if (!reshape_type.hasStaticShape()) return failure();
    ArrayRef<int64_t> reshape_shape = reshape_type.getShape();

    auto input_type = mlir::cast<ShapedType>(op.getInput().getType());
    auto output_type = mlir::cast<ShapedType>(op.getOutput().getType());

    if (!input_type.hasRank() || !output_type.hasRank()) return failure();

    // The pattern attempts to reduce the rank of the input to BroadcastTo.

      return failure();

    Value input = tf_op.getInput();
    RankedTensorType input_type =
        mlir::dyn_cast<RankedTensorType>(input.getType());
    // Only rank size four input will be only available by the tf.Conv2D
    // operator verification.
    if (!input_type || input_type.isDynamicDim(3)) {
      return failure();
    }
    // Check if the given op is based on grouped convolution.

        File input = getInput().get().getAsFile();
        InstrumentationInputType inputType = getInputType(input);
        switch (inputType) {
            case DEPENDENCY_ANALYSIS_DATA:
                doMergeAndOutputAnalysis(input, outputs);
                return;
            case ORIGINAL_ARTIFACT:

  for (auto input : llvm::zip(getOperandTypes(), getInputSpecs())) {
    Type inputType = std::get<0>(input);
    Attribute inputSpec = std::get<1>(input);
    if (!isValidQuantizationSpec(inputSpec, inputType)) {
      return emitOpError() << "has incompatible specification " << inputSpec
                           << " and input type " << inputType;
    }
  }

  for (auto result : llvm::zip(getResultTypes(), getOutputSpecs())) {

  for (auto input : llvm::zip(getOperandTypes(), getInputSpecs())) {
    Type inputType = std::get<0>(input);
    Attribute inputSpec = std::get<1>(input);
    if (!isValidQuantizationSpec(inputSpec, inputType)) {
      return emitOpError() << "has incompatible specification " << inputSpec
                           << " and input type " << inputType;
    }
  }

  for (auto result : llvm::zip(getResultTypes(), getOutputSpecs())) {

    if (dyn_cast_or_null<quantfork::QuantizeCastOp>(next_op)) return failure();

    auto input_type = mlir::cast<ShapedType>(transpose_op.getInput().getType());
    auto perm_type = mlir::cast<ShapedType>(transpose_op.getPerm().getType());
    if (input_type.hasStaticShape() && perm_type.hasStaticShape()) {
      if (perm_type.getNumElements() != input_type.getRank()) {
        return transpose_op.emitOpError(

      return failure();
    }

    const auto input_type = op.getLhs().getType().cast<TensorType>();
    if (!(input_type.getRank() == 2 || input_type.getRank() == 3)) {
      LLVM_DEBUG(llvm::dbgs() << "Input expected to have rank of 2 or 3. Got: "
                              << input_type << ".\n");
      return failure();
    }

    const Value filter = op.getRhs();

           << ", and input of rank " << input_type.getRank();
  }

  if (input_type && output_type) {
    if (input_type.getRank() != output_type.getRank()) {
      return op.emitOpError()
             << "expected rank of input to equal to rank of output"
             << ", got input of rank " << input_type.getRank()
             << ", and output of rank " << output_type.getRank();
    }

  BoolAttr narrow_range = builder.getBoolAttr(false);

  auto add_quantize_op = [&](Location loc, Type input_type, Block* block,
                             Block::iterator insertion_point, Value arg,
                             int i) {
    if (auto shaped = mlir::dyn_cast<ShapedType>(input_type)) {
      if (mlir::isa<FloatType>(shaped.getElementType())) {

        break;
      default:
        return nullptr;  // Not yet supported
    }
  } else {
    return nullptr;  // Not yet supported
  }

  input_type = input_type.clone(new_storage_type);
  return input_type;
}

// Replaces quant.qcast op to composite quantize_i8 function.
class ReplaceQuantizePattern
    : public mlir::OpRewritePattern<quantfork::QuantizeCastOp> {
 public: