TorchDNNKernel Class Reference

A class that implements a single-layer neural network kernel using PyTorch, inheriting from MLFunction. More...

#include <functions.h>

Inheritance diagram for TorchDNNKernel:

Public Member Functions
	TorchDNNKernel (std::string kernel, float *weights, float *bias, std::vector< int > dimensions)
	Constructor that initializes the neural network kernel with weights, biases, and dimensions.
void	apply (const SelectivityVector &rows, std::vector< VectorPtr > &args, const TypePtr &type, exec::EvalCtx &context, VectorPtr &output) const override
	Applies the neural network kernel to the input array.
float *	getTensor () const override
	Returns the tensor associated with this function.
const float *	getWeights () const
	Returns the weights of the neural network kernel.
const float *	getBias () const
	Returns the biases of the neural network kernel.
std::string	getFuncName ()
	Returns the name of the function.
Public Member Functions inherited from MLFunction
virtual	~MLFunction ()=default
	Virtual destructor.
virtual std::vector< int >	getDims ()
	Returns the dimensions of the function.
virtual int	getNumDims ()
	Returns the number of dimensions of the function.
virtual CostEstimate	getCost (std::vector< int > inputDims)
	Estimates the computational cost of applying the function.

Static Public Member Functions
static std::vector< std::shared_ptr< exec::FunctionSignature > >	signatures ()
	Returns the function signatures supported by this class.
static std::string	getName ()
	Static method to return the name of the function.

Additional Inherited Members
Protected Member Functions inherited from MLFunction
double	getWeightedCost (std::string name, float cost)
	Calculates the weighted cost of the function.
std::vector< double >	getCoefficientVector (std::string name)
	Retrieves the cost coefficients for the function.
Protected Attributes inherited from MLFunction
std::vector< int >	dims
	Dimensions of the function.

Detailed Description

A class that implements a single-layer neural network kernel using PyTorch, inheriting from MLFunction.

This class provides functionality to apply a single-layer neural network with configurable kernel types (e.g., Dense, ReLU, Softmax).

Constructor & Destructor Documentation

TorchDNNKernel()

TorchDNNKernel::TorchDNNKernel ( std::string kernel, float * weights, float * bias, std::vector< int > dimensions )

inline

Constructor that initializes the neural network kernel with weights, biases, and dimensions.

Parameters

kernel	The type of kernel (e.g., "Dense", "ReLU", "Softmax").
weights	A pointer to the weight matrix.
bias	A pointer to the bias vector.
dimensions	A vector containing the dimensions of the neural network layer.

Member Function Documentation

apply()

void TorchDNNKernel::apply ( const SelectivityVector & rows, std::vector< VectorPtr > & args, const TypePtr & type, exec::EvalCtx & context, VectorPtr & output ) const

inlineoverride

Applies the neural network kernel to the input array.

This method processes the input array, applies the neural network kernel, and stores the result in the output vector.

Parameters

rows	A SelectivityVector specifying the rows to process.
args	A vector of input arguments (e.g., the input array).
type	The type of the output vector.
context	The execution context.
output	The output vector where the result will be stored.

getBias()

const float * TorchDNNKernel::getBias ( ) const

inline

Returns the biases of the neural network kernel.

Returns

A pointer to the bias vector.

getFuncName()

std::string TorchDNNKernel::getFuncName ( )

inlinevirtual

Returns the name of the function.

Returns

The name of the function as a string.

Reimplemented from MLFunction.

getName()

static std::string TorchDNNKernel::getName ( )

inlinestatic

Static method to return the name of the function.

Returns

The name of the function as a string ("torchnn_kernel").

getTensor()

float * TorchDNNKernel::getTensor ( ) const

inlineoverridevirtual

Returns the tensor associated with this function.

Returns

A pointer to an empty float array (no weights for TorchDNNKernel).

Implements MLFunction.

getWeights()

const float * TorchDNNKernel::getWeights ( ) const

inline

Returns the weights of the neural network kernel.

Returns

A pointer to the weight matrix.

signatures()

static std::vector< std::shared_ptr< exec::FunctionSignature > > TorchDNNKernel::signatures ( )

inlinestatic

Returns the function signatures supported by this class.

Returns

A vector of shared pointers to FunctionSignature objects.

---

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

• functions.h