gko::batch::matrix::Csr#

Batched compressed sparse row matrix. All items share the same sparsity pattern (row_ptrs and col_idxs are stored once); only the values array is per-item. Suitable when many independent systems have the same connectivity but different coefficients — finite-element assemblies of similar local problems are a typical example.

template<typename ValueType = default_precision, typename IndexType = int32>
class Csr #

Inherits from

  • public gko::batch::EnableBatchLinOp<Csr<default_precision, int32>>

  • public ConvertibleTo<Csr<next_precision<default_precision, 2>, int32>>

  • public ConvertibleTo<Csr<next_precision<default_precision, 3>, int32>>

  • public ConvertibleTo<Csr<next_precision<default_precision>, int32>>

Csr is a general sparse matrix format that stores the column indices for each nonzero entry and a cumulative sum of the number of nonzeros in each row. It is one of the most popular sparse matrix formats due to its versatility and ability to store a wide range of sparsity patterns in an efficient fashion.

Note

It is assumed that the sparsity pattern of all the items in the batch is the same and therefore only a single copy of the sparsity pattern is stored.

Note

Currently only IndexType of int32 is supported.

Template Parameters:

  • ValueType – value precision of matrix elements

  • IndexType – index precision of matrix elements

Public Functions

std::unique_ptr<unbatch_type> create_view_for_item(
size_type item_id,
)#

Creates a mutable view (of matrix::Csr type) of one item of the batch::matrix::Csr<value_type> object. Does not perform any deep copies, but only returns a view of the data.

Parameters:

item_id – The index of the batch item

Returns:

a batch::matrix::Csr object with the data from the batch item at the given index.

std::unique_ptr<const unbatch_type> create_const_view_for_item(
size_type item_id,
) const#

Creates a mutable view (of matrix::Csr type) of one item of the batch::matrix::Csr<value_type> object. Does not perform any deep copies, but only returns a view of the data.

Parameters:

item_id – The index of the batch item

Returns:

a batch::matrix::Csr object with the data from the batch item at the given index.

inline value_type *get_values() noexcept#

Returns a pointer to the array of values of the matrix

Returns:

the pointer to the array of values

inline const value_type *get_const_values() const noexcept#

Returns a pointer to the array of values of the matrix

Note

This is the constant version of the function, which can be significantly more memory efficient than the non-constant version, so always prefer this version.

Returns:

the pointer to the array of values

inline index_type *get_col_idxs() noexcept#

Returns a pointer to the array of column indices of the matrix

Returns:

the pointer to the array of column indices

inline const index_type *get_const_col_idxs() const noexcept#

Returns a pointer to the array of column indices of the matrix

Note

This is the constant version of the function, which can be significantly more memory efficient than the non-constant version, so always prefer this version.

Returns:

the pointer to the array of column indices

inline index_type *get_row_ptrs() noexcept#

Returns a pointer to the array of row pointers of the matrix

Returns:

the pointer to the array of row pointers

inline const index_type *get_const_row_ptrs() const noexcept#

Returns a pointer to the array of row pointers of the matrix

Note

This is the constant version of the function, which can be significantly more memory efficient than the non-constant version, so always prefer this version.

Returns:

the pointer to the array of row pointers

inline size_type get_num_stored_elements() const noexcept#

Returns the number of elements explicitly stored in the batch matrix, cumulative across all the batch items.

Returns:

the number of elements explicitly stored in the vector, cumulative across all the batch items

inline size_type get_num_elements_per_item() const noexcept#

Returns the number of stored elements in each batch item.

Returns:

the number of stored elements per batch item.

inline value_type *get_values_for_item(size_type batch_id) noexcept#

Returns a pointer to the array of values of the matrix for a specific batch item.

Parameters:

batch_id – the id of the batch item.

Returns:

the pointer to the array of values

inline const value_type *get_const_values_for_item(
size_type batch_id,
) const noexcept#

Returns a pointer to the array of values of the matrix for a specific batch item.

Note

This is the constant version of the function, which can be significantly more memory efficient than the non-constant version, so always prefer this version.

Parameters:

batch_id – the id of the batch item.

Returns:

the pointer to the array of values

void apply(
ptr_param<const MultiVector<value_type>> b,
ptr_param<MultiVector<value_type>> x,
)#

Apply the matrix to a multi-vector. Represents the matrix vector multiplication, x = A * b, where x and b are both multi-vectors.

Parameters:

  • b – the multi-vector to be applied to

  • x – the output multi-vector

void apply(
ptr_param<const MultiVector<value_type>> alpha,
ptr_param<const MultiVector<value_type>> b,
ptr_param<const MultiVector<value_type>> beta,
ptr_param<MultiVector<value_type>> x,
)#

Apply the matrix to a multi-vector with a linear combination of the given input vector. Represents the matrix vector multiplication, x = alpha * A

  • b + beta * x, where x and b are both multi-vectors.

Parameters:

  • alpha – the scalar to scale the matrix-vector product with

  • b – the multi-vector to be applied to

  • beta – the scalar to scale the x vector with

  • x – the output multi-vector

void scale(
const array<value_type> &row_scale,
const array<value_type> &col_scale,
)#

Performs in-place row and column scaling for this matrix.

Parameters:

  • row_scale – the row scalars

  • col_scale – the column scalars

void add_scaled_identity(
ptr_param<const MultiVector<value_type>> alpha,
ptr_param<const MultiVector<value_type>> beta,
)#

Performs the operation this = alpha*I + beta*this.

Note

Performs the operation in-place for this batch matrix

Note

This operation fails in case this matrix does not have all its diagonal entries.

Parameters:

  • alpha – the scalar for identity

  • beta – the scalar to multiply this matrix

Public Static Functions

static std::unique_ptr<Csr> create(
std::shared_ptr<const Executor> exec,
const batch_dim<2> &size = batch_dim<2>{},
size_type num_nonzeros_per_item = {},
)#

Creates an uninitialized Csr matrix of the specified size.

Parameters:

  • exec – Executor associated to the matrix

  • size – size of the matrix

  • num_nonzeros_per_item – number of nonzeros in each item of the batch matrix

static std::unique_ptr<Csr> create(
std::shared_ptr<const Executor> exec,
const batch_dim<2> &size,
array<value_type> values,
array<index_type> col_idxs,
array<index_type> row_ptrs,
)#

Creates a Csr matrix from an already allocated (and initialized) array. The column indices array needs to be the same for all batch items.

Note

If values is not an rvalue, not an array of ValueType, or is on the wrong executor, an internal copy will be created, and the original array data will not be used in the matrix.

Parameters:

  • exec – Executor associated to the matrix

  • size – size of the matrix

  • values – array of matrix values

  • col_idxs – the col_idxs array of a single batch item of the matrix.

  • row_ptrs – the row_ptrs array of a single batch item of the matrix.

Returns:

A smart pointer to the newly created matrix.

template<typename InputValueType, typename ColIndexType, typename RowPtrType>
static inline std::unique_ptr<Csr> create(
std::shared_ptr<const Executor> exec,
const batch_dim<2> &size,
std::initializer_list<InputValueType> values,
std::initializer_list<ColIndexType> col_idxs,
std::initializer_list<RowPtrType> row_ptrs,
)#

create(std::shared_ptr<const Executor>,const batch_dim<2>&, array<value_type>, array<index_type>,array<index_type>)

create(std::shared_ptr<const Executor>,const batch_dim<2>&, array<value_type>, array<index_type>,array<index_type>)

static std::unique_ptr<const Csr> create_const(
std::shared_ptr<const Executor> exec,
const batch_dim<2> &sizes,
gko::detail::const_array_view<value_type> &&values,
gko::detail::const_array_view<index_type> &&col_idxs,
gko::detail::const_array_view<index_type> &&row_ptrs,
)#

Creates a constant (immutable) batch csr matrix from a constant array. Only a single sparsity pattern (column indices and row pointers) is stored and hence the user needs to ensure that each batch item has the same sparsity pattern.

Parameters:

  • exec – the executor to create the matrix on

  • size – the dimensions of the matrix

  • values – the value array of the matrix

  • col_idxs – the col_idxs array of a single batch item of the matrix.

  • row_ptrs – the row_ptrs array of a single batch item of the matrix.

Returns:

A smart pointer to the constant matrix wrapping the input array (if it resides on the same executor as the matrix) or a copy of the array on the correct executor.

Returns:

A smart pointer to the newly created matrix.