#include <dnnl.hpp>

Inheritance diagram for dnnl::post_ops:

Collaboration diagram for dnnl::post_ops:

Public Member Functions
	post_ops ()
	Constructs an empty sequence of post-ops.

int	len () const
	Returns the number of post-ops entries.

primitive::kind	kind (int index) const
	Returns the primitive kind of post-op at entry with a certain index. More...

void	append_sum (float scale=1.)
	Appends an accumulation (sum) post-op. More...

void	get_params_sum (int index, float &scale) const
	Returns the parameters of an accumulation (sum) post-op. More...

void	append_eltwise (float scale, algorithm algorithm, float alpha, float beta)
	Appends an elementwise post-op. More...

void	get_params_eltwise (int index, float &scale, algorithm &algorithm, float &alpha, float &beta) const
	Returns parameters of an elementwise post-up. More...

void	append_dw_k3s1p1 (memory::data_type weights_data_type, memory::data_type bias_data_type, memory::data_type dst_data_type, int mask, const std::vector< float > &scales)
	Appends a depthwise post-op convolution with stride 1. More...

void	get_params_dw_k3s1p1 (int index, memory::data_type &weights_data_type, memory::data_type &bias_data_type, memory::data_type &dst_data_type, int &mask, std::vector< float > &scales) const
	Returns the parameters of an depthwise post-op with stride 1. More...

void	append_dw_k3s2p1 (memory::data_type weights_data_type, memory::data_type bias_data_type, memory::data_type dst_data_type, int mask, const std::vector< float > &scales)
	Appends a depthwise post-op convolution with stride 2. More...

void	get_params_dw_k3s2p1 (int index, memory::data_type &weights_data_type, memory::data_type &bias_data_type, memory::data_type &dst_data_type, int &mask, std::vector< float > &scales) const
	Returns the parameters of an depthwise post-op with stride 2. More...

Public Member Functions inherited from dnnl::handle< dnnl_post_ops_t >
bool	operator== (const handle< dnnl_post_ops_t, handle_traits< dnnl_post_ops_t > > &other) const
	Equality operator. More...

bool	operator!= (const handle &other) const
	Inequality operator. More...

	handle ()=default
	Constructs an empty handle object. More...

	handle (const handle< dnnl_post_ops_t, handle_traits< dnnl_post_ops_t > > &)=default
	Copy constructor.

	handle (handle< dnnl_post_ops_t, handle_traits< dnnl_post_ops_t > > &&)=default
	Move constructor.

	handle (dnnl_post_ops_t t, bool weak=false)
	Constructs a handle wrapper object from a C API handle. More...

handle< dnnl_post_ops_t, handle_traits< dnnl_post_ops_t > > &	operator= (const handle< dnnl_post_ops_t, handle_traits< dnnl_post_ops_t > > &)=default
	Assignment operator.

handle< dnnl_post_ops_t, handle_traits< dnnl_post_ops_t > > &	operator= (handle< dnnl_post_ops_t, handle_traits< dnnl_post_ops_t > > &&)=default
	Move assignment operator.

void	reset (dnnl_post_ops_t t, bool weak=false)
	Resets the handle wrapper objects to wrap a new C API handle. More...

dnnl_post_ops_t	get (bool allow_empty=false) const
	Returns the underlying C API handle. More...

	operator dnnl_post_ops_t () const
	Converts a handle to the underlying C API handle type. More...

	operator bool () const
	Checks whether the object is empty. More...

Detailed Description

Post-ops.

Post-ops are computations executed after the main primitive computations and are attached to the primitive via primitive attributes.

See also: Primitive Attributes: Post-ops

Examples:: cnn_inference_int8.cpp, cpu_sgemm_and_matmul.cpp, inference_int8_matmul.cpp, and performance_profiling.cpp.

Member Function Documentation

◆ kind()

primitive::kind dnnl::post_ops::kind ( int index ) const

inline

Returns the primitive kind of post-op at entry with a certain index.

Parameters

index Index of the post-op to return the kind for.

Returns: Primitive kind of the post-op at the specified index.

◆ append_sum()

void dnnl::post_ops::append_sum ( float scale = 1. )

inline

Appends an accumulation (sum) post-op.

Prior to accumulating the result, the previous value would be multiplied by a scaling factor scale.

The kind of this post-op is dnnl::primitive::kind::sum.

This feature may improve performance for cases like residual learning blocks, where the result of convolution is accumulated to the previously computed activations. The parameter scale may be used for the integer-based computations when the result and previous activations have different logical scaling factors.

In the simplest case when the accumulation is the only post-op, the computations would be:

dst[:] <- scale * dst[:] + op(...) // instead of dst[:] <- op(...)

Note: This post-op executes in-place and does not change the destination layout.

Parameters

scale Scaling factor.

Examples:: cpu_sgemm_and_matmul.cpp.

◆ get_params_sum()

void dnnl::post_ops::get_params_sum	(	int	index,
		float &	scale
	)		const

inline

Returns the parameters of an accumulation (sum) post-op.

Parameters

index	Index of the sum post-op.
scale	Scaling factor of the sum post-op.

◆ append_eltwise()

void dnnl::post_ops::append_eltwise	(	float	scale,
		algorithm	algorithm,
		float	alpha,
		float	beta
	)

inline

Appends an elementwise post-op.

The kind of this post-op is dnnl::primitive::kind::eltwise.

In the simplest case when the elementwise is the only post-op, the computations would be:

dst[:] <- scale * eltwise_op (op(...)) // instead of dst[:] <- op(...)

where eltwise_op is configured with the given parameters.

Parameters

scale	Scaling factor.
algorithm	Elementwise algorithm.
alpha	Alpha parameter for the elementwise algorithm.
beta	Beta parameter for the elementwise algorithm.

Examples:: cnn_inference_int8.cpp, inference_int8_matmul.cpp, and performance_profiling.cpp.

◆ get_params_eltwise()

void dnnl::post_ops::get_params_eltwise	(	int	index,
		float &	scale,
		algorithm &	algorithm,
		float &	alpha,
		float &	beta
	)		const

inline

Returns parameters of an elementwise post-up.

Parameters

index	Index of the post-op.
scale	Output scaling factor.
algorithm	Output elementwise algorithm kind.
alpha	Output alpha parameter for the elementwise algorithm.
beta	Output beta parameter for the elementwise algorithm.

◆ append_dw_k3s1p1()

void dnnl::post_ops::append_dw_k3s1p1	(	memory::data_type	weights_data_type,
		memory::data_type	bias_data_type,
		memory::data_type	dst_data_type,
		int	mask,
		const std::vector< float > &	scales
	)

inline

Appends a depthwise post-op convolution with stride 1.

This post-op can only be fused with a 2D 1x1 convolution (convolution with weights spatial dimension equal to 1 i.e., kh=kw=1).

The kind of this post-op is dnnl_convolution.

The number of outputs for primitive remain same as before. The output size remain same as the original primitive due to stride=1.

The Post-op can be defined as:

 dst[:] <- scales * (conv_dw(conv_1x1))

See dev_guide_attributes_post_ops_depthwise and dev_guide_attributes_post_ops_depthwise_fusion for more info.

Parameters

weights_data_type	Weights data type of depthwise post-op
bias_data_type	Bias data type of depthwise post-op
dst_data_type	Output data type of depthwise post-op
mask	Output scaling factors correspondence mask that defines the correspondence between the output tensor dimensions and the `scales` array. The set i-th bit indicates that a dedicated output scaling factor is used for each index along that dimension. The mask value of 0 implies a common scaling factor for the whole output tensor.
scales	Output pointer to a constant array of float scaling factors.

◆ get_params_dw_k3s1p1()

void dnnl::post_ops::get_params_dw_k3s1p1	(	int	index,
		memory::data_type &	weights_data_type,
		memory::data_type &	bias_data_type,
		memory::data_type &	dst_data_type,
		int &	mask,
		std::vector< float > &	scales
	)		const

inline

Returns the parameters of an depthwise post-op with stride 1.

Parameters

index	Index of the elementwise post-op.
weights_data_type	Weights data type of depthwise post-op
bias_data_type	Bias data type of depthwise post-op
dst_data_type	Output data type of depthwise post-op
mask	Output scaling factors correspondence mask that defines the correspondence between the output tensor dimensions and the `scales` array. The set i-th bit indicates that a dedicated output scaling factor is used for each index along that dimension. The mask value of 0 implies a common scaling factor for the whole output tensor.
scales	Output pointer to a constant array of float scaling factors.

◆ append_dw_k3s2p1()

void dnnl::post_ops::append_dw_k3s2p1	(	memory::data_type	weights_data_type,
		memory::data_type	bias_data_type,
		memory::data_type	dst_data_type,
		int	mask,
		const std::vector< float > &	scales
	)

inline

Appends a depthwise post-op convolution with stride 2.

This post-op can only be fused with a 2D 1x1 convolution (convolution with weights spatial dimension equal to 1 i.e., kh=kw=1).

The kind of this post-op is dnnl_convolution.

The number of outputs for primitive remain same as before. The output spatial size can be derived as below:

output_height = ceil(output_height_1x1_convolution, stride) output_width = ceil(output_width_1x1_convolution, stride)

The Post-op can be defined as:

 dst[:] <- scales * (conv_dw(conv_1x1))

See dev_guide_attributes_post_ops_depthwise and dev_guide_attributes_post_ops_depthwise_fusion for more info.

Parameters

weights_data_type	Weights data type of depthwise post-op
bias_data_type	Bias data type of depthwise post-op
dst_data_type	Output data type of depthwise post-op
mask	Output scaling factors correspondence mask that defines the correspondence between the output tensor dimensions and the `scales` array. The set i-th bit indicates that a dedicated output scaling factor is used for each index along that dimension. The mask value of 0 implies a common scaling factor for the whole output tensor.
scales	Output pointer to a constant array of float scaling factors.

Returns: dnnl_success on success and a status describing the error otherwise

◆ get_params_dw_k3s2p1()

void dnnl::post_ops::get_params_dw_k3s2p1	(	int	index,
		memory::data_type &	weights_data_type,
		memory::data_type &	bias_data_type,
		memory::data_type &	dst_data_type,
		int &	mask,
		std::vector< float > &	scales
	)		const

inline

Returns the parameters of an depthwise post-op with stride 2.

Parameters

index	Index of the elementwise post-op.
weights_data_type	Weights data type of depthwise post-op
bias_data_type	Bias data type of depthwise post-op
dst_data_type	Output data type of depthwise post-op
mask	Output scaling factors correspondence mask that defines the correspondence between the output tensor dimensions and the `scales` array. The set i-th bit indicates that a dedicated output scaling factor is used for each index along that dimension. The mask value of 0 implies a common scaling factor for the whole output tensor.
scales	Output pointer to a constant array of float scaling factors.

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

include/dnnl.hpp

Public Member Functions

Detailed Description

Member Function Documentation

◆ kind()

◆ append_sum()

◆ get_params_sum()

◆ append_eltwise()

◆ get_params_eltwise()

◆ append_dw_k3s1p1()

◆ get_params_dw_k3s1p1()

◆ append_dw_k3s2p1()

◆ get_params_dw_k3s2p1()