#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/Instructions.h" #include "llvm/IR/IRBuilder.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/Support/TargetSelect.h" #include "llvm/Target/TargetMachine.h" #include "llvm/Transforms/Scalar.h" #include "llvm/Transforms/Scalar/GVN.h" #include "../include/KaleidoscopeJIT.h" #include #include #include #include #include #include #include #include #include #include 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 }; 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; return tok_identifier; } if (isdigit(LastChar) || LastChar == '.') { // Number: [0-9.]+ std::string NumStr; do { NumStr += LastChar; LastChar = getchar(); } while (isdigit(LastChar) || LastChar == '.'); NumVal = strtod(NumStr.c_str(), nullptr); return tok_number; } if (LastChar == '#') { // Comment until end of line. do LastChar = getchar(); while (LastChar != EOF && LastChar != '\n' && LastChar != '\r'); if (LastChar != EOF) return gettok(); } // Check for end of file. Don't eat the EOF. if (LastChar == EOF) return tok_eof; // Otherwise, just return the character as its ascii value. int ThisChar = LastChar; LastChar = getchar(); return ThisChar; } //===----------------------------------------------------------------------===// // Abstract Syntax Tree (aka Parse Tree) //===----------------------------------------------------------------------===// namespace { /// ExprAST - Base class for all expression nodes. class ExprAST { public: virtual ~ExprAST() = default; virtual Value *codegen() = 0; }; /// NumberExprAST - Expression class for numeric literals like "1.0". class NumberExprAST : public ExprAST { double Val; public: NumberExprAST(double Val) : Val(Val) {} Value *codegen() override; }; /// VariableExprAST - Expression class for referencing a variable, like "a". class VariableExprAST : public ExprAST { std::string Name; public: VariableExprAST(const std::string &Name) : Name(Name) {} Value *codegen() override; }; /// BinaryExprAST - Expression class for a binary operator. class BinaryExprAST : public ExprAST { char Op; std::unique_ptr LHS, RHS; public: BinaryExprAST(char Op, std::unique_ptr LHS, std::unique_ptr 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> Args; public: CallExprAST(const std::string &Callee, std::vector> Args) : Callee(Callee), Args(std::move(Args)) {} Value *codegen() override; }; /// IfExprAST - Expression class for if/then/else. class IfExprAST : public ExprAST { std::unique_ptr Cond, Then, Else; public: IfExprAST(std::unique_ptr Cond, std::unique_ptr Then, std::unique_ptr 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 Start, End, Step, Body; public: ForExprAST(const std::string &VarName, std::unique_ptr Start, std::unique_ptr End, std::unique_ptr Step, std::unique_ptr 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). class PrototypeAST { std::string Name; std::vector Args; public: PrototypeAST(const std::string &Name, std::vector Args) : Name(Name), Args(std::move(Args)) {} Function *codegen(); const std::string &getName() const { return Name; } }; /// FunctionAST - This class represents a function definition itself. class FunctionAST { std::unique_ptr Proto; std::unique_ptr Body; public: FunctionAST(std::unique_ptr Proto, std::unique_ptr 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 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 LogError(const char *Str) { fprintf(stderr, "Error: %s\n", Str); return nullptr; } std::unique_ptr LogErrorP(const char *Str) { LogError(Str); return nullptr; } static std::unique_ptr ParseExpression(); /// numberexpr ::= number static std::unique_ptr ParseNumberExpr() { auto Result = llvm::make_unique(NumVal); getNextToken(); // consume the number return std::move(Result); } /// parenexpr ::= '(' expression ')' static std::unique_ptr 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 ParseIdentifierExpr() { std::string IdName = IdentifierStr; getNextToken(); // eat identifier. if (CurTok != '(') // Simple variable ref. return llvm::make_unique(IdName); // Call. getNextToken(); // eat ( std::vector> 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 llvm::make_unique(IdName, std::move(Args)); } /// ifexpr ::= 'if' expression 'then' expression 'else' expression static std::unique_ptr 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 llvm::make_unique(std::move(Cond), std::move(Then), std::move(Else)); } /// forexpr ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression static std::unique_ptr 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 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 llvm::make_unique(IdName, std::move(Start), std::move(End), std::move(Step), std::move(Body)); } /// primary /// ::= identifierexpr /// ::= numberexpr /// ::= parenexpr /// ::= ifexpr /// ::= forexpr static std::unique_ptr 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(); } } /// binoprhs /// ::= ('+' primary)* static std::unique_ptr ParseBinOpRHS(int ExprPrec, std::unique_ptr LHS) { // If this is a binop, find its precedence. while (true) { int TokPrec = GetTokPrecedence(); // If this is a binop that binds at least as tightly as the current binop, // consume it, otherwise we are done. if (TokPrec < ExprPrec) return LHS; // Okay, we know this is a binop. int BinOp = CurTok; getNextToken(); // eat binop // Parse the primary expression after the binary operator. auto RHS = ParsePrimary(); if (!RHS) return nullptr; // If BinOp binds less tightly with RHS than the operator after RHS, let // the pending operator take RHS as its LHS. int NextPrec = GetTokPrecedence(); if (TokPrec < NextPrec) { RHS = ParseBinOpRHS(TokPrec + 1, std::move(RHS)); if (!RHS) return nullptr; } // Merge LHS/RHS. LHS = llvm::make_unique(BinOp, std::move(LHS), std::move(RHS)); } } /// expression /// ::= primary binoprhs /// static std::unique_ptr ParseExpression() { auto LHS = ParsePrimary(); if (!LHS) return nullptr; return ParseBinOpRHS(0, std::move(LHS)); } /// prototype /// ::= id '(' id* ')' static std::unique_ptr ParsePrototype() { if (CurTok != tok_identifier) return LogErrorP("Expected function name in prototype"); std::string FnName = IdentifierStr; getNextToken(); if (CurTok != '(') return LogErrorP("Expected '(' in prototype"); std::vector ArgNames; while (getNextToken() == tok_identifier) ArgNames.push_back(IdentifierStr); if (CurTok != ')') return LogErrorP("Expected ')' in prototype"); // success. getNextToken(); // eat ')'. return llvm::make_unique(FnName, std::move(ArgNames)); } /// definition ::= 'def' prototype expression static std::unique_ptr ParseDefinition() { getNextToken(); // eat def. auto Proto = ParsePrototype(); if (!Proto) return nullptr; if (auto E = ParseExpression()) return llvm::make_unique(std::move(Proto), std::move(E)); return nullptr; } /// toplevelexpr ::= expression static std::unique_ptr ParseTopLevelExpr() { if (auto E = ParseExpression()) { // Make an anonymous proto. auto Proto = llvm::make_unique("__anon_expr", std::vector()); return llvm::make_unique(std::move(Proto), std::move(E)); } return nullptr; } /// external ::= 'extern' prototype static std::unique_ptr ParseExtern() { getNextToken(); // eat extern. return ParsePrototype(); } //===----------------------------------------------------------------------===// // Code Generation //===----------------------------------------------------------------------===// static LLVMContext TheContext; static IRBuilder<> Builder(TheContext); static std::unique_ptr TheModule; static std::map NamedValues; static std::unique_ptr TheFPM; static std::unique_ptr TheJIT; static std::map> FunctionProtos; 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; } Value *NumberExprAST::codegen() { return ConstantFP::get(TheContext, APFloat(Val)); } Value *VariableExprAST::codegen() { // Look this variable up in the function. Value *V = NamedValues[Name]; if (!V) return LogErrorV("Unknown variable name"); return V; } Value *BinaryExprAST::codegen() { Value *L = LHS->codegen(); Value *R = RHS->codegen(); if (!L || !R) return nullptr; switch (Op) { case '+': return Builder.CreateFAdd(L, R, "addtmp"); case '-': return Builder.CreateFSub(L, R, "subtmp"); case '*': return Builder.CreateFMul(L, R, "multmp"); case '<': L = Builder.CreateFCmpULT(L, R, "cmptmp"); // Convert bool 0/1 to double 0.0 or 1.0 return Builder.CreateUIToFP(L, Type::getDoubleTy(TheContext), "booltmp"); default: return LogErrorV("invalid binary operator"); } } Value *CallExprAST::codegen() { // Look up the name in the global module table. Function *CalleeF = 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 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(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->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(TheContext), 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(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); // Start the PHI node with an entry for Start. PHINode *Variable = Builder.CreatePHI(Type::getDoubleTy(TheContext), 2, VarName); 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(TheContext, 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(TheContext, APFloat(0.0)), "loopcond"); // Create the "after loop" block and insert it. BasicBlock *LoopEndBB = Builder.GetInsertBlock(); 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); // 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(TheContext)); } Function *PrototypeAST::codegen() { // Make the function type: double(double,double) etc. std::vector 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; // Create a new basic block to start insertion into. BasicBlock *BB = BasicBlock::Create(TheContext, "entry", TheFunction); Builder.SetInsertPoint(BB); // Record the function arguments in the NamedValues map. NamedValues.clear(); for (auto &Arg : TheFunction->args()) NamedValues[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(); return nullptr; } //===----------------------------------------------------------------------===// // Top-Level parsing and JIT Driver //===----------------------------------------------------------------------===// static void InitializeModuleAndPassManager() { // Open a new module. TheModule = llvm::make_unique("my cool jit", TheContext); TheModule->setDataLayout(TheJIT->getTargetMachine().createDataLayout()); // Create a new pass manager attached to it. TheFPM = llvm::make_unique(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 (true) { fprintf(stderr, "ready> "); switch (CurTok) { case tok_eof: return; case ';': // ignore top-level semicolons. getNextToken(); break; case tok_def: HandleDefinition(); break; case tok_extern: HandleExtern(); break; default: HandleTopLevelExpression(); break; } } } //===----------------------------------------------------------------------===// // "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(); InitializeModuleAndPassManager(); // Run the main "interpreter loop" now. MainLoop(); return 0; }