Kokkos Node API and Local Linear Algebra Kernels Version of the Day
Public Member Functions
TSQR::details::CacheBlockWDP< LocalOrdinal, Scalar > Class Template Reference

Kokkos work-data pair (WDP) for KokkosNodeTsqr's (un_)cache_block() methods. More...

#include <Tsqr_KokkosNodeTsqr.hpp>

List of all members.

Public Member Functions

 CacheBlockWDP (const ConstMatView< LocalOrdinal, Scalar > A_in, const MatView< LocalOrdinal, Scalar > A_out, const CacheBlockingStrategy< LocalOrdinal, Scalar > &strategy, const int numPartitions, const bool unblock)
 Constructor.
void execute (const int partitionIndex)
 Method called by Kokkos' parallel_for.

Detailed Description

template<class LocalOrdinal, class Scalar>
class TSQR::details::CacheBlockWDP< LocalOrdinal, Scalar >

Kokkos work-data pair (WDP) for KokkosNodeTsqr's (un_)cache_block() methods.

Author:
Mark Hoemmen

Definition at line 797 of file Tsqr_KokkosNodeTsqr.hpp.


Constructor & Destructor Documentation

template<class LocalOrdinal , class Scalar >
TSQR::details::CacheBlockWDP< LocalOrdinal, Scalar >::CacheBlockWDP ( const ConstMatView< LocalOrdinal, Scalar >  A_in,
const MatView< LocalOrdinal, Scalar >  A_out,
const CacheBlockingStrategy< LocalOrdinal, Scalar > &  strategy,
const int  numPartitions,
const bool  unblock 
) [inline]

Constructor.

Parameters:
A_in[in] The matrix to (un-)cache-block.
A_out[in/out] Result of (un-)cache-blocking the matrix A_in.
strategy[in] Cache blocking strategy.
numPartitions[in] Number of partitions; maximum available parallelism.
unblock[in] If false, cache-block A_in (a matrix in column-major order) into A_out. If true, un-cache-block A_in into A_out (a matrix in column-major order).

Definition at line 848 of file Tsqr_KokkosNodeTsqr.hpp.


Member Function Documentation

template<class LocalOrdinal , class Scalar >
void TSQR::details::CacheBlockWDP< LocalOrdinal, Scalar >::execute ( const int  partitionIndex) [inline]

Method called by Kokkos' parallel_for.

Parameters:
partitionIndex[in] Zero-based index of the partition of the matrix. We parallelize over partitions. Partitions respect cache blocks.

Definition at line 879 of file Tsqr_KokkosNodeTsqr.hpp.


The documentation for this class was generated from the following file:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends