limitations under the License.
==============================================================================*/
)";

static const char *machine_generated =
    "// This file is MACHINE GENERATED! Do not edit.";

CppFileRenderer::CppFileRenderer(RendererContext context,
                                 const std::vector<OpView> &ops)
    : Renderer(context),
      guard_(context),
      name_space_(context),

using ::tensorflow::SignatureDef;
using ::tensorflow::quantization::PyFunctionLibrary;

// Note for maintainers: the definitions should ONLY mirror existing functions
// defined in different targets. Do not include any extra business logic that
// causes divergence from the semantics of mirrored functions.

absl::Status PywrapQuantizeStaticRangePtq(
    absl::string_view src_saved_model_path,

        TF::TensorFlowDialect::getDialectNamespace())
      return failure();

    // Refining types may have implications to the attached regions or symbol
    // references so do not update such ops.
    if (!op->getRegions().empty() || HasSymbolRefAttr(op)) return failure();

    IRMapping mapper;
    bool has_type_change = false;

}

TEST(PickDeviceForXla, MoreSpecificDevice) {
  CheckPickDeviceResult(kCPU0, false, {kCPU0, kCPU0Partial});
  CheckPickDeviceResult(kGPU0, false, {kGPU0, kGPU0Partial});
  // Unknown devices do not support merging of full and partial specifications.
  CheckPickDeviceHasError(false, {kXPU1, kXPU0Partial});
}

TEST(PickDeviceForXla, DeviceOrder) {
  CheckPickDeviceResult(kGPU0, false, {kGPU0, kCPU0});

// TODO - b/296503614: [Converter Component][TF-Quantizer] Reflect custom traits
// from TF-Quantizer to stableHLO quantization
bool IsOpWithDataMovementTrait(Operation* op) {
  // Supported data movement ops. These ops do not perform any computations and
  // has one result operand.
  return isa<TF::IdentityOp, TF::CastOp, TF::ReshapeOp, TF::XlaShardingOp,
             TF::GatherOp, TF::GatherV2Op, TF::XlaGatherOp, TF::ExpandDimsOp,

    signalPassFailure();
    return;
  }

  // Copy all functions used by this signature to the final MLIR module.
  for (func::FuncOp func : module_ref->getOps<func::FuncOp>()) {
    // Do nothing if the function already exists.
    if (symbol_table.lookup(func.getSymName()) != nullptr) continue;

    // Set the function to private and insert to the module.
    func::FuncOp new_func = func.clone();

      : ConversionTarget(ctx), converter_(converter) {
    markUnknownOpDynamicallyLegal([this](Operation* op) {
      // The FuncOp type can contain types that the op's operand and result
      // types do not contain.
      if (auto func = dyn_cast<func::FuncOp>(op)) {
        if (!converter_.isSignatureLegal(func.getFunctionType())) return false;
      } else if (auto bitcast_convert_op =

//    *different* variables
//  - they make the blanket assumption that any functions called cause or depend
//    on side effects (i.e., access resource variables.)
//
// By moving the logic to compile time, we will be able to do a finer-grained
// data flow analysis in the future, which will enable more optimizations.
// This could happen in two steps:
// (1) build multiple dependency chains (one per variable), still treating

    absl::Span<tensorflow::AbstractTensorHandle* const> inputs,
    absl::Span<tensorflow::AbstractTensorHandle*> outputs) {
  // TODO(srbs): Provide a function execution API on ctx so that we do not
  // expose the internals of how functions are to be executed here.
  std::string fname;
  {
    const tensorflow::FunctionDef* fdef = nullptr;
    TF_RETURN_IF_ERROR(trace->GetFunctionDef(&fdef));

  Graph* graph_;
  int unique_name_counter_;
};

string CloneConstantsForBetterClusteringPassImpl::GenerateUniqueName(
    const absl::flat_hash_set<string>& name_set, absl::string_view prefix) {
  string candidate;
  do {
    candidate = absl::StrCat(prefix, "/clone_", unique_name_counter_++);
  } while (name_set.contains(candidate));
  return candidate;
}

absl::StatusOr<Node*> CloneConstantsForBetterClusteringPassImpl::CloneNode(