path: root/lib/Transforms/Utils/CodeExtractor.cpp

//===- CodeExtractor.cpp - Pull code region into a new function -----------===//
// 
//                     The LLVM Compiler Infrastructure
//
// This file was developed by the LLVM research group and is distributed under
// the University of Illinois Open Source License. See LICENSE.TXT for details.
// 
//===----------------------------------------------------------------------===//
//
// This file implements the interface to tear out a code region, such as an
// individual loop or a parallel section, into a new function, replacing it with
// a call to the new function.
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Utils/FunctionUtils.h"
#include "llvm/Constants.h"
#include "llvm/DerivedTypes.h"
#include "llvm/Instructions.h"
#include "llvm/Module.h"
#include "llvm/Pass.h"
#include "llvm/Analysis/Dominators.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/Verifier.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "Support/Debug.h"
#include "Support/StringExtras.h"
#include <algorithm>
#include <set>
using namespace llvm;

namespace {
  class CodeExtractor {
    typedef std::vector<Value*> Values;
    std::set<BasicBlock*> BlocksToExtract;
    DominatorSet *DS;
  public:
    CodeExtractor(DominatorSet *ds = 0) : DS(ds) {}

    Function *ExtractCodeRegion(const std::vector<BasicBlock*> &code);

  private:
    void findInputsOutputs(Values &inputs, Values &outputs,
                           BasicBlock *newHeader,
                           BasicBlock *newRootNode);

    Function *constructFunction(const Values &inputs,
                                const Values &outputs,
                                BasicBlock *header,
                                BasicBlock *newRootNode, BasicBlock *newHeader,
                                Function *oldFunction, Module *M);

    void moveCodeToFunction(Function *newFunction);

    void emitCallAndSwitchStatement(Function *newFunction,
                                    BasicBlock *newHeader,
                                    Values &inputs,
                                    Values &outputs);

  };
}

void CodeExtractor::findInputsOutputs(Values &inputs, Values &outputs,
                                      BasicBlock *newHeader,
                                      BasicBlock *newRootNode) {
  for (std::set<BasicBlock*>::const_iterator ci = BlocksToExtract.begin(), 
       ce = BlocksToExtract.end(); ci != ce; ++ci) {
    BasicBlock *BB = *ci;
    for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I) {
      // If a used value is defined outside the region, it's an input.  If an
      // instruction is used outside the region, it's an output.
      if (PHINode *PN = dyn_cast<PHINode>(I)) {
        for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i) {
          Value *V = PN->getIncomingValue(i);
          if (!BlocksToExtract.count(PN->getIncomingBlock(i)) &&
              (isa<Instruction>(V) || isa<Argument>(V)))
            inputs.push_back(V);
        }
      } else {
        // All other instructions go through the generic input finder
        // Loop over the operands of each instruction (inputs)
        for (User::op_iterator op = I->op_begin(), opE = I->op_end();
             op != opE; ++op)
          if (Instruction *opI = dyn_cast<Instruction>(*op)) {
            // Check if definition of this operand is within the loop
            if (!BlocksToExtract.count(opI->getParent()))
              inputs.push_back(opI);
          } else if (isa<Argument>(*op)) {
            inputs.push_back(*op);
          }
      }
      
      // Consider uses of this instruction (outputs)
      for (Value::use_iterator UI = I->use_begin(), E = I->use_end();
           UI != E; ++UI)
        if (!BlocksToExtract.count(cast<Instruction>(*UI)->getParent())) {
          outputs.push_back(I);
          break;
        }
    } // for: insts
  } // for: basic blocks
}

/// constructFunction - make a function based on inputs and outputs, as follows:
/// f(in0, ..., inN, out0, ..., outN)
///
Function *CodeExtractor::constructFunction(const Values &inputs,
                                           const Values &outputs,
                                           BasicBlock *header,
                                           BasicBlock *newRootNode,
                                           BasicBlock *newHeader,
                                           Function *oldFunction,
                                           Module *M) {
  DEBUG(std::cerr << "inputs: " << inputs.size() << "\n");
  DEBUG(std::cerr << "outputs: " << outputs.size() << "\n");

  // This function returns unsigned, outputs will go back by reference.
  Type *retTy = Type::UShortTy;
  std::vector<const Type*> paramTy;

  // Add the types of the input values to the function's argument list
  for (Values::const_iterator i = inputs.begin(),
         e = inputs.end(); i != e; ++i) {
    const Value *value = *i;
    DEBUG(std::cerr << "value used in func: " << value << "\n");
    paramTy.push_back(value->getType());
  }

  // Add the types of the output values to the function's argument list.
  for (Values::const_iterator I = outputs.begin(), E = outputs.end();
       I != E; ++I) {
    DEBUG(std::cerr << "instr used in func: " << *I << "\n");
    paramTy.push_back(PointerType::get((*I)->getType()));
  }

  DEBUG(std::cerr << "Function type: " << retTy << " f(");
  for (std::vector<const Type*>::iterator i = paramTy.begin(),
         e = paramTy.end(); i != e; ++i)
    DEBUG(std::cerr << *i << ", ");
  DEBUG(std::cerr << ")\n");

  const FunctionType *funcType = FunctionType::get(retTy, paramTy, false);

  // Create the new function
  Function *newFunction = new Function(funcType,
                                       GlobalValue::InternalLinkage,
                                       oldFunction->getName() + "_code", M);
  newFunction->getBasicBlockList().push_back(newRootNode);

  // Create an iterator to name all of the arguments we inserted.
  Function::aiterator AI = newFunction->abegin();

  // Rewrite all users of the inputs in the extracted region to use the
  // arguments instead.
  for (unsigned i = 0, e = inputs.size(); i != e; ++i, ++AI) {
    AI->setName(inputs[i]->getName());
    std::vector<User*> Users(inputs[i]->use_begin(), inputs[i]->use_end());
    for (std::vector<User*>::iterator use = Users.begin(), useE = Users.end();
         use != useE; ++use)
      if (Instruction* inst = dyn_cast<Instruction>(*use))
        if (BlocksToExtract.count(inst->getParent()))
          inst->replaceUsesOfWith(inputs[i], AI);
  }

  // Set names for all of the output arguments.
  for (unsigned i = 0, e = outputs.size(); i != e; ++i, ++AI)
    AI->setName(outputs[i]->getName()+".out");  


  // Rewrite branches to basic blocks outside of the loop to new dummy blocks
  // within the new function. This must be done before we lose track of which
  // blocks were originally in the code region.
  std::vector<User*> Users(header->use_begin(), header->use_end());
  for (unsigned i = 0, e = Users.size(); i != e; ++i)
    // The BasicBlock which contains the branch is not in the region
    // modify the branch target to a new block
    if (TerminatorInst *TI = dyn_cast<TerminatorInst>(Users[i]))
      if (!BlocksToExtract.count(TI->getParent()) &&
          TI->getParent()->getParent() == oldFunction)
        TI->replaceUsesOfWith(header, newHeader);

  return newFunction;
}

void CodeExtractor::moveCodeToFunction