MultiConvolution.hpp File Reference

Support performing convolutions in parallel. More...

#include "poplin/Convolution.hpp"
#include <poplar/Graph.hpp>
#include <poplar/OptionFlags.hpp>
#include <poplar/Program.hpp>
#include <vector>

Go to the source code of this file.

Classes
struct	poplin::multiconv::CreateTensorArgs
	Multi-convolutions allow for a set of convolutions to be executed in parallel. More...
struct	poplin::multiconv::ConvolutionArgs
struct	poplin::multiconv::CalculateWeightDeltasArgs
struct	poplin::multiconv::ConvWeightUpdateArgs
struct	poplin::multiconv::ConvWeightUpdateArgsScalar

Namespaces
namespace	poplin
	Linear algebra functions.

Functions
poplar::Tensor	poplin::multiconv::createWeights (poplar::Graph &graph, const std::vector< CreateTensorArgs > &args, unsigned weightsIndex, const poplar::OptionFlags &options={}, poplin::PlanningCache *cache=nullptr)
	Create a specific weights tensor for the multiconvolution. More...
poplar::Tensor	poplin::multiconv::createInput (poplar::Graph &graph, const std::vector< CreateTensorArgs > &args, unsigned inputIndex, const poplar::OptionFlags &options={}, poplin::PlanningCache *cache=nullptr)
	Create a specific input tensor for the multiconvolution. More...
void	poplin::multiconv::weightsTransposeChansFlipXY (poplar::Graph &graph, std::vector< ConvolutionArgs > &args, const std::vector< poplar::Tensor > &weightsIn, poplar::program::Sequence &prog, const poplar::OptionFlags &options, const poplar::DebugContext &debugContext, poplin::PlanningCache *cache)
	For each element in the multi-convolution set, copy the corresponding weightsIn element into the convolution weight input such that each element of the kernel is transposed with respect to the input and output channels and each spatial dimension of the kernel is flipped. More...
std::vector< poplar::Tensor >	poplin::multiconv::convolution (poplar::Graph &graph, const std::vector< ConvolutionArgs > &args, bool transposeAndFlipWeights, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, poplin::PlanningCache *cache=nullptr)
	Convolve a set of inputs with a set of weights. More...
std::vector< poplar::Tensor >	poplin::multiconv::calculateWeightDeltas (poplar::Graph &graph, const std::vector< CalculateWeightDeltasArgs > &args, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, poplin::PlanningCache *cache=nullptr)
	Append an operation to generate the set of weight delta tensors. More...
void	poplin::multiconv::convolutionWeightUpdate (poplar::Graph &graph, const std::vector< ConvWeightUpdateArgs > &args, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, poplin::PlanningCache *cache=nullptr)
	Append operations to prog to generate and apply the weight update. More...
void	poplin::multiconv::convolutionWeightUpdate (poplar::Graph &graph, const std::vector< ConvWeightUpdateArgsScalar > &args, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, poplin::PlanningCache *cache=nullptr)
	Append operations to prog to generate and apply the weight update. More...

Detailed Description

Support performing convolutions in parallel.

Function Documentation

calculateWeightDeltas()

std::vector< poplar::Tensor > poplin::multiconv::calculateWeightDeltas	(	poplar::Graph &	graph,
		const std::vector< CalculateWeightDeltasArgs > &	args,
		poplar::program::Sequence &	prog,
		const poplar::DebugContext &	debugContext = {},
		const poplar::OptionFlags &	options = {},
		poplin::PlanningCache *	cache = nullptr
	)

Append an operation to generate the set of weight delta tensors.

See Convolution.hpp for more information.

Parameters

graph	The graph that the operations will be added to.
args	Collection of zDeltas, activations, and convolution parameters specifying each convolution in the multiconvolution.
prog	Poplar program sequence to append the operations onto.
debugContext	Optional debug information.
options	Options controlling the implementation.
cache	Optional pointer to a planning cache to use.

Returns

Set of weight deltas.

convolution()

std::vector< poplar::Tensor > poplin::multiconv::convolution	(	poplar::Graph &	graph,
		const std::vector< ConvolutionArgs > &	args,
		bool	transposeAndFlipWeights,
		poplar::program::Sequence &	prog,
		const poplar::DebugContext &	debugContext = {},
		const poplar::OptionFlags &	options = {},
		poplin::PlanningCache *	cache = nullptr
	)

Convolve a set of inputs with a set of weights.

See Convolution.hpp for more information.

Parameters

graph	The graph that the operations will be added to.
args	Collection of inputs, weights, and convolution parameters specifying each convolution in the multiconvolution.
transposeAndFlipWeights	Prepare the weights for the backwards pass.
prog	Poplar program sequence to append the operations onto.
debugContext	Optional debug information.
options	Options controlling the implementation.
cache	Optional pointer to a planning cache to use.

Returns

Set of convolved output tensors.

convolutionWeightUpdate() [1/2]

void poplin::multiconv::convolutionWeightUpdate	(	poplar::Graph &	graph,
		const std::vector< ConvWeightUpdateArgs > &	args,
		poplar::program::Sequence &	prog,
		const poplar::DebugContext &	debugContext = {},
		const poplar::OptionFlags &	options = {},
		poplin::PlanningCache *	cache = nullptr
	)

Append operations to prog to generate and apply the weight update.

See Convolution.hpp for more information.

Parameters

graph	The graph that the operations will be added to.
args	Collection of zDeltas, activations, scale, and convolution parameters for the weight updates in the multiconvolution.
prog	Poplar program sequence to append the operations onto.
debugContext	Optional debug information.
options	Options controlling the implementation.
cache	Optional pointer to a planning cache to use.

convolutionWeightUpdate() [2/2]

void poplin::multiconv::convolutionWeightUpdate	(	poplar::Graph &	graph,
		const std::vector< ConvWeightUpdateArgsScalar > &	args,
		poplar::program::Sequence &	prog,
		const poplar::DebugContext &	debugContext = {},
		const poplar::OptionFlags &	options = {},
		poplin::PlanningCache *	cache = nullptr
	)

Append operations to prog to generate and apply the weight update.

See Convolution.hpp for more information.

Parameters

graph	The graph that the operations will be added to.
args	Collection of zDeltas, activations, scale, and convolution parameters for the weight updates in the multiconvolution.
prog	Poplar program sequence to append the operations onto.
debugContext	Optional debug information.
options	Options controlling the implementation.
cache	Optional pointer to a planning cache to use.

createInput()

poplar::Tensor poplin::multiconv::createInput	(	poplar::Graph &	graph,
		const std::vector< CreateTensorArgs > &	args,
		unsigned	inputIndex,
		const poplar::OptionFlags &	options = {},
		poplin::PlanningCache *	cache = nullptr
	)

Create a specific input tensor for the multiconvolution.

Parameters

graph	The graph that the tensors will be added to.
args	The same set of parameters as used by convolution().
inputIndex	Index into args describing the convolution which to create the input for.
options	Options controlling the implementation.
cache	Optional pointer to a planning cache to use.

Returns

A tensor suitable for use as an input to convolution().

createWeights()

poplar::Tensor poplin::multiconv::createWeights	(	poplar::Graph &	graph,
		const std::vector< CreateTensorArgs > &	args,
		unsigned	weightsIndex,
		const poplar::OptionFlags &	options = {},
		poplin::PlanningCache *	cache = nullptr
	)

Create a specific weights tensor for the multiconvolution.

Parameters

graph	The graph that the tensors will be added to.
args	The same set of parameters as used by convolution().
weightsIndex	Index into args describing the convolution which to create the weights for.
options	Options controlling the implementation.
cache	Optional pointer to a planning cache to use.

Returns

A weights tensor suitable for use with convolution().

weightsTransposeChansFlipXY()

void poplin::multiconv::weightsTransposeChansFlipXY	(	poplar::Graph &	graph,
		std::vector< ConvolutionArgs > &	args,
		const std::vector< poplar::Tensor > &	weightsIn,
		poplar::program::Sequence &	prog,
		const poplar::OptionFlags &	options,
		const poplar::DebugContext &	debugContext,
		poplin::PlanningCache *	cache
	)

For each element in the multi-convolution set, copy the corresponding weightsIn element into the convolution weight input such that each element of the kernel is transposed with respect to the input and output channels and each spatial dimension of the kernel is flipped.

See Convolution.hpp for more information.

Parameters

graph	The graph that the operations will be added to.
args	Collection of inputs, weights, and convolution parameters specifying each convolution in the multiconvolution.
weightsIn	Collection of weights tensor to copy from, the arrangement of which must correspond with the arrangement of the collection of convolution parameters.
prog	Poplar program sequence to append the operations onto.
options	Options controlling the implementation.
debugContext	Optional debug information.
cache	Optional pointer to a planning cache to use.