C++ reverse_iterator::getIterator方法代码示例

bool SIOptimizeExecMasking::runOnMachineFunction(MachineFunction &MF) {
  if (skipFunction(MF.getFunction()))
    return false;

  const SISubtarget &ST = MF.getSubtarget<SISubtarget>();
  const SIRegisterInfo *TRI = ST.getRegisterInfo();
  const SIInstrInfo *TII = ST.getInstrInfo();

  // Optimize sequences emitted for control flow lowering. They are originally
  // emitted as the separate operations because spill code may need to be
  // inserted for the saved copy of exec.
  //
  //     x = copy exec
  //     z = s_<op>_b64 x, y
  //     exec = copy z
  // =>
  //     x = s_<op>_saveexec_b64 y
  //

  for (MachineBasicBlock &MBB : MF) {
    MachineBasicBlock::reverse_iterator I = fixTerminators(*TII, MBB);
    MachineBasicBlock::reverse_iterator E = MBB.rend();
    if (I == E)
      continue;

    unsigned CopyToExec = isCopyToExec(*I);
    if (CopyToExec == AMDGPU::NoRegister)
      continue;

    // Scan backwards to find the def.
    auto CopyToExecInst = &*I;
    auto CopyFromExecInst = findExecCopy(*TII, MBB, I, CopyToExec);
    if (CopyFromExecInst == E) {
      auto PrepareExecInst = std::next(I);
      if (PrepareExecInst == E)
        continue;
      // Fold exec = COPY (S_AND_B64 reg, exec) -> exec = S_AND_B64 reg, exec
      if (CopyToExecInst->getOperand(1).isKill() &&
          isLogicalOpOnExec(*PrepareExecInst) == CopyToExec) {
        DEBUG(dbgs() << "Fold exec copy: " << *PrepareExecInst);

        PrepareExecInst->getOperand(0).setReg(AMDGPU::EXEC);
        PrepareExecInst->getOperand(0).setIsRenamable(false);

        DEBUG(dbgs() << "into: " << *PrepareExecInst << '\n');

        CopyToExecInst->eraseFromParent();
      }

      continue;
    }

    if (isLiveOut(MBB, CopyToExec)) {
      // The copied register is live out and has a second use in another block.
      DEBUG(dbgs() << "Exec copy source register is live out\n");
      continue;
    }

    unsigned CopyFromExec = CopyFromExecInst->getOperand(0).getReg();
    MachineInstr *SaveExecInst = nullptr;
    SmallVector<MachineInstr *, 4> OtherUseInsts;

    for (MachineBasicBlock::iterator J
           = std::next(CopyFromExecInst->getIterator()), JE = I->getIterator();
         J != JE; ++J) {
      if (SaveExecInst && J->readsRegister(AMDGPU::EXEC, TRI)) {
        DEBUG(dbgs() << "exec read prevents saveexec: " << *J << '\n');
        // Make sure this is inserted after any VALU ops that may have been
        // scheduled in between.
        SaveExecInst = nullptr;
        break;
      }

      bool ReadsCopyFromExec = J->readsRegister(CopyFromExec, TRI);

      if (J->modifiesRegister(CopyToExec, TRI)) {
        if (SaveExecInst) {
          DEBUG(dbgs() << "Multiple instructions modify "
                << printReg(CopyToExec, TRI) << '\n');
          SaveExecInst = nullptr;
          break;
        }

        unsigned SaveExecOp = getSaveExecOp(J->getOpcode());
        if (SaveExecOp == AMDGPU::INSTRUCTION_LIST_END)
          break;

        if (ReadsCopyFromExec) {
          SaveExecInst = &*J;
          DEBUG(dbgs() << "Found save exec op: " << *SaveExecInst << '\n');
          continue;
        } else {
          DEBUG(dbgs() << "Instruction does not read exec copy: " << *J << '\n');
          break;
        }
      } else if (ReadsCopyFromExec && !SaveExecInst) {
        // Make sure no other instruction is trying to use this copy, before it
        // will be rewritten by the saveexec, i.e. hasOneUse. There may have
        // been another use, such as an inserted spill. For example:
        //
//.........这里部分代码省略.........