// TPUReplicatedInput and TPUReplicatedOutput respectively. For example, with
// two component devices, running `x = TPUReplicatedInput(inputs=[a, b])` on the
// parallel device creates a parallel tensor `x` with `a` on the first of
// `underlying_devices` and `b` on the second. Running `a_unpacked, b_unpacked =
// TPUReplicatedOutput(input=x, num_replicas=2)` un-packs the parallel tensor
// into its components.
//

  // Adds `value` to the existing value of the variable.
  void AssignAdd(TFE_Context* context, TFE_TensorHandle* value,
                 TF_Status* status);

 private:
  // Helper for running any single-argument assignment ops (Assign, AssignAdd,
  // AssignSub, ...).
  void GeneralAssignment(const char* op_name, TFE_Context* context,
                         TFE_TensorHandle* value, TF_Status* status);

TF_CAPI_EXPORT extern uint64_t TF_NowSeconds(void);

// Populates a TF_ThreadOptions struct with system-default values.
TF_CAPI_EXPORT extern void TF_DefaultThreadOptions(TF_ThreadOptions* options);

// Returns a new thread that is running work_func and is identified
// (for debugging/performance-analysis) by thread_name.
//
// The given param (which may be null) is passed to work_func when the thread

  //
  // If `is_async=false` (constructor argument), `cancellation_manager` must
  // live until `Join` finishes. If `is_async=true` it must live until `Join` is
  // followed by `TFE_ContextAsyncWait` to clear pending operations. It will be
  // used to cancel all other operations if any fails.
  //
  // Set step_id to configure the step id used for rendezvous creation. step id

//
// The returned string is valid only until TF_DeleteServer is invoked.
TF_CAPI_EXPORT extern const char* TF_ServerTarget(TF_Server* server);

// Destroy an in-process TensorFlow server, frees memory. If server is running
// it will be stopped and joined.
TF_CAPI_EXPORT extern void TF_DeleteServer(TF_Server* server);

// Register a listener method that processes printed messages.
//

TF_CAPI_EXPORT void TF_SetXlaMinClusterSize(int size);

// Gets/Sets TF/XLA flag for whether(true) or not(false) to disable constant
// folding. This is for testing to ensure that XLA is being tested rather than
// Tensorflow's CPU implementation through constant folding.
TF_CAPI_EXPORT unsigned char TF_GetXlaConstantFoldingDisabled();
TF_CAPI_EXPORT void TF_SetXlaConstantFoldingDisabled(
    unsigned char should_enable);

  // source tensors. The output gradients are used if not empty and not
  // null. The result is populated with one tensor per target element.
  // When running backward functions, builds zeros-like tensors for
  // incoming grads which are nullptrs, unless `build_default_zeros_grads`
  // is set to false.
  Status ComputeGradient(

// maximum number of in flight async nodes. Enqueuing of additional async ops
// after the limit is reached blocks until some inflight nodes finishes.
// The effect is bounding the memory held by inflight TensorHandles that are
// referenced by the inflight nodes.
// A recommended value has not been established.
// A value of 0 removes the limit, which is the behavior of TensorFlow 2.11.

  TF_TriState implementation_selector;
  TF_TriState function_optimization;
  TF_TriState common_subgraph_elimination;
  TF_TriState arithmetic_optimization;
  TF_TriState debug_stripper;
  TF_TriState constant_folding;
  TF_TriState shape_optimization;
  TF_TriState auto_mixed_precision;
  TF_TriState auto_mixed_precision_onednn_bfloat16;
  TF_TriState auto_mixed_precision_mkl;
  TF_TriState pin_to_host_optimization;