// 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

  // finished, if any.
  //
  // `cancellation_manager` must live until after `Join` finishes and pending
  // `is_async` operations finish. In addition to allowing the caller to cancel
  // the operation, its `StartCancel` method will be called if op execution
  // fails on any device in order to cancel the others.
  void StartExecute(TFE_Context* context, const char* operation_name,

#include <random>

#include "absl/strings/string_view.h"
#include "tensorflow/c/tf_status_helper.h"
#include "tensorflow/core/platform/path.h"
#include "tensorflow/core/platform/stacktrace_handler.h"
#include "tensorflow/core/platform/test.h"

#define ASSERT_TF_OK(x) ASSERT_EQ(TF_OK, TF_GetCode(x)) << TF_Message(x)
#define EXPECT_TF_OK(x) EXPECT_EQ(TF_OK, TF_GetCode(x)) << TF_Message(x)

}

// Registers filesystem at `index`, if plugin is providing valid information.
//
// Extracted to a separate function so that pointers inside `info` are freed
// by the caller regardless of whether validation/registration failed or not.
//
// Must be called only with `index` a valid index in `info->ops`.
static Status ValidateAndRegisterFilesystems(

#include "tensorflow/core/common_runtime/eager/context.h"
#include "tensorflow/core/common_runtime/eager/custom_device.h"
#include "tensorflow/core/common_runtime/eager/custom_device_op_handler.h"
#include "tensorflow/core/common_runtime/eager/execute.h"
#include "tensorflow/core/common_runtime/eager/placement_utils.h"
#include "tensorflow/core/common_runtime/eager/tensor_handle.h"

  std::vector<std::unique_ptr<Thread>> threads;
  threads.reserve(callers);
  for (int i = 0; i < callers; i++) {
    threads.emplace_back(
        Env::Default()->StartThread({}, "caller", [block_size, &cache, i]() {
          std::vector<char> out;
          TF_EXPECT_OK(
              ReadCache(&cache, "a", i * block_size, block_size, &out));
          std::vector<char> x(block_size, 'x');