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.