Contents

enum dnnl_graph_tensor_property_t

Overview

Logical tensor property. More…

#include <dnnl_graph_types.h>

enum dnnl_graph_tensor_property_t
{
    dnnl_graph_tensor_property_undef       = 0,
    dnnl_graph_tensor_property_variable    = 1,
    dnnl_graph_tensor_property_constant    = 2,
    dnnl_graph_tensor_property_host_scalar = 3,
};

Detailed Documentation

Logical tensor property.

Enum Values

dnnl_graph_tensor_property_undef

Undefined tensor property.

dnnl_graph_tensor_property_variable

Variable means the tensor may be changed during computation or between different iterations.

dnnl_graph_tensor_property_constant

Constant means the tensor will keep unchanged during computation and between different iterations.

It’s useful for the library to apply optimizations for constant tensors or cache constant tensors inside the library. For example, constant weight tensors in inference scenarios.

dnnl_graph_tensor_property_host_scalar

Host scalar means the tensor will be a 0-D scalar tensor on host.

It should be used with a CPU engine when creating the tensor.

enum dnnl_graph_layout_type_t struct dnnl_graph_logical_tensor_t