dnnl::vanilla_rnn_forward::desc Struct Reference

Descriptor for a vanilla RNN forward propagation primitive. More...

#include <dnnl.hpp>

Collaboration diagram for dnnl::vanilla_rnn_forward::desc:

Public Member Functions
	desc (prop_kind prop_kind, algorithm activation, rnn_direction direction, const memory::desc &src_layer_desc, const memory::desc &src_iter_desc, const memory::desc &weights_layer_desc, const memory::desc &weights_iter_desc, const memory::desc &bias_desc, const memory::desc &dst_layer_desc, const memory::desc &dst_iter_desc, rnn_flags flags=rnn_flags::undef, float alpha=0.0f, float beta=0.0f)
	Constructs a descriptor for a vanilla RNN forward propagation primitive. More...

Detailed Description

Descriptor for a vanilla RNN forward propagation primitive.

Constructor & Destructor Documentation

desc()

dnnl::vanilla_rnn_forward::desc::desc ( prop_kind  prop_kind, algorithm  activation, rnn_direction  direction, const memory::desc &  src_layer_desc, const memory::desc &  src_iter_desc, const memory::desc &  weights_layer_desc, const memory::desc &  weights_iter_desc, const memory::desc &  bias_desc, const memory::desc &  dst_layer_desc, const memory::desc &  dst_iter_desc, rnn_flags  flags = rnn_flags::undef, float  alpha = 0.0f, float  beta = 0.0f  )

inline

Constructs a descriptor for a vanilla RNN forward propagation primitive.

The src_iter_desc, bias_desc, and dst_iter_desc may point to a zero memory descriptor. This would then indicate that the RNN forward propagation primitive should not use them and should default to zero values instead.

Note

All memory descriptors except src_iter_desc can be initialized with an dnnl::memory::format_tag::any value of format_tag.

Inputs:

• src_layer (dnnl::primitive_desc_base::src_desc (0))
• src_iter (dnnl::primitive_desc_base::src_desc (1)), if used
• weights_layer (dnnl::primitive_desc_base::weights_desc (0))
• weights_iter (dnnl::primitive_desc_base::weights_desc (1))
• bias (dnnl::primitive_desc_base::weights_desc (2)), if used

Outputs:

• dst_layer (dnnl::primitive_desc_base::dst_desc (0))
• dst_iter (dnnl::primitive_desc_base::dst_desc (1)), if used
• workspace (dnnl::primitive_desc_base::workspace_desc (0)), if prop_kind equals dnnl::prop_kind::forward_training; must be queried for using dnnl::primitive_desc_base::query_md() after a corresponding primitive descriptor is created

Parameters

prop_kind	Propagation kind. Possible values are dnnl::prop_kind::forward_training, and dnnl::prop_kind::forward_inference.
activation	Activation kind. Possible values are dnnl::algorithm::eltwise_relu, dnnl::algorithm::eltwise_tanh, or dnnl::algorithm::eltwise_logistic.
direction	RNN direction. See dnnl::rnn_direction for more info.
src_layer_desc	Memory descriptor for the input vector.
src_iter_desc	Memory descriptor for the input recurrent hidden state vector.
weights_layer_desc	Memory descriptor for the weights applied to the layer input.
weights_iter_desc	Memory descriptor for the weights applied to the recurrent input.
bias_desc	Bias memory descriptor.
dst_layer_desc	Memory descriptor for the output vector.
dst_iter_desc	Memory descriptor for the output recurrent hidden state vector.
flags	Unused.
alpha	Negative slope if activation is dnnl::algorithm::eltwise_relu.
beta	Unused.

---

The documentation for this struct was generated from the following file:

• include/dnnl.hpp