tatami_mult::MultiplyDenseRowWithSparseRowMatrixToColumnOutputOptions Struct Reference

Options for multiply_dense_row_with_sparse_row_matrix_to_column_output(). More...

#include <row_to_column.hpp>

Public Attributes
int	num_threads = 1
int	block_size = 16

Detailed Description

Options for multiply_dense_row_with_sparse_row_matrix_to_column_output().

Member Data Documentation

block_size

int tatami_mult::MultiplyDenseRowWithSparseRowMatrixToColumnOutputOptions::block_size = 16

Block size, i.e., number of LHS rows to be loaded at once. This is used to transpose the row-major LHS for more efficient operation with column-major output.

The block size should be positive. Larger values improve speed at the cost of increased memory usage. If this is set to 1, no blocking is performed.

num_threads

int tatami_mult::MultiplyDenseRowWithSparseRowMatrixToColumnOutputOptions::num_threads = 1

Number of threads to use. Different numbers of threads will not change the results.

---

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

• tatami_mult/sparse_matrix/dense_row/row_to_column.hpp