OP_REQUIRES(context, context->input_type(i * 3) == DT_FLOAT,
                  absl::AbortedError("The input `min` must have float type."));
      OP_REQUIRES(context, context->input_type(i * 3 + 1) == DT_FLOAT,
                  absl::AbortedError("The input `max` must have float type."));
      OP_REQUIRES(
          context, context->input_type(i * 3 + 2) == DT_INT64,

    for (int index : dynamic_shape_arg_index) {
      BlockArgument arg = func.getArgument(index);
      auto inputType = mlir::dyn_cast<RankedTensorType>(arg.getType());
      // Only rank 1 tensor is supported for now.
      if (!inputType || inputType.getRank() != 1) continue;
      auto shape = llvm::to_vector<4>(inputType.getShape());
      llvm::SmallVector<int64_t, 4> bounds(shape.begin(), shape.end());
      // Mark the dim as dynamic dim.

// Quantizes the input model represented as `model_buffer` and writes the result
// to the `output_buffer`. Both `model_buffer` and `output_buffer` should be a
// valid FlatBuffer format for Model supported by TFLite.
//
// The `input_type`, `output_type` and `inference_type` can be float32 / qint8 /
// int8 / int16.
//
// Returns a partially quantized model if `fully_quantize` is false. Returns a
// non-OK status if the quantization fails.
//

               << ", input_inference_type: "
               << tflite::EnumNameTensorType(input_type)
               << ", output_inference_type: "
               << tflite::EnumNameTensorType(output_type) << "\n";
  mlir::Builder mlir_builder(&context);
  mlir::Type input_mlir_type =
      tflite::ConvertElementType(input_type, mlir_builder);
  mlir::Type output_mlir_type =

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

        }

        List<Object> inputs = new ArrayList<>(inputTypes.size());
        for (Class<?> inputType : inputTypes) {
            if (inputType == ComponentMetadata.class) {
                inputs.add(metadataProvider.getComponentMetadata());
                continue;
            }
            if (inputType == IvyModuleDescriptor.class) {
                inputs.add(metadataProvider.getIvyModuleDescriptor());

  EXPECT_EQ("XTimesY", kernel_->name());
  EXPECT_EQ("XTimesY", kernel_->type_string());

  EXPECT_EQ(2, kernel_->num_inputs());
  EXPECT_EQ(DT_FLOAT, kernel_->input_type(0));
  EXPECT_EQ(DT_RESOURCE, kernel_->input_type(1));
  EXPECT_EQ(DEVICE_MEMORY, kernel_->input_memory_types()[0]);
  EXPECT_EQ(HOST_MEMORY, kernel_->input_memory_types()[1]);

  EXPECT_EQ(1, kernel_->num_outputs());

  }

  std::vector<Value> inputs;
  std::vector<Value> outputs;
  computeInputsOutputs(ops, &inputs, &outputs);

  std::vector<Type> input_types;
  std::vector<Type> output_types;

  input_types.reserve(inputs.size());
  for (Value v : inputs) {
    input_types.push_back(v.getType());
  }
  output_types.reserve(outputs.size());
  for (Value v : outputs) {
    output_types.push_back(v.getType());
  }

    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.

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