const std::function<void(BackwardFunction*)>& backward_function_deleter);

  void DeleteTrace(int64_t tensor_id);

  // Consumes the internal state of the tape (so cannot be called more than
  // once) and produces the gradient of the target tensors with respect to the
  // source tensors. The output gradients are used if not empty and not
  // null. The result is populated with one tensor per target element.

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);

@@ -748,27 +422,11 @@ __stpcpy_small (char *__dest,
   }
   return __dest + __srclen - 1;
 }
-#   endif
 #  endif
 # endif
 #endif
 
 
-/* Copy no more than N characters of SRC to DEST.  */
-#ifndef _HAVE_STRING_ARCH_strncpy
-# if __GNUC_PREREQ (3, 2)
-#  define strncpy(dest, src, n) __builtin_strncpy (dest, src, n)
-# else
-#  define strncpy(dest, src, n) \

  // less synchronization than a thread pool would for this task, since Execute
  // acquires each thread in order (and so only one Execute will schedule
  // blocking collective operations at a time), and avoids some dynamic
  // allocation/scheduling.
  //
  // TODO(allenl): Keep a map from outer thread to list of inner threads rather
  // than a single list of threads so aliased nested parallel devices don't

  CHECK(tensorflow::protobuf::TextFormat::ParseFromString(
      VariableAddFunctionSignature(), &def));
  return def.SerializeAsString();
}

// A graph optimization pass that would fail when triggered for more than once.
class GraphErrorInjectionPass : public tensorflow::GraphOptimizationPass {
 public:
  static bool enabled_;
  GraphErrorInjectionPass() {}

  tensorflow::Status Run(

          f'Bazel invocations.\n'
          f'ResultStore contains individual representations of each target '
          f'that were run/built during the invocation.\n'
          f'These results are generally easier to read than looking through '
          f'the entire build log:\n')
  i = 1
  for url, invocation_results in result_store_dict.items():
    line_str = f'Invocation #{i} ({invocation_results["status"]}):\n'

#include "tensorflow/c/eager/c_api.h"
#include "tensorflow/c/eager/c_api_experimental.h"
#include "tensorflow/core/platform/test.h"

// NOTE(allenl): These tests currently go through TFE_Execute and so are
// integration testing rather than purely testing the parallel device. They
// correspond fairly well to the implementation, but testing the C++ directly is
// another option.

namespace tensorflow {
namespace parallel_device {

      auto& indices = iter->second;
      if (std::find(indices.begin(), indices.end(), idx) != indices.end()) {
        return InvalidArgument("TF_Output ", node->name(), ":", idx,
                               " appears more than once in the input list");
      }
      indices.push_back(idx);
    }
  }
  return absl::OkStatus();
}

// Converts `noutputs` and `outputs` into `outputs_tensors` and does various
// checks while doing so.

#include "tensorflow/core/lib/core/status_test_util.h"
#include "tensorflow/core/platform/test.h"

// NOTE(allenl): These tests currently go through TFE_Execute and so are
// integration testing rather than purely testing the parallel device. They
// correspond fairly well to the implementation, but testing the C++ directly is
// another option.

namespace tensorflow {
namespace parallel_device {