#include "tensorflow/c/eager/gradients.h"
#include "tensorflow/c/eager/unified_api_testutil.h"
#include "tensorflow/c/experimental/ops/math_ops.h"
#include "tensorflow/c/tf_status_helper.h"
#include "tensorflow/core/platform/errors.h"
#include "tensorflow/core/platform/test.h"

namespace tensorflow {
namespace gradients {
namespace internal {
namespace {
using std::vector;

#include "tensorflow/c/eager/unified_api_testutil.h"
#include "tensorflow/c/experimental/gradients/grad_test_helper.h"
#include "tensorflow/c/experimental/gradients/tape/tape_context.h"
#include "tensorflow/c/experimental/ops/math_ops.h"
#include "tensorflow/c/tf_status_helper.h"
#include "tensorflow/core/platform/tensor_float_32_utils.h"
#include "tensorflow/core/platform/test.h"

namespace tensorflow {

#include <sys/mman.h>
#include <sys/stat.h>
#include <unistd.h>

#include "tensorflow/c/experimental/filesystem/filesystem_interface.h"
#include "tensorflow/c/experimental/filesystem/plugins/posix/posix_filesystem_helper.h"
#include "tensorflow/c/tf_file_statistics.h"
#include "tensorflow/c/tf_status.h"

// Implementation of a filesystem for POSIX environments.
// This filesystem will support `file://` and empty (local) URI schemes.

  // scheduled on that same threadpool, causing a deadlock in cases where the
  // caller of event_mgr->ThenExecute() blocks on the completion of the callback
  // (as in the case of ConstOp kernel creation on GPU, which involves copying a
  // CPU tensor to GPU).
  // Setting a larger thread pool does not help with the Swift caller, as we use
  // a different TFE context for each thread of execution (for running graph

  // Fetches the current Jacobian-vector product associated with `tensor_id`, or
  // a nullptr if none is available.
  //
  // Returns a borrowed reference, i.e. does not run VSpace::MarkAsResult on its
  // return value. The caller should increment the reference count before
  // deleting the ForwardAccumulator or calling DeleteGradient if keeping a
  // persistent reference to a non-null result.
  Gradient* FetchJVP(int64_t tensor_id);

# BEGIN TF CACHE HELPER OPTIONS
# Options when using remote execution
# WARNING: THESE OPTIONS WONT WORK IF YOU DO NOT HAVE PROPER AUTHENTICATION AND PERMISSIONS

# Use --config=tf_public_cache to try and use the TensorFlow public build cache

    # but this also hurts the performance. Let users decide what they want.
    write_to_bazelrc('build --define=override_eigen_strong_inline=true')


def config_info_line(name, help_text):
  """Helper function to print formatted help text for Bazel config options."""
  print('\t--config=%-12s\t# %s' % (name, help_text))


def configure_ios(environ_cp):
  """Configures TensorFlow for iOS builds."""

  // before `StartExecute` is called again. Using `StartExecute` with `Join`
  // allows the caller to schedule computation on multiple ParallelDevices
  // without sequencing those operations (first call `StartExecute` on each
  // parallel device, then call `Join` on each; even if some of the `Join`s
  // return a bad status the caller must run all of the `Join`s or any future
  // `StartExecute`s will deadlock).
  //

                                        TF_Status* status);

// Helper to un-pack `num_replicas` TFE_TensorHandles from one parallel handle.
template <std::size_t num_replicas>
void ExtractPerDeviceValues(
    TFE_Context* context, TFE_TensorHandle* input,
    std::array<TensorHandlePtr, num_replicas>* components, TF_Status* status);

// Helper to pack `num_replicas` TFE_TensorHandles into one parallel handle.

// temporary storage. You can iterate through the list with TF_StringStreamNext.
// The caller is responsible for freeing the list (see TF_StringStreamDone).
TF_CAPI_EXPORT extern TF_StringStream* TF_GetLocalTempDirectories(void);

// Creates a temporary file name with an extension.
// The caller is responsible for freeing the returned pointer.
TF_CAPI_EXPORT extern char* TF_GetTempFileName(const char* extension);