CPU implementation of the encoder operation for neural networks. More...

Inheritance diagram for Mila::Dnn::Compute::CpuEncoderOp:

[legend]

Collaboration diagram for Mila::Dnn::Compute::CpuEncoderOp:

[legend]

Public Types
using	MR = typename CpuDevice::MR

using	OperationBase = UnaryOperation< DeviceType::Cpu, int, float >

Public Types inherited from Mila::Dnn::Compute::UnaryOperation< DeviceType::Cpu, int, float >
using	MR = std::conditional_t< TDeviceType==DeviceType::Cuda, CudaMemoryResource, HostMemoryResource >
	Memory resource type based on device type.

Public Member Functions
	CpuEncoderOp (const EncoderConfig &config)
	Constructs a new CPU Encoder operation with the default device context.

	CpuEncoderOp (std::shared_ptr< DeviceContext > context, const EncoderConfig &config)
	Constructs a new CPU Encoder operation with a specific device context.

void	backward (const Tensor< int, MR > &input, const Tensor< float, MR > &output, const Tensor< float, MR > &output_gradient, const std::vector< std::shared_ptr< Tensor< float, MR > > > &parameters, std::vector< std::shared_ptr< Tensor< float, MR > > > &parameter_gradients, Tensor< int, MR > &input_gradient, const OperationAttributes &attributes, const std::vector< std::shared_ptr< Tensor< float, MR > > > &output_state) const
	Performs the backward pass of the encoder operation.

void	forward (const Tensor< int, MR > &input, const std::vector< std::shared_ptr< Tensor< float, MR > > > &parameters, const OperationAttributes &attributes, Tensor< float, MR > &output, std::vector< std::shared_ptr< Tensor< float, MR > > > &output_state) const override
	Performs the forward pass of the encoder operation.

std::string	getName () const override
	Gets the name of this operation.

Public Member Functions inherited from Mila::Dnn::Compute::UnaryOperation< DeviceType::Cpu, int, float >
	UnaryOperation (OperationType operation_type)
	Constructs a UnaryOperation with the specified operation type.

	UnaryOperation (OperationType operation_type, std::shared_ptr< DeviceContext > context)
	Constructs a UnaryOperation with the specified operation type and device context.

virtual	~UnaryOperation ()=default
	Virtual destructor for proper cleanup of derived classes.

virtual void	backward (const Tensor< int, MR > &grad, const std::vector< std::shared_ptr< Tensor< float, MR > > > &parameters, std::vector< std::shared_ptr< Tensor< float, MR > > > &output_grads) const
	Executes the backward pass of a unary operation.

virtual void	backward (const Tensor< int, MR > &input, const Tensor< float, MR > &output_grad, const std::vector< std::shared_ptr< Tensor< float, MR > > > &parameters, std::vector< std::shared_ptr< Tensor< float, MR > > > &parameter_grads, Tensor< int, MR > &input_grad, const OperationAttributes &properties, const std::vector< std::shared_ptr< Tensor< float, MR > > > &output_state) const
	Executes the comprehensive backward pass of a unary operation.

virtual void	forward (const Tensor< int, MR > &input, const std::vector< std::shared_ptr< Tensor< float, MR > > > &parameters, const OperationAttributes &properties, Tensor< float, MR > &output, std::vector< std::shared_ptr< Tensor< float, MR > > > &output_state) const=0
	Executes the forward pass of a unary operation.

Public Member Functions inherited from Mila::Dnn::Compute::OperationBase< TDeviceType, TInput1, TInput2, TOutput >
	OperationBase (OperationType operation_type, std::shared_ptr< DeviceContext > context)
	Constructs an OperationBase object with a specific device context and compute precision.

virtual	~OperationBase ()=default
	Virtual destructor for the OperationBase class.

std::shared_ptr< DeviceContext >	getDeviceContext () const
	Gets the device context associated with this operation.

DeviceType	getDeviceType () const
	Gets the device type for this operation.

OperationType	getOperationType () const
	Gets the operation type enumeration value.

Private Attributes
EncoderConfig	config_
	Configuration for the encoder operation.

Detailed Description

CPU implementation of the encoder operation for neural networks.

This class provides a CPU-based implementation of the encoder operation, which combines token embeddings and positional embeddings.

Template Parameters

TInput	The data type of the input tensor elements (typically int for token indices).
TDataType	The data type used for computation and output (typically float).

Member Typedef Documentation

◆ MR

using Mila::Dnn::Compute::CpuEncoderOp::MR = typename CpuDevice::MR

◆ OperationBase

using Mila::Dnn::Compute::CpuEncoderOp::OperationBase = UnaryOperation<DeviceType::Cpu, int, float>

Constructor & Destructor Documentation

◆ CpuEncoderOp() [1/2]

Mila::Dnn::Compute::CpuEncoderOp::CpuEncoderOp ( const EncoderConfig & config )

inline

Constructs a new CPU Encoder operation with the default device context.

CPU operations always use full precision regardless of policy settings.

◆ CpuEncoderOp() [2/2]

Mila::Dnn::Compute::CpuEncoderOp::CpuEncoderOp	(	std::shared_ptr< DeviceContext >	context,
		const EncoderConfig &	config
	)

inline

Constructs a new CPU Encoder operation with a specific device context.

CPU operations always use full precision regardless of policy settings.

Parameters

context The device context to use for this operation.

Exceptions

std::runtime_error If the context is not for a CPU device.

Member Function Documentation

◆ backward()

void Mila::Dnn::Compute::CpuEncoderOp::backward	(	const Tensor< int, MR > &	input,
		const Tensor< float, MR > &	output,
		const Tensor< float, MR > &	output_gradient,
		const std::vector< std::shared_ptr< Tensor< float, MR > > > &	parameters,
		std::vector< std::shared_ptr< Tensor< float, MR > > > &	parameter_gradients,
		Tensor< int, MR > &	input_gradient,
		const OperationAttributes &	attributes,
		const std::vector< std::shared_ptr< Tensor< float, MR > > > &	output_state
	)		const

inline

Performs the backward pass of the encoder operation.

Computes gradients with respect to inputs and parameters.

Parameters

input	Input tensor from the forward pass.
output	Output tensor from the forward pass.
output_gradient	Gradient of the loss with respect to the output.
parameters	Parameters tensor from forward pass.
parameter_gradients	Gradients for parameters.
input_gradient	Gradient of the loss with respect to the input.
attributes	Additional attributes for the operation.
output_state	Cache tensors from forward pass.

Here is the call graph for this function:

◆ forward()

void Mila::Dnn::Compute::CpuEncoderOp::forward	(	const Tensor< int, MR > &	input,
		const std::vector< std::shared_ptr< Tensor< float, MR > > > &	parameters,
		const OperationAttributes &	attributes,
		Tensor< float, MR > &	output,
		std::vector< std::shared_ptr< Tensor< float, MR > > > &	output_state
	)		const

inlineoverride

Performs the forward pass of the encoder operation.

Combines token embeddings and positional embeddings for input token indices.

Parameters

input	Input tensor containing token indices.
parameters	Parameters tensor containing embeddings and other parameters.
attributes	Additional attributes for the operation.
output	Output tensor to store the resulting embeddings.
output_state	Cache for storing intermediate results (used in backward pass).

Here is the call graph for this function:

◆ getName()

std::string Mila::Dnn::Compute::CpuEncoderOp::getName ( ) const

inlineoverridevirtual

Gets the name of this operation.

Returns: std::string The name of the operation ("Cpu::EncoderOp").

Implements Mila::Dnn::Compute::OperationBase< TDeviceType, TInput1, TInput2, TOutput >.

Member Data Documentation

◆ config_

EncoderConfig Mila::Dnn::Compute::CpuEncoderOp::config_

private

Configuration for the encoder operation.

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

/home/runner/work/Mila/Mila/Mila/Src/Dnn/Compute/Operations/Cpu/CpuEncoderOp.ixx

Public Types

Public Member Functions

Private Attributes

Detailed Description

Member Typedef Documentation

◆ MR

◆ OperationBase

Constructor & Destructor Documentation

◆ CpuEncoderOp() [1/2]

◆ CpuEncoderOp() [2/2]

Member Function Documentation

◆ backward()

◆ forward()

◆ getName()

Member Data Documentation

◆ config_