BlockSparse.hpp File Reference

Block sparse operations. More...

#include <array>
#include <string>
#include <vector>
#include <poplar/Graph.hpp>
#include <poplar/Program.hpp>
#include <poplar/Tensor.hpp>
#include <poplar/Type.hpp>

Go to the source code of this file.

Namespaces
namespace	popsparse
	Support for sparse matrices.

Enumerations
enum class	popsparse::experimental::SubBlockMask { None , ZeroUpperTriangle , ZeroLowerTriangle }
	Define the sparsity mask inside a block. More...

Functions
poplar::Tensor	popsparse::experimental::bsSoftmax (poplar::Graph &graph, poplar::Tensor sparseTensor, const std::array< int, 2 > &dim, const std::array< int, 2 > &blockSize, const std::vector< unsigned char > &sparsity, SubBlockMask subBlockMaskType, unsigned numGroups, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={})
	This function computes softmax on a sparse tensor. More...
void	popsparse::experimental::bsSoftmaxInPlace (poplar::Graph &graph, poplar::Tensor sparseTensor, const std::array< int, 2 > &dim, const std::array< int, 2 > &blockSize, const std::vector< unsigned char > &sparsity, SubBlockMask subBlockMaskType, unsigned numGroups, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={})
	This function computes softmax on a sparse tensor, in place. More...
poplar::Tensor	popsparse::experimental::bsSoftmaxGrad (poplar::Graph &graph, poplar::Tensor sparseOut, poplar::Tensor sparseOutGrad, const std::array< int, 2 > &dim, const std::array< int, 2 > &blockSize, const std::vector< unsigned char > &sparsity, poplar::program::Sequence &prog, const poplar::DebugContext &debugContext={})
	This function computes softmax gradient on a sparse tensor. More...

Detailed Description

Block sparse operations.

Enumeration Type Documentation

SubBlockMask

enum class popsparse::experimental::SubBlockMask

strong

Define the sparsity mask inside a block.

The diagonal is defined across sll the non-sparse matrix dimensions, where the row index is equal to the column index.

Enumerator
None	No elements are zeroed out.
ZeroUpperTriangle	Elements in the upper triangle, above the diagonal, are zeroed out.
ZeroLowerTriangle	Elements in the lower triangle, below the diagonal, are zeroed out.

Function Documentation

bsSoftmax()

poplar::Tensor popsparse::experimental::bsSoftmax	(	poplar::Graph &	graph,
		poplar::Tensor	sparseTensor,
		const std::array< int, 2 > &	dim,
		const std::array< int, 2 > &	blockSize,
		const std::vector< unsigned char > &	sparsity,
		SubBlockMask	subBlockMaskType,
		unsigned	numGroups,
		poplar::program::Sequence &	prog,
		const poplar::DebugContext &	debugContext = {}
	)

This function computes softmax on a sparse tensor.

Parameters

graph	The Poplar graph.
sparseTensor	The input sparse 2D tensor. It must be in a block-sparse format.
dim[0]	Number of rows of the original dense tensor.
dim[1]	Number of columns of the original dense tensor.
blockSize[0]	Block size of the rows.
blockSize[1]	Block size of the columns.
sparsity	The 2D sparsity mask for the block-sparse tensor, in which '1' is a non zero block and '0' is a zero block.
subBlockMaskType	Sub-block mask type. Elements in upper (or lower) triangle are filled by zeroes in the result.
numGroups	The umber of groups for group operation or 1 for non-group operation. This parameter affects sub-block mask application only. The 0 dimension of the dense representation is logically divided into groups and sub-block mask applies individually for each group.
prog	A reference to the program sequence to which the code to perform the softmax will be appended.

bsSoftmaxGrad()

poplar::Tensor popsparse::experimental::bsSoftmaxGrad	(	poplar::Graph &	graph,
		poplar::Tensor	sparseOut,
		poplar::Tensor	sparseOutGrad,
		const std::array< int, 2 > &	dim,
		const std::array< int, 2 > &	blockSize,
		const std::vector< unsigned char > &	sparsity,
		poplar::program::Sequence &	prog,
		const poplar::DebugContext &	debugContext = {}
	)

This function computes softmax gradient on a sparse tensor.

Parameters

graph	The Poplar graph
sparseOut	The outer (activation) sparse 2D tensor. It must be in block-sparse format.
sparseOutGrad	The outer gradient sparse 2D tensor. It must be in a block-sparse format.
dim[0]	Number of rows of the original dense tensor.
dim[1]	Number of columns of the original dense tensor.
blockSize[0]	Block size of the rows.
blockSize[1]	Block size of the columns.
sparsity	The 2D sparsity mask for the block-sparse tensor, in which '1' is a non zero block and '0' is a zero block.
prog	A reference to a program sequence which will be appended with the code to perform the softmax.

bsSoftmaxInPlace()

void popsparse::experimental::bsSoftmaxInPlace	(	poplar::Graph &	graph,
		poplar::Tensor	sparseTensor,
		const std::array< int, 2 > &	dim,
		const std::array< int, 2 > &	blockSize,
		const std::vector< unsigned char > &	sparsity,
		SubBlockMask	subBlockMaskType,
		unsigned	numGroups,
		poplar::program::Sequence &	prog,
		const poplar::DebugContext &	debugContext = {}
	)

This function computes softmax on a sparse tensor, in place.

Parameters

graph	The Poplar graph.
sparseTensor	The input sparse 2D tensor. It must be in a block-sparse format.
dim[0]	Number of rows of the original dense tensor.
dim[1]	Number of columns of the original dense tensor.
blockSize[0]	Block size of the rows.
blockSize[1]	Block size of the columns.
sparsity	The 2D sparsity mask for the block-sparse tensor, in which '1' is a non zero block and '0' is a zero block.
subBlockMaskType	Sub-block mask type. Elements in upper (or lower) triangle are filled by zeroes in the result.
numGroups	The umber of groups for group operation or 1 for non-group operation. This parameter affects sub-block mask application only. The 0 dimension of the dense representation is logically divided into groups and sub-block mask applies individually for each group.
prog	A reference to a program sequence which will be appended with the code to perform the softmax.