Convolution.hpp File Reference

Functions and data types to support performing convolutions. More...

#include "ConvParams.hpp"
#include <poplar/Graph.hpp>
#include <poplar/OptionFlags.hpp>
#include <poplar/Program.hpp>
#include <set>
#include <tuple>

Go to the source code of this file.

Classes
struct	poplin::PlanCosts
	Structure for estimated costs returned by reportPlanEstimatedCosts() More...

Namespaces
namespace	poplin
	Linear algebra functions.

Functions
uint64_t	poplin::getFwdFlops (const ConvParams &params)
	Calculate the minimum number of floating point operations required to perform the forward pass convolution given a set of params.
uint64_t	poplin::getBwdFlops (const ConvParams &params)
	Calculate the minimum number of floating point operations required to perform the backward pass convolution given a set of params.
uint64_t	poplin::getWuFlops (const ConvParams &params)
	Calculate minimum number of floating point operations required to perform the weight update pass convolution given a set of params.
double	poplin::getFwdPerfectCycleCount (const poplar::Graph &graph, const ConvParams &params)
	Calculate the number of cycles to perform the forward pass assuming maximal utilisation of target hardware performing the minimum number of floating point operations. More...
double	poplin::getBwdPerfectCycleCount (const poplar::Graph &graph, const ConvParams &params)
	Calculate the number of cycles to perform the backward pass assuming maximal utilisation of the target hardware, performing the minimum number of floating point operations. More...
double	poplin::getWuPerfectCycleCount (const poplar::Graph &graph, const ConvParams &params)
	Calculate the number of cycles to perform the weight update pass assuming maximal utilisation of the target hardware, performing the minimum number of floating point operations. More...
poplar::Tensor	poplin::createWeights (poplar::Graph &graph, const ConvParams &params, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Create a weight tensor suitable for use with convolution() More...
poplar::Tensor	poplin::createBiases (poplar::Graph &graph, const poplar::Tensor &activations, const poplar::DebugContext &debugContext={"biases"})
	Create a bias tensor suitable for input to the addBias() function. More...
poplar::Tensor	poplin::createBiases (poplar::Graph &graph, const poplar::Tensor &activations, const ConvParams &params, const poplar::DebugContext &debugContext={"biases"}, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Create a bias tensor suitable for input to the addBias() function with allocation consistent with plan parameters. More...
poplar::Tensor	poplin::createInput (poplar::Graph &graph, const ConvParams &params, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Create an input tensor for a convolution. More...
poplar::Tensor	poplin::createConvOutput (poplar::Graph &graph, const ConvParams &params, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Create an output tensor for a convolution. More...
poplar::Tensor	poplin::convolution (poplar::Graph &graph, const poplar::Tensor &in, const poplar::Tensor &weights, const ConvParams &params, bool transposeAndFlipWeights, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Convolve an input with a set of weights. More...
void	poplin::convolutionWithOutput (poplar::Graph &graph, const poplar::Tensor &in, const poplar::Tensor &weights, const poplar::Tensor &out, const ConvParams &params, bool transposeAndFlipWeights, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Convolve an input with a set of weights into a pre-allocated output tensor. More...
void	poplin::preplanConvolutions (const std::set< ConvPlanParams > &convs, PlanningCache &cache)
void	poplin::preplanConvolutions (poplar::Graph &graph, const std::set< ConvPlanParams > &convs, PlanningCache &cache)
void	poplin::weightsTransposeChansFlipXY (poplar::Graph &graph, const poplar::Tensor &weightsIn, const poplar::Tensor &weightsOut, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={})
	Copy the weights in weightsIn into weightsOut such that each element of the kernel is transposed with respect to the input and output channels and flip each spatial dimension of the kernel. More...
poplar::Tensor	poplin::calculateWeightDeltas (poplar::Graph &graph, const poplar::Tensor &zDeltas, const poplar::Tensor &activations, const ConvParams &params, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Append an operation to a poplar::Program to generate the tensor of weight deltas. More...
void	poplin::convolutionWeightUpdate (poplar::Graph &graph, const poplar::Tensor &zDeltas, const poplar::Tensor &weights, const poplar::Tensor &activations, ConvParams params, const poplar::Tensor &scale, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Append operations to a poplar::Program to generate and apply the weight update. More...
void	poplin::convolutionWeightUpdate (poplar::Graph &graph, const poplar::Tensor &zDeltas, const poplar::Tensor &weights, const poplar::Tensor &activations, ConvParams params, float scale, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Append operations to a poplar::Program to generate and apply the weight update. More...
void	poplin::convolutionBiasUpdate (poplar::Graph &graph, const poplar::Tensor &zDeltas, const poplar::Tensor &biases, const poplar::Tensor &scale, const poplar::OptionFlags &options, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={})
	Add a program to update biases tensor with the gradients derived from the zDeltas tensor. More...
void	poplin::convolutionBiasUpdate (poplar::Graph &graph, const poplar::Tensor &zDeltas, const poplar::Tensor &biases, float scale, const poplar::OptionFlags &options, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={})
	Add a program to update biases tensor with the gradients derived from the zDeltas tensor. More...
void	poplin::addBias (poplar::Graph &graph, const poplar::Tensor &in, const poplar::Tensor &biases, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={})
	Adds a program to prog which adds biases to activations tensor. More...
void	poplin::reportPlanInfo (std::ostream &out, const poplar::Graph &graph, const ConvParams &params, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Report the convolution plan corresponding to the params and options provided. More...
PlanCosts	poplin::reportPlanEstimatedCosts (const poplar::Graph &graph, const ConvParams &params, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Report the estimated cycles and memory costs of the convolution plan corresponding to the params and options provided. More...
void	poplin::reportWeightUpdatePlanInfo (std::ostream &out, const poplar::Graph &graph, const ConvParams &fwdParams, const poplar::OptionFlags &fwdOptions={}, PlanningCache *cache=nullptr)
	Report the convolution plan corresponding to the weight update pass given the forward pass params and options. More...
poplar::Tensor	poplin::fullyConnectedWeightTranspose (poplar::Graph &graph, poplar::Tensor weights, const ConvParams &params, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={}, const poplar::OptionFlags &options={}, PlanningCache *cache=nullptr)
	Arranges the weights (activations) such that they are suited for the backward pass in a fully connected layer. More...
void	poplin::convolutionValidateOptions (const poplar::OptionFlags &options)
	Provides an interface to validate the convolution options. More...

Detailed Description

Functions and data types to support performing convolutions.