struct dnnl::primitive_attr

Overview

Primitive attributes. More…

#include <dnnl.hpp>

struct primitive_attr: public dnnl::handle
{
    // construction

    primitive_attr();
    primitive_attr(dnnl_primitive_attr_t attr);

    // methods

    scratchpad_mode get_scratchpad_mode() const;
    void set_scratchpad_mode(scratchpad_mode mode);
    void get_output_scales(int& mask, std::vector<float>& scales) const;
    void set_output_scales(int mask, const std::vector<float>& scales);
    void get_scales(int arg, int& mask, std::vector<float>& scales) const;
    void set_scales(int arg, int mask, const std::vector<float>& scales);
    void get_zero_points(int arg, int& mask, std::vector<int32_t>& zero_points) const;
    void set_zero_points(int arg, int mask, const std::vector<int32_t>& zero_points);
    const post_ops get_post_ops() const;
    void set_post_ops(const post_ops ops);
    void set_rnn_data_qparams(float scale, float shift);
    void get_rnn_data_qparams(float& scale, float& shift);
    void set_rnn_weights_qparams(int mask, const std::vector<float>& scales);
    void get_rnn_weights_qparams(int& mask, std::vector<float>& scales);

    void set_rnn_weights_projection_qparams(
        int mask,
        const std::vector<float>& scales
        );

    void get_rnn_weights_projection_qparams(int& mask, std::vector<float>& scales);
};

Inherited Members

public:
    // methods

    handle<T, traits>& operator = (const handle<T, traits>&);
    handle<T, traits>& operator = (handle<T, traits>&&);
    void reset(T t, bool weak = false);
    T get(bool allow_empty = false) const;
    operator T () const;
    operator bool () const;
    bool operator == (const handle<T, traits>& other) const;
    bool operator != (const handle& other) const;

Detailed Documentation

Primitive attributes.

See also:

Primitive Attributes

Construction

primitive_attr()

Constructs default (empty) primitive attributes.

primitive_attr(dnnl_primitive_attr_t attr)

Creates primitive attributes from a C API dnnl_primitive_attr_t handle.

The resulting handle is not weak and the C handle will be destroyed during the destruction of the C++ object.

Parameters:

attr

The C API primitive attributes.

Methods

scratchpad_mode get_scratchpad_mode() const

Returns the scratchpad mode.

void set_scratchpad_mode(scratchpad_mode mode)

Sets scratchpad mode.

Parameters:

mode

Specified scratchpad mode.

void get_output_scales(int& mask, std::vector<float>& scales) const

Returns output scaling factors correspondence mask and values.

Parameters:

mask

Scaling factors correspondence mask that defines the correspondence between the output tensor dimensions and the scales vector. 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 output scaling factor for the whole output tensor.

scales

Vector of output scaling factors.

void set_output_scales(int mask, const std::vector<float>& scales)

Sets output scaling factors correspondence mask and values.

Example usage:

int mb = 32, oc = 32,
    oh = 14, ow = 14; // convolution output params
// unique output scales per output channel
vector<float> scales = { ... };
int oc_dim = 1; // mb_dim = 0, channel_dim = 1, height_dim = 2, ...

// construct a convolution descriptor
dnnl::convolution::desc conv_d;

dnnl::primitive_attr attr;
attr.set_output_scales(attr, oc, 1 << oc_dim, scales);

dnnl::primitive_desc conv_pd(conv_d, attr, engine);

Note

The order of dimensions does not depend on how elements are laid out in memory. For example:

  • for a 2D CNN activations tensor the order is always (n, c)

  • for a 4D CNN activations tensor the order is always (n, c, h, w)

  • for a 5D CNN weights tensor the order is always (g, oc, ic, kh, kw)

Parameters:

mask

Defines the correspondence between the output tensor dimensions and the scales vector. The set i-th bit indicates that a dedicated scaling factor is used for each index along that dimension. Set the mask to 0 to use a common output scaling factor for the whole output tensor.

scales

Constant vector of output scaling factors. If the scaling factors are known at the time of this call, the following equality must hold: \(scales.size() = \prod\limits_{d \in mask} output.dims[d].\) Violations can only be detected when the attributes are used to create a primitive descriptor. If the scaling factors are not known at the time of the call, this vector must contain a single DNNL_RUNTIME_F32_VAL value and the output scaling factors must be passed at execution time as an argument with index DNNL_ARG_ATTR_OUTPUT_SCALES.

void get_scales(int arg, int& mask, std::vector<float>& scales) const

Returns scaling factors correspondence mask and values for a given memory argument.

Parameters:

arg

Parameter argument index as passed to the primitive::execute() call.

mask

Scaling factors correspondence mask that defines the correspondence between the output tensor dimensions and the scales vector. The set i-th bit indicates that a dedicated scaling factor is used for each index along that dimension. Set the mask to 0 to use a common scaling factor for the whole output tensor.

scales

Output vector of scaling factors.

void set_scales(int arg, int mask, const std::vector<float>& scales)

Sets scaling factors for primitive operations for a given memory argument.

Parameters:

arg

Parameter argument index as passed to the primitive::execute() call.

mask

Scaling factors correspondence mask that defines the correspondence between the tensor dimensions and the scales vector. The set i-th bit indicates that a dedicated scaling factor is used for each index along that dimension. Set the mask to 0 to use a common scaling factor for the whole output tensor.

scales

Constant vector of scaling factors. The following equality must hold: \(scales.size() = \prod\limits_{d \in mask} argument.dims[d].\)

See also:

dnnl_primitive_attr_set_scales

dnnl::primitive_attr::set_output_scales

void get_zero_points(int arg, int& mask, std::vector<int32_t>& zero_points) const

Returns zero points correspondence mask and values.

Parameters:

arg

Parameter argument index as passed to the primitive::execute() call.

mask

Zero points correspondence mask that defines the correspondence between the output tensor dimensions and the zero_points vector. The set i-th bit indicates that a dedicated zero point is used for each index along that dimension. Set the mask to 0 to use a common zero point for the whole output tensor.

zero_points

Output vector of zero points.

void set_zero_points(int arg, int mask, const std::vector<int32_t>& zero_points)

Sets zero points for primitive operations for a given memory argument.

Parameters:

arg

Parameter argument index as passed to the primitive::execute() call.

mask

Zero point correspondence mask that defines the correspondence between the tensor dimensions and the zero_points vector. The set i-th bit indicates that a dedicated zero point is used for each index along that dimension. Set the mask to 0 to use a common zero point for the whole output tensor.

zero_points

Constant vector of zero points. If the zero points are known at the time of this call, the following equality must hold: \(zero\_points.size() = \prod\limits_{d \in mask} argument.dims[d].\) If the zero points are not known at the time of the call, this vector must contain a single DNNL_RUNTIME_S32_VAL value and the zero points must be passed at execution time as an argument with index DNNL_ARG_ATTR_ZERO_POINTS.

See also:

dnnl_primitive_attr_set_zero_points

dnnl::primitive_attr::set_output_scales

const post_ops get_post_ops() const

Returns post-ops previously set via set_post_ops().

Returns:

Post-ops.

void set_post_ops(const post_ops ops)

Sets post-ops.

Note

There is no way to check whether the post-ops would be supported by the target primitive. Any error will be reported by the respective primitive descriptor constructor.

Parameters:

ops

Post-ops object to copy post-ops from.

void set_rnn_data_qparams(float scale, float shift)

Sets quantization scale and shift parameters for RNN data tensors.

For performance reasons, the low-precision configuration of the RNN primitives expect input activations to have the unsigned 8-bit integer data type. The scale and shift parameters are used to quantize floating-point data to unsigned integer and must be passed to the RNN primitive using attributes.

The quantization formula is scale * data + shift.

Example usage:

// RNN parameters
int l = 2, t = 2, mb = 32, sic = 32, slc = 32, dic = 32, dlc = 32;
// Activations quantization parameters
float scale = 63.f, shift = 64.f;

primitive_attr attr;

// Set scale and shift for int8 quantization of activation
attr.set_rnn_data_qparams(scale, shift);

// Create and configure rnn op_desc
vanilla_rnn_forward::desc rnn_d(/* arguments */);
vanilla_rnn_forward::primitive_desc rnn_d(rnn_d, attr, engine);

Note

Quantization scale and shift are common for src_layer, src_iter, dst_iter, and dst_layer.

Parameters:

scale

The value to scale the data by.

shift

The value to shift the data by.

void get_rnn_data_qparams(float& scale, float& shift)

Returns the quantization scale and shift parameters for RNN data tensors.

Note

Quantization scale and shift are common for src_layer, src_iter, dst_iter, and dst_layer.

Parameters:

scale

The value to scale the data by.

shift

The value to shift the data by.

void set_rnn_weights_qparams(int mask, const std::vector<float>& scales)

Sets quantization scaling factors for RNN weights tensors.

The low-precision configuration of the RNN primitives expect input weights to use the signed 8-bit integer data type. The scaling factors are used to quantize floating-point data to signed integer and must be passed to RNN primitives using attributes.

Note

The dimension order is always native and does not depend on the actual layout used. For example, five-dimensional weights always have (l, d, i, g, o) logical dimension ordering.

Note

Quantization scales are common for weights_layer and weights_iteration

Parameters:

mask

Scaling factors correspondence mask that defines the correspondence between the output tensor dimensions and the scales vector. The set i-th bit indicates that a dedicated scaling factor should be used each index along that dimension. Set the mask to 0 to use a common scaling factor for the whole output tensor.

scales

Constant vector of output scaling factors. The following equality must hold: \(scales.size() = \prod\limits_{d \in mask} weights.dims[d].\) Violations can only be detected when the attributes are used to create a primitive descriptor.

void get_rnn_weights_qparams(int& mask, std::vector<float>& scales)

Returns the quantization scaling factors for RNN projection weights tensors.

Note

The dimension order is always native and does not depend on the actual layout used. For example, five-dimensional weights always have (l, d, i, g, o) logical dimension ordering.

Parameters:

mask

Scaling factors correspondence mask that defines the correspondence between the output tensor dimensions and the scales vector. The set i-th bit indicates that a dedicated scaling factor should be used each index along that dimension. Set the mask to 0 to use a common scaling factor for the whole output tensor.

scales

Constant vector of output scaling factors. The following equality must hold: \(scales.size() = \prod\limits_{d \in mask} weights.dims[d].\) Violations can only be detected when the attributes are used to create a primitive descriptor.

void set_rnn_weights_projection_qparams(
    int mask,
    const std::vector<float>& scales
    )

Sets quantization scaling factors for RNN projection weights tensors.

passed to RNN primitives using attributes.

Note

The dimension order is always native and does not depend on the actual layout used. For example, five-dimensional weights always have (l, d, i, g, o) logical dimension ordering.

Note

Quantization scales are common for weights_layer and weights_iteration

Parameters:

mask

Scaling factors correspondence mask that defines the correspondence between the output tensor dimensions and the scales vector. The set i-th bit indicates that a dedicated scaling factor should be used each index along that dimension. Set the mask to 0 to use a common scaling factor for the whole output tensor.

scales

Constant vector of output scaling factors. The following equality must hold: \(scales.size() = \prod\limits_{d \in mask} weights.dims[d].\) Violations can only be detected when the attributes are used to create a primitive descriptor.

void get_rnn_weights_projection_qparams(int& mask, std::vector<float>& scales)

Returns the quantization scaling factors for RNN projection weights tensors.

Note

The dimension order is always native and does not depend on the actual layout used. For example, five-dimensional weights always have (l, d, i, g, o) logical dimension ordering.

Parameters:

mask

Scaling factors correspondence mask that defines the correspondence between the output tensor dimensions and the scales vector. The set i-th bit indicates that a dedicated scaling factor should be used each index along that dimension. Set the mask to 0 to use a common scaling factor for the whole output tensor.

scales

Constant vector of output scaling factors. The following equality must hold: \(scales.size() = \prod\limits_{d \in mask} weights.dims[d].\) Violations can only be detected when the attributes are used to create a primitive descriptor.