Mila::Dnn::Compute::CpuResidualOp Class Reference

CPU Residual operation (FP32) implementing BinaryOperation interface. More...

Inheritance diagram for Mila::Dnn::Compute::CpuResidualOp:

Collaboration diagram for Mila::Dnn::Compute::CpuResidualOp:

Public Types
using	MR = CpuMemoryResource
Public Types inherited from Mila::Dnn::Compute::BinaryOperation< DeviceType::Cpu, TensorDataType::FP32 >
using	MR
using	ParameterGradTensor
using	ParameterTensor
using	TensorLeftType
using	TensorOutputType
using	TensorRightType
Public Types inherited from Mila::Dnn::Compute::Operation< TDeviceType, TPrecision >
using	DataTypeTraits

Public Member Functions
	CpuResidualOp (IExecutionContext *context, const ResidualConfig &config)
	Construct with optional CPU execution context.
void	backward (const ITensor &input_a, const ITensor &input_b, const ITensor &output_grad, ITensor &input_a_grad, ITensor &input_b_grad) const override
	Backward pass: propagate output gradient equally to both inputs.
void	forward (const ITensor &input_a, const ITensor &input_b, ITensor &output) const override
	Forward pass: element-wise add inputA and inputB into output.
std::string	getName () const override
	Human-readable operation name.
OperationType	getOperationType () const override
	Operation type identifier.
Public Member Functions inherited from Mila::Dnn::Compute::BinaryOperation< DeviceType::Cpu, TensorDataType::FP32 >
virtual	~BinaryOperation ()=default
Public Member Functions inherited from Mila::Dnn::Compute::Operation< TDeviceType, TPrecision >
virtual	~Operation ()=default
virtual void	build (const BuildContext &build_context)
	Prepare the operation for a concrete input shape.
virtual void	clearGradients () noexcept
	Clear any cached gradient pointers held by the operation.
virtual TensorDataType	getDataType () const
	Tensor data type for this operation.
virtual DeviceType	getDeviceType () const
	Device type for this operation.
virtual std::size_t	getStateMemorySize () const
	Returns the number of bytes of state memory allocated by this operation.
virtual bool	isBuilt () const
	Whether build() completed successfully for a concrete input shape.
virtual bool	isEvalMode () const
	Query whether operation is configured for training.
virtual void	setGradients (ITensor *weight_grad, ITensor *bias_grad)
	Bind module-owned gradient tensors to the operation.
virtual void	setParameters (ITensor *weight, ITensor *bias)
	Bind module-owned parameter tensors to the operation.
virtual void	setTrainingMode (TrainingMode training_mode)
	Configure operation training-mode behavior.

Private Attributes
ResidualConfig	config_
IExecutionContext *	context_

Additional Inherited Members
Static Public Attributes inherited from Mila::Dnn::Compute::Operation< TDeviceType, TPrecision >
static constexpr TensorDataType	data_type
static constexpr DeviceType	device_type
Static Protected Member Functions inherited from Mila::Dnn::Compute::BinaryOperation< DeviceType::Cpu, TensorDataType::FP32 >
static const TensorLeftType &	asLeftTensor (const ITensor &t)
static TensorOutputType &	asOutputTensor (ITensor &t)
static const TensorRightType &	asRightTensor (const ITensor &t)
Protected Attributes inherited from Mila::Dnn::Compute::Operation< TDeviceType, TPrecision >
bool	is_built_
TrainingMode	training_mode_

Detailed Description

CPU Residual operation (FP32) implementing BinaryOperation interface.

This class implements forward and backward using ITensor raw data pointers and targets CPU execution. It follows the same interface style as other CPU operations (e.g., CpuGeluOp).

Member Typedef Documentation

MR

using Mila::Dnn::Compute::CpuResidualOp::MR = CpuMemoryResource

Constructor & Destructor Documentation

CpuResidualOp()

Mila::Dnn::Compute::CpuResidualOp::CpuResidualOp ( IExecutionContext * context, const ResidualConfig & config )

inline

Construct with optional CPU execution context.

Parameters

context	Optional CPU execution context. If provided, it is validated.
config	Residual operation configuration.

Here is the call graph for this function:

Member Function Documentation

backward()

void Mila::Dnn::Compute::CpuResidualOp::backward ( const ITensor & input_a, const ITensor & input_b, const ITensor & output_grad, ITensor & input_a_grad, ITensor & input_b_grad ) const

inlineoverridevirtual

Backward pass: propagate output gradient equally to both inputs.

Adds output_gradient into both input gradients (in-place accumulation).

Implements Mila::Dnn::Compute::BinaryOperation< DeviceType::Cpu, TensorDataType::FP32 >.

Here is the call graph for this function:

forward()

void Mila::Dnn::Compute::CpuResidualOp::forward ( const ITensor & input_a, const ITensor & input_b, ITensor & output ) const

inlineoverridevirtual

Forward pass: element-wise add inputA and inputB into output.

Parameters and output_state are currently unused.

Implements Mila::Dnn::Compute::BinaryOperation< DeviceType::Cpu, TensorDataType::FP32 >.

Here is the call graph for this function:

getName()

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

inlineoverridevirtual

Human-readable operation name.

Implements Mila::Dnn::Compute::Operation< TDeviceType, TPrecision >.

getOperationType()

OperationType Mila::Dnn::Compute::CpuResidualOp::getOperationType ( ) const

inlineoverridevirtual

Operation type identifier.

Implements Mila::Dnn::Compute::Operation< TDeviceType, TPrecision >.

Member Data Documentation

config_

ResidualConfig Mila::Dnn::Compute::CpuResidualOp::config_

private

context_

IExecutionContext* Mila::Dnn::Compute::CpuResidualOp::context_

private

---

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

• /__w/Mila/Mila/Mila/Src/Dnn/Compute/Devices/Cpu/Operations/CpuResidualOp.ixx