TF_CAPI_EXPORT extern bool TFE_ExecutorIsAsync(TFE_Executor*);

// Causes the calling thread to block till all ops dispatched in this executor
// have been executed. Note that "execution" here refers to kernel execution /
// scheduling of copies, etc. Similar to sync execution, it doesn't guarantee
// that lower level device queues (like GPU streams) have been flushed.
//

                                                 size_t name_len,
                                                 TF_Status* status);

// --------------------------------------------------------------------------
// Kernel definition information.

// Returns a serialized KernelList protocol buffer containing KernelDefs for all
// registered kernels.
TF_CAPI_EXPORT extern TF_Buffer* TF_GetAllRegisteredKernels(TF_Status* status);

  TF_DeleteStatus(s);
  return NULL;
}

// A compute function. This will never actually get called in this test, it's
// just nice to know that it compiles.
void compute(void* kernel, TF_OpKernelContext* ctx) {
  TF_Tensor* input;
  TF_Status* s = TF_NewStatus();
  TF_GetInput(ctx, 0, &input, s);
  TF_DeleteTensor(input);
  TF_DeleteStatus(s);
}

// Exercises tensorflow's C API.

// and return "non-ready" handles in `retvals`. Note that any handles contained
// in 'op' should not be mutated till the kernel execution actually finishes.
//
// For sync execution, if any of the inputs to `op` are not ready, this call
// will block till they become ready and then return when the kernel execution
// is done.
// TODO(agarwal): change num_retvals to int from int*.

  // Get a list of the names of functions that have been registered.
  virtual std::vector<string> ListFunctionNames() = 0;

  struct CacheStats {
    int64_t kernel_cache_size;
    int64_t device_cache_size;
    std::map<std::string, int64_t> func_kernel_cache_entries;
    int64_t local_rendezvous_cache_active_size;
  };
  virtual CacheStats GetCacheStats() = 0;