diff options
author | rdivacky <rdivacky@FreeBSD.org> | 2009-10-14 17:57:32 +0000 |
---|---|---|
committer | rdivacky <rdivacky@FreeBSD.org> | 2009-10-14 17:57:32 +0000 |
commit | cd749a9c07f1de2fb8affde90537efa4bc3e7c54 (patch) | |
tree | b21f6de4e08b89bb7931806bab798fc2a5e3a686 /examples | |
parent | 72621d11de5b873f1695f391eb95f0b336c3d2d4 (diff) | |
download | FreeBSD-src-cd749a9c07f1de2fb8affde90537efa4bc3e7c54.zip FreeBSD-src-cd749a9c07f1de2fb8affde90537efa4bc3e7c54.tar.gz |
Update llvm to r84119.
Diffstat (limited to 'examples')
28 files changed, 4784 insertions, 120 deletions
diff --git a/examples/BrainF/BrainF.cpp b/examples/BrainF/BrainF.cpp index d3261d7..5cf2b88 100644 --- a/examples/BrainF/BrainF.cpp +++ b/examples/BrainF/BrainF.cpp @@ -43,7 +43,7 @@ Module *BrainF::parse(std::istream *in1, int mem, CompileFlags cf, comflag = cf; header(Context); - readloop(0, 0, 0); + readloop(0, 0, 0, Context); delete builder; return module; } @@ -54,39 +54,39 @@ void BrainF::header(LLVMContext& C) { //Function prototypes //declare void @llvm.memset.i32(i8 *, i8, i32, i32) - const Type *Tys[] = { Type::Int32Ty }; + const Type *Tys[] = { Type::getInt32Ty(C) }; Function *memset_func = Intrinsic::getDeclaration(module, Intrinsic::memset, Tys, 1); //declare i32 @getchar() getchar_func = cast<Function>(module-> - getOrInsertFunction("getchar", IntegerType::Int32Ty, NULL)); + getOrInsertFunction("getchar", IntegerType::getInt32Ty(C), NULL)); //declare i32 @putchar(i32) putchar_func = cast<Function>(module-> - getOrInsertFunction("putchar", IntegerType::Int32Ty, - IntegerType::Int32Ty, NULL)); + getOrInsertFunction("putchar", IntegerType::getInt32Ty(C), + IntegerType::getInt32Ty(C), NULL)); //Function header //define void @brainf() brainf_func = cast<Function>(module-> - getOrInsertFunction("brainf", Type::VoidTy, NULL)); + getOrInsertFunction("brainf", Type::getVoidTy(C), NULL)); - builder = new IRBuilder<>(BasicBlock::Create(label, brainf_func)); + builder = new IRBuilder<>(BasicBlock::Create(C, label, brainf_func)); //%arr = malloc i8, i32 %d - ConstantInt *val_mem = ConstantInt::get(APInt(32, memtotal)); - ptr_arr = builder->CreateMalloc(IntegerType::Int8Ty, val_mem, "arr"); + ConstantInt *val_mem = ConstantInt::get(C, APInt(32, memtotal)); + ptr_arr = builder->CreateMalloc(IntegerType::getInt8Ty(C), val_mem, "arr"); //call void @llvm.memset.i32(i8 *%arr, i8 0, i32 %d, i32 1) { Value *memset_params[] = { ptr_arr, - ConstantInt::get(APInt(8, 0)), + ConstantInt::get(C, APInt(8, 0)), val_mem, - ConstantInt::get(APInt(32, 1)) + ConstantInt::get(C, APInt(32, 1)) }; CallInst *memset_call = builder-> @@ -97,12 +97,12 @@ void BrainF::header(LLVMContext& C) { //%arrmax = getelementptr i8 *%arr, i32 %d if (comflag & flag_arraybounds) { ptr_arrmax = builder-> - CreateGEP(ptr_arr, ConstantInt::get(APInt(32, memtotal)), "arrmax"); + CreateGEP(ptr_arr, ConstantInt::get(C, APInt(32, memtotal)), "arrmax"); } //%head.%d = getelementptr i8 *%arr, i32 %d curhead = builder->CreateGEP(ptr_arr, - ConstantInt::get(APInt(32, memtotal/2)), + ConstantInt::get(C, APInt(32, memtotal/2)), headreg); @@ -110,13 +110,13 @@ void BrainF::header(LLVMContext& C) { //Function footer //brainf.end: - endbb = BasicBlock::Create(label, brainf_func); + endbb = BasicBlock::Create(C, label, brainf_func); //free i8 *%arr new FreeInst(ptr_arr, endbb); //ret void - ReturnInst::Create(endbb); + ReturnInst::Create(C, endbb); @@ -124,28 +124,28 @@ void BrainF::header(LLVMContext& C) { if (comflag & flag_arraybounds) { //@aberrormsg = internal constant [%d x i8] c"\00" - Constant *msg_0 = ConstantArray:: - get("Error: The head has left the tape.", true); + Constant *msg_0 = + ConstantArray::get(C, "Error: The head has left the tape.", true); GlobalVariable *aberrormsg = new GlobalVariable( + *module, msg_0->getType(), true, GlobalValue::InternalLinkage, msg_0, - "aberrormsg", - module); + "aberrormsg"); //declare i32 @puts(i8 *) Function *puts_func = cast<Function>(module-> - getOrInsertFunction("puts", IntegerType::Int32Ty, - PointerType::getUnqual(IntegerType::Int8Ty), NULL)); + getOrInsertFunction("puts", IntegerType::getInt32Ty(C), + PointerType::getUnqual(IntegerType::getInt8Ty(C)), NULL)); //brainf.aberror: - aberrorbb = BasicBlock::Create(label, brainf_func); + aberrorbb = BasicBlock::Create(C, label, brainf_func); //call i32 @puts(i8 *getelementptr([%d x i8] *@aberrormsg, i32 0, i32 0)) { - Constant *zero_32 = Constant::getNullValue(IntegerType::Int32Ty); + Constant *zero_32 = Constant::getNullValue(IntegerType::getInt32Ty(C)); Constant *gep_params[] = { zero_32, @@ -172,7 +172,8 @@ void BrainF::header(LLVMContext& C) { } } -void BrainF::readloop(PHINode *phi, BasicBlock *oldbb, BasicBlock *testbb) { +void BrainF::readloop(PHINode *phi, BasicBlock *oldbb, BasicBlock *testbb, + LLVMContext &C) { Symbol cursym = SYM_NONE; int curvalue = 0; Symbol nextsym = SYM_NONE; @@ -197,7 +198,7 @@ void BrainF::readloop(PHINode *phi, BasicBlock *oldbb, BasicBlock *testbb) { //%tape.%d = trunc i32 %tape.%d to i8 Value *tape_1 = builder-> - CreateTrunc(tape_0, IntegerType::Int8Ty, tapereg); + CreateTrunc(tape_0, IntegerType::getInt8Ty(C), tapereg); //store i8 %tape.%d, i8 *%head.%d builder->CreateStore(tape_1, curhead); @@ -211,7 +212,7 @@ void BrainF::readloop(PHINode *phi, BasicBlock *oldbb, BasicBlock *testbb) { //%tape.%d = sext i8 %tape.%d to i32 Value *tape_1 = builder-> - CreateSExt(tape_0, IntegerType::Int32Ty, tapereg); + CreateSExt(tape_0, IntegerType::getInt32Ty(C), tapereg); //call i32 @putchar(i32 %tape.%d) Value *putchar_params[] = { @@ -228,7 +229,7 @@ void BrainF::readloop(PHINode *phi, BasicBlock *oldbb, BasicBlock *testbb) { { //%head.%d = getelementptr i8 *%head.%d, i32 %d curhead = builder-> - CreateGEP(curhead, ConstantInt::get(APInt(32, curvalue)), + CreateGEP(curhead, ConstantInt::get(C, APInt(32, curvalue)), headreg); //Error block for array out of bounds @@ -247,7 +248,7 @@ void BrainF::readloop(PHINode *phi, BasicBlock *oldbb, BasicBlock *testbb) { CreateOr(test_0, test_1, testreg); //br i1 %test.%d, label %main.%d, label %main.%d - BasicBlock *nextbb = BasicBlock::Create(label, brainf_func); + BasicBlock *nextbb = BasicBlock::Create(C, label, brainf_func); builder->CreateCondBr(test_2, aberrorbb, nextbb); //main.%d: @@ -263,7 +264,7 @@ void BrainF::readloop(PHINode *phi, BasicBlock *oldbb, BasicBlock *testbb) { //%tape.%d = add i8 %tape.%d, %d Value *tape_1 = builder-> - CreateAdd(tape_0, ConstantInt::get(APInt(8, curvalue)), tapereg); + CreateAdd(tape_0, ConstantInt::get(C, APInt(8, curvalue)), tapereg); //store i8 %tape.%d, i8 *%head.%d\n" builder->CreateStore(tape_1, curhead); @@ -273,23 +274,23 @@ void BrainF::readloop(PHINode *phi, BasicBlock *oldbb, BasicBlock *testbb) { case SYM_LOOP: { //br label %main.%d - BasicBlock *testbb = BasicBlock::Create(label, brainf_func); + BasicBlock *testbb = BasicBlock::Create(C, label, brainf_func); builder->CreateBr(testbb); //main.%d: BasicBlock *bb_0 = builder->GetInsertBlock(); - BasicBlock *bb_1 = BasicBlock::Create(label, brainf_func); + BasicBlock *bb_1 = BasicBlock::Create(C, label, brainf_func); builder->SetInsertPoint(bb_1); // Make part of PHI instruction now, wait until end of loop to finish PHINode *phi_0 = - PHINode::Create(PointerType::getUnqual(IntegerType::Int8Ty), + PHINode::Create(PointerType::getUnqual(IntegerType::getInt8Ty(C)), headreg, testbb); phi_0->reserveOperandSpace(2); phi_0->addIncoming(curhead, bb_0); curhead = phi_0; - readloop(phi_0, bb_1, testbb); + readloop(phi_0, bb_1, testbb, C); } break; @@ -427,12 +428,11 @@ void BrainF::readloop(PHINode *phi, BasicBlock *oldbb, BasicBlock *testbb) { LoadInst *tape_0 = new LoadInst(head_0, tapereg, testbb); //%test.%d = icmp eq i8 %tape.%d, 0 - ICmpInst *test_0 = new ICmpInst(ICmpInst::ICMP_EQ, tape_0, - ConstantInt::get(APInt(8, 0)), testreg, - testbb); + ICmpInst *test_0 = new ICmpInst(*testbb, ICmpInst::ICMP_EQ, tape_0, + ConstantInt::get(C, APInt(8, 0)), testreg); //br i1 %test.%d, label %main.%d, label %main.%d - BasicBlock *bb_0 = BasicBlock::Create(label, brainf_func); + BasicBlock *bb_0 = BasicBlock::Create(C, label, brainf_func); BranchInst::Create(bb_0, oldbb, test_0, testbb); //main.%d: @@ -440,7 +440,7 @@ void BrainF::readloop(PHINode *phi, BasicBlock *oldbb, BasicBlock *testbb) { //%head.%d = phi i8 *[%head.%d, %main.%d] PHINode *phi_1 = builder-> - CreatePHI(PointerType::getUnqual(IntegerType::Int8Ty), headreg); + CreatePHI(PointerType::getUnqual(IntegerType::getInt8Ty(C)), headreg); phi_1->reserveOperandSpace(1); phi_1->addIncoming(head_0, testbb); curhead = phi_1; diff --git a/examples/BrainF/BrainF.h b/examples/BrainF/BrainF.h index 053ddaa..add0687 100644 --- a/examples/BrainF/BrainF.h +++ b/examples/BrainF/BrainF.h @@ -70,7 +70,8 @@ class BrainF { /// The main loop for parsing. It calls itself recursively /// to handle the depth of nesting of "[]". - void readloop(PHINode *phi, BasicBlock *oldbb, BasicBlock *testbb); + void readloop(PHINode *phi, BasicBlock *oldbb, + BasicBlock *testbb, LLVMContext &Context); /// Constants during parsing int memtotal; diff --git a/examples/BrainF/BrainFDriver.cpp b/examples/BrainF/BrainFDriver.cpp index 4eaa494..6f4ba69 100644 --- a/examples/BrainF/BrainFDriver.cpp +++ b/examples/BrainF/BrainFDriver.cpp @@ -32,11 +32,12 @@ #include "llvm/Bitcode/ReaderWriter.h" #include "llvm/ExecutionEngine/GenericValue.h" #include "llvm/ExecutionEngine/JIT.h" +#include "llvm/Target/TargetSelect.h" #include "llvm/Support/CommandLine.h" #include "llvm/Support/ManagedStatic.h" -#include "llvm/Target/TargetSelect.h" -#include <fstream> +#include "llvm/Support/raw_ostream.h" #include <iostream> +#include <fstream> using namespace llvm; //Command line options @@ -58,9 +59,10 @@ JIT("jit", cl::desc("Run program Just-In-Time")); void addMainFunction(Module *mod) { //define i32 @main(i32 %argc, i8 **%argv) Function *main_func = cast<Function>(mod-> - getOrInsertFunction("main", IntegerType::Int32Ty, IntegerType::Int32Ty, + getOrInsertFunction("main", IntegerType::getInt32Ty(mod->getContext()), + IntegerType::getInt32Ty(mod->getContext()), PointerType::getUnqual(PointerType::getUnqual( - IntegerType::Int8Ty)), NULL)); + IntegerType::getInt8Ty(mod->getContext()))), NULL)); { Function::arg_iterator args = main_func->arg_begin(); Value *arg_0 = args++; @@ -70,7 +72,7 @@ void addMainFunction(Module *mod) { } //main.0: - BasicBlock *bb = BasicBlock::Create("main.0", main_func); + BasicBlock *bb = BasicBlock::Create(mod->getContext(), "main.0", main_func); //call void @brainf() { @@ -80,59 +82,58 @@ void addMainFunction(Module *mod) { } //ret i32 0 - ReturnInst::Create(ConstantInt::get(APInt(32, 0)), bb); + ReturnInst::Create(mod->getContext(), + ConstantInt::get(mod->getContext(), APInt(32, 0)), bb); } int main(int argc, char **argv) { cl::ParseCommandLineOptions(argc, argv, " BrainF compiler\n"); - LLVMContext Context; + LLVMContext &Context = getGlobalContext(); if (InputFilename == "") { - std::cerr<<"Error: You must specify the filename of the program to " + errs() << "Error: You must specify the filename of the program to " "be compiled. Use --help to see the options.\n"; abort(); } //Get the output stream - std::ostream *out = &std::cout; + raw_ostream *out = &outs(); if (!JIT) { if (OutputFilename == "") { std::string base = InputFilename; - if (InputFilename == "-") {base = "a";} + if (InputFilename == "-") { base = "a"; } - //Use default filename - const char *suffix = ".bc"; - OutputFilename = base+suffix; + // Use default filename. + OutputFilename = base+".bc"; } if (OutputFilename != "-") { - out = new std:: - ofstream(OutputFilename.c_str(), - std::ios::out | std::ios::trunc | std::ios::binary); + std::string ErrInfo; + out = new raw_fd_ostream(OutputFilename.c_str(), ErrInfo, + raw_fd_ostream::F_Binary); } } //Get the input stream std::istream *in = &std::cin; - if (InputFilename != "-") { + if (InputFilename != "-") in = new std::ifstream(InputFilename.c_str()); - } //Gather the compile flags BrainF::CompileFlags cf = BrainF::flag_off; - if (ArrayBoundsChecking) { + if (ArrayBoundsChecking) cf = BrainF::CompileFlags(cf | BrainF::flag_arraybounds); - } //Read the BrainF program BrainF bf; Module *mod = bf.parse(in, 65536, cf, Context); //64 KiB - if (in != &std::cin) {delete in;} + if (in != &std::cin) + delete in; addMainFunction(mod); //Verify generated code if (verifyModule(*mod)) { - std::cerr<<"Error: module failed verification. This shouldn't happen.\n"; + errs() << "Error: module failed verification. This shouldn't happen.\n"; abort(); } @@ -140,9 +141,8 @@ int main(int argc, char **argv) { if (JIT) { InitializeNativeTarget(); - std::cout << "------- Running JIT -------\n"; - ExistingModuleProvider *mp = new ExistingModuleProvider(mod); - ExecutionEngine *ee = ExecutionEngine::create(mp, false); + outs() << "------- Running JIT -------\n"; + ExecutionEngine *ee = EngineBuilder(mod).create(); std::vector<GenericValue> args; Function *brainf_func = mod->getFunction("brainf"); GenericValue gv = ee->runFunction(brainf_func, args); @@ -151,7 +151,8 @@ int main(int argc, char **argv) { } //Clean up - if (out != &std::cout) {delete out;} + if (out != &outs()) + delete out; delete mod; llvm_shutdown(); diff --git a/examples/Fibonacci/fibonacci.cpp b/examples/Fibonacci/fibonacci.cpp index c3431fc..b1a4691 100644 --- a/examples/Fibonacci/fibonacci.cpp +++ b/examples/Fibonacci/fibonacci.cpp @@ -36,35 +36,36 @@ #include "llvm/Support/raw_ostream.h" using namespace llvm; -static Function *CreateFibFunction(Module *M) { +static Function *CreateFibFunction(Module *M, LLVMContext &Context) { // Create the fib function and insert it into module M. This function is said // to return an int and take an int parameter. Function *FibF = - cast<Function>(M->getOrInsertFunction("fib", Type::Int32Ty, Type::Int32Ty, + cast<Function>(M->getOrInsertFunction("fib", Type::getInt32Ty(Context), + Type::getInt32Ty(Context), (Type *)0)); // Add a basic block to the function. - BasicBlock *BB = BasicBlock::Create("EntryBlock", FibF); + BasicBlock *BB = BasicBlock::Create(Context, "EntryBlock", FibF); // Get pointers to the constants. - Value *One = ConstantInt::get(Type::Int32Ty, 1); - Value *Two = ConstantInt::get(Type::Int32Ty, 2); + Value *One = ConstantInt::get(Type::getInt32Ty(Context), 1); + Value *Two = ConstantInt::get(Type::getInt32Ty(Context), 2); // Get pointer to the integer argument of the add1 function... Argument *ArgX = FibF->arg_begin(); // Get the arg. ArgX->setName("AnArg"); // Give it a nice symbolic name for fun. // Create the true_block. - BasicBlock *RetBB = BasicBlock::Create("return", FibF); + BasicBlock *RetBB = BasicBlock::Create(Context, "return", FibF); // Create an exit block. - BasicBlock* RecurseBB = BasicBlock::Create("recurse", FibF); + BasicBlock* RecurseBB = BasicBlock::Create(Context, "recurse", FibF); // Create the "if (arg <= 2) goto exitbb" - Value *CondInst = new ICmpInst(ICmpInst::ICMP_SLE, ArgX, Two, "cond", BB); + Value *CondInst = new ICmpInst(*BB, ICmpInst::ICMP_SLE, ArgX, Two, "cond"); BranchInst::Create(RetBB, RecurseBB, CondInst, BB); // Create: ret int 1 - ReturnInst::Create(One, RetBB); + ReturnInst::Create(Context, One, RetBB); // create fib(x-1) Value *Sub = BinaryOperator::CreateSub(ArgX, One, "arg", RecurseBB); @@ -82,7 +83,7 @@ static Function *CreateFibFunction(Module *M) { "addresult", RecurseBB); // Create the return instruction and add it to the basic block - ReturnInst::Create(Sum, RecurseBB); + ReturnInst::Create(Context, Sum, RecurseBB); return FibF; } @@ -97,11 +98,10 @@ int main(int argc, char **argv) { Module *M = new Module("test", Context); // We are about to create the "fib" function: - Function *FibF = CreateFibFunction(M); + Function *FibF = CreateFibFunction(M, Context); // Now we going to create JIT - ExistingModuleProvider *MP = new ExistingModuleProvider(M); - ExecutionEngine *EE = ExecutionEngine::create(MP, false); + ExecutionEngine *EE = EngineBuilder(M).create(); errs() << "verifying... "; if (verifyModule(*M)) { diff --git a/examples/HowToUseJIT/HowToUseJIT.cpp b/examples/HowToUseJIT/HowToUseJIT.cpp index 6734547..ec9c2e6 100644 --- a/examples/HowToUseJIT/HowToUseJIT.cpp +++ b/examples/HowToUseJIT/HowToUseJIT.cpp @@ -61,15 +61,16 @@ int main() { // function will have a return type of "int" and take an argument of "int". // The '0' terminates the list of argument types. Function *Add1F = - cast<Function>(M->getOrInsertFunction("add1", Type::Int32Ty, Type::Int32Ty, + cast<Function>(M->getOrInsertFunction("add1", Type::getInt32Ty(Context), + Type::getInt32Ty(Context), (Type *)0)); // Add a basic block to the function. As before, it automatically inserts // because of the last argument. - BasicBlock *BB = BasicBlock::Create("EntryBlock", Add1F); + BasicBlock *BB = BasicBlock::Create(Context, "EntryBlock", Add1F); // Get pointers to the constant `1'. - Value *One = ConstantInt::get(Type::Int32Ty, 1); + Value *One = ConstantInt::get(Type::getInt32Ty(Context), 1); // Get pointers to the integer argument of the add1 function... assert(Add1F->arg_begin() != Add1F->arg_end()); // Make sure there's an arg @@ -80,7 +81,7 @@ int main() { Instruction *Add = BinaryOperator::CreateAdd(One, ArgX, "addresult", BB); // Create the return instruction and add it to the basic block - ReturnInst::Create(Add, BB); + ReturnInst::Create(Context, Add, BB); // Now, function add1 is ready. @@ -88,24 +89,24 @@ int main() { // Now we going to create function `foo', which returns an int and takes no // arguments. Function *FooF = - cast<Function>(M->getOrInsertFunction("foo", Type::Int32Ty, (Type *)0)); + cast<Function>(M->getOrInsertFunction("foo", Type::getInt32Ty(Context), + (Type *)0)); // Add a basic block to the FooF function. - BB = BasicBlock::Create("EntryBlock", FooF); + BB = BasicBlock::Create(Context, "EntryBlock", FooF); // Get pointers to the constant `10'. - Value *Ten = ConstantInt::get(Type::Int32Ty, 10); + Value *Ten = ConstantInt::get(Type::getInt32Ty(Context), 10); // Pass Ten to the call call: CallInst *Add1CallRes = CallInst::Create(Add1F, Ten, "add1", BB); Add1CallRes->setTailCall(true); // Create the return instruction and add it to the basic block. - ReturnInst::Create(Add1CallRes, BB); + ReturnInst::Create(Context, Add1CallRes, BB); // Now we create the JIT. - ExistingModuleProvider* MP = new ExistingModuleProvider(M); - ExecutionEngine* EE = ExecutionEngine::create(MP, false); + ExecutionEngine* EE = EngineBuilder(M).create(); outs() << "We just constructed this LLVM module:\n\n" << *M; outs() << "\n\nRunning foo: "; diff --git a/examples/Kaleidoscope/CMakeLists.txt b/examples/Kaleidoscope/CMakeLists.txt index 9a18aae..8c87ac5 100644 --- a/examples/Kaleidoscope/CMakeLists.txt +++ b/examples/Kaleidoscope/CMakeLists.txt @@ -1,5 +1,6 @@ -set(LLVM_LINK_COMPONENTS core jit native) - -add_llvm_example(Kaleidoscope - toy.cpp - ) +add_subdirectory(Chapter2) +add_subdirectory(Chapter3) +add_subdirectory(Chapter4) +add_subdirectory(Chapter5) +add_subdirectory(Chapter6) +add_subdirectory(Chapter7) diff --git a/examples/Kaleidoscope/Chapter2/CMakeLists.txt b/examples/Kaleidoscope/Chapter2/CMakeLists.txt new file mode 100644 index 0000000..79f2b17 --- /dev/null +++ b/examples/Kaleidoscope/Chapter2/CMakeLists.txt @@ -0,0 +1,3 @@ +add_llvm_example(Kaleidoscope-Ch2 + toy.cpp + ) diff --git a/examples/Kaleidoscope/Chapter2/Makefile b/examples/Kaleidoscope/Chapter2/Makefile new file mode 100644 index 0000000..1a9b94c --- /dev/null +++ b/examples/Kaleidoscope/Chapter2/Makefile @@ -0,0 +1,13 @@ +##===- examples/Kaleidoscope/Chapter2/Makefile -------------*- Makefile -*-===## +# +# The LLVM Compiler Infrastructure +# +# This file is distributed under the University of Illinois Open Source +# License. See LICENSE.TXT for details. +# +##===----------------------------------------------------------------------===## +LEVEL = ../../.. +TOOLNAME = Kaleidoscope-Ch2 +EXAMPLE_TOOL = 1 + +include $(LEVEL)/Makefile.common diff --git a/examples/Kaleidoscope/Chapter2/toy.cpp b/examples/Kaleidoscope/Chapter2/toy.cpp new file mode 100644 index 0000000..f4f09d0 --- /dev/null +++ b/examples/Kaleidoscope/Chapter2/toy.cpp @@ -0,0 +1,398 @@ +#include <cstdio> +#include <cstdlib> +#include <string> +#include <map> +#include <vector> + +//===----------------------------------------------------------------------===// +// 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() {} +}; + +/// NumberExprAST - Expression class for numeric literals like "1.0". +class NumberExprAST : public ExprAST { + double Val; +public: + NumberExprAST(double val) : Val(val) {} +}; + +/// VariableExprAST - Expression class for referencing a variable, like "a". +class VariableExprAST : public ExprAST { + std::string Name; +public: + VariableExprAST(const std::string &name) : Name(name) {} +}; + +/// 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) {} +}; + +/// 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) {} +}; + +/// PrototypeAST - This class represents the "prototype" for a function, +/// which captures its name, and its argument names (thus implicitly the number +/// of arguments the function takes). +class PrototypeAST { + std::string Name; + std::vector<std::string> Args; +public: + PrototypeAST(const std::string &name, const std::vector<std::string> &args) + : Name(name), Args(args) {} + +}; + +/// FunctionAST - This class represents a function definition itself. +class FunctionAST { + PrototypeAST *Proto; + ExprAST *Body; +public: + FunctionAST(PrototypeAST *proto, ExprAST *body) + : Proto(proto), Body(body) {} + +}; + +//===----------------------------------------------------------------------===// +// 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. +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 +/// ::= identifier +/// ::= identifier '(' expression* ')' +static ExprAST *ParseIdentifierExpr() { + std::string IdName = IdentifierStr; + + getNextToken(); // eat identifier. + + if (CurTok != '(') // Simple variable ref. + return new VariableExprAST(IdName); + + // Call. + getNextToken(); // eat ( + std::vector<ExprAST*> Args; + if (CurTok != ')') { + while (1) { + ExprAST *Arg = ParseExpression(); + if (!Arg) return 0; + Args.push_back(Arg); + + if (CurTok == ')') break; + + if (CurTok != ',') + return Error("Expected ')' or ',' in argument list"); + 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(); +} + +//===----------------------------------------------------------------------===// +// Top-Level parsing +//===----------------------------------------------------------------------===// + +static void HandleDefinition() { + if (ParseDefinition()) { + fprintf(stderr, "Parsed a function definition.\n"); + } else { + // Skip token for error recovery. + getNextToken(); + } +} + +static void HandleExtern() { + if (ParseExtern()) { + fprintf(stderr, "Parsed an extern\n"); + } else { + // Skip token for error recovery. + getNextToken(); + } +} + +static void HandleTopLevelExpression() { + // Evaluate a top-level expression into an anonymous function. + if (ParseTopLevelExpr()) { + fprintf(stderr, "Parsed a top-level expr\n"); + } 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; + } + } +} + +//===----------------------------------------------------------------------===// +// Main driver code. +//===----------------------------------------------------------------------===// + +int main() { + // Install standard binary operators. + // 1 is lowest precedence. + BinopPrecedence['<'] = 10; + BinopPrecedence['+'] = 20; + BinopPrecedence['-'] = 20; + BinopPrecedence['*'] = 40; // highest. + + // Prime the first token. + fprintf(stderr, "ready> "); + getNextToken(); + + // Run the main "interpreter loop" now. + MainLoop(); + + return 0; +} diff --git a/examples/Kaleidoscope/Chapter3/CMakeLists.txt b/examples/Kaleidoscope/Chapter3/CMakeLists.txt new file mode 100644 index 0000000..1af8db0 --- /dev/null +++ b/examples/Kaleidoscope/Chapter3/CMakeLists.txt @@ -0,0 +1,5 @@ +set(LLVM_LINK_COMPONENTS core) + +add_llvm_example(Kaleidoscope-Ch3 + toy.cpp + ) diff --git a/examples/Kaleidoscope/Chapter3/Makefile b/examples/Kaleidoscope/Chapter3/Makefile new file mode 100644 index 0000000..4cc6948 --- /dev/null +++ b/examples/Kaleidoscope/Chapter3/Makefile @@ -0,0 +1,15 @@ +##===- examples/Kaleidoscope/Chapter3/Makefile -------------*- Makefile -*-===## +# +# The LLVM Compiler Infrastructure +# +# This file is distributed under the University of Illinois Open Source +# License. See LICENSE.TXT for details. +# +##===----------------------------------------------------------------------===## +LEVEL = ../../.. +TOOLNAME = Kaleidoscope-Ch3 +EXAMPLE_TOOL = 1 + +LINK_COMPONENTS := core + +include $(LEVEL)/Makefile.common diff --git a/examples/Kaleidoscope/Chapter3/toy.cpp b/examples/Kaleidoscope/Chapter3/toy.cpp new file mode 100644 index 0000000..73520d8 --- /dev/null +++ b/examples/Kaleidoscope/Chapter3/toy.cpp @@ -0,0 +1,563 @@ +#include "llvm/DerivedTypes.h" +#include "llvm/LLVMContext.h" +#include "llvm/Module.h" +#include "llvm/Analysis/Verifier.h" +#include "llvm/Support/IRBuilder.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 name, and its argument names (thus implicitly the number +/// of arguments the function takes). +class PrototypeAST { + std::string Name; + std::vector<std::string> Args; +public: + PrototypeAST(const std::string &name, 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 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. +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 +/// ::= identifier +/// ::= identifier '(' expression* ')' +static ExprAST *ParseIdentifierExpr() { + std::string IdName = IdentifierStr; + + getNextToken(); // eat identifier. + + if (CurTok != '(') // Simple variable ref. + return new VariableExprAST(IdName); + + // Call. + getNextToken(); // eat ( + std::vector<ExprAST*> Args; + if (CurTok != ')') { + while (1) { + ExprAST *Arg = ParseExpression(); + if (!Arg) return 0; + Args.push_back(Arg); + + if (CurTok == ')') break; + + if (CurTok != ',') + return Error("Expected ')' or ',' in argument list"); + 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 IRBuilder<> Builder(getGlobalContext()); +static std::map<std::string, Value*> NamedValues; + +Value *ErrorV(const char *Str) { Error(Str); return 0; } + +Value *NumberExprAST::Codegen() { + return ConstantFP::get(getGlobalContext(), 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, "cmptmp"); + // Convert bool 0/1 to double 0.0 or 1.0 + return Builder.CreateUIToFP(L, Type::getDoubleTy(getGlobalContext()), + "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. + std::vector<const 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); + + // 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. + BasicBlock *BB = BasicBlock::Create(getGlobalContext(), "entry", TheFunction); + Builder.SetInsertPoint(BB); + + if (Value *RetVal = Body->Codegen()) { + // Finish off the function. + Builder.CreateRet(RetVal); + + // Validate the generated code, checking for consistency. + verifyFunction(*TheFunction); + + return TheFunction; + } + + // Error reading body, remove function. + TheFunction->eraseFromParent(); + return 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() { + LLVMContext &Context = getGlobalContext(); + + // Install standard binary operators. + // 1 is lowest precedence. + BinopPrecedence['<'] = 10; + BinopPrecedence['+'] = 20; + BinopPrecedence['-'] = 20; + BinopPrecedence['*'] = 40; // highest. + + // Prime the first token. + fprintf(stderr, "ready> "); + getNextToken(); + + // Make the module, which holds all the code. + TheModule = new Module("my cool jit", Context); + + // Run the main "interpreter loop" now. + MainLoop(); + + // Print out all of the generated code. + TheModule->dump(); + + return 0; +} diff --git a/examples/Kaleidoscope/Chapter4/CMakeLists.txt b/examples/Kaleidoscope/Chapter4/CMakeLists.txt new file mode 100644 index 0000000..0d1ac53 --- /dev/null +++ b/examples/Kaleidoscope/Chapter4/CMakeLists.txt @@ -0,0 +1,5 @@ +set(LLVM_LINK_COMPONENTS core jit interpreter native) + +add_llvm_example(Kaleidoscope-Ch4 + toy.cpp + ) diff --git a/examples/Kaleidoscope/Chapter4/Makefile b/examples/Kaleidoscope/Chapter4/Makefile new file mode 100644 index 0000000..7bc742f --- /dev/null +++ b/examples/Kaleidoscope/Chapter4/Makefile @@ -0,0 +1,15 @@ +##===- examples/Kaleidoscope/Chapter4/Makefile -------------*- Makefile -*-===## +# +# The LLVM Compiler Infrastructure +# +# This file is distributed under the University of Illinois Open Source +# License. See LICENSE.TXT for details. +# +##===----------------------------------------------------------------------===## +LEVEL = ../../.. +TOOLNAME = Kaleidoscope-Ch4 +EXAMPLE_TOOL = 1 + +LINK_COMPONENTS := core jit interpreter native + +include $(LEVEL)/Makefile.common diff --git a/examples/Kaleidoscope/Chapter4/toy.cpp b/examples/Kaleidoscope/Chapter4/toy.cpp new file mode 100644 index 0000000..d136635 --- /dev/null +++ b/examples/Kaleidoscope/Chapter4/toy.cpp @@ -0,0 +1,610 @@ +#include "llvm/DerivedTypes.h" +#include "llvm/ExecutionEngine/ExecutionEngine.h" +#include "llvm/ExecutionEngine/Interpreter.h" +#include "llvm/ExecutionEngine/JIT.h" +#include "llvm/LLVMContext.h" +#include "llvm/Module.h" +#include "llvm/ModuleProvider.h" +#include "llvm/PassManager.h" +#include "llvm/Analysis/Verifier.h" +#include "llvm/Target/TargetData.h" +#include "llvm/Target/TargetSelect.h" +#include "llvm/Transforms/Scalar.h" +#include "llvm/Support/IRBuilder.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 name, and its argument names (thus implicitly the number +/// of arguments the function takes). +class PrototypeAST { + std::string Name; + std::vector<std::string> Args; +public: + PrototypeAST(const std::string &name, 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 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. +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 +/// ::= identifier +/// ::= identifier '(' expression* ')' +static ExprAST *ParseIdentifierExpr() { + std::string IdName = IdentifierStr; + + getNextToken(); // eat identifier. + + if (CurTok != '(') // Simple variable ref. + return new VariableExprAST(IdName); + + // Call. + getNextToken(); // eat ( + std::vector<ExprAST*> Args; + if (CurTok != ')') { + while (1) { + ExprAST *Arg = ParseExpression(); + if (!Arg) return 0; + Args.push_back(Arg); + + if (CurTok == ')') break; + + if (CurTok != ',') + return Error("Expected ')' or ',' in argument list"); + 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 IRBuilder<> Builder(getGlobalContext()); +static std::map<std::string, Value*> NamedValues; +static FunctionPassManager *TheFPM; + +Value *ErrorV(const char *Str) { Error(Str); return 0; } + +Value *NumberExprAST::Codegen() { + return ConstantFP::get(getGlobalContext(), 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, "cmptmp"); + // Convert bool 0/1 to double 0.0 or 1.0 + return Builder.CreateUIToFP(L, Type::getDoubleTy(getGlobalContext()), + "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. + std::vector<const 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); + + // 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. + BasicBlock *BB = BasicBlock::Create(getGlobalContext(), "entry", TheFunction); + Builder.SetInsertPoint(BB); + + if (Value *RetVal = Body->Codegen()) { + // Finish off the function. + Builder.CreateRet(RetVal); + + // Validate the generated code, checking for consistency. + verifyFunction(*TheFunction); + + // Optimize the function. + TheFPM->run(*TheFunction); + + return TheFunction; + } + + // Error reading body, remove function. + TheFunction->eraseFromParent(); + return 0; +} + +//===----------------------------------------------------------------------===// +// Top-Level parsing and JIT Driver +//===----------------------------------------------------------------------===// + +static ExecutionEngine *TheExecutionEngine; + +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()) { + // JIT the function, returning a function pointer. + void *FPtr = TheExecutionEngine->getPointerToFunction(LF); + + // 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)FPtr; + fprintf(stderr, "Evaluated to %f\n", FP()); + } + } 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() { + InitializeNativeTarget(); + LLVMContext &Context = getGlobalContext(); + + // Install standard binary operators. + // 1 is lowest precedence. + BinopPrecedence['<'] = 10; + BinopPrecedence['+'] = 20; + BinopPrecedence['-'] = 20; + BinopPrecedence['*'] = 40; // highest. + + // Prime the first token. + fprintf(stderr, "ready> "); + getNextToken(); + + // Make the module, which holds all the code. + TheModule = new Module("my cool jit", Context); + + ExistingModuleProvider *OurModuleProvider = + new ExistingModuleProvider(TheModule); + + // Create the JIT. This takes ownership of the module and module provider. + TheExecutionEngine = EngineBuilder(OurModuleProvider).create(); + + FunctionPassManager OurFPM(OurModuleProvider); + + // Set up the optimizer pipeline. Start with registering info about how the + // target lays out data structures. + OurFPM.add(new TargetData(*TheExecutionEngine->getTargetData())); + // Do simple "peephole" optimizations and bit-twiddling optzns. + OurFPM.add(createInstructionCombiningPass()); + // Reassociate expressions. + OurFPM.add(createReassociatePass()); + // Eliminate Common SubExpressions. + OurFPM.add(createGVNPass()); + // Simplify the control flow graph (deleting unreachable blocks, etc). + OurFPM.add(createCFGSimplificationPass()); + + OurFPM.doInitialization(); + + // Set the global so the code gen can use this. + TheFPM = &OurFPM; + + // Run the main "interpreter loop" now. + MainLoop(); + + TheFPM = 0; + + // Print out all of the generated code. + TheModule->dump(); + + return 0; +} diff --git a/examples/Kaleidoscope/Chapter5/CMakeLists.txt b/examples/Kaleidoscope/Chapter5/CMakeLists.txt new file mode 100644 index 0000000..2d75ad3 --- /dev/null +++ b/examples/Kaleidoscope/Chapter5/CMakeLists.txt @@ -0,0 +1,5 @@ +set(LLVM_LINK_COMPONENTS core jit interpreter native) + +add_llvm_example(Kaleidoscope-Ch5 + toy.cpp + ) diff --git a/examples/Kaleidoscope/Chapter5/Makefile b/examples/Kaleidoscope/Chapter5/Makefile new file mode 100644 index 0000000..5a8355d --- /dev/null +++ b/examples/Kaleidoscope/Chapter5/Makefile @@ -0,0 +1,15 @@ +##===- examples/Kaleidoscope/Chapter5/Makefile -------------*- Makefile -*-===## +# +# The LLVM Compiler Infrastructure +# +# This file is distributed under the University of Illinois Open Source +# License. See LICENSE.TXT for details. +# +##===----------------------------------------------------------------------===## +LEVEL = ../../.. +TOOLNAME = Kaleidoscope-Ch5 +EXAMPLE_TOOL = 1 + +LINK_COMPONENTS := core jit interpreter native + +include $(LEVEL)/Makefile.common diff --git a/examples/Kaleidoscope/Chapter5/toy.cpp b/examples/Kaleidoscope/Chapter5/toy.cpp new file mode 100644 index 0000000..c2613e3 --- /dev/null +++ b/examples/Kaleidoscope/Chapter5/toy.cpp @@ -0,0 +1,855 @@ +#include "llvm/DerivedTypes.h" +#include "llvm/ExecutionEngine/ExecutionEngine.h" +#include "llvm/ExecutionEngine/Interpreter.h" +#include "llvm/ExecutionEngine/JIT.h" +#include "llvm/LLVMContext.h" +#include "llvm/Module.h" +#include "llvm/ModuleProvider.h" +#include "llvm/PassManager.h" +#include "llvm/Analysis/Verifier.h" +#include "llvm/Target/TargetData.h" +#include "llvm/Target/TargetSelect.h" +#include "llvm/Transforms/Scalar.h" +#include "llvm/Support/IRBuilder.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, + + // 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(), 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(); +}; + +/// IfExprAST - Expression class for if/then/else. +class IfExprAST : public ExprAST { + ExprAST *Cond, *Then, *Else; +public: + IfExprAST(ExprAST *cond, ExprAST *then, ExprAST *_else) + : Cond(cond), Then(then), Else(_else) {} + virtual Value *Codegen(); +}; + +/// ForExprAST - Expression class for for/in. +class ForExprAST : public ExprAST { + std::string VarName; + ExprAST *Start, *End, *Step, *Body; +public: + ForExprAST(const std::string &varname, ExprAST *start, ExprAST *end, + ExprAST *step, ExprAST *body) + : VarName(varname), Start(start), End(end), Step(step), Body(body) {} + 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). +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 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. +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 +/// ::= identifier +/// ::= identifier '(' expression* ')' +static ExprAST *ParseIdentifierExpr() { + std::string IdName = IdentifierStr; + + getNextToken(); // eat identifier. + + if (CurTok != '(') // Simple variable ref. + return new VariableExprAST(IdName); + + // Call. + getNextToken(); // eat ( + std::vector<ExprAST*> Args; + if (CurTok != ')') { + while (1) { + ExprAST *Arg = ParseExpression(); + if (!Arg) return 0; + Args.push_back(Arg); + + if (CurTok == ')') break; + + if (CurTok != ',') + return Error("Expected ')' or ',' in argument list"); + 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; +} + +/// ifexpr ::= 'if' expression 'then' expression 'else' expression +static ExprAST *ParseIfExpr() { + getNextToken(); // eat the if. + + // condition. + ExprAST *Cond = ParseExpression(); + if (!Cond) return 0; + + if (CurTok != tok_then) + return Error("expected then"); + getNextToken(); // eat the then + + ExprAST *Then = ParseExpression(); + if (Then == 0) return 0; + + if (CurTok != tok_else) + return Error("expected else"); + + getNextToken(); + + ExprAST *Else = ParseExpression(); + if (!Else) return 0; + + return new IfExprAST(Cond, Then, Else); +} + +/// forexpr ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression +static 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 '='. + + + ExprAST *Start = ParseExpression(); + if (Start == 0) return 0; + if (CurTok != ',') + return Error("expected ',' after for start value"); + getNextToken(); + + ExprAST *End = ParseExpression(); + if (End == 0) return 0; + + // The step value is optional. + ExprAST *Step = 0; + if (CurTok == ',') { + getNextToken(); + Step = ParseExpression(); + if (Step == 0) return 0; + } + + if (CurTok != tok_in) + return Error("expected 'in' after for"); + getNextToken(); // eat 'in'. + + ExprAST *Body = ParseExpression(); + if (Body == 0) return 0; + + return new ForExprAST(IdName, Start, End, Step, Body); +} + +/// primary +/// ::= identifierexpr +/// ::= numberexpr +/// ::= parenexpr +/// ::= ifexpr +/// ::= forexpr +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(); + case tok_if: return ParseIfExpr(); + case tok_for: return ParseForExpr(); + } +} + +/// 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 IRBuilder<> Builder(getGlobalContext()); +static std::map<std::string, Value*> NamedValues; +static FunctionPassManager *TheFPM; + +Value *ErrorV(const char *Str) { Error(Str); return 0; } + +Value *NumberExprAST::Codegen() { + return ConstantFP::get(getGlobalContext(), 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, "cmptmp"); + // Convert bool 0/1 to double 0.0 or 1.0 + return Builder.CreateUIToFP(L, Type::getDoubleTy(getGlobalContext()), + "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"); +} + +Value *IfExprAST::Codegen() { + Value *CondV = Cond->Codegen(); + if (CondV == 0) return 0; + + // 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 == 0) return 0; + + 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 == 0) return 0; + + 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()), + "iftmp"); + + PN->addIncoming(ThenV, ThenBB); + PN->addIncoming(ElseV, ElseBB); + return PN; +} + +Value *ForExprAST::Codegen() { + // Output this 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: + + // Emit the start code first, without 'variable' in scope. + Value *StartVal = Start->Codegen(); + if (StartVal == 0) return 0; + + // 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()), 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() == 0) + return 0; + + // Emit the step value. + Value *StepVal; + if (Step) { + StepVal = Step->Codegen(); + if (StepVal == 0) return 0; + } else { + // If not specified, use 1.0. + StepVal = ConstantFP::get(getGlobalContext(), APFloat(1.0)); + } + + Value *NextVar = Builder.CreateAdd(Variable, StepVal, "nextvar"); + + // Compute the end condition. + Value *EndCond = End->Codegen(); + if (EndCond == 0) return EndCond; + + // 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<const 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); + + // 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. + BasicBlock *BB = BasicBlock::Create(getGlobalContext(), "entry", TheFunction); + Builder.SetInsertPoint(BB); + + if (Value *RetVal = Body->Codegen()) { + // Finish off the function. + Builder.CreateRet(RetVal); + + // Validate the generated code, checking for consistency. + verifyFunction(*TheFunction); + + // Optimize the function. + TheFPM->run(*TheFunction); + + return TheFunction; + } + + // Error reading body, remove function. + TheFunction->eraseFromParent(); + return 0; +} + +//===----------------------------------------------------------------------===// +// Top-Level parsing and JIT Driver +//===----------------------------------------------------------------------===// + +static ExecutionEngine *TheExecutionEngine; + +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()) { + // JIT the function, returning a function pointer. + void *FPtr = TheExecutionEngine->getPointerToFunction(LF); + + // 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)FPtr; + fprintf(stderr, "Evaluated to %f\n", FP()); + } + } 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() { + InitializeNativeTarget(); + LLVMContext &Context = getGlobalContext(); + + // Install standard binary operators. + // 1 is lowest precedence. + BinopPrecedence['<'] = 10; + BinopPrecedence['+'] = 20; + BinopPrecedence['-'] = 20; + BinopPrecedence['*'] = 40; // highest. + + // Prime the first token. + fprintf(stderr, "ready> "); + getNextToken(); + + // Make the module, which holds all the code. + TheModule = new Module("my cool jit", Context); + + ExistingModuleProvider *OurModuleProvider = + new ExistingModuleProvider(TheModule); + + // Create the JIT. This takes ownership of the module and module provider. + TheExecutionEngine = EngineBuilder(OurModuleProvider).create(); + + FunctionPassManager OurFPM(OurModuleProvider); + + // Set up the optimizer pipeline. Start with registering info about how the + // target lays out data structures. + OurFPM.add(new TargetData(*TheExecutionEngine->getTargetData())); + // Do simple "peephole" optimizations and bit-twiddling optzns. + OurFPM.add(createInstructionCombiningPass()); + // Reassociate expressions. + OurFPM.add(createReassociatePass()); + // Eliminate Common SubExpressions. + OurFPM.add(createGVNPass()); + // Simplify the control flow graph (deleting unreachable blocks, etc). + OurFPM.add(createCFGSimplificationPass()); + + OurFPM.doInitialization(); + + // Set the global so the code gen can use this. + TheFPM = &OurFPM; + + // Run the main "interpreter loop" now. + MainLoop(); + + TheFPM = 0; + + // Print out all of the generated code. + TheModule->dump(); + + return 0; +} diff --git a/examples/Kaleidoscope/Chapter6/CMakeLists.txt b/examples/Kaleidoscope/Chapter6/CMakeLists.txt new file mode 100644 index 0000000..2e15a5f --- /dev/null +++ b/examples/Kaleidoscope/Chapter6/CMakeLists.txt @@ -0,0 +1,5 @@ +set(LLVM_LINK_COMPONENTS core jit interpreter native) + +add_llvm_example(Kaleidoscope-Ch6 + toy.cpp + ) diff --git a/examples/Kaleidoscope/Chapter6/Makefile b/examples/Kaleidoscope/Chapter6/Makefile new file mode 100644 index 0000000..de2d758 --- /dev/null +++ b/examples/Kaleidoscope/Chapter6/Makefile @@ -0,0 +1,15 @@ +##===- examples/Kaleidoscope/Chapter6/Makefile -------------*- Makefile -*-===## +# +# The LLVM Compiler Infrastructure +# +# This file is distributed under the University of Illinois Open Source +# License. See LICENSE.TXT for details. +# +##===----------------------------------------------------------------------===## +LEVEL = ../../.. +TOOLNAME = Kaleidoscope-Ch6 +EXAMPLE_TOOL = 1 + +LINK_COMPONENTS := core jit interpreter native + +include $(LEVEL)/Makefile.common diff --git a/examples/Kaleidoscope/Chapter6/toy.cpp b/examples/Kaleidoscope/Chapter6/toy.cpp new file mode 100644 index 0000000..638a340 --- /dev/null +++ b/examples/Kaleidoscope/Chapter6/toy.cpp @@ -0,0 +1,973 @@ +#include "llvm/DerivedTypes.h" +#include "llvm/ExecutionEngine/ExecutionEngine.h" +#include "llvm/ExecutionEngine/Interpreter.h" +#include "llvm/ExecutionEngine/JIT.h" +#include "llvm/LLVMContext.h" +#include "llvm/Module.h" +#include "llvm/ModuleProvider.h" +#include "llvm/PassManager.h" +#include "llvm/Analysis/Verifier.h" +#include "llvm/Target/TargetData.h" +#include "llvm/Target/TargetSelect.h" +#include "llvm/Transforms/Scalar.h" +#include "llvm/Support/IRBuilder.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, + + // 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(), 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(); +}; + +/// UnaryExprAST - Expression class for a unary operator. +class UnaryExprAST : public ExprAST { + char Opcode; + ExprAST *Operand; +public: + UnaryExprAST(char opcode, ExprAST *operand) + : Opcode(opcode), Operand(operand) {} + 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(); +}; + +/// IfExprAST - Expression class for if/then/else. +class IfExprAST : public ExprAST { + ExprAST *Cond, *Then, *Else; +public: + IfExprAST(ExprAST *cond, ExprAST *then, ExprAST *_else) + : Cond(cond), Then(then), Else(_else) {} + virtual Value *Codegen(); +}; + +/// ForExprAST - Expression class for for/in. +class ForExprAST : public ExprAST { + std::string VarName; + ExprAST *Start, *End, *Step, *Body; +public: + ForExprAST(const std::string &varname, ExprAST *start, ExprAST *end, + ExprAST *step, ExprAST *body) + : VarName(varname), Start(start), End(end), Step(step), Body(body) {} + 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), 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, const std::vector<std::string> &args, + bool isoperator = false, unsigned prec = 0) + : Name(name), Args(args), isOperator(isoperator), Precedence(prec) {} + + 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; } + + 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 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. +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 +/// ::= identifier +/// ::= identifier '(' expression* ')' +static ExprAST *ParseIdentifierExpr() { + std::string IdName = IdentifierStr; + + getNextToken(); // eat identifier. + + if (CurTok != '(') // Simple variable ref. + return new VariableExprAST(IdName); + + // Call. + getNextToken(); // eat ( + std::vector<ExprAST*> Args; + if (CurTok != ')') { + while (1) { + ExprAST *Arg = ParseExpression(); + if (!Arg) return 0; + Args.push_back(Arg); + + if (CurTok == ')') break; + + if (CurTok != ',') + return Error("Expected ')' or ',' in argument list"); + 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; +} + +/// ifexpr ::= 'if' expression 'then' expression 'else' expression +static ExprAST *ParseIfExpr() { + getNextToken(); // eat the if. + + // condition. + ExprAST *Cond = ParseExpression(); + if (!Cond) return 0; + + if (CurTok != tok_then) + return Error("expected then"); + getNextToken(); // eat the then + + ExprAST *Then = ParseExpression(); + if (Then == 0) return 0; + + if (CurTok != tok_else) + return Error("expected else"); + + getNextToken(); + + ExprAST *Else = ParseExpression(); + if (!Else) return 0; + + return new IfExprAST(Cond, Then, Else); +} + +/// forexpr ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression +static 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 '='. + + + ExprAST *Start = ParseExpression(); + if (Start == 0) return 0; + if (CurTok != ',') + return Error("expected ',' after for start value"); + getNextToken(); + + ExprAST *End = ParseExpression(); + if (End == 0) return 0; + + // The step value is optional. + ExprAST *Step = 0; + if (CurTok == ',') { + getNextToken(); + Step = ParseExpression(); + if (Step == 0) return 0; + } + + if (CurTok != tok_in) + return Error("expected 'in' after for"); + getNextToken(); // eat 'in'. + + ExprAST *Body = ParseExpression(); + if (Body == 0) return 0; + + return new ForExprAST(IdName, Start, End, Step, Body); +} + +/// primary +/// ::= identifierexpr +/// ::= numberexpr +/// ::= parenexpr +/// ::= ifexpr +/// ::= forexpr +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(); + case tok_if: return ParseIfExpr(); + case tok_for: return ParseForExpr(); + } +} + +/// unary +/// ::= primary +/// ::= '!' unary +static 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 (ExprAST *Operand = ParseUnary()) + return new UnaryExprAST(Opc, Operand); + return 0; +} + +/// binoprhs +/// ::= ('+' unary)* +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 unary expression after the binary operator. + ExprAST *RHS = ParseUnary(); + 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 +/// ::= unary binoprhs +/// +static ExprAST *ParseExpression() { + ExprAST *LHS = ParseUnary(); + if (!LHS) return 0; + + return ParseBinOpRHS(0, LHS); +} + +/// prototype +/// ::= id '(' id* ')' +/// ::= binary LETTER number? (id, id) +/// ::= unary LETTER (id) +static 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 new PrototypeAST(FnName, ArgNames, Kind != 0, BinaryPrecedence); +} + +/// 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 IRBuilder<> Builder(getGlobalContext()); +static std::map<std::string, Value*> NamedValues; +static FunctionPassManager *TheFPM; + +Value *ErrorV(const char *Str) { Error(Str); return 0; } + +Value *NumberExprAST::Codegen() { + return ConstantFP::get(getGlobalContext(), APFloat(Val)); +} + +Value *VariableExprAST::Codegen() { + // Look this variable up in the function. + Value *V = NamedValues[Name]; + return V ? V : ErrorV("Unknown variable name"); +} + +Value *UnaryExprAST::Codegen() { + Value *OperandV = Operand->Codegen(); + if (OperandV == 0) return 0; + + Function *F = TheModule->getFunction(std::string("unary")+Opcode); + if (F == 0) + return ErrorV("Unknown unary operator"); + + return Builder.CreateCall(F, OperandV, "unop"); +} + +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, "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 = TheModule->getFunction(std::string("binary")+Op); + assert(F && "binary operator not found!"); + + Value *Ops[] = { L, R }; + return Builder.CreateCall(F, Ops, Ops+2, "binop"); +} + +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"); +} + +Value *IfExprAST::Codegen() { + Value *CondV = Cond->Codegen(); + if (CondV == 0) return 0; + + // 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 == 0) return 0; + + 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 == 0) return 0; + + 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()), + "iftmp"); + + PN->addIncoming(ThenV, ThenBB); + PN->addIncoming(ElseV, ElseBB); + return PN; +} + +Value *ForExprAST::Codegen() { + // Output this 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: + + // Emit the start code first, without 'variable' in scope. + Value *StartVal = Start->Codegen(); + if (StartVal == 0) return 0; + + // 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()), 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() == 0) + return 0; + + // Emit the step value. + Value *StepVal; + if (Step) { + StepVal = Step->Codegen(); + if (StepVal == 0) return 0; + } else { + // If not specified, use 1.0. + StepVal = ConstantFP::get(getGlobalContext(), APFloat(1.0)); + } + + Value *NextVar = Builder.CreateAdd(Variable, StepVal, "nextvar"); + + // Compute the end condition. + Value *EndCond = End->Codegen(); + if (EndCond == 0) return EndCond; + + // 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<const 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); + + // 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; + + // If this is an operator, install it. + if (Proto->isBinaryOp()) + BinopPrecedence[Proto->getOperatorName()] = Proto->getBinaryPrecedence(); + + // Create a new basic block to start insertion into. + BasicBlock *BB = BasicBlock::Create(getGlobalContext(), "entry", TheFunction); + Builder.SetInsertPoint(BB); + + if (Value *RetVal = Body->Codegen()) { + // Finish off the function. + Builder.CreateRet(RetVal); + + // Validate the generated code, checking for consistency. + verifyFunction(*TheFunction); + + // Optimize the function. + TheFPM->run(*TheFunction); + + return TheFunction; + } + + // Error reading body, remove function. + TheFunction->eraseFromParent(); + + if (Proto->isBinaryOp()) + BinopPrecedence.erase(Proto->getOperatorName()); + return 0; +} + +//===----------------------------------------------------------------------===// +// Top-Level parsing and JIT Driver +//===----------------------------------------------------------------------===// + +static ExecutionEngine *TheExecutionEngine; + +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()) { + // JIT the function, returning a function pointer. + void *FPtr = TheExecutionEngine->getPointerToFunction(LF); + + // 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)FPtr; + fprintf(stderr, "Evaluated to %f\n", FP()); + } + } 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; +} + +/// printd - printf that takes a double prints it as "%f\n", returning 0. +extern "C" +double printd(double X) { + printf("%f\n", X); + return 0; +} + +//===----------------------------------------------------------------------===// +// Main driver code. +//===----------------------------------------------------------------------===// + +int main() { + InitializeNativeTarget(); + LLVMContext &Context = getGlobalContext(); + + // Install standard binary operators. + // 1 is lowest precedence. + BinopPrecedence['<'] = 10; + BinopPrecedence['+'] = 20; + BinopPrecedence['-'] = 20; + BinopPrecedence['*'] = 40; // highest. + + // Prime the first token. + fprintf(stderr, "ready> "); + getNextToken(); + + // Make the module, which holds all the code. + TheModule = new Module("my cool jit", Context); + + ExistingModuleProvider *OurModuleProvider = + new ExistingModuleProvider(TheModule); + + // Create the JIT. This takes ownership of the module and module provider. + TheExecutionEngine = EngineBuilder(OurModuleProvider).create(); + + FunctionPassManager OurFPM(OurModuleProvider); + + // Set up the optimizer pipeline. Start with registering info about how the + // target lays out data structures. + OurFPM.add(new TargetData(*TheExecutionEngine->getTargetData())); + // Do simple "peephole" optimizations and bit-twiddling optzns. + OurFPM.add(createInstructionCombiningPass()); + // Reassociate expressions. + OurFPM.add(createReassociatePass()); + // Eliminate Common SubExpressions. + OurFPM.add(createGVNPass()); + // Simplify the control flow graph (deleting unreachable blocks, etc). + OurFPM.add(createCFGSimplificationPass()); + + OurFPM.doInitialization(); + + // Set the global so the code gen can use this. + TheFPM = &OurFPM; + + // Run the main "interpreter loop" now. + MainLoop(); + + TheFPM = 0; + + // Print out all of the generated code. + TheModule->dump(); + + return 0; +} diff --git a/examples/Kaleidoscope/Chapter7/CMakeLists.txt b/examples/Kaleidoscope/Chapter7/CMakeLists.txt new file mode 100644 index 0000000..9b8227c --- /dev/null +++ b/examples/Kaleidoscope/Chapter7/CMakeLists.txt @@ -0,0 +1,5 @@ +set(LLVM_LINK_COMPONENTS core jit interpreter native) + +add_llvm_example(Kaleidoscope-Ch7 + toy.cpp + ) diff --git a/examples/Kaleidoscope/Chapter7/Makefile b/examples/Kaleidoscope/Chapter7/Makefile new file mode 100644 index 0000000..9d2df6f --- /dev/null +++ b/examples/Kaleidoscope/Chapter7/Makefile @@ -0,0 +1,15 @@ +##===- examples/Kaleidoscope/Chapter7/Makefile -------------*- Makefile -*-===## +# +# The LLVM Compiler Infrastructure +# +# This file is distributed under the University of Illinois Open Source +# License. See LICENSE.TXT for details. +# +##===----------------------------------------------------------------------===## +LEVEL = ../../.. +TOOLNAME = Kaleidoscope-Ch7 +EXAMPLE_TOOL = 1 + +LINK_COMPONENTS := core jit interpreter native + +include $(LEVEL)/Makefile.common diff --git a/examples/Kaleidoscope/Chapter7/toy.cpp b/examples/Kaleidoscope/Chapter7/toy.cpp new file mode 100644 index 0000000..8b0c321 --- /dev/null +++ b/examples/Kaleidoscope/Chapter7/toy.cpp @@ -0,0 +1,1139 @@ +#include "llvm/DerivedTypes.h" +#include "llvm/ExecutionEngine/ExecutionEngine.h" +#include "llvm/ExecutionEngine/Interpreter.h" +#include "llvm/ExecutionEngine/JIT.h" +#include "llvm/LLVMContext.h" +#include "llvm/Module.h" +#include "llvm/ModuleProvider.h" +#include "llvm/PassManager.h" +#include "llvm/Analysis/Verifier.h" +#include "llvm/Target/TargetData.h" +#include "llvm/Target/TargetSelect.h" +#include "llvm/Transforms/Scalar.h" +#include "llvm/Support/IRBuilder.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, + + // control + tok_if = -6, tok_then = -7, tok_else = -8, + tok_for = -9, tok_in = -10, + + // operators + tok_binary = -11, tok_unary = -12, + + // var definition + tok_var = -13 +}; + +static std::string IdentifierStr; // Filled in if tok_identifier +static double NumVal; // Filled in if tok_number + +/// gettok - Return the next token from standard input. +static int gettok() { + static int LastChar = ' '; + + // Skip any whitespace. + while (isspace(LastChar)) + LastChar = getchar(); + + if (isalpha(LastChar)) { // identifier: [a-zA-Z][a-zA-Z0-9]* + IdentifierStr = LastChar; + while (isalnum((LastChar = getchar()))) + IdentifierStr += LastChar; + + if (IdentifierStr == "def") return tok_def; + if (IdentifierStr == "extern") return tok_extern; + if (IdentifierStr == "if") return tok_if; + if (IdentifierStr == "then") return tok_then; + if (IdentifierStr == "else") return tok_else; + if (IdentifierStr == "for") return tok_for; + if (IdentifierStr == "in") return tok_in; + if (IdentifierStr == "binary") return tok_binary; + if (IdentifierStr == "unary") return tok_unary; + if (IdentifierStr == "var") return tok_var; + return tok_identifier; + } + + if (isdigit(LastChar) || LastChar == '.') { // Number: [0-9.]+ + std::string NumStr; + do { + NumStr += LastChar; + LastChar = getchar(); + } while (isdigit(LastChar) || LastChar == '.'); + + NumVal = strtod(NumStr.c_str(), 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) {} + const std::string &getName() const { return Name; } + virtual Value *Codegen(); +}; + +/// UnaryExprAST - Expression class for a unary operator. +class UnaryExprAST : public ExprAST { + char Opcode; + ExprAST *Operand; +public: + UnaryExprAST(char opcode, ExprAST *operand) + : Opcode(opcode), Operand(operand) {} + 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(); +}; + +/// IfExprAST - Expression class for if/then/else. +class IfExprAST : public ExprAST { + ExprAST *Cond, *Then, *Else; +public: + IfExprAST(ExprAST *cond, ExprAST *then, ExprAST *_else) + : Cond(cond), Then(then), Else(_else) {} + virtual Value *Codegen(); +}; + +/// ForExprAST - Expression class for for/in. +class ForExprAST : public ExprAST { + std::string VarName; + ExprAST *Start, *End, *Step, *Body; +public: + ForExprAST(const std::string &varname, ExprAST *start, ExprAST *end, + ExprAST *step, ExprAST *body) + : VarName(varname), Start(start), End(end), Step(step), Body(body) {} + virtual Value *Codegen(); +}; + +/// VarExprAST - Expression class for var/in +class VarExprAST : public ExprAST { + std::vector<std::pair<std::string, ExprAST*> > VarNames; + ExprAST *Body; +public: + VarExprAST(const std::vector<std::pair<std::string, ExprAST*> > &varnames, + ExprAST *body) + : VarNames(varnames), Body(body) {} + + 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; + bool isOperator; + unsigned Precedence; // Precedence if a binary op. +public: + PrototypeAST(const std::string &name, const std::vector<std::string> &args, + bool isoperator = false, unsigned prec = 0) + : Name(name), Args(args), isOperator(isoperator), Precedence(prec) {} + + 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; } + + Function *Codegen(); + + void CreateArgumentAllocas(Function *F); +}; + +/// 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 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. +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 +/// ::= identifier +/// ::= identifier '(' expression* ')' +static ExprAST *ParseIdentifierExpr() { + std::string IdName = IdentifierStr; + + getNextToken(); // eat identifier. + + if (CurTok != '(') // Simple variable ref. + return new VariableExprAST(IdName); + + // Call. + getNextToken(); // eat ( + std::vector<ExprAST*> Args; + if (CurTok != ')') { + while (1) { + ExprAST *Arg = ParseExpression(); + if (!Arg) return 0; + Args.push_back(Arg); + + if (CurTok == ')') break; + + if (CurTok != ',') + return Error("Expected ')' or ',' in argument list"); + 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; +} + +/// ifexpr ::= 'if' expression 'then' expression 'else' expression +static ExprAST *ParseIfExpr() { + getNextToken(); // eat the if. + + // condition. + ExprAST *Cond = ParseExpression(); + if (!Cond) return 0; + + if (CurTok != tok_then) + return Error("expected then"); + getNextToken(); // eat the then + + ExprAST *Then = ParseExpression(); + if (Then == 0) return 0; + + if (CurTok != tok_else) + return Error("expected else"); + + getNextToken(); + + ExprAST *Else = ParseExpression(); + if (!Else) return 0; + + return new IfExprAST(Cond, Then, Else); +} + +/// forexpr ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression +static 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 '='. + + + ExprAST *Start = ParseExpression(); + if (Start == 0) return 0; + if (CurTok != ',') + return Error("expected ',' after for start value"); + getNextToken(); + + ExprAST *End = ParseExpression(); + if (End == 0) return 0; + + // The step value is optional. + ExprAST *Step = 0; + if (CurTok == ',') { + getNextToken(); + Step = ParseExpression(); + if (Step == 0) return 0; + } + + if (CurTok != tok_in) + return Error("expected 'in' after for"); + getNextToken(); // eat 'in'. + + ExprAST *Body = ParseExpression(); + if (Body == 0) return 0; + + return new ForExprAST(IdName, Start, End, Step, Body); +} + +/// varexpr ::= 'var' identifier ('=' expression)? +// (',' identifier ('=' expression)?)* 'in' expression +static ExprAST *ParseVarExpr() { + getNextToken(); // eat the var. + + std::vector<std::pair<std::string, ExprAST*> > VarNames; + + // At least one variable name is required. + if (CurTok != tok_identifier) + return Error("expected identifier after var"); + + while (1) { + std::string Name = IdentifierStr; + getNextToken(); // eat identifier. + + // Read the optional initializer. + ExprAST *Init = 0; + if (CurTok == '=') { + getNextToken(); // eat the '='. + + Init = ParseExpression(); + if (Init == 0) return 0; + } + + VarNames.push_back(std::make_pair(Name, Init)); + + // End of var list, exit loop. + if (CurTok != ',') break; + getNextToken(); // eat the ','. + + if (CurTok != tok_identifier) + return Error("expected identifier list after var"); + } + + // At this point, we have to have 'in'. + if (CurTok != tok_in) + return Error("expected 'in' keyword after 'var'"); + getNextToken(); // eat 'in'. + + ExprAST *Body = ParseExpression(); + if (Body == 0) return 0; + + return new VarExprAST(VarNames, Body); +} + +/// primary +/// ::= identifierexpr +/// ::= numberexpr +/// ::= parenexpr +/// ::= ifexpr +/// ::= forexpr +/// ::= varexpr +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(); + case tok_if: return ParseIfExpr(); + case tok_for: return ParseForExpr(); + case tok_var: return ParseVarExpr(); + } +} + +/// unary +/// ::= primary +/// ::= '!' unary +static 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 (ExprAST *Operand = ParseUnary()) + return new UnaryExprAST(Opc, Operand); + return 0; +} + +/// binoprhs +/// ::= ('+' unary)* +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 unary expression after the binary operator. + ExprAST *RHS = ParseUnary(); + 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 +/// ::= unary binoprhs +/// +static ExprAST *ParseExpression() { + ExprAST *LHS = ParseUnary(); + if (!LHS) return 0; + + return ParseBinOpRHS(0, LHS); +} + +/// prototype +/// ::= id '(' id* ')' +/// ::= binary LETTER number? (id, id) +/// ::= unary LETTER (id) +static 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 new PrototypeAST(FnName, ArgNames, Kind != 0, BinaryPrecedence); +} + +/// 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 IRBuilder<> Builder(getGlobalContext()); +static std::map<std::string, AllocaInst*> NamedValues; +static FunctionPassManager *TheFPM; + +Value *ErrorV(const char *Str) { Error(Str); return 0; } + +/// CreateEntryBlockAlloca - Create an alloca instruction in the entry block of +/// the function. This is used for mutable variables etc. +static AllocaInst *CreateEntryBlockAlloca(Function *TheFunction, + const std::string &VarName) { + IRBuilder<> TmpB(&TheFunction->getEntryBlock(), + TheFunction->getEntryBlock().begin()); + return TmpB.CreateAlloca(Type::getDoubleTy(getGlobalContext()), 0, + VarName.c_str()); +} + +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 == 0) return ErrorV("Unknown variable name"); + + // Load the value. + return Builder.CreateLoad(V, Name.c_str()); +} + +Value *UnaryExprAST::Codegen() { + Value *OperandV = Operand->Codegen(); + if (OperandV == 0) return 0; + + Function *F = TheModule->getFunction(std::string("unary")+Opcode); + if (F == 0) + return ErrorV("Unknown unary operator"); + + return Builder.CreateCall(F, OperandV, "unop"); +} + +Value *BinaryExprAST::Codegen() { + // Special case '=' because we don't want to emit the LHS as an expression. + if (Op == '=') { + // Assignment requires the LHS to be an identifier. + VariableExprAST *LHSE = dynamic_cast<VariableExprAST*>(LHS); + if (!LHSE) + return ErrorV("destination of '=' must be a variable"); + // Codegen the RHS. + Value *Val = RHS->Codegen(); + if (Val == 0) return 0; + + // Look up the name. + Value *Variable = NamedValues[LHSE->getName()]; + if (Variable == 0) return ErrorV("Unknown variable name"); + + Builder.CreateStore(Val, Variable); + return Val; + } + + 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, "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 = TheModule->getFunction(std::string("binary")+Op); + assert(F && "binary operator not found!"); + + Value *Ops[] = { L, R }; + return Builder.CreateCall(F, Ops, Ops+2, "binop"); +} + +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"); +} + +Value *IfExprAST::Codegen() { + Value *CondV = Cond->Codegen(); + if (CondV == 0) return 0; + + // 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 == 0) return 0; + + 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 == 0) return 0; + + 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()), + "iftmp"); + + PN->addIncoming(ThenV, ThenBB); + PN->addIncoming(ElseV, ElseBB); + return PN; +} + +Value *ForExprAST::Codegen() { + // Output this as: + // var = alloca double + // ... + // start = startexpr + // store start -> var + // goto loop + // loop: + // ... + // bodyexpr + // ... + // loopend: + // step = stepexpr + // endcond = endexpr + // + // curvar = load var + // nextvar = curvar + step + // store nextvar -> var + // br endcond, loop, endloop + // outloop: + + Function *TheFunction = Builder.GetInsertBlock()->getParent(); + + // Create an alloca for the variable in the entry block. + AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, VarName); + + // Emit the start code first, without 'variable' in scope. + Value *StartVal = Start->Codegen(); + if (StartVal == 0) return 0; + + // Store the value into the alloca. + Builder.CreateStore(StartVal, Alloca); + + // Make the new basic block for the loop header, inserting after current + // block. + BasicBlock *LoopBB = BasicBlock::Create(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); + + // Within the loop, the variable is defined equal to the PHI node. If it + // shadows an existing variable, we have to restore it, so save it now. + AllocaInst *OldVal = NamedValues[VarName]; + NamedValues[VarName] = Alloca; + + // Emit the body of the loop. This, like any other expr, can change the + // current BB. Note that we ignore the value computed by the body, but don't + // allow an error. + if (Body->Codegen() == 0) + return 0; + + // Emit the step value. + Value *StepVal; + if (Step) { + StepVal = Step->Codegen(); + if (StepVal == 0) return 0; + } else { + // If not specified, use 1.0. + StepVal = ConstantFP::get(getGlobalContext(), APFloat(1.0)); + } + + // Compute the end condition. + Value *EndCond = End->Codegen(); + if (EndCond == 0) return EndCond; + + // Reload, increment, and restore the alloca. This handles the case where + // the body of the loop mutates the variable. + Value *CurVar = Builder.CreateLoad(Alloca, VarName.c_str()); + Value *NextVar = Builder.CreateAdd(CurVar, StepVal, "nextvar"); + Builder.CreateStore(NextVar, Alloca); + + // 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 *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); + + // 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())); +} + +Value *VarExprAST::Codegen() { + std::vector<AllocaInst *> OldBindings; + + Function *TheFunction = Builder.GetInsertBlock()->getParent(); + + // Register all variables and emit their initializer. + for (unsigned i = 0, e = VarNames.size(); i != e; ++i) { + const std::string &VarName = VarNames[i].first; + ExprAST *Init = VarNames[i].second; + + // Emit the initializer before adding the variable to scope, this prevents + // the initializer from referencing the variable itself, and permits stuff + // like this: + // var a = 1 in + // var a = a in ... # refers to outer 'a'. + Value *InitVal; + if (Init) { + InitVal = Init->Codegen(); + if (InitVal == 0) return 0; + } else { // If not specified, use 0.0. + InitVal = ConstantFP::get(getGlobalContext(), APFloat(0.0)); + } + + AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, VarName); + Builder.CreateStore(InitVal, Alloca); + + // Remember the old variable binding so that we can restore the binding when + // we unrecurse. + OldBindings.push_back(NamedValues[VarName]); + + // Remember this binding. + NamedValues[VarName] = Alloca; + } + + // Codegen the body, now that all vars are in scope. + Value *BodyVal = Body->Codegen(); + if (BodyVal == 0) return 0; + + // Pop all our variables from scope. + for (unsigned i = 0, e = VarNames.size(); i != e; ++i) + NamedValues[VarNames[i].first] = OldBindings[i]; + + // Return the body computation. + return BodyVal; +} + +Function *PrototypeAST::Codegen() { + // Make the function type: double(double,double) etc. + std::vector<const 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); + + // 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]); + + return F; +} + +/// CreateArgumentAllocas - Create an alloca for each argument and register the +/// argument in the symbol table so that references to it will succeed. +void PrototypeAST::CreateArgumentAllocas(Function *F) { + Function::arg_iterator AI = F->arg_begin(); + for (unsigned Idx = 0, e = Args.size(); Idx != e; ++Idx, ++AI) { + // Create an alloca for this variable. + AllocaInst *Alloca = CreateEntryBlockAlloca(F, Args[Idx]); + + // Store the initial value into the alloca. + Builder.CreateStore(AI, Alloca); + + // Add arguments to variable symbol table. + NamedValues[Args[Idx]] = Alloca; + } +} + +Function *FunctionAST::Codegen() { + NamedValues.clear(); + + Function *TheFunction = Proto->Codegen(); + if (TheFunction == 0) + return 0; + + // If this is an operator, install it. + if (Proto->isBinaryOp()) + BinopPrecedence[Proto->getOperatorName()] = Proto->getBinaryPrecedence(); + + // Create a new basic block to start insertion into. + BasicBlock *BB = BasicBlock::Create(getGlobalContext(), "entry", TheFunction); + Builder.SetInsertPoint(BB); + + // Add all arguments to the symbol table and create their allocas. + Proto->CreateArgumentAllocas(TheFunction); + + if (Value *RetVal = Body->Codegen()) { + // Finish off the function. + Builder.CreateRet(RetVal); + + // Validate the generated code, checking for consistency. + verifyFunction(*TheFunction); + + // Optimize the function. + TheFPM->run(*TheFunction); + + return TheFunction; + } + + // Error reading body, remove function. + TheFunction->eraseFromParent(); + + if (Proto->isBinaryOp()) + BinopPrecedence.erase(Proto->getOperatorName()); + return 0; +} + +//===----------------------------------------------------------------------===// +// Top-Level parsing and JIT Driver +//===----------------------------------------------------------------------===// + +static ExecutionEngine *TheExecutionEngine; + +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()) { + // JIT the function, returning a function pointer. + void *FPtr = TheExecutionEngine->getPointerToFunction(LF); + + // 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)FPtr; + fprintf(stderr, "Evaluated to %f\n", FP()); + } + } 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; +} + +/// printd - printf that takes a double prints it as "%f\n", returning 0. +extern "C" +double printd(double X) { + printf("%f\n", X); + return 0; +} + +//===----------------------------------------------------------------------===// +// Main driver code. +//===----------------------------------------------------------------------===// + +int main() { + InitializeNativeTarget(); + LLVMContext &Context = getGlobalContext(); + + // Install standard binary operators. + // 1 is lowest precedence. + BinopPrecedence['='] = 2; + BinopPrecedence['<'] = 10; + BinopPrecedence['+'] = 20; + BinopPrecedence['-'] = 20; + BinopPrecedence['*'] = 40; // highest. + + // Prime the first token. + fprintf(stderr, "ready> "); + getNextToken(); + + // Make the module, which holds all the code. + TheModule = new Module("my cool jit", Context); + + ExistingModuleProvider *OurModuleProvider = + new ExistingModuleProvider(TheModule); + + // Create the JIT. This takes ownership of the module and module provider. + TheExecutionEngine = EngineBuilder(OurModuleProvider).create(); + + FunctionPassManager OurFPM(OurModuleProvider); + + // Set up the optimizer pipeline. Start with registering info about how the + // target lays out data structures. + OurFPM.add(new TargetData(*TheExecutionEngine->getTargetData())); + // Promote allocas to registers. + OurFPM.add(createPromoteMemoryToRegisterPass()); + // Do simple "peephole" optimizations and bit-twiddling optzns. + OurFPM.add(createInstructionCombiningPass()); + // Reassociate expressions. + OurFPM.add(createReassociatePass()); + // Eliminate Common SubExpressions. + OurFPM.add(createGVNPass()); + // Simplify the control flow graph (deleting unreachable blocks, etc). + OurFPM.add(createCFGSimplificationPass()); + + OurFPM.doInitialization(); + + // Set the global so the code gen can use this. + TheFPM = &OurFPM; + + // Run the main "interpreter loop" now. + MainLoop(); + + TheFPM = 0; + + // Print out all of the generated code. + TheModule->dump(); + + return 0; +} diff --git a/examples/Kaleidoscope/Makefile b/examples/Kaleidoscope/Makefile index c1759a0..bd0c252 100644 --- a/examples/Kaleidoscope/Makefile +++ b/examples/Kaleidoscope/Makefile @@ -6,10 +6,10 @@ # License. See LICENSE.TXT for details. # ##===----------------------------------------------------------------------===## -LEVEL = ../.. -TOOLNAME = Kaleidoscope -EXAMPLE_TOOL = 1 +LEVEL=../.. -LINK_COMPONENTS := core jit native +include $(LEVEL)/Makefile.config + +PARALLEL_DIRS:= Chapter2 Chapter3 Chapter4 Chapter5 Chapter6 Chapter7 include $(LEVEL)/Makefile.common diff --git a/examples/ModuleMaker/ModuleMaker.cpp b/examples/ModuleMaker/ModuleMaker.cpp index 59a86d0..6bc52c1 100644 --- a/examples/ModuleMaker/ModuleMaker.cpp +++ b/examples/ModuleMaker/ModuleMaker.cpp @@ -19,7 +19,7 @@ #include "llvm/Constants.h" #include "llvm/Instructions.h" #include "llvm/Bitcode/ReaderWriter.h" -#include <iostream> +#include "llvm/Support/raw_ostream.h" using namespace llvm; int main() { @@ -30,7 +30,8 @@ int main() { Module *M = new Module("test", Context); // Create the main function: first create the type 'int ()' - FunctionType *FT = FunctionType::get(Type::Int32Ty, /*not vararg*/false); + FunctionType *FT = + FunctionType::get(Type::getInt32Ty(Context), /*not vararg*/false); // By passing a module as the last parameter to the Function constructor, // it automatically gets appended to the Module. @@ -38,11 +39,11 @@ int main() { // Add a basic block to the function... again, it automatically inserts // because of the last argument. - BasicBlock *BB = BasicBlock::Create("EntryBlock", F); + BasicBlock *BB = BasicBlock::Create(Context, "EntryBlock", F); // Get pointers to the constant integers... - Value *Two = ConstantInt::get(Type::Int32Ty, 2); - Value *Three = ConstantInt::get(Type::Int32Ty, 3); + Value *Two = ConstantInt::get(Type::getInt32Ty(Context), 2); + Value *Three = ConstantInt::get(Type::getInt32Ty(Context), 3); // Create the add instruction... does not insert... Instruction *Add = BinaryOperator::Create(Instruction::Add, Two, Three, @@ -52,10 +53,10 @@ int main() { BB->getInstList().push_back(Add); // Create the return instruction and add it to the basic block - BB->getInstList().push_back(ReturnInst::Create(Add)); + BB->getInstList().push_back(ReturnInst::Create(Context, Add)); // Output the bitcode file to stdout - WriteBitcodeToFile(M, std::cout); + WriteBitcodeToFile(M, outs()); // Delete the module and all of its contents. delete M; diff --git a/examples/ParallelJIT/CMakeLists.txt b/examples/ParallelJIT/CMakeLists.txt index d8dd708..fbdc6e5 100644 --- a/examples/ParallelJIT/CMakeLists.txt +++ b/examples/ParallelJIT/CMakeLists.txt @@ -4,4 +4,6 @@ add_llvm_example(ParallelJIT ParallelJIT.cpp ) -target_link_libraries(ParallelJIT pthread) +if(HAVE_LIBPTHREAD) + target_link_libraries(ParallelJIT pthread) +endif(HAVE_LIBPTHREAD) diff --git a/examples/ParallelJIT/ParallelJIT.cpp b/examples/ParallelJIT/ParallelJIT.cpp index eadd0f5..be40a28 100644 --- a/examples/ParallelJIT/ParallelJIT.cpp +++ b/examples/ParallelJIT/ParallelJIT.cpp @@ -36,15 +36,17 @@ static Function* createAdd1(Module *M) { // function will have a return type of "int" and take an argument of "int". // The '0' terminates the list of argument types. Function *Add1F = - cast<Function>(M->getOrInsertFunction("add1", Type::Int32Ty, Type::Int32Ty, + cast<Function>(M->getOrInsertFunction("add1", + Type::getInt32Ty(M->getContext()), + Type::getInt32Ty(M->getContext()), (Type *)0)); // Add a basic block to the function. As before, it automatically inserts // because of the last argument. - BasicBlock *BB = BasicBlock::Create("EntryBlock", Add1F); + BasicBlock *BB = BasicBlock::Create(M->getContext(), "EntryBlock", Add1F); // Get pointers to the constant `1'. - Value *One = ConstantInt::get(Type::Int32Ty, 1); + Value *One = ConstantInt::get(Type::getInt32Ty(M->getContext()), 1); // Get pointers to the integer argument of the add1 function... assert(Add1F->arg_begin() != Add1F->arg_end()); // Make sure there's an arg @@ -55,7 +57,7 @@ static Function* createAdd1(Module *M) { Instruction *Add = BinaryOperator::CreateAdd(One, ArgX, "addresult", BB); // Create the return instruction and add it to the basic block - ReturnInst::Create(Add, BB); + ReturnInst::Create(M->getContext(), Add, BB); // Now, function add1 is ready. return Add1F; @@ -65,31 +67,33 @@ static Function *CreateFibFunction(Module *M) { // Create the fib function and insert it into module M. This function is said // to return an int and take an int parameter. Function *FibF = - cast<Function>(M->getOrInsertFunction("fib", Type::Int32Ty, Type::Int32Ty, + cast<Function>(M->getOrInsertFunction("fib", + Type::getInt32Ty(M->getContext()), + Type::getInt32Ty(M->getContext()), (Type *)0)); // Add a basic block to the function. - BasicBlock *BB = BasicBlock::Create("EntryBlock", FibF); + BasicBlock *BB = BasicBlock::Create(M->getContext(), "EntryBlock", FibF); // Get pointers to the constants. - Value *One = ConstantInt::get(Type::Int32Ty, 1); - Value *Two = ConstantInt::get(Type::Int32Ty, 2); + Value *One = ConstantInt::get(Type::getInt32Ty(M->getContext()), 1); + Value *Two = ConstantInt::get(Type::getInt32Ty(M->getContext()), 2); // Get pointer to the integer argument of the add1 function... Argument *ArgX = FibF->arg_begin(); // Get the arg. ArgX->setName("AnArg"); // Give it a nice symbolic name for fun. // Create the true_block. - BasicBlock *RetBB = BasicBlock::Create("return", FibF); + BasicBlock *RetBB = BasicBlock::Create(M->getContext(), "return", FibF); // Create an exit block. - BasicBlock* RecurseBB = BasicBlock::Create("recurse", FibF); + BasicBlock* RecurseBB = BasicBlock::Create(M->getContext(), "recurse", FibF); // Create the "if (arg < 2) goto exitbb" - Value *CondInst = new ICmpInst(ICmpInst::ICMP_SLE, ArgX, Two, "cond", BB); + Value *CondInst = new ICmpInst(*BB, ICmpInst::ICMP_SLE, ArgX, Two, "cond"); BranchInst::Create(RetBB, RecurseBB, CondInst, BB); // Create: ret int 1 - ReturnInst::Create(One, RetBB); + ReturnInst::Create(M->getContext(), One, RetBB); // create fib(x-1) Value *Sub = BinaryOperator::CreateSub(ArgX, One, "arg", RecurseBB); @@ -104,7 +108,7 @@ static Function *CreateFibFunction(Module *M) { BinaryOperator::CreateAdd(CallFibX1, CallFibX2, "addresult", RecurseBB); // Create the return instruction and add it to the basic block - ReturnInst::Create(Sum, RecurseBB); + ReturnInst::Create(M->getContext(), Sum, RecurseBB); return FibF; } @@ -242,8 +246,7 @@ int main() { Function* fibF = CreateFibFunction( M ); // Now we create the JIT. - ExistingModuleProvider* MP = new ExistingModuleProvider(M); - ExecutionEngine* EE = ExecutionEngine::create(MP, false); + ExecutionEngine* EE = EngineBuilder(M).create(); //~ std::cout << "We just constructed this LLVM module:\n\n" << *M; //~ std::cout << "\n\nRunning foo: " << std::flush; |