.. index:: pair: struct; dnnl::primitive_attr .. _doxid-structdnnl_1_1primitive__attr: struct dnnl::primitive_attr =========================== .. toctree:: :hidden: Overview ~~~~~~~~ Primitive attributes. :ref:`More...` .. ref-code-block:: cpp :class: doxyrest-overview-code-block #include struct primitive_attr: public :ref:`dnnl::handle` { // construction :ref:`primitive_attr`(); :ref:`primitive_attr`(:ref:`dnnl_primitive_attr_t` attr); // methods void :ref:`get_dropout`(:ref:`memory::desc`& mask_desc) const; void :ref:`get_dropout`( :ref:`memory::desc`& mask_desc, :ref:`memory::data_type`& seed_dt, bool& use_offset, bool& use_host_scalars ) const; void :ref:`set_dropout`(const :ref:`memory::desc`& mask_desc); void :ref:`set_dropout`( const :ref:`memory::desc`& mask_desc, :ref:`memory::data_type` seed_dt, bool use_offset, bool use_host_scalars ); :ref:`fpmath_mode` :ref:`get_fpmath_mode`() const; void :ref:`get_fpmath_mode`(:ref:`fpmath_mode`& mode, bool& apply_to_int) const; void :ref:`set_fpmath_mode`(:ref:`fpmath_mode` mode, bool apply_to_int = false); :ref:`accumulation_mode` :ref:`get_accumulation_mode`() const; void :ref:`set_accumulation_mode`(:ref:`accumulation_mode` mode); bool :ref:`get_deterministic`() const; void :ref:`set_deterministic`(bool value); :ref:`rounding_mode` :ref:`get_rounding_mode`(int arg) const; void :ref:`set_rounding_mode`(int arg, :ref:`rounding_mode` mode); :ref:`scratchpad_mode` :ref:`get_scratchpad_mode`() const; void :ref:`set_scratchpad_mode`(:ref:`scratchpad_mode` mode); void :ref:`set_scales_mask`(int arg, int mask); void :ref:`set_scales`( int arg, int mask, const :ref:`memory::dims`& groups, :ref:`memory::data_type` data_type = :ref:`memory::data_type::f32`, bool is_on_host = false, :ref:`quantization_mode` qmode = :ref:`quantization_mode::static_sazp` ); void :ref:`set_host_scale`( int arg, :ref:`memory::data_type` data_type = :ref:`memory::data_type::f32` ); void :ref:`set_zero_points_mask`(int arg, int mask); void :ref:`set_zero_points`( int arg, int mask, const :ref:`memory::dims`& groups, :ref:`memory::data_type` data_type = :ref:`memory::data_type::s32`, bool is_on_host = false ); void :ref:`set_host_zero_point`( int arg, :ref:`memory::data_type` data_type = :ref:`memory::data_type::s32` ); void :ref:`set_precomputed_reductions`( int arg, int mask, const :ref:`memory::dims`& groups, :ref:`memory::data_type` data_type = :ref:`memory::data_type::s32` ); :ref:`post_ops` :ref:`get_post_ops`() const; void :ref:`set_post_ops`(const :ref:`post_ops`& ops); void :ref:`set_rnn_data_qparams`(float scale, float shift); void :ref:`get_rnn_data_qparams`(float& scale, float& shift); void :ref:`set_rnn_weights_qparams`(int mask, const std::vector& scales); void :ref:`get_rnn_weights_qparams`(int& mask, std::vector& scales); void :ref:`set_rnn_weights_projection_qparams`( int mask, const std::vector& scales ); void :ref:`get_rnn_weights_projection_qparams`(int& mask, std::vector& scales); }; Inherited Members ----------------- .. ref-code-block:: cpp :class: doxyrest-overview-inherited-code-block public: // methods :ref:`handle`& :ref:`operator =` (const :ref:`handle`&); :ref:`handle`& :ref:`operator =` (:ref:`handle`&&); void :ref:`reset`(T t, bool weak = false); T :ref:`get`(bool allow_empty = false) const; :ref:`operator T` () const; :ref:`operator bool` () const; bool :ref:`operator ==` (const :ref:`handle`& other) const; bool :ref:`operator !=` (const :ref:`handle`& other) const; protected: // methods bool :ref:`operator ==` (const T other) const; bool :ref:`operator !=` (const T other) const; .. _details-structdnnl_1_1primitive__attr: Detailed Documentation ~~~~~~~~~~~~~~~~~~~~~~ Primitive attributes. .. rubric:: See also: :ref:`Primitive Attributes ` Construction ------------ .. index:: pair: function; primitive_attr .. _doxid-structdnnl_1_1primitive__attr_1acfbfd85b7ca82bf97e2b07c2427427de: .. ref-code-block:: cpp :class: doxyrest-title-code-block primitive_attr() Constructs default (empty) primitive attributes. .. index:: pair: function; primitive_attr .. _doxid-structdnnl_1_1primitive__attr_1aafb54e73f3abe59555f1cfe62407280e: .. ref-code-block:: cpp :class: doxyrest-title-code-block primitive_attr(:ref:`dnnl_primitive_attr_t` attr) Creates primitive attributes from a C API :ref:`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. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - attr - The C API primitive attributes. Methods ------- .. index:: pair: function; get_dropout .. _doxid-structdnnl_1_1primitive__attr_1a2f037ab4ec2520d9a0b12777b30522d6: .. ref-code-block:: cpp :class: doxyrest-title-code-block void get_dropout(:ref:`memory::desc`& mask_desc) const Returns the parameters of a dropout attribute. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - mask_desc - Output memory descriptor for dropout masks. If a default memory descriptor is returned, the mask values will not be written to the output memory buffer during the primitive execution. .. index:: pair: function; get_dropout .. _doxid-structdnnl_1_1primitive__attr_1a10b9f24b2bada56db20e97abde158106: .. ref-code-block:: cpp :class: doxyrest-title-code-block void get_dropout( :ref:`memory::desc`& mask_desc, :ref:`memory::data_type`& seed_dt, bool& use_offset, bool& use_host_scalars ) const Returns the parameters of a dropout attribute. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - mask_desc - Output memory descriptor for dropout masks. If a default memory descriptor is returned, the mask values will not be written to the output memory buffer during the primitive execution. * - seed_dt - Output datatype for seed argument. * - use_offset - Output boolean. If true, an offset argument must be passed at the execution and will be used in random number generation. * - use_host_scalars - Output boolean. If true, probability, seed and offset arguments are passed as host_scalar memory objects. .. index:: pair: function; set_dropout .. _doxid-structdnnl_1_1primitive__attr_1abe989b6c932434a755bade257d299755: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_dropout(const :ref:`memory::desc`& mask_desc) Sets dropout probability. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - mask_desc - Memory descriptor for dropout masks. If a default memory descriptor is passed, the mask values will not be written to the output memory buffer during the primitive execution. .. index:: pair: function; set_dropout .. _doxid-structdnnl_1_1primitive__attr_1aaa48c660f55da2225941943478d334b0: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_dropout( const :ref:`memory::desc`& mask_desc, :ref:`memory::data_type` seed_dt, bool use_offset, bool use_host_scalars ) Sets dropout probability. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - mask_desc - Memory descriptor for dropout masks. If a default memory descriptor is passed, the mask values will not be written to the output memory buffer during the primitive execution. * - seed_dt - Datatype for seed argument. * - use_offset - If true, an offset argument must be passed at the execution and will be used in random number generation. * - use_host_scalars - If true, probability, seed and offset arguments are passed as host_scalar memory objects. .. index:: pair: function; get_fpmath_mode .. _doxid-structdnnl_1_1primitive__attr_1af335f8e1e74b69c5b2d4da0ecf8a23d5: .. ref-code-block:: cpp :class: doxyrest-title-code-block :ref:`fpmath_mode` get_fpmath_mode() const Returns the fpmath mode. .. index:: pair: function; get_fpmath_mode .. _doxid-structdnnl_1_1primitive__attr_1a4c5566628d4c893a321a8f053a5cc5fd: .. ref-code-block:: cpp :class: doxyrest-title-code-block void get_fpmath_mode(:ref:`fpmath_mode`& mode, bool& apply_to_int) const Returns the fpmath mode .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - mode - Specified fpmath mode. * - apply_to_int - Use floating-point arithmetic for integer primitives. .. index:: pair: function; set_fpmath_mode .. _doxid-structdnnl_1_1primitive__attr_1ab00639157a283596834ee5b0e8478a2d: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_fpmath_mode(:ref:`fpmath_mode` mode, bool apply_to_int = false) Sets fpmath mode. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - mode - Specified fpmath mode. * - apply_to_int - Boolean. Use of floating-point arithmetic for integer primitives. .. index:: pair: function; get_accumulation_mode .. _doxid-structdnnl_1_1primitive__attr_1a054e1d0097e9e85411cfb539bd45e247: .. ref-code-block:: cpp :class: doxyrest-title-code-block :ref:`accumulation_mode` get_accumulation_mode() const Returns the accumulation mode. .. index:: pair: function; set_accumulation_mode .. _doxid-structdnnl_1_1primitive__attr_1a8348fcd2259553c3537194430b7de4f4: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_accumulation_mode(:ref:`accumulation_mode` mode) Sets accumulation mode. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - mode - Specified accumulation mode. .. index:: pair: function; get_deterministic .. _doxid-structdnnl_1_1primitive__attr_1a29e003998b46762e5fa0532844ca12c4: .. ref-code-block:: cpp :class: doxyrest-title-code-block bool get_deterministic() const Returns the deterministic attribute value. .. index:: pair: function; set_deterministic .. _doxid-structdnnl_1_1primitive__attr_1ad4c1ea7156ce31cd231a00d4e3399add: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_deterministic(bool value) Sets deterministic attribute value .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - value - Specified deterministic mode. .. index:: pair: function; get_rounding_mode .. _doxid-structdnnl_1_1primitive__attr_1a28c514670e3e1f4678000af6a6655fcf: .. ref-code-block:: cpp :class: doxyrest-title-code-block :ref:`rounding_mode` get_rounding_mode(int arg) const Returns the rounding mode attribute value .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - arg - Argument for which rounding mode query applies. .. rubric:: Returns: The rounding mode applied to the specified argument. .. index:: pair: function; set_rounding_mode .. _doxid-structdnnl_1_1primitive__attr_1ad303ce73cb473dc552ed96cad07d8d9e: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_rounding_mode(int arg, :ref:`rounding_mode` mode) Sets the rounding mode attribute value for a given argument .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - arg - Argument for which to set rounding mode. * - mode - Rounding mode to apply. .. index:: pair: function; get_scratchpad_mode .. _doxid-structdnnl_1_1primitive__attr_1af4131b946ec3af3bc2974b603d30029b: .. ref-code-block:: cpp :class: doxyrest-title-code-block :ref:`scratchpad_mode` get_scratchpad_mode() const Returns the scratchpad mode. .. index:: pair: function; set_scratchpad_mode .. _doxid-structdnnl_1_1primitive__attr_1a91a597649afa13b7d2416b708d0620d2: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_scratchpad_mode(:ref:`scratchpad_mode` mode) Sets scratchpad mode. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - mode - Specified scratchpad mode. .. index:: pair: function; set_scales_mask .. _doxid-structdnnl_1_1primitive__attr_1ac3dc9efa6702a5eba6f289f1b3907590: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_scales_mask(int arg, int mask) Sets scaling factors for primitive operations for a given memory argument. The scaling factors must be passed at execution time as an argument with index :ref:`DNNL_ARG_ATTR_SCALES ` \| arg. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - arg - Parameter argument index as passed to the :ref:`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. .. rubric:: See also: :ref:`dnnl_primitive_attr_set_scales_mask ` .. index:: pair: function; set_scales .. _doxid-structdnnl_1_1primitive__attr_1a35152c75fb7d3e44aa7e51e9ac25c3b0: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_scales( int arg, int mask, const :ref:`memory::dims`& groups, :ref:`memory::data_type` data_type = :ref:`memory::data_type::f32`, bool is_on_host = false, :ref:`quantization_mode` qmode = :ref:`quantization_mode::static_sazp` ) Sets primitive attributes scaling factors for a given memory argument. The scaling factors must be passed at execution time as an argument with index :ref:`DNNL_ARG_ATTR_SCALES ` \| arg. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - arg - Parameter argument index as passed to the primitive :ref:`execute() ` call. * - mask - Scaling factors correspondence mask that defines the correspondence between the tensor dimensions and the ``scales`` array. 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 tensor. * - groups - Block sizes for the last two tensor dimensions: ``{G0, G1}`` where ``G0`` subdivides the second-to-last tensor dimension and ``G1`` subdivides the last. The corresponding mask bits must be set. Use ``1`` for no sub-blocking. ``{}`` indicates no grouping. * - data_type - Scaling factors data_type. * - is_on_host - Indicates whether the scaling factor is a host-side scalar. * - qmode - Quantization mode, can be :ref:`quantization_mode::static_sazp ` or :ref:`quantization_mode::dynamic_mx ` .. rubric:: See also: :ref:`dnnl_primitive_attr_set_scales_v3 ` .. index:: pair: function; set_host_scale .. _doxid-structdnnl_1_1primitive__attr_1a7b035390cde177453afae9c5b5a7c29e: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_host_scale( int arg, :ref:`memory::data_type` data_type = :ref:`memory::data_type::f32` ) Sets a single host-side scalar scaling factor for the specified memory argument. The scaling factor should be passed as a host scalar memory object at execution time with index :ref:`DNNL_ARG_ATTR_SCALES ` \| arg. .. note:: Using this API to set the scaling factor implies that the scales attribute has ``mask == 0`` and an empty groups vector. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - arg - Parameter argument index as passed to the :ref:`primitive::execute() ` call. * - data_type - Scaling factors data_type. .. rubric:: See also: :ref:`dnnl_primitive_attr_set_scales_v2 ` .. index:: pair: function; set_zero_points_mask .. _doxid-structdnnl_1_1primitive__attr_1a8935d36d48fe5db9476b30b02791d822: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_zero_points_mask(int arg, int mask) Sets zero points for primitive operations for a given memory argument. The zero points must be passed at execution time as an argument with index :ref:`DNNL_ARG_ATTR_ZERO_POINTS ` \| arg. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - arg - Parameter argument index as passed to the :ref:`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. .. rubric:: See also: :ref:`dnnl_primitive_attr_set_zero_points_mask ` .. index:: pair: function; set_zero_points .. _doxid-structdnnl_1_1primitive__attr_1a2a8693f2aba0541ccd59470b41321175: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_zero_points( int arg, int mask, const :ref:`memory::dims`& groups, :ref:`memory::data_type` data_type = :ref:`memory::data_type::s32`, bool is_on_host = false ) Sets zero points for primitive operations for a given memory argument. The zero points must be passed at execution time as an argument with index :ref:`DNNL_ARG_ATTR_ZERO_POINTS ` \| arg. .. note:: If ``is_on_host`` is true, sets a single host-side zero point for the specified memory argument. The zero point should be passed as a host scalar memory object at execution time with index :ref:`DNNL_ARG_ATTR_ZERO_POINTS ` \| arg. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - arg - Parameter argument index as passed to the :ref:`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. * - groups - Block sizes for the last two tensor dimensions: ``{G0, G1}`` where ``G0`` subdivides the second-to-last tensor dimension and ``G1`` subdivides the last. The corresponding mask bits must be set. Use ``1`` for no sub-blocking. ``{}`` indicates no grouping. * - data_type - Zero point factors data_type. * - is_on_host - Indicates whether the zero point is a host-side scalar. .. rubric:: See also: :ref:`dnnl_primitive_attr_set_zero_points ` .. index:: pair: function; set_host_zero_point .. _doxid-structdnnl_1_1primitive__attr_1ac6aac2aa4418da036964baa3a35ed879: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_host_zero_point( int arg, :ref:`memory::data_type` data_type = :ref:`memory::data_type::s32` ) Sets a single host-side zero point for the specified memory argument. The zero point should be passed as a host scalar memory object at execution time with index :ref:`DNNL_ARG_ATTR_ZERO_POINTS ` \| arg. .. note:: Using this API to set the zero point implies that the zero point attribute has ``mask == 0`` and an empty groups vector. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - arg - Parameter argument index as passed to the :ref:`primitive::execute() ` call. * - data_type - Zero point data type. .. rubric:: See also: :ref:`dnnl_primitive_attr_set_zero_points_v2 ` .. index:: pair: function; set_precomputed_reductions .. _doxid-structdnnl_1_1primitive__attr_1a24a349d345ac97756a54b01b634b1b3c: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_precomputed_reductions( int arg, int mask, const :ref:`memory::dims`& groups, :ref:`memory::data_type` data_type = :ref:`memory::data_type::s32` ) Sets precomputed reductions for primitive operations for a given memory argument. The precomputed reductions must be passed at execution time as an argument with index :ref:`DNNL_ARG_ATTR_PRECOMPUTED_REDUCTIONS ` \| arg. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - arg - Parameter argument index as passed to the :ref:`primitive::execute() ` call. * - mask - Precomputed reductions correspondence mask that defines the correspondence between the tensor dimensions and the precomputed reductions vector. The set i-th bit indicates that a dedicated precomputed reduction point is used for each index along that dimension. * - groups - Block sizes for the last two tensor dimensions: ``{G0, G1}`` where ``G0`` subdivides the second-to-last tensor dimension and ``G1`` subdivides the last. The corresponding mask bits must be set. Use ``1`` for no sub-blocking. ``{}`` indicates no grouping. * - data_type - Precomputed reduction factors data_type. .. rubric:: See also: :ref:`dnnl_primitive_attr_set_precomputed_reductions ` .. index:: pair: function; get_post_ops .. _doxid-structdnnl_1_1primitive__attr_1a8c09d334d9ccf9f9d3ee0d9941ca3da4: .. ref-code-block:: cpp :class: doxyrest-title-code-block :ref:`post_ops` get_post_ops() const Returns post-ops previously set via :ref:`set_post_ops() `. .. rubric:: Returns: Post-ops. .. index:: pair: function; set_post_ops .. _doxid-structdnnl_1_1primitive__attr_1a1850cd1e0c191b12ed4595f7939d3f9b: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_post_ops(const :ref:`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. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - ops - Post-ops object to copy post-ops from. .. index:: pair: function; set_rnn_data_qparams .. _doxid-structdnnl_1_1primitive__attr_1a39ce5aa8b06ed331d8e2158108cc8324: .. ref-code-block:: cpp :class: doxyrest-title-code-block 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: .. ref-code-block:: cpp // 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 an RNN primitive descriptor. vanilla_rnn_forward::primitive_desc rnn_d( engine, /* arguments */, attr); .. note:: Quantization scale and shift are common for src_layer, src_iter, dst_iter, and dst_layer. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - scale - The value to scale the data by. * - shift - The value to shift the data by. .. index:: pair: function; get_rnn_data_qparams .. _doxid-structdnnl_1_1primitive__attr_1a47d567defa762761daa2af604798d799: .. ref-code-block:: cpp :class: doxyrest-title-code-block 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. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - scale - The value to scale the data by. * - shift - The value to shift the data by. .. index:: pair: function; set_rnn_weights_qparams .. _doxid-structdnnl_1_1primitive__attr_1a61bd70f97baa628fd49b2c8b334b913e: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_rnn_weights_qparams(int mask, const std::vector& 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 .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - 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: :math:`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. .. index:: pair: function; get_rnn_weights_qparams .. _doxid-structdnnl_1_1primitive__attr_1a3bbe9ac516e3aabe7dfea214210a3335: .. ref-code-block:: cpp :class: doxyrest-title-code-block void get_rnn_weights_qparams(int& mask, std::vector& 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. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - 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: :math:`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. .. index:: pair: function; set_rnn_weights_projection_qparams .. _doxid-structdnnl_1_1primitive__attr_1a6e5a8c12f28421c249633bf2092fbe3f: .. ref-code-block:: cpp :class: doxyrest-title-code-block void set_rnn_weights_projection_qparams( int mask, const std::vector& 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 .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - 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: :math:`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. .. index:: pair: function; get_rnn_weights_projection_qparams .. _doxid-structdnnl_1_1primitive__attr_1a53c41b29c5cd74d9485b5e753ba57f1d: .. ref-code-block:: cpp :class: doxyrest-title-code-block void get_rnn_weights_projection_qparams(int& mask, std::vector& 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. .. rubric:: Parameters: .. list-table:: :widths: 20 80 * - 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: :math:`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.