// make sure all nodes are finished.
TF_CAPI_EXPORT extern void TFE_DeleteExecutor(TFE_Executor*);

// Returns true if the executor is in async mode.
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

    **Note:** You can add `--test_sharding_strategy=disabled` to the `flags` to
    disable the sharding so that all the test outputs are in one file. However,
    it may slow down the tests for not running in parallel and may cause the
    test to timeout but it could be useful when you need to execute a single
    test or more in general your filtered/selected tests have a very low
    execution time and the sharding

      // ones_like for variants.
      aid = output_tensor.ZerosLike();
    } else {
      // TODO(allenl): Figure out why using zeros_like everywhere causes issues
      // for some gradient functions and if there's another way to work around
      // it (e.g. conds instead of ifs). The value shouldn't really matter.

                        const int in_flight_nodes_limit)
      : status_(TF_NewStatus()),
        // If the context's default exector is set to async, re-using that in
        // each thread would cause collectives to deadlock. For consistency we
        // create a new sync executor for every thread.
        //
        // TODO(allenl): We should have an async API that works with the
        // parallel device.