+  if (auto ProtoAST = ParseExtern()) {
+    if (auto *FnIR = ProtoAST->codegen()) {
+      fprintf(stderr, "Read extern: ");
+      FnIR->dump();
+      FunctionProtos[ProtoAST->getName()] = std::move(ProtoAST);
+    }
+  } else {
+    // Skip token for error recovery.
+    getNextToken();
+  }
+}
+
+static void HandleTopLevelExpression() {
+  // Evaluate a top-level expression into an anonymous function.
+  if (auto FnAST = ParseTopLevelExpr()) {
+    if (FnAST->codegen()) {
+
+      // JIT the module containing the anonymous expression, keeping a handle so
+      // we can free it later.
+      auto H = TheJIT->addModule(std::move(TheModule));
+      InitializeModuleAndPassManager();
+
+      // Search the JIT for the __anon_expr symbol.
+      auto ExprSymbol = TheJIT->findSymbol("__anon_expr");
+      assert(ExprSymbol && "Function not found");
+
+      // Get the symbol's address and cast it to the right type (takes no
+      // arguments, returns a double) so we can call it as a native function.
+      double (*FP)() = (double (*)())(intptr_t)ExprSymbol.getAddress();
+      fprintf(stderr, "Evaluated to %f\n", FP());
+
+      // Delete the anonymous expression module from the JIT.
+      TheJIT->removeModule(H);
+    }
+  } else {
+    // Skip token for error recovery.
+    getNextToken();
+  }
+}
+
+/// top ::= definition | external | expression | ';'
+static void MainLoop() {
+  while (1) {
+    fprintf(stderr, "ready> ");
+    switch (CurTok) {
+    case tok_eof:
+      return;
+    case ';': // ignore top-level semicolons.
+      getNextToken();
+      break;
+    case tok_def:
+      HandleDefinition();
+      break;
+    case tok_extern:
+      HandleExtern();
+      break;
+    default:
+      HandleTopLevelExpression();
+      break;
+    }
+  }
+}
+
+//===----------------------------------------------------------------------===//
+// "Library" functions that can be "extern'd" from user code.
+//===----------------------------------------------------------------------===//
+
+/// putchard - putchar that takes a double and returns 0.
+extern "C" double putchard(double X) {
+  fputc((char)X, stderr);
+  return 0;
+}
+
+/// printd - printf that takes a double prints it as "%f\n", returning 0.
+extern "C" double printd(double X) {
+  fprintf(stderr, "%f\n", X);
+  return 0;
+}
+
+//===----------------------------------------------------------------------===//
+// Main driver code.
+//===----------------------------------------------------------------------===//
+
+int main() {
+  InitializeNativeTarget();
+  InitializeNativeTargetAsmPrinter();
+  InitializeNativeTargetAsmParser();
+
+  // Install standard binary operators.
+  // 1 is lowest precedence.
+  BinopPrecedence['<'] = 10;
+  BinopPrecedence['+'] = 20;
+  BinopPrecedence['-'] = 20;
+  BinopPrecedence['*'] = 40; // highest.
+
+  // Prime the first token.
+  fprintf(stderr, "ready> ");
+  getNextToken();
+
+  TheJIT = llvm::make_unique<KaleidoscopeJIT>();
+
+  InitializeModuleAndPassManager();
+
+  // Run the main "interpreter loop" now.
+  MainLoop();
+
+  return 0;
+}

+ 4 - 0
source/Lexer.cpp

@@ -37,6 +37,10 @@ int gettok() {
       return tok_for;
     if (LexerObjects::IdentifierStr == "in")
       return tok_in;
+    if (LexerObjects::IdentifierStr == "binary")
+      return tok_binary;
+    if (LexerObjects::IdentifierStr == "unary")
+      return tok_unary;
     return tok_identifier;
   }
 

+ 4 - 1
source/Lexer.h

@@ -23,7 +23,10 @@ enum Token {
   tok_then = -7,
   tok_else = -8,
   tok_for = -9,
-  tok_in = -10
+  tok_in = -10,
+  // operators
+  tok_binary = -11,
+  tok_unary = -12
 };
 
 struct LexerObjects {

+ 67 - 9
source/Parser.cpp

@@ -219,8 +219,24 @@ static std::unique_ptr<ExprAST> ParsePrimary() {
   }
 }
 
+/// 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 llvm::make_unique<UnaryExprAST>(Opc, std::move(Operand));
+  return nullptr;
+}
+
 /// binoprhs
-///   ::= ('+' primary)*
+///   ::= ('+' unary)*
 static std::unique_ptr<ExprAST> ParseBinOpRHS(int ExprPrec,
                                               std::unique_ptr<ExprAST> LHS) {
   // If this is a binop, find its precedence.
@@ -236,8 +252,8 @@ static std::unique_ptr<ExprAST> ParseBinOpRHS(int ExprPrec,
     int BinOp = CurTok;
     getNextToken(); // eat binop
 
-    // Parse the primary expression after the binary operator.
-    auto RHS = ParsePrimary();
+    // Parse the unary expression after the binary operator.
+    auto RHS = ParseUnary();
     if (!RHS)
       return nullptr;
 
@@ -257,10 +273,10 @@ static std::unique_ptr<ExprAST> ParseBinOpRHS(int ExprPrec,
 }
 
 /// expression
-///   ::= primary binoprhs
+///   ::= unary binoprhs
 ///
 static std::unique_ptr<ExprAST> ParseExpression() {
-  auto LHS = ParsePrimary();
+  auto LHS = ParseUnary();
   if (!LHS)
     return nullptr;
 
@@ -269,12 +285,49 @@ static std::unique_ptr<ExprAST> ParseExpression() {
 
 /// prototype
 ///   ::= id '(' id* ')'
+///   ::= binary LETTER number? (id, id)
+///   ::= unary LETTER (id)
 static std::unique_ptr<PrototypeAST> ParsePrototype() {
-  if (CurTok != tok_identifier)
+  std::string FnName;
+
+  unsigned Kind = 0; // 0 = identifier, 1 = unary, 2 = binary.
+  unsigned BinaryPrecedence = 30;
+
+  switch (CurTok) {
+  default:
     return ErrorP("Expected function name in prototype");
+  case tok_identifier:
+    FnName = LexerObjects::IdentifierStr;
+    Kind = 0;
+    getNextToken();
+    break;
+  case tok_unary:
+    getNextToken();
+    if (!isascii(CurTok))
+      return ErrorP("Expected unary operator");
+    FnName = "unary";
+    FnName += (char)CurTok;
+    Kind = 1;
+    getNextToken();
+    break;
+  case tok_binary:
+    getNextToken();
+    if (!isascii(CurTok))
+      return ErrorP("Expected binary operator");
+    FnName = "binary";
+    FnName += (char)CurTok;
+    Kind = 2;
+    getNextToken();
 
-  std::string FnName = LexerObjects::IdentifierStr;
-  getNextToken();
+    // Read the precedence if present.
+    if (CurTok == tok_number) {
+      if (LexerObjects::NumVal < 1 || LexerObjects::NumVal > 100)
+        return ErrorP("Invalid precedecnce: must be 1..100");
+      BinaryPrecedence = (unsigned)LexerObjects::NumVal;
+      getNextToken();
+    }
+    break;
+  }
 
   if (CurTok != '(')
     return ErrorP("Expected '(' in prototype");
@@ -288,7 +341,12 @@ static std::unique_ptr<PrototypeAST> ParsePrototype() {
   // success.
   getNextToken(); // eat ')'.
 
-  return llvm::make_unique<PrototypeAST>(FnName, std::move(ArgNames));
+  // Verify right number of names for operator.
+  if (Kind && ArgNames.size() != Kind)
+    return ErrorP("Invalid number of operands for operator");
+
+  return llvm::make_unique<PrototypeAST>(FnName, ArgNames, Kind != 0,
+                                         BinaryPrecedence);
 }
 
 /// definition ::= 'def' prototype expression

+ 1 - 0
source/Parser.h

@@ -25,6 +25,7 @@ static std::unique_ptr<ExprAST> ParseIdentifierExpr();
 static std::unique_ptr<ExprAST> ParseIfExpr();
 static std::unique_ptr<ExprAST> ParseForExpr();
 static std::unique_ptr<ExprAST> ParsePrimary();
+static std::unique_ptr<ExprAST> ParseUnary();
 static std::unique_ptr<ExprAST> ParseBinOpRHS(int ExprPrec,
                                               std::unique_ptr<ExprAST> LHS);
 static std::unique_ptr<PrototypeAST> ParsePrototype();