/// Determines the optimal series of memory ops to replace the memset / memcpy.
/// Return true if the number of memory ops is below the threshold (Limit).
/// It returns the types of the sequence of memory ops to perform
/// memset / memcpy by reference.
static bool FindOptimalMemOpLowering(std::vector<EVT> &MemOps,
                                     unsigned Limit, uint64_t Size,
                                     unsigned DstAlign, unsigned SrcAlign,
                                     bool IsMemset,
                                     bool ZeroMemset,
                                     bool MemcpyStrSrc,
                                     bool AllowOverlap,
                                     unsigned DstAS, unsigned SrcAS,
                                     SelectionDAG &DAG,
                                     const TargetLowering &TLI) {
  assert((SrcAlign == 0 || SrcAlign >= DstAlign) &&
         "Expecting memcpy / memset source to meet alignment requirement!");
  // If 'SrcAlign' is zero, that means the memory operation does not need to
  // load the value, i.e. memset or memcpy from constant string. Otherwise,
  // it's the inferred alignment of the source. 'DstAlign', on the other hand,
  // is the specified alignment of the memory operation. If it is zero, that
  // means it's possible to change the alignment of the destination.
  // 'MemcpyStrSrc' indicates whether the memcpy source is constant so it does
  // not need to be loaded.
  EVT VT = TLI.getOptimalMemOpType(Size, DstAlign, SrcAlign,
                                   IsMemset, ZeroMemset, MemcpyStrSrc,
                                   DAG.getMachineFunction());

  if (VT == MVT::Other) {
    // Use the largest integer type whose alignment constraints are satisfied.
    
    if (DstAlign == 0)
      DstAlign = SrcAlign;
    
    VT = MVT::i64;
    while (DstAlign && DstAlign < VT.getSizeInBits() / 8 &&
           !TLI.allowsMisalignedMemoryAccesses(VT, DstAS, DstAlign))
      VT = (MVT::SimpleValueType)(VT.getSimpleVT().SimpleTy - 1);
    assert(VT.isInteger());

    // Find the largest legal integer type.
    MVT LVT = MVT::i64;
    while (!TLI.isTypeLegal(LVT))
      LVT = (MVT::SimpleValueType)(LVT.SimpleTy - 1);
    assert(LVT.isInteger());

    // If the type we've chosen is larger than the largest legal integer type
    // then use that instead.
    if (VT.bitsGT(LVT))
      VT = LVT;
  }

  unsigned NumMemOps = 0;
  while (Size != 0) {
    unsigned VTSize = VT.getSizeInBits() / 8;
    while (VTSize > Size) {
      // For now, only use non-vector load / store's for the left-over pieces.
      EVT NewVT = VT;
      unsigned NewVTSize;

      bool Found = false;
      if (VT.isVector() || VT.isFloatingPoint()) {
        NewVT = (VT.getSizeInBits() > 64) ? MVT::i64 : MVT::i32;
        if (TLI.isOperationLegalOrCustom(ISD::STORE, NewVT) &&
            TLI.isSafeMemOpType(NewVT.getSimpleVT()))
          Found = true;
        else if (NewVT == MVT::i64 &&
                 TLI.isOperationLegalOrCustom(ISD::STORE, MVT::f64) &&
                 TLI.isSafeMemOpType(MVT::f64)) {
          // i64 is usually not legal on 32-bit targets, but f64 may be.
          NewVT = MVT::f64;
          Found = true;
        }
      }

      if (!Found) {
        do {
          NewVT = (MVT::SimpleValueType)(NewVT.getSimpleVT().SimpleTy - 1);
          if (NewVT == MVT::i8)
            break;
        } while (!TLI.isSafeMemOpType(NewVT.getSimpleVT()));
      }
      NewVTSize = NewVT.getSizeInBits() / 8;

      // If the new VT cannot cover all of the remaining bits, then consider
      // issuing a (or a pair of) unaligned and overlapping load / store.
      // FIXME: Only does this for 64-bit or more since we don't have proper
      // cost model for unaligned load / store.
      bool Fast;
      if (NumMemOps && AllowOverlap &&
          VTSize >= 8 && NewVTSize < Size &&
          TLI.allowsMisalignedMemoryAccesses(VT, DstAS, DstAlign, &Fast) && Fast)
        VTSize = Size;
      else {
        VT = NewVT;
        VTSize = NewVTSize;
      }
    }

    if (++NumMemOps > Limit)
      return false;

    MemOps.push_back(VT);
    Size -= VTSize;
  }

  return true;
}