// Returns the number of elements in dimension `dim_index`.
// Tensor representation on device can be transposed from its representation
// on host. The data contained in dimension `dim_index` on device
// can correspond to the data contained in another dimension in on-host
// representation. The dimensions are indexed using the standard TensorFlow
// major-to-minor order (slowest varying dimension first),

        // broadcast, i.e. set as the input to each parallel operation. This
        // allows code like "tf.constant(1.)" or "tf.reduce_sum(..., axis=1)"
        // (where the value starts on the host), without allowing other implicit
        // copies/broadcasts. Other implicit copies may be supported eventually,
        // but need special handling for gradients (gradient of copy-on is not

    CHECK_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
    TFE_TensorHandle* on_host =
        TFE_TensorHandleCopyToDevice(copy_aliased, ctx, "CPU:0", status);
    CHECK_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
    TF_Tensor* resolved = TFE_TensorHandleResolve(on_host, status);
    CHECK_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
    const float* resolved_data =

+      __attribute_nonstring__;	/* Devicename.  */
+    char ut_user[UT_NAMESIZE]
+      __attribute_nonstring__;	/* Username.  */
 #define ut_name ut_user
-    char ut_host[UT_HOSTSIZE];
+    char ut_host[UT_HOSTSIZE]
+      __attribute_nonstring__;	/* Hostname for remote login.  */
     long int ut_time;
   };
 
diff --git a/misc/sys/cdefs.h b/misc/sys/cdefs.h
index 30482a1..551d5fd 100644
--- a/misc/sys/cdefs.h
+++ b/misc/sys/cdefs.h

*   Include unit tests when you contribute new features, as they help to a)
    prove that your code works correctly, and b) guard against future breaking
    changes to lower the maintenance cost.
*   Bug fixes also generally require unit tests, because the presence of bugs
    usually indicates insufficient test coverage.
*   Keep API compatibility in mind when you change code in core TensorFlow,
    e.g., code in

  TF_TriState constant_folding;
  TF_TriState shape_optimization;
  TF_TriState auto_mixed_precision;
  TF_TriState auto_mixed_precision_onednn_bfloat16;
  TF_TriState auto_mixed_precision_mkl;
  TF_TriState pin_to_host_optimization;
  TF_TriState layout_optimizer;
  TF_TriState remapping;
  TF_TriState loop_optimization;
  TF_TriState dependency_optimization;
  TF_TriState auto_parallel;
  TF_TriState memory_optimization;

    int num_dims, void* data, size_t len,
    void (*deallocator)(void* data, size_t len, void* arg),
    void* deallocator_arg, TF_Status* status);

// Retrieves the address space (i.e. job, replia, task) of the local host and
// saves it in the buffer.
TF_CAPI_EXPORT extern void TFE_HostAddressSpace(TFE_Context* ctx,
                                                TF_Buffer* buf);

  CONFIG_TOGGLE(shape_optimization);
  CONFIG_TOGGLE(auto_mixed_precision);
  CONFIG_TOGGLE(auto_mixed_precision_onednn_bfloat16);
  CONFIG_TOGGLE(auto_mixed_precision_mkl);
  CONFIG_TOGGLE(pin_to_host_optimization);
  CONFIG_TOGGLE(layout_optimizer);
  CONFIG_TOGGLE(remapping);
  CONFIG_TOGGLE(loop_optimization);
  CONFIG_TOGGLE(dependency_optimization);
  CONFIG_TOGGLE(auto_parallel);

  DEVICE_PLACEMENT_EXPLICIT = 0,
  // Copy the tensor to the right device but log a warning.
  DEVICE_PLACEMENT_WARN = 1,
  // Silently copy the tensor, which has a performance cost since the operation
  // will be blocked till the copy completes. This is the default policy.
  DEVICE_PLACEMENT_SILENT = 2,
  // Placement policy which silently copies int32 tensors but not other dtypes.

  BlockMap block_map_ ABSL_GUARDED_BY(mu_);

  /// The LRU list of block keys. The front of the list identifies the most
  /// recently accessed block.
  std::list<Key> lru_list_ ABSL_GUARDED_BY(mu_);

  /// The LRA (least recently added) list of block keys. The front of the list
  /// identifies the most recently added block.
  ///
  /// Note: blocks are added to lra_list_ only after they have successfully been